NIH_data_prep.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#load dependencies\n",
    "import requests\n",
    "import json\n",
    "import pandas as pd\n",
    "import time\n",
    "from math import ceil"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 102,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>keyterm</th>\n",
       "      <th>client_list_frequency</th>\n",
       "      <th>NIH_result_output</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>next generation sequencing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>next-generation sequencing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>gext gen sequencing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>next-gen sequencing</td>\n",
       "      <td>31</td>\n",
       "      <td>1778</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>RNA sequencing</td>\n",
       "      <td>14</td>\n",
       "      <td>6953</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      keyterm client_list_frequency NIH_result_output\n",
       "0  next generation sequencing                   NaN               NaN\n",
       "1  next-generation sequencing                   NaN               NaN\n",
       "2         gext gen sequencing                   NaN               NaN\n",
       "3         next-gen sequencing                    31              1778\n",
       "4              RNA sequencing                    14              6953"
      ]
     },
     "execution_count": 102,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# key term list\n",
    "key_terms_df = pd.read_csv(\"client_keyword_results.csv\")\n",
    "key_terms = key_terms_df['keyterm']\n",
    "key_terms_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['https://api.federalreporter.nih.gov/v1/projects/search?query=text:next+generation+sequencing',\n",
       " 'https://api.federalreporter.nih.gov/v1/projects/search?query=text:next-generation+sequencing',\n",
       " 'https://api.federalreporter.nih.gov/v1/projects/search?query=text:gext+gen+sequencing',\n",
       " 'https://api.federalreporter.nih.gov/v1/projects/search?query=text:next-gen+sequencing',\n",
       " 'https://api.federalreporter.nih.gov/v1/projects/search?query=text:RNA+sequencing']"
      ]
     },
     "execution_count": 94,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "url_list = []\n",
    "\n",
    "for word in key_terms:\n",
    "    word = word.strip().replace(' ', '+')\n",
    "    url = f\"https://api.federalreporter.nih.gov/v1/projects/search?query=text:{word}\"\n",
    "    url_list.append(url)\n",
    "\n",
    "url_list[:5]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0  Acer; Address; Area; Bacteria; Bacteriophages; base; Biological; Biology; college; Communities; cost effective; Data; Data Set; Databases; Deposition; design; DNA Sequence; DNA Sequencing Facility; Education; Faculty; Funding; Gene Expression; General Population; Generations; Genes; Genome; genome sequencing; Genomics; Giardia lamblia; Grant; Horizontal Gene Transfer; Housing; Individual; innovation; Institution; instrumentation; International; Ions; Laboratories; Laboratory Research; Michigan; microbial; Mycobacteriophages; next generation; novel; Parasites; Peer Review; Phylogenetic Analysis; Plants; Plastids; programs; Publications; Research; Research Personnel; Research Project Grants; research study; Research Training; Science; Scientific Advances and Accomplishments; Scientist; Source; STEM field; Students; symposium; Technology; Testing; Training; undergraduate research; university student; Virus\n",
      "1  base; Base Sequence; Biological Models; Biological Process; Chromosome Mapping; Communities; comparative genomics; Complement; Computational Technique; Computer Simulation; Computer software; computerized tools; Computing Methodologies; cost effective; Data; Databases; design; Development; Developmental Biology; DNA; DNA Sequence; experimental analysis; Experimental Designs; Expressed Sequence Tags; Fishes; gene discovery; gene function; Gene Mutation; Genes; Genetic; genetic analysis; genetic manipulation; Genetic Markers; Genetic Recombination; Genetic Variation; genome sequencing; Genomics; human disease; Investigation; knowledge translation; Maps; Methods; Microsatellite Repeats; Modeling; Mutagenesis; mutant; Mutation; next generation; Phenotype; Population; positional cloning; Positioning Attribute; Protocols documentation; rapid technique; Relative (related person); research study; Sampling; Scanning; Siblings; Software Tools; Source; Statistical Methods; stem; System; Technology; Variant; web-accessible; Zebrafish; zebrafish genome\n",
      "2  base; Biological; Clinic; Collaborations; college; cost; Cytochrome P450; design; Discipline; DNA; DNA Resequencing; DNA Sequence; Enzymes; Evaluation; experience; Foundations; Funding; Gene Family; Genes; Genome; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; Goals; Human Genome; Letters; Link; Medical; Medicine; Mind; next generation; Outcome; Peer Review; Pharmaceutical Preparations; Pharmacogenetics; Pharmacogenomics; Phase; Process; programs; Protocols documentation; Research; Research Infrastructure; Resources; Science; Series; Signal Transduction; Techniques; Technology\n",
      "3  Accounting; Affect; Africa South of the Sahara; African; African Trypanosomiasis; Animals; base; Cataloging; Catalogs; Cattle; Characteristics; Comparative Study; Complement; Confusion; Country; Data; Development; Diagnostic; Disease; Disease Outbreaks; disease transmission; disorder control; Drug resistance; Eastern Africa; Economics; Endemic Diseases; Epidemic; Epidemiologic Studies; Epidemiology; Evaluation; Evolution; experience; Foundations; Future; Genetic; Genetic Markers; Genetic Polymorphism; Genetic Population Study; Genome; genome sequencing; Genomics; Genotype; Human; human disease; improved; insight; Knowledge; Laboratories; Laboratory Markers; Methods; Molecular; molecular marker; Monitor; Morphology; Mutation; Nature; neglect; next generation; Nucleotides; Outcome; Parasites; Pilot Projects; Polymorphic Microsatellite Marker; Population; Population Genetics; prevent; Recording of previous events; Relative (related person); Research; Role; Sampling; Severity of illness; Shapes; social; Structure; Target Populations; Technology; Testing; Time; tool; trait; Trypanosoma; Trypanosoma brucei brucei; Trypanosoma brucei rhodesiense; Trypanosomatina; Uganda; Validation; Variant; vector\n",
      "4  Address; Adopted; Advisory Committees; Animal Model; anticancer research; Archives; Area; Award; base; Bioinformatics; Biomedical Research; Budgets; Cancer Center; Cancer Center Support Grant; Cancer Hospital; Capillary Electrophoresis; Cells; Chemistry; Chromatin; Chromatin Structure; Commit; Complex; Copy Number Polymorphism; Core Facility; cost; cost effective; Data; Data Analyses; Data Quality; Detection; Development; digital; DNA; DNA Methylation; DNA Resequencing; DNA Sequence; Ensure; Equipment; Evaluation; Exons; experience; Faculty; Fees; Funding; Future; Gene Expression; Genes; Genetic Polymorphism; Genetic Transcription; Genome; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; genotyping technology; Goals; Grant; Growth; high throughput technology; Hour; Housing; Human; Human Resources; human tissue; Individual; Information Technology; Institutes; Institution; Investments; Laboratories; Malignant Neoplasms; Measures; medical schools; member; MicroRNAs; Microsatellite Repeats; mRNA Expression; neoplastic cell; new technology; next generation; Normal Cell; North Carolina; Paper; Patients; Peer Review; Positioning Attribute; Preparation; Price; rapid growth; Reading; Research; Research Personnel; Resources; RNA; RNA analysis; RNA Sequences; Sampling; Scientist; Services; single molecule; Site; SNP genotyping; Solid; success; Technology; technology development; The Cancer Genome Atlas; Time; Training; trait; tumor; Universities; Variant; Wages; Whole-Genome Shotgun Sequencing; Work\n",
      "5  Actinobacteria class; Anabolism; analog; Antibiotics; base; Biochemical; Biochemistry; Bioinformatics; Biological; Biological Assay; Biological Factors; Cell Culture Techniques; Chemical Structure; chemotherapy; Clinic; comparative; Data Set; Development; DNA; DNA Sequence; Engineering; Enzymes; Event; fascinate; Future; Gene Cluster; Generations; Genes; Genetic; Genome; genome sequencing; Genomic Library; Genomics; Goals; Human; human disease; In Vitro; in vivo; Knock-out; Knowledge; Laboratories; Lead; Libraries; Link; Marines; methicillin resistant Staphylococcus aureus; microorganism; Mining; Molecular Biology; Multi-Drug Resistance; next generation; novel; Pathway interactions; Pharmacologic Substance; Phase; Play; Production; public health relevance; Reading; Research; research study; Role; Screening procedure; Series; Staphylococcus aureus; Streptomyces; Technology; Testing; Time; tool\n",
      "6  Adoption; Appointment; Base Pairing; Base Sequence; Binding Sites; Bioinformatics; Biological; Boxing; Calendar; cancer genetics; chromatin modification; Clinical; Comprehensive Cancer Center; computer science; computing resources; Consult; Consultations; Core Facility; cost; Custom; Data; Data Analyses; design; DNA; DNA Methylation; DNA Resequencing; DNA Sequencing Facility; Engineering; Ensure; Epigenetic Process; Equipment; Experimental Designs; Faculty; flexibility; Gene Expression Profile; Genetic Research; Genome; genome-wide; Genomics; Goals; Gold; image processing; innovation; instrument; Laboratories; Libraries; Malignant Neoplasms; member; Memory; Molecular Biology; Molecular Genetics; Mutation; new technology; next generation; oncology; Partner in relationship; Preparation; Process; Protocols documentation; Quality Control; Reading; Research; Research Personnel; research study; Resource Sharing; Running; Sampling; Scheme; Sequence Alignment; Services; Sonication; structural genomics; Synapses; Technology; Time; transcription factor; Translations; Variant\n",
      "7  Acute Myelocytic Leukemia; Address; Affect; Back; base; Blood capillaries; cancer therapy; capillary; Case-Control Studies; CCL18 gene; Cleaved cell; Clinical Data; cohort; Communities; Complex; cost; Coupled; Data; Data Element; design; Development; Disease; Disease susceptibility; DNA; DNA Resequencing; DNA Sequence; drug metabolism; Exercise; exome; Funding; Genes; Genetic; Genome; genome wide association study; Genomics; Glioblastoma; Grant; Head; Heart failure; Human; Human Resources; interest; Knowledge; Laboratories; Light; Liquid substance; Lung Adenocarcinoma; Malignant neoplasm of ovary; Malignant Neoplasms; Maps; Medical; member; Mental Retardation; Metabolic syndrome; Methods; Mutation; National Human Genome Research Institute; new technology; next generation; novel; novel strategies; Nucleotides; Pathway interactions; Pharmaceutical Preparations; Pharmacogenetics; Pharmacogenomics; Phase; Pilot Projects; Play; PPP3CA gene; Process; Production; protein structure; Qualifying; Reaction; Reading; Reporting; Research; Research Personnel; research study; response; Retinitis Pigmentosa; Robotics; Role; Sampling; Sequence Analysis; Services; Severities; Shotguns; Solutions; success; Syndrome; Technology; The Cancer Genome Atlas; trait; Universities; Update; Validation; Variant; Washington; Work\n",
      "8  Address; Adopted; Advisory Committees; Animal Model; anticancer research; Archives; Area; Award; base; Bioinformatics; Biomedical Research; Budgets; Cancer Center; Cancer Center Support Grant; Cancer Hospital; Capillary Electrophoresis; Cells; Chemistry; Chromatin; Chromatin Structure; Commit; Complex; Copy Number Polymorphism; Core Facility; cost; cost effective; Data; Data Analyses; Data Quality; Detection; Development; digital; DNA; DNA Methylation; DNA Resequencing; DNA Sequence; Ensure; Equipment; Evaluation; Exons; experience; Faculty; Fees; Funding; Future; Gene Expression; Genes; Genetic Polymorphism; Genetic Transcription; Genome; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; genotyping technology; Goals; Grant; Growth; high throughput technology; Hour; Housing; Human; Human Resources; human tissue; Individual; Information Technology; Institutes; Institution; Investments; Laboratories; Malignant Neoplasms; Measures; medical schools; member; MicroRNAs; Microsatellite Repeats; mRNA Expression; neoplastic cell; new technology; next generation; Normal Cell; North Carolina; Paper; Patients; Peer Review; Positioning Attribute; Preparation; Price; rapid growth; Reading; Research; Research Personnel; Resources; RNA; RNA analysis; RNA Sequences; Sampling; Scientist; Services; single molecule; Site; SNP genotyping; Solid; success; Technology; technology development; The Cancer Genome Atlas; Time; Training; trait; tumor; Universities; Variant; Wages; Whole-Genome Shotgun Sequencing; Work\n",
      "9  abstracting; Alu Elements; Award; Beryllium; Bioinformatics; Biology; career; Computational Biology; cost; Data; Data Analyses; data management; Data Set; DNA; DNA Insertion Elements; DNA Sequence; Elements; Etiology; Evolution; Family; Genes; Genetic Markers; Genetic Polymorphism; Genetic Research; Genetic Variation; Genome; genome sequencing; Genomics; Genotype; Goals; Grant; Guanine + Cytosine Composition; Hereditary Disease; high throughput technology; Human; human disease; Human Genetics; Human Genome; indexing; Indium; Individual; insight; Institution; interest; Knowledge; L1 Elements; Libraries; Location; Mentors; Methods; next generation; novel; Organism; Phase; Population; Population Genetics; Primates; Procedures; Process; Property; Protocols documentation; Recording of previous events; Research; Research Personnel; Research Training; Resources; Sampling; Scanning; Site; Structure; Techniques; Technology; Time; tool; Training; transposon/insertion element; Variant; Writing\n",
      "10  Address; Allelotyping; Automation; base; Bioinformatics; Biological; Biomedical Research; ChIP-seq; Computer software; computerized tools; computing resources; Data; Data Analyses; data mining; data reduction; Data Set; design; DNA Resequencing; Educational process of instructing; experience; Experimental Designs; Future; Gene Expression Profile; Genome; genome sequencing; Genomics; Goals; Graph; Individual; Institution; Internet; Learning; Maps; Memory; Messenger RNA; next generation; novel; Operating System; Participant; Paste substance; Procedures; programs; Reading; Recipe; Research; Research Personnel; research study; Running; Sampling; Scientist; Sequence Analysis; skills; Source; Students; System; Techniques; Technology; Thinking; tool; Training; transcriptomics; web services; Work\n",
      "11  Adopted; anticancer research; Automobile Driving; Award; base; Base Sequence; Bioinformatics; Biological Markers; Cancer Biology; cancer therapy; career development; Chimera organism; ChIP-seq; clinical application; cohort; Common Carcinoma; comparative genomic hybridization; Complement; computing resources; Data; Data Collection; Detection; Development; Development Plans; Diagnostic; Environment; Evaluation; Event; evidence base; Exons; experience; Funding; Gene Expression; Gene Expression Profile; Gene Fusion; Gene Structure; Genes; Genetic; Genome; Genomics; Goals; high throughput analysis; Human; human data; Imagery; improved; indexing; knowledge base; Lead; Malignant neoplasm of pancreas; Malignant neoplasm of prostate; Malignant Neoplasms; Manuscripts; Medicine; melanoma; Mentors; Methodology; Methods; Michigan; Mutation; National Center for Integrative Biomedical Informatics; Nature; new therapeutic target; next generation; novel; novel diagnostics; Pathology; Pathway interactions; Patient Care; Performance; Phase; Prevalence; prognostic; Prostate; Prostatic Neoplasms; Recurrence; Research; Research Personnel; Research Proposals; Research Training; RNA; Sampling; Sequence Analysis; Solid; Specificity; success; Technology; Testing; Therapeutic; therapeutic target; tool; Translating; Translational Research; tumor; United States National Institutes of Health; Universities; Walking; Work\n",
      "12  Algorithms; analytical method; base; biodefense; biothreat; Collaborations; Computers; Computing Methodologies; Data; Detection; Environment; Evolution; experience; Family; genetic analysis; genome sequencing; Genomics; graduate student; Informatics; Knowledge; metagenomic sequencing; Metagenomics; Microbe; microbial; microbial community; Microbiology; Mining; multidisciplinary; National Security; Nature; next generation; novel; Organism; Postdoctoral Fellow; Research Personnel; scientific computing; Scientist; Single Nucleotide Polymorphism; sound; statistics; Technology; tool; Training\n",
      "13  Algorithms; analytical method; base; biodefense; biothreat; Collaborations; Computers; Computing Methodologies; Data; Detection; Environment; Evolution; experience; Family; genetic analysis; genome sequencing; Genomics; graduate student; Informatics; Knowledge; metagenomic sequencing; Metagenomics; Microbe; microbial; microbial community; Microbiology; Mining; multidisciplinary; National Security; Nature; next generation; novel; Organism; Postdoctoral Fellow; Research Personnel; scientific computing; Scientist; Single Nucleotide Polymorphism; sound; statistics; Technology; tool; Training\n",
      "14  Address; Algorithms; base; Behavior; Binding; Biological; bisulfite; Cells; ChIP-seq; Chromatin; cofactor; Collaborations; Computer software; computerized tools; Computing Methodologies; cost; Cytosine; Data; Data Analyses; Data Files; data integration; Data Set; design; Development; DNA; DNA Methylation; Ensure; Epigenetic Process; epigenomics; Family; Future; Gene Expression; Genetic Transcription; genome-wide; Genomics; Goals; histone modification; Histones; Hypersensitivity; insight; Institutes; instrument; Linker DNA; Malignant Neoplasms; Methods; MicroRNAs; Modeling; Molecular Biology; Names; National Human Genome Research Institute; next generation; novel; Nucleosomes; Positioning Attribute; Process; programs; public health relevance; Reading; Research Personnel; research study; Resolution; RNA; Running; Sequence Analysis; Software Tools; Source; STAT1 gene; STAT3 gene; Statistical Methods; Technology; Thymine; tool; transcription factor; Transcriptional Regulation; United States National Institutes of Health; Variant; Work\n",
      "15  Achievement; Bacteria; base; Bioinformatics; Biological; Biological Sciences; Biology; Biotechnology; Cattle; Communities; Computer software; cost; Cues; Data; Development; Device or Instrument Development; Disease Resistance; Dissection; DNA; DNA Sequence; Droughts; Faculty; Foundations; Gap Junctions; Generations; Genetic Code; genome sequencing; Genomics; Hour; Human; Human Genome; Institutes; Life; Magnetic Resonance Imaging; meetings; member; Metagenomics; Microbe; next generation; Oceans; Organism; Outcome; pathogen; Plants; Postdoctoral Fellow; Process; programs; Publications; Research; Rumen; Schedule; stem; Students; Technology; Texas; Universities; web site\n",
      "16  Actinium; Address; Bioinformatics; Collection; Communities; cost effective; Databases; design; DNA; DNA Insertion Elements; DNA Sequence; DNA Transposable Elements; Elements; gene function; Genes; Genetic; genetic resource; Genome; genome sequencing; indexing; Informatics; Institution; Internet; Knock-out; Maize; Maps; Methods; Modeling; Molecular Biology; Mutation; next generation; novel; Nurseries; Organism; positional cloning; Production; Reading; Research Personnel; Research Training; Resources; Sequence Analysis; Site; Students; Technology; Transgenic Organisms; Universities; Validation; Visual\n",
      "17  Address; Animals; Area; Award; base; Biodiversity; Bioinformatics; Biological; Biomass; Commit; cost; Data Collection; denaturing gradient gel electrophoresis; density; Dideoxy Chain Termination DNA Sequencing; Eating; Ecology; Educational process of instructing; Environment; Environmental Risk Factor; Eukaryota; exhaustion; experience; Experimental Designs; Fingerprint; Fishes; Food Webs; Individual; Informatics; Laboratories; Learning; Libraries; light microscopy; Manuscripts; Marines; Measures; meter; Methods; Microbe; microbial; Molecular; Molecular Evolution; next generation; Oceanography; Oceans; Organism; Phytoplankton; Plankton; Plants; Postdoctoral Fellow; Preparation; Process; programs; Recruitment Activity; Research; Research Personnel; Resources; Sampling; Science; Sister; Structure; Students; System; Taxonomy; teacher; Techniques; Technology; Time; Training; Work; Zooplankton\n",
      "18  Address; Animals; Area; Award; base; Biodiversity; Bioinformatics; Biological; Biomass; Commit; cost; Data Collection; denaturing gradient gel electrophoresis; density; Dideoxy Chain Termination DNA Sequencing; Eating; Ecology; Educational process of instructing; Environment; Environmental Risk Factor; Eukaryota; exhaustion; experience; Experimental Designs; Fingerprint; Fishes; Food Webs; Individual; Informatics; Laboratories; Learning; Libraries; light microscopy; Manuscripts; Marines; Measures; meter; Methods; Microbe; microbial; Molecular; Molecular Evolution; next generation; Oceanography; Oceans; Organism; Phytoplankton; Plankton; Plants; Postdoctoral Fellow; Preparation; Process; programs; Recruitment Activity; Research; Research Personnel; Resources; Sampling; Science; Sister; Structure; Students; System; Taxonomy; teacher; Techniques; Technology; Time; Training; Work; Zooplankton\n",
      "19  Area; Basic Science; Biotechnology; Computing Methodologies; District of Columbia; DNA Sequence; Educational workshop; Europe; European; Future; Genes; Genome; genome sequencing; Genomics; Grant; Marines; meetings; Methodology; Microbe; microbial; Microbiology; next generation; Outcome; Process; Property; Recommendation; Reporting; Research; Science; Scientist; Technology; tool; Training; United States; Work\n",
      "20  Address; Anodes; Area; base; Base Pairing; Base Sequence; Blood capillaries; capillary; Capillary Electrophoresis; Cells; Clinical; complex biological systems; cost; Data; Data Quality; density; design; design and construction; Detection; Development; Diagnosis; Dideoxy Chain Termination DNA Sequencing; Disease; disorder prevention; DNA; DNA Sequence; Drug Formulations; Electrolytes; Electrophoresis; epigenomics; Fluorescence; fluorescence imaging; Foundations; Future; Gel; Gene Expression Profile; genetic analysis; Genetic Variation; Genome; Genomics; Goals; Health; Hour; Human; Image; instrument; Lasers; Length; Medical Research; Methods; Microspheres; next generation; novel strategies; Optics; Other Genetics; Performance; Pharmaceutical Preparations; Phase; Polymerase; Population; Preparation; Process; prototype; public health relevance; Reaction; Reading; Reagent; Research; response; RNA; RNA Sequences; Running; Sampling; Scanning; Scientist; Signal Transduction; single molecule; Speed; synthetic construct; System; Technology; technology development; Temperature; Testing; Time; vector\n",
      "21  Address; Algorithms; Area; Attention; base; Bioinformatics; Biological; chromatin immunoprecipitation; Clinical; cluster computing; Communities; comparative genomic hybridization; Computer Systems; computerized data processing; Computing Methodologies; Confidence Intervals; Copy Number Polymorphism; cost; Data; Data Sources; design; Detection; Development; Disease; disease phenotype; DNA copy number; experience; Experimental Designs; Genome; genome sequencing; Genomics; Health; Human; Human Genome; improved; Individual; interest; Length; Location; Malignant Neoplasms; Maps; markov model; method development; Modeling; Morphologic artifacts; Nature; next generation; novel; Patients; Phenotype; Population; Procedures; Process; Reading; Research; Research Design; Research Infrastructure; Research Personnel; research study; Resolution; Resources; Sampling; Sensitivity and Specificity; Series; Single Nucleotide Polymorphism; Solid; Statistical Methods; Structure; System; Techniques; Technology; tool; Translating; Translations; user-friendly; Variant; web interface; Work\n",
      "22  Accounting; Adult; Affect; African American; Age; Aging; Alleles; Amino Acids; Architecture; Arthritis; Atherosclerosis; Bioinformatics; Candidate Disease Gene; Cardiovascular system; case control; Caucasians; Caucasoid Race; Clinical; cohort; Communities; Complex; cost; Data; data management; database of Genotypes and Phenotypes; Deposition; design; Disease; Disease Progression; DNA Resequencing; DNA Sequence; Drug Delivery Systems; Educational workshop; Elements; Epidemiology; Etiology; Exons; follow-up; Framingham Heart Study; Gene Expression; Gene Frequency; Gene Targeting; Genes; Genetic; genetic variant; genome sequencing; genome wide association study; Genomics; Genotype; Gout; Health; Heart; Human; Human Genome; improved; Individual; Intercistronic Region; interest; Investigation; Joints; Laboratories; Lead; Learning; Measures; Medical; Medical Technology; Messenger RNA; Molecular; multidisciplinary; next generation; Nonsense Codon; novel; Outpatients; Pain; Phenotype; Prevention; Process; programs; Promoter Regions; protein structure; public health relevance; Quality Control; Research; Research Personnel; Resources; Risk; Risk Factors; RNA Splicing; Serum; Solid; success; Susceptibility Gene; System; Technology; Testing; Tissues; tool; trait; United States National Institutes of Health; Urate; Uric Acid; Variant; Visit\n",
      "23  Algorithms; American; anticancer research; Atlases; Back; base; Base Sequence; Cancer Etiology; cancer genome; cancer genomics; Cancer Patient; cancer type; Cervix carcinoma; Cloning; cohort; Communities; Complementary DNA; Computer Analysis; Computer software; Data; Data Analyses; Data Set; Databases; Diagnostic; DNA; Floods; Formalin; Funding; Future; Gene Expression Profile; Genetic; Genome; genome sequencing; Genomics; Germ Lines; Goals; Hepatitis B Vaccination; Human; Human Genome; Human Papillomavirus; improved; Infectious Agent; Lead; Left; Malignant neoplasm of liver; Malignant Neoplasms; Methods; National Cancer Institute; next generation; novel; novel virus; Nucleic acid sequencing; Nucleic Acids; Oncogenic Viruses; Paraffin Embedding; pathogen; Phase; Pilot Projects; prevent; Preventive; programs; Public Health; public health relevance; Reading; Recovery; Recurrence; Research; Research Infrastructure; Research Personnel; Residual state; response; RNA; RNA Sequences; Running; Sampling; Sequence Analysis; Technology; Testing; Therapeutic; Tissues; transcriptomics; Vaccination; Validation; Viral; Virus\n",
      "24  Address; Anodes; Area; base; Base Pairing; Base Sequence; Blood capillaries; capillary; Capillary Electrophoresis; Cells; Clinical; complex biological systems; cost; Data; Data Quality; density; design; design and construction; Detection; Development; Diagnosis; Dideoxy Chain Termination DNA Sequencing; Disease; disorder prevention; DNA; DNA Sequence; Drug Formulations; Electrolytes; Electrophoresis; epigenomics; Fluorescence; fluorescence imaging; Foundations; Future; Gel; Gene Expression Profile; genetic analysis; Genetic Variation; Genome; Genomics; Goals; Health; Hour; Human; Image; instrument; Lasers; Length; Medical Research; Methods; Microspheres; next generation; novel strategies; Optics; Other Genetics; Performance; Pharmaceutical Preparations; Phase; Polymerase; Population; Preparation; Process; prototype; public health relevance; Reaction; Reading; Reagent; Research; response; RNA; RNA Sequences; Running; Sampling; Scanning; Scientist; Signal Transduction; single molecule; Speed; synthetic construct; System; Technology; technology development; Temperature; Testing; Time; vector\n",
      "25  Address; Area; base; Behavior; Biological Assay; Biological Preservation; cancer genetics; Cancer Patient; cancer recurrence; cancer therapy; Candidate Disease Gene; Cataloging; Catalogs; Clinical; Clinical Pathology; clinical phenotype; Clinical Research; Code; Colorectal Cancer; Computers; cost; design; Development; Diagnostic; DNA; DNA Resequencing; DNA Sequence; Drug Delivery Systems; Epidermal Growth Factor Receptor; Exons; Formalin; Freezing; Gene Mutation; Gene Targeting; Genes; Genetic; genome sequencing; Genomics; Human; improved; indexing; Individual; innovation; KRAS2 gene; Laboratories; Large Intestine Carcinoma; Lead; Malignant Neoplasms; Mediating; Methods; Modeling; Molecular; Molecular Analysis; Monoclonal Antibodies; Mutation; Mutation Analysis; Mutation Detection; neoplastic; next generation; novel; Oncogenes; Operating System; Other Genetics; Outcome; outcome forecast; Paraffin; Paraffin Embedding; Patients; Performance; Pharmaceutical Preparations; Process; public health relevance; Research; response; Running; sample fixation; Sampling; Scanning; Scientist; Sequence Analysis; Solid Neoplasm; Somatic Mutation; Source; Specimen; Staining method; Stains; Surveys; Technology; Temperature; Time; Tissue Sample; Tissues; tumor; tumor growth; Tumor Tissue; Validation; Variant; Work\n",
      "26  Arts; base; Biological; Clinic; Collaborations; college; cost; Cytochrome P450; design; Discipline; DNA; DNA Resequencing; DNA Sequence; Evaluation; experience; Foundations; Funding; Gene Family; Genes; Genome; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; Goals; Human Genome; Letters; Link; Medical; Medicine; Mind; next generation; Outcome; Peer Review; Pharmacogenomics; Process; programs; Protocols documentation; Research; Research Infrastructure; Resources; Science; Series; Signal Transduction; Techniques; Technology\n",
      "27  Address; Algorithms; Area; Attention; base; Bioinformatics; Biological; chromatin immunoprecipitation; Clinical; cluster computing; Communities; comparative genomic hybridization; Computer Systems; computerized data processing; Computing Methodologies; Confidence Intervals; Copy Number Polymorphism; cost; Data; Data Sources; design; Detection; Development; Disease; disease phenotype; DNA copy number; experience; Experimental Designs; Genome; genome sequencing; Genomics; Health; Human; Human Genome; improved; Individual; interest; Length; Location; Malignant Neoplasms; Maps; markov model; method development; Modeling; Morphologic artifacts; Nature; next generation; novel; Patients; Phenotype; Population; Procedures; Process; Reading; Research; Research Design; Research Infrastructure; Research Personnel; research study; Resolution; Resources; Sampling; Sensitivity and Specificity; Series; Single Nucleotide Polymorphism; Solid; Statistical Methods; Structure; System; Techniques; Technology; tool; Translating; Translations; user-friendly; Variant; web interface; Work\n",
      "28  Algorithms; American; anticancer research; Atlases; Back; base; Base Sequence; Cancer Etiology; cancer genome; cancer genomics; Cancer Patient; cancer type; Cervix carcinoma; Cloning; cohort; Communities; Complementary DNA; Computer Analysis; Computer software; Data; Data Analyses; Data Set; Databases; Diagnostic; DNA; Floods; Formalin; Funding; Future; Gene Expression Profile; Genetic; Genome; genome sequencing; Genomics; Germ Lines; Goals; Hepatitis B Vaccination; Human; Human Genome; Human Papillomavirus; improved; Infectious Agent; Lead; Left; Malignant neoplasm of liver; Malignant Neoplasms; Methods; National Cancer Institute; next generation; novel; novel virus; Nucleic acid sequencing; Nucleic Acids; Oncogenic Viruses; Paraffin Embedding; pathogen; Phase; Pilot Projects; prevent; Preventive; programs; Public Health; public health relevance; Reading; Recovery; Recurrence; Research; Research Infrastructure; Research Personnel; Residual state; response; RNA; RNA Sequences; Running; Sampling; Sequence Analysis; Technology; Testing; Therapeutic; Tissues; transcriptomics; Vaccination; Validation; Viral; Virus\n",
      "29  Accounting; Adult; Affect; African American; Age; Aging; Alleles; Amino Acids; Architecture; Arthritis; Atherosclerosis; Bioinformatics; Candidate Disease Gene; Cardiovascular system; case control; Caucasians; Caucasoid Race; Clinical; cohort; Communities; Complex; cost; Data; data management; database of Genotypes and Phenotypes; Deposition; design; Disease; Disease Progression; DNA Resequencing; DNA Sequence; Drug Delivery Systems; Educational workshop; Elements; Epidemiology; Etiology; Exons; follow-up; Framingham Heart Study; Gene Expression; Gene Frequency; Gene Targeting; Genes; Genetic; genetic variant; genome sequencing; genome wide association study; Genomics; Genotype; Gout; Health; Heart; Human; Human Genome; improved; Individual; Intercistronic Region; interest; Investigation; Joints; Laboratories; Lead; Learning; Measures; Medical; Medical Technology; Messenger RNA; Molecular; multidisciplinary; next generation; Nonsense Codon; novel; Outpatients; Pain; Phenotype; Prevention; Process; programs; Promoter Regions; protein structure; public health relevance; Quality Control; Research; Research Personnel; Resources; Risk; Risk Factors; RNA Splicing; Serum; Solid; success; Susceptibility Gene; System; Technology; Testing; Tissues; tool; trait; United States National Institutes of Health; Urate; Uric Acid; Variant; Visit\n",
      "30  Award; Bioinformatics; Biology; career; Computational Biology; cost; Data; Data Analyses; data management; Data Set; DNA; DNA Insertion Elements; DNA Sequence; Elements; Etiology; Evolution; Family; Genes; Genetic Markers; Genetic Polymorphism; Genetic Research; Genetic Variation; Genome; genome sequencing; Genomics; Genotype; Goals; Grant; Guanine + Cytosine Composition; Hereditary Disease; high throughput technology; Human; human disease; Human Genetics; Human Genome; indexing; Indium; Individual; insight; Institution; interest; Knowledge; L1 Elements; Libraries; Location; Mentors; Methods; next generation; novel; Organism; Phase; Population; Population Genetics; Primates; Procedures; Process; Property; Protocols documentation; public health relevance; Recording of previous events; Research; Research Personnel; Research Training; Resources; Sampling; Scanning; Site; Structure; Techniques; Technology; Time; tool; Training; transposon/insertion element; Variant; Writing\n",
      "31  Actinobacteria class; Anabolism; analog; Antibiotics; base; Biochemical; Biochemistry; Bioinformatics; Biological; Biological Assay; Biological Factors; Cell Culture Techniques; Chemical Structure; chemotherapy; Clinic; comparative; Data Set; Development; DNA; DNA Sequence; Engineering; Enzymes; Event; fascinate; Future; Gene Cluster; Generations; Genes; Genetic; Genome; genome sequencing; Genomic Library; Genomics; Goals; Human; human disease; In Vitro; in vivo; Knock-out; Knowledge; Laboratories; Lead; Libraries; Link; Marines; methicillin resistant Staphylococcus aureus; microorganism; Mining; Molecular Biology; Multi-Drug Resistance; next generation; novel; Pathway interactions; Pharmacologic Substance; Phase; Play; Production; Reading; Research; research study; Role; Screening procedure; Series; Staphylococcus aureus; Streptomyces; Technology; Testing; Time; tool\n",
      "32  Accounting; Affect; Africa South of the Sahara; African; African Trypanosomiasis; Animals; base; Cataloging; Catalogs; Cattle; Characteristics; Comparative Study; Complement; Confusion; Country; Data; Development; Diagnostic; Disease; Disease Outbreaks; disease transmission; disorder control; Drug resistance; Eastern Africa; Economics; Endemic Diseases; Epidemic; Epidemiologic Studies; Epidemiology; Evaluation; Evolution; experience; Foundations; Future; Genetic; Genetic Markers; Genetic Polymorphism; Genetic Population Study; Genome; genome sequencing; Genomics; Genotype; Human; human disease; improved; insight; Knowledge; Laboratories; Laboratory Markers; Methods; Molecular; molecular marker; Monitor; Morphology; Mutation; Nature; neglect; next generation; Nucleotides; Outcome; Parasites; Pilot Projects; Polymorphic Microsatellite Marker; Population; Population Genetics; prevent; Recording of previous events; Relative (related person); Research; Role; Sampling; Severity of illness; Shapes; social; Structure; Target Populations; Technology; Testing; Time; tool; trait; Trypanosoma; Trypanosoma brucei brucei; Trypanosoma brucei rhodesiense; Trypanosomatina; Uganda; Validation; Variant; vector\n",
      "33  Address; Area; base; Behavior; Biological Assay; Biological Preservation; cancer genetics; Cancer Patient; cancer recurrence; cancer therapy; Candidate Disease Gene; Cataloging; Catalogs; Clinical; Clinical Pathology; clinical phenotype; Clinical Research; Code; Colorectal Cancer; Computers; cost; cost effective; design; Development; Diagnostic; DNA; DNA Resequencing; DNA Sequence; Drug Delivery Systems; Epidermal Growth Factor Receptor; Exons; Formalin; Freezing; Gene Mutation; Gene Targeting; Genes; Genetic; genome sequencing; Genomics; Human; improved; indexing; Individual; innovation; KRAS2 gene; Laboratories; Large Intestine Carcinoma; Lead; Malignant Neoplasms; Mediating; Methods; Modeling; Molecular; Molecular Analysis; Monoclonal Antibodies; Mutation; Mutation Analysis; Mutation Detection; neoplastic; next generation; novel; Oncogenes; Operating System; Other Genetics; Outcome; outcome forecast; Paraffin; Paraffin Embedding; Patients; Performance; Pharmaceutical Preparations; Process; public health relevance; Research; response; Running; sample fixation; Sampling; Scanning; Scientist; Sequence Analysis; Solid Neoplasm; Somatic Mutation; Source; Specimen; Staining method; Stains; Surveys; Technology; Temperature; Time; Tissue Sample; Tissues; translational study; tumor; tumor growth; Tumor Tissue; Validation; Variant; Work\n",
      "34  Address; Allelotyping; Automation; base; Bioinformatics; Biological; Biomedical Research; Computer software; computerized tools; computing resources; Data; Data Analyses; data mining; data reduction; Data Set; design; DNA Resequencing; Educational process of instructing; experience; Experimental Designs; Future; Gene Expression Profile; Genome; genome sequencing; Genomics; Goals; Graph; Individual; Institution; Internet; Learning; Maps; Memory; Messenger RNA; next generation; novel; Operating System; Participant; Paste substance; Procedures; programs; Reading; Recipe; Research; Research Personnel; research study; Running; Sampling; Scientist; Sequence Analysis; skills; Source; Students; System; Techniques; Technology; Thinking; tool; Training; transcriptomics; web services; Work\n",
      "35  Alu Elements; Award; Beryllium; Bioinformatics; Biology; career; Computational Biology; cost; Data; Data Analyses; data management; Data Set; DNA; DNA Insertion Elements; DNA Sequence; Elements; Etiology; Evolution; Family; Genes; Genetic Markers; Genetic Polymorphism; Genetic Research; Genetic Variation; Genome; genome sequencing; Genomics; Genotype; Goals; Grant; Guanine + Cytosine Composition; Hereditary Disease; high throughput technology; Human; human disease; Human Genetics; Human Genome; indexing; Indium; Individual; insight; Institution; interest; Knowledge; L1 Elements; Libraries; Location; Mentors; Methods; next generation; novel; Organism; Phase; Population; Population Genetics; Primates; Procedures; Process; Property; Protocols documentation; public health relevance; Recording of previous events; Research; Research Personnel; Research Training; Resources; Sampling; Scanning; Site; Structure; Techniques; Technology; Time; tool; Training; transposon/insertion element; Variant; Writing\n",
      "36  base; Biological; Clinic; Collaborations; college; cost; Cytochrome P450; design; Discipline; DNA; DNA Resequencing; DNA Sequence; Enzymes; Evaluation; experience; Foundations; Funding; Gene Family; Genes; Genome; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; Goals; Human Genome; Letters; Link; Medical; Medicine; Mind; next generation; Outcome; Peer Review; Pharmaceutical Preparations; Pharmacogenetics; Pharmacogenomics; Phase; Process; programs; Protocols documentation; Research; Research Infrastructure; Resources; Science; Series; Signal Transduction; Techniques; Technology\n",
      "37  Address; Adopted; Advisory Committees; Animal Model; anticancer research; Archives; Area; Award; base; Bioinformatics; Biomedical Research; Budgets; Cancer Center; Cancer Center Support Grant; Cancer Hospital; Capillary Electrophoresis; Cells; Chemistry; Chromatin; Chromatin Structure; Commit; Complex; Copy Number Polymorphism; Core Facility; cost; cost effective; Data; Data Analyses; Data Quality; Detection; Development; digital; DNA; DNA Methylation; DNA Resequencing; DNA Sequence; Ensure; Equipment; Evaluation; Exons; experience; Faculty; Fees; Funding; Future; Gene Expression; Genes; Genetic Polymorphism; Genetic Transcription; Genome; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; genotyping technology; Goals; Grant; Growth; high throughput technology; Hour; Housing; Human; Human Resources; human tissue; Individual; Information Technology; Institutes; Institution; Investments; Laboratories; Malignant Neoplasms; Measures; medical schools; member; MicroRNAs; Microsatellite Repeats; mRNA Expression; neoplastic cell; new technology; next generation; Normal Cell; North Carolina; Paper; Patients; Peer Review; Positioning Attribute; Preparation; Price; rapid growth; Reading; Research; Research Personnel; Resources; RNA; RNA analysis; RNA Sequences; Sampling; Scientist; Services; single molecule; Site; SNP genotyping; Solid; success; Technology; technology development; The Cancer Genome Atlas; Time; Training; trait; tumor; Universities; Variant; Wages; Whole-Genome Shotgun Sequencing; Work\n",
      "38  abstracting; Alu Elements; Award; Beryllium; Bioinformatics; Biology; career; Computational Biology; cost; Data; Data Analyses; data management; Data Set; DNA; DNA Insertion Elements; DNA Sequence; Elements; Etiology; Evolution; Family; Genes; Genetic Markers; Genetic Polymorphism; Genetic Research; Genetic Variation; Genome; genome sequencing; Genomics; Genotype; Goals; Grant; Guanine + Cytosine Composition; Hereditary Disease; high throughput technology; Human; human disease; Human Genetics; Human Genome; indexing; Indium; Individual; insight; Institution; interest; Knowledge; L1 Elements; Libraries; Location; Mentors; Methods; next generation sequencing; novel; Organism; Phase; Population; Population Genetics; Primates; Procedures; Process; Property; Protocols documentation; Recording of previous events; Research; Research Personnel; Research Training; Resources; Sampling; Scanning; Site; Structure; Techniques; Technology; Time; tool; Training; transposon/insertion element; Variant; Writing\n",
      "39  Acute Myelocytic Leukemia; Address; Affect; Back; base; Blood capillaries; cancer therapy; capillary; Case-Control Studies; CCL18 gene; Cleaved cell; Clinical Data; cohort; Communities; Complex; cost; Coupled; Data; Data Element; design; Development; Disease; Disease susceptibility; DNA; DNA Resequencing; DNA Sequence; drug metabolism; Exercise; exome; Funding; Genes; Genetic; Genome; genome wide association study; Genomics; Glioblastoma; Grant; Head; Heart failure; Human; Human Resources; interest; Knowledge; Laboratories; Light; Liquid substance; Lung Adenocarcinoma; Malignant neoplasm of ovary; Malignant Neoplasms; Maps; Medical; member; Mental Retardation; Metabolic syndrome; Methods; Mutation; National Human Genome Research Institute; new technology; next generation; next generation sequencing; novel; novel strategies; Nucleotides; Pathway interactions; Pharmaceutical Preparations; Pharmacogenetics; Pharmacogenomics; Phase; Pilot Projects; Play; PPP3CA gene; Process; Production; protein structure; Qualifying; Reaction; Reading; Reporting; Research; Research Personnel; research study; response; Retinitis Pigmentosa; Robotics; Role; Sampling; Sequence Analysis; Services; Severities; Shotguns; Solutions; success; Syndrome; Targeted Resequencing; Technology; The Cancer Genome Atlas; trait; Universities; Update; Validation; Variant; Washington; Work\n",
      "40  Address; Adopted; Advisory Committees; Animal Model; anticancer research; Archives; Area; Award; base; Bioinformatics; Biomedical Research; Budgets; Cancer Center; Cancer Center Support Grant; Cancer Hospital; Capillary Electrophoresis; Cells; Chemistry; Chromatin; Chromatin Structure; Commit; Complex; Copy Number Polymorphism; Core Facility; cost; cost effective; Data; Data Analyses; Data Quality; Detection; Development; digital; DNA; DNA Methylation; DNA Resequencing; DNA Sequence; Ensure; Equipment; Evaluation; Exons; experience; Faculty; Fees; Funding; Future; Gene Expression; Genes; Genetic Polymorphism; Genetic Transcription; Genome; genome analysis; genome sequencing; genome wide association study; genome-wide; Genomics; Genotype; genotyping technology; Goals; Grant; Growth; high throughput technology; Hour; Housing; Human; Human Resources; human tissue; Individual; Information Technology; Institutes; Institution; Investments; Laboratories; Malignant Neoplasms; Measures; medical schools; member; MicroRNAs; Microsatellite Repeats; mRNA Expression; neoplastic cell; new technology; next generation; next generation sequencing; Normal Cell; North Carolina; Paper; Patients; Peer Review; Positioning Attribute; Preparation; Price; rapid growth; Reading; Research; Research Personnel; Resources; RNA analysis; RNA Sequences; Sampling; Scientist; Services; single molecule; Site; SNP genotyping; Solid; success; Technology; technology development; The Cancer Genome Atlas; Time; Training; trait; transcriptome sequencing; tumor; Universities; Variant; Wages; Whole-Genome Shotgun Sequencing; Work\n",
      "41  Address; Alcohol abuse; Alcohol consumption; Alcohol dependence; alcohol exposure; alcohol research; Alcohols; Alternative Splicing; Amygdaloid structure; Animal Model; Anterior; Autopsy; Award; base; Biological; Biological Process; Brain; Brain region; cDNA Arrays; Cell physiology; Chromosome Mapping; cingulate cortex; Classification; Clinical; Code; Collaborations; Complex; cost; Cromolyn Sodium; Data; Dependence; Detection; Diagnosis; DNA Microarray Chip; Dorsal; drug of abuse; drug reward; Event; functional group; Functional RNA; Gene Expression; Gene Expression Profile; Gene Structure; Genes; Genome; Genomics; Goals; Heavy Drinking; Human; Human body; human disease; human subject; human tissue; Indiana; Individual; innovation; interest; Kinetics; Knowledge; Life; Macaca; Medial; Mediating; Medical; Methodology; Methods; Microarray Analysis; Modeling; Molecular; Molecular Profiling; Mus; National Institute on Alcohol Abuse and Alcoholism; Neurosciences; new technology; next generation; next generation sequencing; novel; Outcome; Pathway Analysis; Pattern; Pilot Projects; Population; Prefrontal Cortex; Price; problem drinker; Property; Publishing; Reliance; Reporting; Research Personnel; research study; Reverse Transcriptase Polymerase Chain Reaction; Rewards; RNA; RNA Splicing; Rodent; Sampling; Signal Transduction; Single Nucleotide Polymorphism; Site; Small RNA; Systems Biology; Technology; Testing; tissue resource; Tissues; Transcript; transcriptome sequencing; Universities; Variant; Weight; Work\n",
      "42  Alabama; Applications Grants; Bioinformatics; Biotechnology; career; Characteristics; Clinical; Communities; Complex; Complex Genetic Trait; Consultations; Data; Data Analyses; Development; disability; Disease; Education; education evaluation; Educational process of instructing; Evaluation; experience; Faculty; Fees; Funding; Genetic; Genomics; Glean; graduate student; Human; Institutes; Instruction; Laboratories; Language; Lead; Learning; lectures; Location; meetings; Methods; Modification; Molecular; next generation sequencing; Participant; Postdoctoral Fellow; programs; public health relevance; Request for Proposals; Research; Research Personnel; Resources; responsible research conduct; Selection Criteria; Sequence Analysis; Series; Staging; Statistical Methods; Students; Susceptibility Gene; Technology; Training; trait; Universities; web site; Work\n",
      "43  base; Biological Models; Biological Process; Chromosome Mapping; Communities; comparative genomics; Complement; Computational Technique; Computer Simulation; Computer software; computerized tools; Computing Methodologies; cost effective; Data; Databases; design; Development; Developmental Biology; DNA; DNA Sequence; experimental analysis; Experimental Designs; Expressed Sequence Tags; Fishes; gene discovery; gene function; Gene Mutation; Genes; Genetic; genetic analysis; genetic manipulation; Genetic Markers; Genetic Recombination; Genetic Variation; genome sequencing; Genomics; human disease; Investigation; knowledge translation; Maps; Methods; Microsatellite Repeats; Modeling; Mutagenesis; mutant; Mutation; next generation sequencing; Phenotype; Population; positional cloning; Positioning Attribute; Protocols documentation; public health relevance; rapid technique; Relative (related person); research study; Sampling; Scanning; Siblings; Software Tools; Source; Statistical Methods; stem; System; Technology; Variant; web-accessible; Zebrafish; zebrafish genome\n",
      "44  Accounting; Advanced Malignant Neoplasm; Age at Menarche; Algorithms; anticancer research; base; Base Sequence; Biological Markers; cancer genetics; cancer prevention; cancer risk; cancer therapy; case control; cohort; Complex; Computer software; Data; Data Analyses; density; Diagnosis; Disease; disorder risk; drug discovery; Educational workshop; Environment; Environmental Exposure; Environmental Risk Factor; Epidemiologic Studies; epigenomics; Evaluation; Event; exome; exome sequencing; Family Study; Future; gene discovery; gene environment interaction; Genes; Genetic; Genetic Markers; Genetic Research; Genetic Risk; genetic variant; Genome; genome wide association study; Genomics; Goals; Health Sciences; Hereditary Disease; Heritability; Human Genetics; improved; Informatics; innovation; Instruction; Intervention; Leadership; malignant breast neoplasm; Malignant neoplasm of lung; Malignant Neoplasms; Mammography; Measurement; Mediating; Mediation; Medicine; Menopause; Methods; Modeling; Molecular; next generation sequencing; novel; Observational Study; Patients; Performance; Pharmacology; Play; population based; Prevention strategy; programs; Research Infrastructure; Research Personnel; Resources; Risk; Role; simulation; Smoking; Social Behavior; Statistical Computing; Statistical Methods; Technology; Testing; Time; trait; treatment strategy; tumor progression; user-friendly; Variant\n",
      "45  Alleles; Amniocentesis; analytical method; analytical tool; Aneuploidy; Anxiety; Apoptotic; Biological Assay; Blood Circulation; Cells; Chorionic villi; Chorionic Villi Sampling; Chromosomes, Human, Pair 13; clinical care; clinical Diagnosis; clinical practice; cohort; Collaborations; Communities; computer science; Computer software; cost; cost effective; Data; Data Analyses; Detection; Development; Diagnosis; Diagnostic Procedure; Diagnostics Research; Discipline of obstetrics; DNA; DNA Sequence; Down Syndrome; Economics; fetal; Fetal Diseases; Fetus; First Pregnancy Trimester; Genomics; Genotype; Goals; graphical user interface; Hereditary Disease; high throughput analysis; improved; Inherited; Karyotype; Laboratory Technicians; Methods; minimally invasive; Morbidity - disease rate; mortality; Mothers; next generation; next generation sequencing; Non-Invasive Cancer Detection; novel; Nucleic Acids; open source; Plasma; Positioning Attribute; Pregnancy; Pregnant Women; prenatal; Prenatal Diagnosis; prevent; Procedures; public health relevance; Publishing; Research; research study; Risk; RNA; Sampling; screening; Sensitivity and Specificity; Serum; Serum Proteins; Shotguns; Spontaneous abortion; statistics; Technology; Testing; tool; Translations; Ultrasonography; Work\n",
      "46  Adoption; Appointment; Base Pairing; Base Sequence; Binding Sites; Bioinformatics; Biological; Boxing; Calendar; cancer genetics; chromatin modification; Clinical; Comprehensive Cancer Center; computer science; computing resources; Consult; Consultations; Core Facility; cost; Custom; Data; Data Analyses; design; DNA; DNA Methylation; DNA Sequencing Facility; Engineering; Ensure; Epigenetic Process; Equipment; Experimental Designs; Faculty; flexibility; Gene Expression Profile; Genetic Research; Genome; genome-wide; Genomics; Goals; Gold; image processing; innovation; instrument; Laboratories; Libraries; Malignant Neoplasms; member; Memory; Molecular Biology; Molecular Genetics; Mutation; new technology; next generation sequencing; oncology; Partner in relationship; Preparation; Process; Protocols documentation; Quality Control; Reading; Research; Research Personnel; research study; Resource Sharing; Running; Sampling; Scheme; Sequence Alignment; Services; Sonication; structural genomics; Synapses; Targeted Resequencing; Technology; Time; transcription factor; Translations; Variant\n",
      "47  Address; Algorithms; base; Behavior; Binding; Biological; bisulfite; Cells; ChIP-seq; Chromatin; cofactor; Collaborations; Computer software; computerized tools; Computing Methodologies; cost; Cytosine; Data; Data Analyses; Data Files; data integration; Data Set; design; Development; DNA; DNA Methylation; Ensure; Epigenetic Process; epigenomics; Family; Future; Gene Expression; Genetic Transcription; genome-wide; Genomics; Goals; histone modification; Histones; Hypersensitivity; insight; Institutes; instrument; Linker DNA; Malignant Neoplasms; Methods; MicroRNAs; Modeling; Molecular Biology; Names; National Human Genome Research Institute; next generation sequencing; novel; Nucleosomes; Positioning Attribute; Process; programs; public health relevance; Reading; Research Personnel; research study; Resolution; Running; Sequence Analysis; Software Tools; Source; STAT1 gene; STAT3 gene; Statistical Methods; Technology; Thymine; tool; transcription factor; Transcriptional Regulation; transcriptome sequencing; United States National Institutes of Health; Variant; Work\n",
      "48  addiction; Age of Onset; Algorithms; Amyotrophic Lateral Sclerosis; Animal Model; base; Bioinformatics; Biological Assay; Biometry; Brain Stem; Candidate Disease Gene; career; career development; Cessation of life; Clinical; Code; cohort; Collaborations; Communities; Coupled; Cytoplasm; Data; Dementia; Development Plans; Disease; Disease Management; disease-causing mutation; DNA; effective therapy; exome; exome sequencing; Exons; experience; Familial Amyotrophic Lateral Sclerosis; Family; follow-up; Future; gene discovery; gene function; Gene Mutation; Genes; Genetic; Genetic Heterogeneity; genetic linkage analysis; genetic pedigree; Genetic Techniques; Genome; Genomics; Genotype; Goals; Human; Human Genetics; Human Genome; Incidence; Individual; Inherited; innovation; insight; Institution; Introns; Laboratories; Lead; Light; Mentors; Methods; Minority; Modeling; Molecular; Molecular Genetics; motor neuron degeneration; Motor Neurons; Mutation; Nerve Degeneration; Neurodegenerative Disorders; neurodevelopment; neurogenetics; Neurologic; Neurologist; Neuromuscular Diseases; Neuropharmacology; next generation sequencing; novel; novel strategies; Nuclear; palliation; Paralysed; Pathogenesis; Pathogenicity; Pathway interactions; Patients; Penetrance; proband; protein TDP-43; public health relevance; repository; Research; Research Personnel; Research Project Grants; Research Proposals; respiratory; Respiratory Failure; RNA Processing; RNA-Binding Proteins; Sampling; segregation; Spinal Cord; Symptoms; Techniques; Technology; Testing; therapeutic development; tissue culture; tool; Training; Universities; Variant; Washington; Work\n",
      "49  Address; Allelotyping; Area; Automation; base; Bioinformatics; Biological; Biology; Biomedical Research; ChIP-seq; Collaborations; Computer software; computerized tools; computing resources; cost; Data; Data Analyses; data mining; data reduction; Data Set; design; DNA Resequencing; Educational process of instructing; Educational workshop; Evaluation; experience; Experimental Designs; Funding; Future; Genome; genome sequencing; Genomics; Goals; Graph; Individual; Institution; Internet; Learning; Maps; Memory; Messenger RNA; next generation; next generation sequencing; novel; Operating System; Participant; Paste substance; Procedures; Programmed Learning; programs; public health relevance; Publications; Reading; Recipe; Research; Research Personnel; research study; Resources; Running; Sampling; Scientist; Sequence Analysis; skills; statistics; Students; System; Techniques; Technology; Thinking; tool; Training; transcriptome sequencing; transcriptomics; web services; Work\n"
     ]
    }
   ],
   "source": [
    "i = 0 \n",
    "j = 0\n",
    "try:\n",
    "    param = {\"offset\": i}  #offsets the page number of search results by amount i (start at page i of [total pages])\n",
    "    response = requests.get('https://api.federalreporter.nih.gov/v1/projects/search?query=text:next+generation+sequencing', params=param).json()  #following requests with page offset\n",
    "\n",
    "    for item in response['items']:\n",
    "        print(j, item['terms'])\n",
    "        j+=1\n",
    "        \n",
    "    i += 50\n",
    "    time.sleep(0.4)\n",
    "except:\n",
    "    pass"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"Advances in sequencing technology have dramatically shifted the way science is performed in many fields of Biology, which has also shifted the way education of the next generation of scientists must be conducted. However, the generation of sequencing data has been restricted to large laboratories, consortia of laboratories, and core sequencing facilities, limiting the exposure of undergraduates to these technologies. The recent introduction of benchtop next generation sequencing platforms promises to make moderately high throughput sequencing available to many individual research laboratories and smaller institutions. This Major Research Instrumentation grant supports the acquisition of an Ion Torrent Personal Genome Machine (Ion PGM) sequencing platform by Hope College. The Ion PGM will have significant impact on undergraduate research and training at Hope College by making affordable, high throughput sequencing capacity available to faculty and undergraduate researchers for use in established and emerging research and education programs. These programs include research focusing on: 1) the genome sequences of viruses that infect bacteria (Mycobacteriophage) that are discovered by first year college students as part of introductory biology laboratory courses; 2) long-term environmental studies of the local Lake Macatawa Watershed to identify and track microbial sources of contamination through whole genome sequencing of novel bacterial isolates; 3) advancing understanding of fundamental gene expression mechanisms of the mammalian parasite Giardia lamblia; 4) understanding phylogenetic and biogeographic relationships among maples found across the World; and 5) testing potential horizontal gene transfers of plastid genes between parasitic plants and their photosynthetic hosts. The projects advance scientific understanding of a wide range of biological and environmental problems that can be addressed through DNA sequencing at different scales. Each project will be made more effective by the in house availability of the Ion PGM, which is uniquely versatile in being able to generate sequence data at vastly different scales in a cost effective manner.<br/><br/>This sequencing platform will allow Hope College to effectively train undergraduates in the design of experiments requiring sequencing data; usage of next generation sequencing technology to generate necessary data; and analysis, interpretation, and dissemination of large scale data sets in both research laboratory and classroom laboratory settings. The Ion PGM will immediately enhance projects and programs that impact over 100 undergraduates during each academic year. First year students will be impacted through Hope College's highly successful yearlong course in phage genomics research, which is designed to retain high quality students in STEM fields. Students at all levels will participate in the research laboratories of the PI?s and their collaborators. Students in upper level Biology courses will use the technology in classroom laboratory-based research projects. Hope College?s established summer research programs will allow us to broaden exposure of students across the nation and of students from underrepresented groups in sciences in the use of leading edge sequencing technology. Faculty will be impacted through their ability to take advantage of next generation sequencing technology to advance projects into new and innovative areas and generate preliminary data for sustaining extramurally funded research programs. Student-faculty collaborative research will be disseminated to the scientific community through local, regional, and national/international scientific conferences and peer-reviewed publications and to the general public through community-based popular seminars. Sequence data will be deposited to appropriate openly accessible databases. Regional and national collaborators will use the Ion PGM, broadening its impact beyond Hope College to students in West Michigan and throughout the nation.\""
      ]
     },
     "execution_count": 133,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "response['items'][0]['abstract']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 95,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>keyterm</th>\n",
       "      <th>client_list_frequency</th>\n",
       "      <th>NIH_result_output</th>\n",
       "      <th>url</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>next generation sequencing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://api.federalreporter.nih.gov/v1/project...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>next-generation sequencing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://api.federalreporter.nih.gov/v1/project...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>gext gen sequencing</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>https://api.federalreporter.nih.gov/v1/project...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>next-gen sequencing</td>\n",
       "      <td>31</td>\n",
       "      <td>1778</td>\n",
       "      <td>https://api.federalreporter.nih.gov/v1/project...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>RNA sequencing</td>\n",
       "      <td>14</td>\n",
       "      <td>6953</td>\n",
       "      <td>https://api.federalreporter.nih.gov/v1/project...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      keyterm client_list_frequency NIH_result_output  \\\n",
       "0  next generation sequencing                   NaN               NaN   \n",
       "1  next-generation sequencing                   NaN               NaN   \n",
       "2         gext gen sequencing                   NaN               NaN   \n",
       "3         next-gen sequencing                    31              1778   \n",
       "4              RNA sequencing                    14              6953   \n",
       "\n",
       "                                                 url  \n",
       "0  https://api.federalreporter.nih.gov/v1/project...  \n",
       "1  https://api.federalreporter.nih.gov/v1/project...  \n",
       "2  https://api.federalreporter.nih.gov/v1/project...  \n",
       "3  https://api.federalreporter.nih.gov/v1/project...  \n",
       "4  https://api.federalreporter.nih.gov/v1/project...  "
      ]
     },
     "execution_count": 95,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "key_terms_df['url'] = url_list\n",
    "key_terms_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [],
   "source": [
    "# NIH query using key words from list\n",
    "# collect the following info \n",
    "\n",
    "key_words = []\n",
    "project_abstract = []\n",
    "project_title = []\n",
    "project_number = []\n",
    "project_start_date = []\n",
    "project_end_date = []\n",
    "department = []\n",
    "agency = []\n",
    "PI = []\n",
    "latitude = []\n",
    "longitude = []\n",
    "org_name = []\n",
    "org_city = []\n",
    "org_state = []\n",
    "org_zip = []\n",
    "org_country = []\n",
    "budget_start_date = []\n",
    "budget_end_date = []\n",
    "CFDA_code = []\n",
    "fiscal_year = []\n",
    "total_cost = []\n",
    "seed_term = []\n",
    "\n",
    "for url in url_list:\n",
    "    i = 0 \n",
    "    param = {\"offset\": i}  #offsets the page number of search results by amount i (start at page i of [total pages])\n",
    "    response = requests.get(url, params=param).json()  #following requests with page offset\n",
    "    \n",
    "    try:\n",
    "        for item in response['items']:\n",
    "            seed_term.append(url[66:])\n",
    "            key_words.append(item['terms'])\n",
    "            project_abstract.append(item['abstract'])\n",
    "            project_title.append(item['title'])\n",
    "            project_number.append(item['projectNumber'])\n",
    "            project_start_date.append(item['projectStartDate'])\n",
    "            project_end_date.append(item['projectEndDate'])\n",
    "            department.append(item['department'])                        \n",
    "            agency.append(item['agency'])                \n",
    "            PI.append(item['contactPi'])\n",
    "            latitude.append(item['latitude'])\n",
    "            longitude.append(item['longitude'])\n",
    "            org_name.append(item['orgName'])                 \n",
    "            org_city.append(item['orgCity'])\n",
    "            org_state.append(item['orgState'])                \n",
    "            org_zip.append(item['orgZipCode'])\n",
    "            org_country.append(item['orgCountry'])               \n",
    "            budget_start_date.append(item['projectStartDate'])               \n",
    "            budget_end_date.append(item['projectEndDate'])\n",
    "            CFDA_code.append(item['cfdaCode'])                      \n",
    "            fiscal_year.append(item['fy'])                       \n",
    "            total_cost.append(item['totalCostAmount'])\n",
    "\n",
    "        i += 50\n",
    "        time.sleep(0.4)\n",
    "        \n",
    "    except:\n",
    "        print(f\"No search results for {url}\")\n",
    "        pass\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2803"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(key_words)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 111,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Agency</th>\n",
       "      <th>Budget End Date</th>\n",
       "      <th>Budget Start Date</th>\n",
       "      <th>CFDA code</th>\n",
       "      <th>Department</th>\n",
       "      <th>Fiscal Year</th>\n",
       "      <th>Key Words</th>\n",
       "      <th>Latitude</th>\n",
       "      <th>Longitude</th>\n",
       "      <th>Organization City</th>\n",
       "      <th>...</th>\n",
       "      <th>Organization State</th>\n",
       "      <th>Organization ZIP</th>\n",
       "      <th>Principal Investigator</th>\n",
       "      <th>Project Abstract</th>\n",
       "      <th>Project End Date</th>\n",
       "      <th>Project Number</th>\n",
       "      <th>Project Start Date</th>\n",
       "      <th>Project Title</th>\n",
       "      <th>Seed Term</th>\n",
       "      <th>Total Cost</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2015-08-31T00:00:00</td>\n",
       "      <td>2012-09-01T00:00:00</td>\n",
       "      <td>47.074</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acer; Address; Area; Bacteria; Bacteriophages...</td>\n",
       "      <td>42.787172</td>\n",
       "      <td>-86.101102</td>\n",
       "      <td>HOLLAND</td>\n",
       "      <td>...</td>\n",
       "      <td>MI</td>\n",
       "      <td>49422-9000</td>\n",
       "      <td>BEST, AARON A</td>\n",
       "      <td>Advances in sequencing technology have dramati...</td>\n",
       "      <td>2015-08-31T00:00:00</td>\n",
       "      <td>1229585</td>\n",
       "      <td>2012-09-01T00:00:00</td>\n",
       "      <td>MRI: ACQUISITION OF A BENCHTOP NEXT GENERATION...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>171877.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2016-08-31T00:00:00</td>\n",
       "      <td>2012-09-21T00:00:00</td>\n",
       "      <td>847</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>base; Base Sequence; Biological Models; Biolo...</td>\n",
       "      <td>42.334978</td>\n",
       "      <td>-71.105987</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>021156110</td>\n",
       "      <td>GOESSLING, WOLFRAM</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The power...</td>\n",
       "      <td>2016-08-31T00:00:00</td>\n",
       "      <td>1R01DK095721-01</td>\n",
       "      <td>2012-09-21T00:00:00</td>\n",
       "      <td>MUTANT MAPPING AND IDENTIFICATION IN ZEBRAFISH...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>530443.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>NIH</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>base; Biological; Clinic; Collaborations; col...</td>\n",
       "      <td>44.055948</td>\n",
       "      <td>-92.525906</td>\n",
       "      <td>ROCHESTER</td>\n",
       "      <td>...</td>\n",
       "      <td>MN</td>\n",
       "      <td>559050001</td>\n",
       "      <td>WEINSHILBOUM, RICHARD M.</td>\n",
       "      <td>OVERALL SUMMARY AND SPECIFIC AIMS: NETWORK RES...</td>\n",
       "      <td>None</td>\n",
       "      <td>5U19GM061388-13 (7593)</td>\n",
       "      <td>None</td>\n",
       "      <td>NEXT GENERATION DNA SEQUENCING NETWORK RESOURCE</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>482387.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-10-31T00:00:00</td>\n",
       "      <td>2011-08-15T00:00:00</td>\n",
       "      <td>855</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Accounting; Affect; Africa South of the Sahar...</td>\n",
       "      <td>41.302711</td>\n",
       "      <td>-72.931986</td>\n",
       "      <td>NEW HAVEN</td>\n",
       "      <td>...</td>\n",
       "      <td>CT</td>\n",
       "      <td>065208327</td>\n",
       "      <td>CACCONE, ADALGISA</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Human Afr...</td>\n",
       "      <td>2013-10-31T00:00:00</td>\n",
       "      <td>5R21AI094615-02</td>\n",
       "      <td>2011-08-15T00:00:00</td>\n",
       "      <td>NEXT GENERATION SEQUENCING OF EAST AFRICAN TRY...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>209013.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NIH</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Address; Adopted; Advisory Committees; Animal...</td>\n",
       "      <td>35.366248</td>\n",
       "      <td>-79.429394</td>\n",
       "      <td>CHAPEL HILL</td>\n",
       "      <td>...</td>\n",
       "      <td>NC</td>\n",
       "      <td>275990001</td>\n",
       "      <td>MARZLUFF, WILLIAM F.</td>\n",
       "      <td>Next Generation Sequencing and Genotyping Core...</td>\n",
       "      <td>None</td>\n",
       "      <td>5P30CA016086-36 (8778)</td>\n",
       "      <td>None</td>\n",
       "      <td>NEXT GENERATION SEQUENCING AND GENOTYPING CORE...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>270636.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-03-05T00:00:00</td>\n",
       "      <td>2011-02-01T00:00:00</td>\n",
       "      <td>859</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Actinobacteria class; Anabolism; analog; Anti...</td>\n",
       "      <td>37.240049</td>\n",
       "      <td>-119.503236</td>\n",
       "      <td>LA JOLLA</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>920930934</td>\n",
       "      <td>BERNHARDT, PETER</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Actinomyc...</td>\n",
       "      <td>2012-03-05T00:00:00</td>\n",
       "      <td>5F32GM096711-02</td>\n",
       "      <td>2011-02-01T00:00:00</td>\n",
       "      <td>NEXT-GENERATION SEQUENCING AS A PLATFORM FOR A...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>8124.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2017-04-30T00:00:00</td>\n",
       "      <td>2012-08-09T00:00:00</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Adoption; Appointment; Base Pairing; Base Seq...</td>\n",
       "      <td>39.298737</td>\n",
       "      <td>-76.594342</td>\n",
       "      <td>BALTIMORE</td>\n",
       "      <td>...</td>\n",
       "      <td>MD</td>\n",
       "      <td>212051832</td>\n",
       "      <td>YEGNASUBRAMANIAN, SRINIVASAN</td>\n",
       "      <td>To maintain and build on the Sidney Kimmel Com...</td>\n",
       "      <td>2017-04-30T00:00:00</td>\n",
       "      <td>2P30CA006973-49 (5858)</td>\n",
       "      <td>2012-08-09T00:00:00</td>\n",
       "      <td>NEXT GENERATION SEQUENCING</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>229477.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-06-30T00:00:00</td>\n",
       "      <td>2010-07-15T00:00:00</td>\n",
       "      <td>859</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute Myelocytic Leukemia; Address; Affect; B...</td>\n",
       "      <td>38.648424</td>\n",
       "      <td>-90.309068</td>\n",
       "      <td>SAINT LOUIS</td>\n",
       "      <td>...</td>\n",
       "      <td>MO</td>\n",
       "      <td>631304862</td>\n",
       "      <td>MARDIS, ELAINE R</td>\n",
       "      <td>Pharmacogenomics began with a focus on the fun...</td>\n",
       "      <td>2015-06-30T00:00:00</td>\n",
       "      <td>5U01GM097119-03</td>\n",
       "      <td>2010-07-15T00:00:00</td>\n",
       "      <td>NEXT GENERATION SEQUENCING ADD-ON-PHARMACOGENO...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>572671.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>NIH</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Address; Adopted; Advisory Committees; Animal...</td>\n",
       "      <td>35.366248</td>\n",
       "      <td>-79.429394</td>\n",
       "      <td>CHAPEL HILL</td>\n",
       "      <td>...</td>\n",
       "      <td>NC</td>\n",
       "      <td>275990001</td>\n",
       "      <td>MARZLUFF, WILLIAM F.</td>\n",
       "      <td>Next Generation Sequencing and Genotyping Core...</td>\n",
       "      <td>None</td>\n",
       "      <td>3P30CA016086-36S1 (8778)</td>\n",
       "      <td>None</td>\n",
       "      <td>NEXT GENERATION SEQUENCING AND GENOTYPING CORE...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>2552.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-02-28T00:00:00</td>\n",
       "      <td>2010-09-26T00:00:00</td>\n",
       "      <td>172</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>abstracting; Alu Elements; Award; Beryllium; ...</td>\n",
       "      <td>40.481906</td>\n",
       "      <td>-74.457066</td>\n",
       "      <td>PISCATAWAY</td>\n",
       "      <td>...</td>\n",
       "      <td>NJ</td>\n",
       "      <td>088543925</td>\n",
       "      <td>XING, JINCHUAN</td>\n",
       "      <td>Project Summary/Abstract Mobile DNA elements a...</td>\n",
       "      <td>2015-02-28T00:00:00</td>\n",
       "      <td>4R00HG005846-03</td>\n",
       "      <td>2010-09-26T00:00:00</td>\n",
       "      <td>HIGH-THROUGHPUT MOBILE ELEMENT GENOTYPING USIN...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>249000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>2011-08-23T00:00:00</td>\n",
       "      <td>172</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Address; Allelotyping; Automation; base; Bioi...</td>\n",
       "      <td>42.748478</td>\n",
       "      <td>-84.483276</td>\n",
       "      <td>EAST LANSING</td>\n",
       "      <td>...</td>\n",
       "      <td>MI</td>\n",
       "      <td>488242600</td>\n",
       "      <td>BROWN, C. TITUS</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Modern bi...</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>5R25HG006243-02</td>\n",
       "      <td>2011-08-23T00:00:00</td>\n",
       "      <td>ANALYZING NEXT-GENERATION SEQUENCING DATA</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>53653.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-08-31T00:00:00</td>\n",
       "      <td>2011-09-01T00:00:00</td>\n",
       "      <td>395</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Adopted; anticancer research; Automobile Driv...</td>\n",
       "      <td>38.648424</td>\n",
       "      <td>-90.309068</td>\n",
       "      <td>SAINT LOUIS</td>\n",
       "      <td>...</td>\n",
       "      <td>MO</td>\n",
       "      <td>631304862</td>\n",
       "      <td>MAHER, CHRISTOPHER A</td>\n",
       "      <td>PROJECT SUMMARY/ABSTRACT The impact of high-th...</td>\n",
       "      <td>2014-08-31T00:00:00</td>\n",
       "      <td>5R00CA149182-04</td>\n",
       "      <td>2011-09-01T00:00:00</td>\n",
       "      <td>CHARACTERIZATION OF CANCER TRANSCRIPTOMES USIN...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>231830.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2016-07-31T00:00:00</td>\n",
       "      <td>2012-08-15T00:00:00</td>\n",
       "      <td>47.049</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2012</td>\n",
       "      <td>Algorithms; analytical method; base; biodefen...</td>\n",
       "      <td>40.092617</td>\n",
       "      <td>-88.247723</td>\n",
       "      <td>CHAMPAIGN</td>\n",
       "      <td>...</td>\n",
       "      <td>IL</td>\n",
       "      <td>61820-7473</td>\n",
       "      <td>MA, PING</td>\n",
       "      <td>Recently, the emerging new field of metagenomi...</td>\n",
       "      <td>2016-07-31T00:00:00</td>\n",
       "      <td>1222718</td>\n",
       "      <td>2012-08-15T00:00:00</td>\n",
       "      <td>COLLABORATIVE RESEARCH: ATD: INTEGRATED STATIS...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>372098.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2016-07-31T00:00:00</td>\n",
       "      <td>2012-08-15T00:00:00</td>\n",
       "      <td>47.049</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2012</td>\n",
       "      <td>Algorithms; analytical method; base; biodefen...</td>\n",
       "      <td>33.968143</td>\n",
       "      <td>-117.335853</td>\n",
       "      <td>RIVERSIDE</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>92521-1000</td>\n",
       "      <td>CUI, XINPING</td>\n",
       "      <td>Recently, the emerging new field of metagenomi...</td>\n",
       "      <td>2016-07-31T00:00:00</td>\n",
       "      <td>1223107</td>\n",
       "      <td>2012-08-15T00:00:00</td>\n",
       "      <td>COLLABORATIVE RESEARCH: ATD: INTEGRATED STATIS...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>532114.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-02-28T00:00:00</td>\n",
       "      <td>2010-06-01T00:00:00</td>\n",
       "      <td>172</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Address; Algorithms; base; Behavior; Binding;...</td>\n",
       "      <td>42.336250</td>\n",
       "      <td>-71.070668</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>021182340</td>\n",
       "      <td>JOHNSON, WILLIAM EVAN</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Next-gene...</td>\n",
       "      <td>2015-02-28T00:00:00</td>\n",
       "      <td>7R01HG005692-03</td>\n",
       "      <td>2010-06-01T00:00:00</td>\n",
       "      <td>STATISTICAL TOOLS AND METHODS FOR NEXT-GENERAT...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>336105.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>2009-09-01T00:00:00</td>\n",
       "      <td>47.074</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2009</td>\n",
       "      <td>Achievement; Bacteria; base; Bioinformatics; ...</td>\n",
       "      <td>30.605842</td>\n",
       "      <td>-96.368935</td>\n",
       "      <td>COLLEGE STATION</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>77845-0000</td>\n",
       "      <td>DICKMAN, MARTIN B</td>\n",
       "      <td>During the past 10 years, there has been a maj...</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>0923502</td>\n",
       "      <td>2009-09-01T00:00:00</td>\n",
       "      <td>MRI: ACQUISITION OF A ROCHE 454 FLX PYROSEQUEN...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>612019.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>2009-09-01T00:00:00</td>\n",
       "      <td>47.074</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2009</td>\n",
       "      <td>Actinium; Address; Bioinformatics; Collection...</td>\n",
       "      <td>40.477702</td>\n",
       "      <td>-74.425495</td>\n",
       "      <td>NEW BRUNSWICK</td>\n",
       "      <td>...</td>\n",
       "      <td>NJ</td>\n",
       "      <td>08901-8559</td>\n",
       "      <td>DOONER, HUGO K</td>\n",
       "      <td>PI: Hugo K. Dooner (Rutgers University)&lt;br/&gt;Co...</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>0923950</td>\n",
       "      <td>2009-09-01T00:00:00</td>\n",
       "      <td>FACILE PRODUCTION AND EFFICIENT INDEXING OF TR...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>1242967.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2014-08-31T00:00:00</td>\n",
       "      <td>2011-09-01T00:00:00</td>\n",
       "      <td>47.050</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2011</td>\n",
       "      <td>Address; Animals; Area; Award; base; Biodiver...</td>\n",
       "      <td>41.808431</td>\n",
       "      <td>-72.249523</td>\n",
       "      <td>STORRS</td>\n",
       "      <td>...</td>\n",
       "      <td>CT</td>\n",
       "      <td>06269-1133</td>\n",
       "      <td>MCMANUS, GEORGE B</td>\n",
       "      <td>The Ocean's biomass and diversity are predomin...</td>\n",
       "      <td>2014-08-31T00:00:00</td>\n",
       "      <td>1130033</td>\n",
       "      <td>2011-09-01T00:00:00</td>\n",
       "      <td>COLLABORATIVE RESEARCH: DIVERSITY AND DYNAMICS...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>408830.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2014-08-31T00:00:00</td>\n",
       "      <td>2011-09-01T00:00:00</td>\n",
       "      <td>47.050</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2011</td>\n",
       "      <td>Address; Animals; Area; Award; base; Biodiver...</td>\n",
       "      <td>42.317789</td>\n",
       "      <td>-72.635903</td>\n",
       "      <td>NORTHAMPTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>01063-6304</td>\n",
       "      <td>KATZ, LAURA A</td>\n",
       "      <td>The Ocean's biomass and diversity are predomin...</td>\n",
       "      <td>2014-08-31T00:00:00</td>\n",
       "      <td>1129734</td>\n",
       "      <td>2011-09-01T00:00:00</td>\n",
       "      <td>COLLABORATIVE RESEARCH: DIVERSITY AND DYNAMICS...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>421638.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2011-09-30T00:00:00</td>\n",
       "      <td>2010-10-15T00:00:00</td>\n",
       "      <td>47.074</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2011</td>\n",
       "      <td>Area; Basic Science; Biotechnology; Computing...</td>\n",
       "      <td>32.832811</td>\n",
       "      <td>-117.271272</td>\n",
       "      <td>LA JOLLA</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>92093-0210</td>\n",
       "      <td>BARTLETT, DOUGLAS H</td>\n",
       "      <td>This grant will support a workshop focused on ...</td>\n",
       "      <td>2011-09-30T00:00:00</td>\n",
       "      <td>1068643</td>\n",
       "      <td>2010-10-15T00:00:00</td>\n",
       "      <td>US-EC WORKSHOP ON MARINE GENOMICS: NEXT GENERA...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>25000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2011-07-31T00:00:00</td>\n",
       "      <td>2009-08-01T00:00:00</td>\n",
       "      <td>279</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2009</td>\n",
       "      <td>Address; Anodes; Area; base; Base Pairing; Ba...</td>\n",
       "      <td>29.673047</td>\n",
       "      <td>-95.413789</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770545029</td>\n",
       "      <td>GAO, XIAOLIAN</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  This p...</td>\n",
       "      <td>2011-07-31T00:00:00</td>\n",
       "      <td>1R41DA029169-01</td>\n",
       "      <td>2009-08-01T00:00:00</td>\n",
       "      <td>LONG READ NEXT GENERATION SEQUENCING TECHNOLOG...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>277737.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2011-06-30T00:00:00</td>\n",
       "      <td>2009-09-22T00:00:00</td>\n",
       "      <td>701</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2009</td>\n",
       "      <td>Address; Algorithms; Area; Attention; base; B...</td>\n",
       "      <td>42.335814</td>\n",
       "      <td>-71.105033</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>021156027</td>\n",
       "      <td>PARK, PETER J</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  This a...</td>\n",
       "      <td>2011-06-30T00:00:00</td>\n",
       "      <td>1RC1HG005482-01</td>\n",
       "      <td>2009-09-22T00:00:00</td>\n",
       "      <td>STATISTICAL METHODS FOR ESTIMATION OF COPY NUM...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>397116.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2011-08-31T00:00:00</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>701</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2009</td>\n",
       "      <td>Accounting; Adult; Affect; African American; ...</td>\n",
       "      <td>29.703025</td>\n",
       "      <td>-95.403303</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>77030</td>\n",
       "      <td>HIXSON, JAMES E.</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  This p...</td>\n",
       "      <td>2011-08-31T00:00:00</td>\n",
       "      <td>1RC2HG005697-01</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>NEXT-GENERATION MEDICAL RESEQUENCING OF GOUT D...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>1317671.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2011-08-31T00:00:00</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>701</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2009</td>\n",
       "      <td>Algorithms; American; anticancer research; At...</td>\n",
       "      <td>42.337854</td>\n",
       "      <td>-71.108326</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>022155450</td>\n",
       "      <td>MEYERSON, MATTHEW L.</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Our goa...</td>\n",
       "      <td>2011-08-31T00:00:00</td>\n",
       "      <td>1RC2CA148317-01</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>AN INFRASTRUCTURE FOR CANCER VIRUS DISCOVERY F...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>765137.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-07-31T00:00:00</td>\n",
       "      <td>2009-08-01T00:00:00</td>\n",
       "      <td>279</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2010</td>\n",
       "      <td>Address; Anodes; Area; base; Base Pairing; Ba...</td>\n",
       "      <td>29.673047</td>\n",
       "      <td>-95.413789</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770545029</td>\n",
       "      <td>GAO, XIAOLIAN</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  This p...</td>\n",
       "      <td>2012-07-31T00:00:00</td>\n",
       "      <td>5R41DA029169-02</td>\n",
       "      <td>2009-08-01T00:00:00</td>\n",
       "      <td>LONG READ NEXT GENERATION SEQUENCING TECHNOLOG...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>294692.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-07-31T00:00:00</td>\n",
       "      <td>2010-08-19T00:00:00</td>\n",
       "      <td>394</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2010</td>\n",
       "      <td>Address; Area; base; Behavior; Biological Ass...</td>\n",
       "      <td>37.430351</td>\n",
       "      <td>-122.178210</td>\n",
       "      <td>STANFORD</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>943041222</td>\n",
       "      <td>JI, HANLEE P</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Creatin...</td>\n",
       "      <td>2012-07-31T00:00:00</td>\n",
       "      <td>1R21CA140089-01A1</td>\n",
       "      <td>2010-08-19T00:00:00</td>\n",
       "      <td>MUTATION ANALYSIS OF PARAFFIN-EMBEDDED TUMORS ...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>208800.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-06-30T00:00:00</td>\n",
       "      <td>2010-07-01T00:00:00</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2010</td>\n",
       "      <td>Arts; base; Biological; Clinic; Collaboration...</td>\n",
       "      <td>44.055948</td>\n",
       "      <td>-92.525906</td>\n",
       "      <td>ROCHESTER</td>\n",
       "      <td>...</td>\n",
       "      <td>MN</td>\n",
       "      <td>559050001</td>\n",
       "      <td>WEINSHILBOUM, RICHARD M.</td>\n",
       "      <td>OVERALL SUMMARY AND SPECIFIC AIMS: NETWORK RES...</td>\n",
       "      <td>2015-06-30T00:00:00</td>\n",
       "      <td>2U19GM061388-11 (7593)</td>\n",
       "      <td>2010-07-01T00:00:00</td>\n",
       "      <td>NEXT GENERATION DNA SEQUENCING NETWORK RESOURCE</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>519037.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-06-30T00:00:00</td>\n",
       "      <td>2009-09-22T00:00:00</td>\n",
       "      <td>701</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2010</td>\n",
       "      <td>Address; Algorithms; Area; Attention; base; B...</td>\n",
       "      <td>42.335814</td>\n",
       "      <td>-71.105033</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>021156027</td>\n",
       "      <td>PARK, PETER J</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  This a...</td>\n",
       "      <td>2012-06-30T00:00:00</td>\n",
       "      <td>5RC1HG005482-02</td>\n",
       "      <td>2009-09-22T00:00:00</td>\n",
       "      <td>STATISTICAL METHODS FOR ESTIMATION OF COPY NUM...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>376168.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>701</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2010</td>\n",
       "      <td>Algorithms; American; anticancer research; At...</td>\n",
       "      <td>42.337854</td>\n",
       "      <td>-71.108326</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>022155450</td>\n",
       "      <td>MEYERSON, MATTHEW L.</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Our goa...</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>5RC2CA148317-02</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>AN INFRASTRUCTURE FOR CANCER VIRUS DISCOVERY F...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>786413.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>701</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2010</td>\n",
       "      <td>Accounting; Adult; Affect; African American; ...</td>\n",
       "      <td>29.703025</td>\n",
       "      <td>-95.403303</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>77030</td>\n",
       "      <td>HIXSON, JAMES E.</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  This p...</td>\n",
       "      <td>2012-08-31T00:00:00</td>\n",
       "      <td>5RC2HG005697-02</td>\n",
       "      <td>2009-09-30T00:00:00</td>\n",
       "      <td>NEXT-GENERATION MEDICAL RESEQUENCING OF GOUT D...</td>\n",
       "      <td>next+generation+sequencing</td>\n",
       "      <td>1448896.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2773</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-06-30T00:00:00</td>\n",
       "      <td>2009-09-14T00:00:00</td>\n",
       "      <td>398</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute Myelocytic Leukemia; Adverse event; AMD...</td>\n",
       "      <td>38.648424</td>\n",
       "      <td>-90.309068</td>\n",
       "      <td>SAINT LOUIS</td>\n",
       "      <td>...</td>\n",
       "      <td>MO</td>\n",
       "      <td>631304862</td>\n",
       "      <td>UY, GEOFFREY L</td>\n",
       "      <td>DESCRIPTION (provided by applicant): This care...</td>\n",
       "      <td>2014-06-30T00:00:00</td>\n",
       "      <td>5K23CA140707-04</td>\n",
       "      <td>2009-09-14T00:00:00</td>\n",
       "      <td>TARGETING LEUKEMIA STROMAL INTERACTIONS IN AML</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>158853.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2774</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-08-31T00:00:00</td>\n",
       "      <td>2010-09-03T00:00:00</td>\n",
       "      <td>398</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>1-Phosphatidylinositol 3-Kinase; Acute Myeloc...</td>\n",
       "      <td>39.952982</td>\n",
       "      <td>-75.192768</td>\n",
       "      <td>PHILADELPHIA</td>\n",
       "      <td>...</td>\n",
       "      <td>PA</td>\n",
       "      <td>191046205</td>\n",
       "      <td>PERL, ALEXANDER E.</td>\n",
       "      <td>DESCRIPTION (provided by applicant): AML is a ...</td>\n",
       "      <td>2015-08-31T00:00:00</td>\n",
       "      <td>5K23CA141054-03</td>\n",
       "      <td>2010-09-03T00:00:00</td>\n",
       "      <td>MTOR INHIBITION AS A THERAPEUTIC STRATEGY FOR ...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>172368.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2775</th>\n",
       "      <td>NSF</td>\n",
       "      <td>2012-12-31T00:00:00</td>\n",
       "      <td>2012-01-01T00:00:00</td>\n",
       "      <td>47.041</td>\n",
       "      <td>NSF</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute leukemia; Adult; adult leukemia; Cell C...</td>\n",
       "      <td>45.670519</td>\n",
       "      <td>-111.065608</td>\n",
       "      <td>BOZEMAN</td>\n",
       "      <td>...</td>\n",
       "      <td>MT</td>\n",
       "      <td>59718-4012</td>\n",
       "      <td>NAGY, JON O</td>\n",
       "      <td>This Small Business Innovation Research (SBIR)...</td>\n",
       "      <td>2012-12-31T00:00:00</td>\n",
       "      <td>1143342</td>\n",
       "      <td>2012-01-01T00:00:00</td>\n",
       "      <td>SBIR PHASE I: TARGETED NANOPARTICLE DELIVERY A...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>164848.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2776</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-01-31T00:00:00</td>\n",
       "      <td>2009-04-20T00:00:00</td>\n",
       "      <td>393</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute; Acute leukemia; Acute Lymphocytic Leuk...</td>\n",
       "      <td>36.059402</td>\n",
       "      <td>-80.321981</td>\n",
       "      <td>WINSTON-SALEM</td>\n",
       "      <td>...</td>\n",
       "      <td>NC</td>\n",
       "      <td>271570001</td>\n",
       "      <td>ORNELLES, DAVID ARNOLD</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Acute leu...</td>\n",
       "      <td>2014-01-31T00:00:00</td>\n",
       "      <td>5R01CA127621-04</td>\n",
       "      <td>2009-04-20T00:00:00</td>\n",
       "      <td>PRENATAL ADENOVIRUS INFECTION, INHIBITION OF D...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>409936.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2777</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>2008-05-01T00:00:00</td>\n",
       "      <td>394</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute leukemia; Acute Promyelocytic Leukemia;...</td>\n",
       "      <td>29.681814</td>\n",
       "      <td>-82.345358</td>\n",
       "      <td>GAINESVILLE</td>\n",
       "      <td>...</td>\n",
       "      <td>FL</td>\n",
       "      <td>326115500</td>\n",
       "      <td>LI, YING</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Today, mi...</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>5R01CA129311-05</td>\n",
       "      <td>2008-05-01T00:00:00</td>\n",
       "      <td>APTAMER BASED TECHNOLOGY FOR MOLECULAR ANALYSI...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>294868.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2778</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-12-31T00:00:00</td>\n",
       "      <td>2009-01-01T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Accounting; adult leukemia; Age; aged; Antige...</td>\n",
       "      <td>40.066768</td>\n",
       "      <td>-75.092750</td>\n",
       "      <td>PHILADELPHIA</td>\n",
       "      <td>...</td>\n",
       "      <td>PA</td>\n",
       "      <td>191112434</td>\n",
       "      <td>HAYAKAWA, KYOKO</td>\n",
       "      <td>SummaryB CLL (B cell chronic lymphocytic leuke...</td>\n",
       "      <td>2013-12-31T00:00:00</td>\n",
       "      <td>5R01CA129330-04</td>\n",
       "      <td>2009-01-01T00:00:00</td>\n",
       "      <td>ORIGIN OF CD5+ B CELL LYMPHOMA/LEUKEMIA IN MICE</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>351225.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2779</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-01-31T00:00:00</td>\n",
       "      <td>2008-04-01T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Accounting; Acute Lymphocytic Leukemia; Acute...</td>\n",
       "      <td>40.841253</td>\n",
       "      <td>-73.940404</td>\n",
       "      <td>NEW YORK</td>\n",
       "      <td>...</td>\n",
       "      <td>NY</td>\n",
       "      <td>100323702</td>\n",
       "      <td>FERRANDO, ADOLFO A.</td>\n",
       "      <td>The role of AKT signaling in NOTCH1-induced le...</td>\n",
       "      <td>2014-01-31T00:00:00</td>\n",
       "      <td>5R01CA129382-05</td>\n",
       "      <td>2008-04-01T00:00:00</td>\n",
       "      <td>THE ROLE OF AKT SIGNALING IN NOTCH1 INDUCED LE...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>324613.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2780</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>2009-04-06T00:00:00</td>\n",
       "      <td>839</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute leukemia; Adhesions; Apoptosis; base; b...</td>\n",
       "      <td>39.140663</td>\n",
       "      <td>-84.501007</td>\n",
       "      <td>CINCINNATI</td>\n",
       "      <td>...</td>\n",
       "      <td>OH</td>\n",
       "      <td>452293039</td>\n",
       "      <td>CANCELAS, JOSE A</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Rac GTPas...</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>5R01HL087159-04</td>\n",
       "      <td>2009-04-06T00:00:00</td>\n",
       "      <td>RAC GTPASE INHIBITION IN CHRONIC MYELOGENOUS L...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>371250.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2781</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-06-30T00:00:00</td>\n",
       "      <td>2012-07-20T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Accounting; Address; Adult; Animals; Biologic...</td>\n",
       "      <td>40.444095</td>\n",
       "      <td>-79.956899</td>\n",
       "      <td>PITTSBURGH</td>\n",
       "      <td>...</td>\n",
       "      <td>PA</td>\n",
       "      <td>152132303</td>\n",
       "      <td>WANG, QINGDE</td>\n",
       "      <td>DESCRIPTION (provided by applicant): This proj...</td>\n",
       "      <td>2014-06-30T00:00:00</td>\n",
       "      <td>1R21CA158650-01A1</td>\n",
       "      <td>2012-07-20T00:00:00</td>\n",
       "      <td>FUNCTION OF ADAR1 IN HEMATOPOIETIC AND LEUKEMI...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>196729.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2782</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-04-30T00:00:00</td>\n",
       "      <td>2012-05-15T00:00:00</td>\n",
       "      <td>394</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Abnormal Cell; Acute Myelocytic Leukemia; Aff...</td>\n",
       "      <td>41.502739</td>\n",
       "      <td>-81.607334</td>\n",
       "      <td>CLEVELAND</td>\n",
       "      <td>...</td>\n",
       "      <td>OH</td>\n",
       "      <td>441061712</td>\n",
       "      <td>JACOBBERGER, JAMES WILLIAM</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The long ...</td>\n",
       "      <td>2014-04-30T00:00:00</td>\n",
       "      <td>1R21CA158659-01A1</td>\n",
       "      <td>2012-05-15T00:00:00</td>\n",
       "      <td>CELL SIGNALING AS A LEUKEMIA BIOMARKER</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>204885.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2783</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-03-31T00:00:00</td>\n",
       "      <td>2012-04-01T00:00:00</td>\n",
       "      <td>395</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Ablation; Acute Myelocytic Leukemia; addictio...</td>\n",
       "      <td>40.764910</td>\n",
       "      <td>-73.955055</td>\n",
       "      <td>NEW YORK</td>\n",
       "      <td>...</td>\n",
       "      <td>NY</td>\n",
       "      <td>100654805</td>\n",
       "      <td>GUZMAN, MONICA L</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Acute mye...</td>\n",
       "      <td>2014-03-31T00:00:00</td>\n",
       "      <td>1R21CA158728-01A1</td>\n",
       "      <td>2012-04-01T00:00:00</td>\n",
       "      <td>A ROLE FOR ELEVATED AUTOPHAGY IN SURVIVAL AND ...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>220545.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2784</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>2012-03-01T00:00:00</td>\n",
       "      <td>394</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute; Acute leukemia; Acute Lymphocytic Leuk...</td>\n",
       "      <td>47.628707</td>\n",
       "      <td>-122.330795</td>\n",
       "      <td>SEATTLE</td>\n",
       "      <td>...</td>\n",
       "      <td>WA</td>\n",
       "      <td>981094433</td>\n",
       "      <td>BEDALOV, ANTONIO</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The goal ...</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>1R21CA164545-01</td>\n",
       "      <td>2012-03-01T00:00:00</td>\n",
       "      <td>PROTEIN BIOMARKERS IN CHILDHOOD ACUTE MYELOID ...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>245687.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2785</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2017-08-31T00:00:00</td>\n",
       "      <td>2012-09-18T00:00:00</td>\n",
       "      <td>398</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acceleration; Activator Appliances; Acute leu...</td>\n",
       "      <td>34.065915</td>\n",
       "      <td>-118.196446</td>\n",
       "      <td>LOS ANGELES</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>900339263</td>\n",
       "      <td>MERCHANT, AKIL</td>\n",
       "      <td>DESCRIPTION (provided by applicant): This prop...</td>\n",
       "      <td>2017-08-31T00:00:00</td>\n",
       "      <td>1K08CA154975-01A1</td>\n",
       "      <td>2012-09-18T00:00:00</td>\n",
       "      <td>THE ROLE OF HEDGEHOG/GLI IN NORMAL HEMATOPOIES...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>175824.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2786</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>2003-08-05T00:00:00</td>\n",
       "      <td>397</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>abstracting; Acute Myelocytic Leukemia; Area;...</td>\n",
       "      <td>29.706319</td>\n",
       "      <td>-95.397195</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770304009</td>\n",
       "      <td>KANTARJIAN, HAGOP</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The Unive...</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>5P50CA100632-10</td>\n",
       "      <td>2003-08-05T00:00:00</td>\n",
       "      <td>UNIVERSITY OF TEXAS M.D. ANDERSON CANCER CENTE...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>2300000.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2787</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Adoptive Cell Transfers; Affinity; Agonist; A...</td>\n",
       "      <td>29.706319</td>\n",
       "      <td>-95.397195</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770304009</td>\n",
       "      <td>MOLLDREM, JEFFREY J</td>\n",
       "      <td>There is increasing evidence that lymphocytes ...</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>5P50CA100632-10 (0002)</td>\n",
       "      <td>None</td>\n",
       "      <td>ADOPTIVE CELLULAR THERAPY FOR MYELOID LEUKEMIA</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>234003.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2788</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>Acute Myelocytic Leukemia; Affinity; Aftercar...</td>\n",
       "      <td>29.706319</td>\n",
       "      <td>-95.397195</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770304009</td>\n",
       "      <td>ANDREEFF, MICHAEL</td>\n",
       "      <td>The main therapeutic challenge in the treatmen...</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>5P50CA100632-10 (0003)</td>\n",
       "      <td>None</td>\n",
       "      <td>P53 ACTIVATION AS NOVEL THERAPEUTIC STRATGEY F...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>221325.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2789</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>None</td>\n",
       "      <td>None</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2012</td>\n",
       "      <td>3-Dimensional; abstracting; Achievement; acti...</td>\n",
       "      <td>29.706319</td>\n",
       "      <td>-95.397195</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770304009</td>\n",
       "      <td>PLUNKETT, WILLIAM K</td>\n",
       "      <td>Effective therapies for acute leukemias have b...</td>\n",
       "      <td>2013-08-31T00:00:00</td>\n",
       "      <td>5P50CA100632-10 (0005)</td>\n",
       "      <td>None</td>\n",
       "      <td>DEVELOPMENT OF SAPACITABINE THERAPY IN LEUKEMIAS</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>188182.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2790</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-12-31T00:00:00</td>\n",
       "      <td>2010-02-05T00:00:00</td>\n",
       "      <td>242</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>8 year old; Acute; Acute Lymphocytic Leukemia...</td>\n",
       "      <td>35.150278</td>\n",
       "      <td>-90.041851</td>\n",
       "      <td>MEMPHIS</td>\n",
       "      <td>...</td>\n",
       "      <td>TN</td>\n",
       "      <td>381053678</td>\n",
       "      <td>KRULL, KEVIN R</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  Surviv...</td>\n",
       "      <td>2014-12-31T00:00:00</td>\n",
       "      <td>5R01MH085849-02</td>\n",
       "      <td>2010-02-05T00:00:00</td>\n",
       "      <td>RISK FOR PSYCHOPATHOLOGY AND NEUROCOGNITIVE IM...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>499368.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2791</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-01-31T00:00:00</td>\n",
       "      <td>2010-02-09T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>1-Phosphatidylinositol 3-Kinase; Acute Myeloc...</td>\n",
       "      <td>32.635016</td>\n",
       "      <td>-86.809379</td>\n",
       "      <td>BIRMINGHAM</td>\n",
       "      <td>...</td>\n",
       "      <td>AL</td>\n",
       "      <td>352940001</td>\n",
       "      <td>KLUG, CHRISTOPHER A</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Constit...</td>\n",
       "      <td>2015-01-31T00:00:00</td>\n",
       "      <td>5R01CA144248-02</td>\n",
       "      <td>2010-02-09T00:00:00</td>\n",
       "      <td>ROLE OF NF-KB IN HEMATOPOIETIC STEM CELLS AND ...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>294868.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2792</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-12-31T00:00:00</td>\n",
       "      <td>2011-02-01T00:00:00</td>\n",
       "      <td>395</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Acute Lymphocytic Leukemia; Address; Affect; ...</td>\n",
       "      <td>29.706319</td>\n",
       "      <td>-95.397195</td>\n",
       "      <td>HOUSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>TX</td>\n",
       "      <td>770304009</td>\n",
       "      <td>KONOPLEVA, MARINA Y</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The mai...</td>\n",
       "      <td>2015-12-31T00:00:00</td>\n",
       "      <td>1R01CA155056-01</td>\n",
       "      <td>2011-02-01T00:00:00</td>\n",
       "      <td>TARGETING HYPOXIC MICROENVIRONMENT IN ACUTE LY...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>341354.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2793</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2012-02-29T00:00:00</td>\n",
       "      <td>2009-03-01T00:00:00</td>\n",
       "      <td>839</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Address; Blood; CD34 gene; Cell Differentiati...</td>\n",
       "      <td>41.302711</td>\n",
       "      <td>-72.931986</td>\n",
       "      <td>NEW HAVEN</td>\n",
       "      <td>...</td>\n",
       "      <td>CT</td>\n",
       "      <td>065208327</td>\n",
       "      <td>NOLDE, MONA</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The lon...</td>\n",
       "      <td>2012-02-29T00:00:00</td>\n",
       "      <td>5F32HL095308-03</td>\n",
       "      <td>2009-03-01T00:00:00</td>\n",
       "      <td>THE ROLE OF MAMMALIAN PIWI PROTEINS AND PIRNAS...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>54734.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2794</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>2009-05-01T00:00:00</td>\n",
       "      <td>393</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Address; Affinity; Aliquot; Alleles; Antibodi...</td>\n",
       "      <td>44.055948</td>\n",
       "      <td>-92.525906</td>\n",
       "      <td>ROCHESTER</td>\n",
       "      <td>...</td>\n",
       "      <td>MN</td>\n",
       "      <td>559050001</td>\n",
       "      <td>JELINEK, DIANE F</td>\n",
       "      <td>DESCRIPTION (provided by applicant): B cell ...</td>\n",
       "      <td>2014-02-28T00:00:00</td>\n",
       "      <td>5R01CA136591-03</td>\n",
       "      <td>2009-05-01T00:00:00</td>\n",
       "      <td>ROLE OF THE BCR IN B CELL CHRONIC LYMPHOCYTIC ...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>304127.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2795</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2014-04-30T00:00:00</td>\n",
       "      <td>2011-07-01T00:00:00</td>\n",
       "      <td>393</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Accounting; Acute Lymphocytic Leukemia; Afric...</td>\n",
       "      <td>37.786097</td>\n",
       "      <td>-122.448391</td>\n",
       "      <td>SAN FRANCISCO</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>941186215</td>\n",
       "      <td>WIEMELS, JOSEPH LEO</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Althoug...</td>\n",
       "      <td>2014-04-30T00:00:00</td>\n",
       "      <td>1R01CA155461-01</td>\n",
       "      <td>2011-07-01T00:00:00</td>\n",
       "      <td>GENOME-WIDE ASSOCIATION STUDY OF CHILDHOOD LEU...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>1566078.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2796</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2016-06-30T00:00:00</td>\n",
       "      <td>2011-07-01T00:00:00</td>\n",
       "      <td>398</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Acute leukemia; Acute Myelocytic Leukemia; Ad...</td>\n",
       "      <td>42.336891</td>\n",
       "      <td>-71.105371</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>021155724</td>\n",
       "      <td>NEFF, TOBIAS</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Increas...</td>\n",
       "      <td>2016-06-30T00:00:00</td>\n",
       "      <td>1K08CA154777-01</td>\n",
       "      <td>2011-07-01T00:00:00</td>\n",
       "      <td>EZH2 IN MLL-AF9 MEDIATED ACUTE MYELOID LEUKEMIA</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>146016.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2797</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-07-31T00:00:00</td>\n",
       "      <td>2011-08-18T00:00:00</td>\n",
       "      <td>394</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Accident and Emergency department; Acute leuk...</td>\n",
       "      <td>37.870295</td>\n",
       "      <td>-122.268133</td>\n",
       "      <td>BERKELEY</td>\n",
       "      <td>...</td>\n",
       "      <td>CA</td>\n",
       "      <td>947045940</td>\n",
       "      <td>SOHN, LYDIA L</td>\n",
       "      <td>DESCRIPTION (provided by applicant): We prop...</td>\n",
       "      <td>2013-07-31T00:00:00</td>\n",
       "      <td>1R21CA156139-01</td>\n",
       "      <td>2011-08-18T00:00:00</td>\n",
       "      <td>RAPID LABEL-FREE DETECTION OF ACUTE PROMYELOCY...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>162098.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2798</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-11-30T00:00:00</td>\n",
       "      <td>2010-12-03T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Accounting; Acute T Cell Leukemia; Address; A...</td>\n",
       "      <td>40.841253</td>\n",
       "      <td>-73.940404</td>\n",
       "      <td>NEW YORK</td>\n",
       "      <td>...</td>\n",
       "      <td>NY</td>\n",
       "      <td>100323702</td>\n",
       "      <td>FERRANDO, ADOLFO A.</td>\n",
       "      <td>DESCRIPTION (provided by applicant): This pr...</td>\n",
       "      <td>2015-11-30T00:00:00</td>\n",
       "      <td>1R01CA155743-01</td>\n",
       "      <td>2010-12-03T00:00:00</td>\n",
       "      <td>THE ROLE OF PHF6 IN T-CELL ACUTE LYMPHOBLASTIC...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>333211.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2799</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-01-31T00:00:00</td>\n",
       "      <td>2010-03-01T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>11q23; Acute leukemia; Acute Lymphocytic Leuk...</td>\n",
       "      <td>42.336891</td>\n",
       "      <td>-71.105371</td>\n",
       "      <td>BOSTON</td>\n",
       "      <td>...</td>\n",
       "      <td>MA</td>\n",
       "      <td>021155724</td>\n",
       "      <td>ARMSTRONG, SCOTT A</td>\n",
       "      <td>DESCRIPTION (provided by applicant): Acute l...</td>\n",
       "      <td>2015-01-31T00:00:00</td>\n",
       "      <td>5R01CA140575-02</td>\n",
       "      <td>2010-03-01T00:00:00</td>\n",
       "      <td>MOLECULAR PATHOGENESIS OF MLL-AF4 LEUKEMIAS</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>347535.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2800</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-03-31T00:00:00</td>\n",
       "      <td>2010-04-01T00:00:00</td>\n",
       "      <td>393</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Address; adult leukemia; Affect; Attention; b...</td>\n",
       "      <td>44.055948</td>\n",
       "      <td>-92.525906</td>\n",
       "      <td>ROCHESTER</td>\n",
       "      <td>...</td>\n",
       "      <td>MN</td>\n",
       "      <td>559050001</td>\n",
       "      <td>SLAGER, SUSAN L.</td>\n",
       "      <td>DESCRIPTION (provided by applicant):  Chronic ...</td>\n",
       "      <td>2013-03-31T00:00:00</td>\n",
       "      <td>5R01CA148690-02</td>\n",
       "      <td>2010-04-01T00:00:00</td>\n",
       "      <td>POOLING AND EXPANSION OF CHRONIC LYMPHOCYTIC L...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>547062.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2801</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2013-02-28T00:00:00</td>\n",
       "      <td>2001-12-01T00:00:00</td>\n",
       "      <td>395</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>4-ethoxymethylene-2-phenyl-2-oxazoline-5-one;...</td>\n",
       "      <td>40.790552</td>\n",
       "      <td>-73.953850</td>\n",
       "      <td>NEW YORK</td>\n",
       "      <td>...</td>\n",
       "      <td>NY</td>\n",
       "      <td>100296574</td>\n",
       "      <td>JING, YONGKUI</td>\n",
       "      <td>DESCRIPTION (provided by applicant): The out...</td>\n",
       "      <td>2013-02-28T00:00:00</td>\n",
       "      <td>5R01CA093533-08</td>\n",
       "      <td>2001-12-01T00:00:00</td>\n",
       "      <td>ARSENIC TRIOXIDE AND ACUTE MYELOID LEUKEMIA</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>247445.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2802</th>\n",
       "      <td>NIH</td>\n",
       "      <td>2015-01-31T00:00:00</td>\n",
       "      <td>2010-04-01T00:00:00</td>\n",
       "      <td>396</td>\n",
       "      <td>HHS</td>\n",
       "      <td>2011</td>\n",
       "      <td>Acute; Acute T Cell Leukemia; Address; Adhesi...</td>\n",
       "      <td>40.745221</td>\n",
       "      <td>-73.978294</td>\n",
       "      <td>NEW YORK</td>\n",
       "      <td>...</td>\n",
       "      <td>NY</td>\n",
       "      <td>100165802</td>\n",
       "      <td>AIFANTIS, IANNIS</td>\n",
       "      <td>DESCRIPTION (provided by applicant): T cell ...</td>\n",
       "      <td>2015-01-31T00:00:00</td>\n",
       "      <td>5R01CA149655-02</td>\n",
       "      <td>2010-04-01T00:00:00</td>\n",
       "      <td>MECHANISMS OF T CELL LEUKEMIA INDUCTION AND MA...</td>\n",
       "      <td>leukemia</td>\n",
       "      <td>340155.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2803 rows × 22 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Agency      Budget End Date    Budget Start Date CFDA code Department  \\\n",
       "0       NSF  2015-08-31T00:00:00  2012-09-01T00:00:00    47.074        NSF   \n",
       "1       NIH  2016-08-31T00:00:00  2012-09-21T00:00:00       847        HHS   \n",
       "2       NIH                 None                 None      None        HHS   \n",
       "3       NIH  2013-10-31T00:00:00  2011-08-15T00:00:00       855        HHS   \n",
       "4       NIH                 None                 None      None        HHS   \n",
       "5       NIH  2012-03-05T00:00:00  2011-02-01T00:00:00       859        HHS   \n",
       "6       NIH  2017-04-30T00:00:00  2012-08-09T00:00:00      None        HHS   \n",
       "7       NIH  2015-06-30T00:00:00  2010-07-15T00:00:00       859        HHS   \n",
       "8       NIH                 None                 None      None        HHS   \n",
       "9       NIH  2015-02-28T00:00:00  2010-09-26T00:00:00       172        HHS   \n",
       "10      NIH  2013-08-31T00:00:00  2011-08-23T00:00:00       172        HHS   \n",
       "11      NIH  2014-08-31T00:00:00  2011-09-01T00:00:00       395        HHS   \n",
       "12      NSF  2016-07-31T00:00:00  2012-08-15T00:00:00    47.049        NSF   \n",
       "13      NSF  2016-07-31T00:00:00  2012-08-15T00:00:00    47.049        NSF   \n",
       "14      NIH  2015-02-28T00:00:00  2010-06-01T00:00:00       172        HHS   \n",
       "15      NSF  2012-08-31T00:00:00  2009-09-01T00:00:00    47.074        NSF   \n",
       "16      NSF  2012-08-31T00:00:00  2009-09-01T00:00:00    47.074        NSF   \n",
       "17      NSF  2014-08-31T00:00:00  2011-09-01T00:00:00    47.050        NSF   \n",
       "18      NSF  2014-08-31T00:00:00  2011-09-01T00:00:00    47.050        NSF   \n",
       "19      NSF  2011-09-30T00:00:00  2010-10-15T00:00:00    47.074        NSF   \n",
       "20      NIH  2011-07-31T00:00:00  2009-08-01T00:00:00       279        HHS   \n",
       "21      NIH  2011-06-30T00:00:00  2009-09-22T00:00:00       701        HHS   \n",
       "22      NIH  2011-08-31T00:00:00  2009-09-30T00:00:00       701        HHS   \n",
       "23      NIH  2011-08-31T00:00:00  2009-09-30T00:00:00       701        HHS   \n",
       "24      NIH  2012-07-31T00:00:00  2009-08-01T00:00:00       279        HHS   \n",
       "25      NIH  2012-07-31T00:00:00  2010-08-19T00:00:00       394        HHS   \n",
       "26      NIH  2015-06-30T00:00:00  2010-07-01T00:00:00      None        HHS   \n",
       "27      NIH  2012-06-30T00:00:00  2009-09-22T00:00:00       701        HHS   \n",
       "28      NIH  2012-08-31T00:00:00  2009-09-30T00:00:00       701        HHS   \n",
       "29      NIH  2012-08-31T00:00:00  2009-09-30T00:00:00       701        HHS   \n",
       "...     ...                  ...                  ...       ...        ...   \n",
       "2773    NIH  2014-06-30T00:00:00  2009-09-14T00:00:00       398        HHS   \n",
       "2774    NIH  2015-08-31T00:00:00  2010-09-03T00:00:00       398        HHS   \n",
       "2775    NSF  2012-12-31T00:00:00  2012-01-01T00:00:00    47.041        NSF   \n",
       "2776    NIH  2014-01-31T00:00:00  2009-04-20T00:00:00       393        HHS   \n",
       "2777    NIH  2014-02-28T00:00:00  2008-05-01T00:00:00       394        HHS   \n",
       "2778    NIH  2013-12-31T00:00:00  2009-01-01T00:00:00       396        HHS   \n",
       "2779    NIH  2014-01-31T00:00:00  2008-04-01T00:00:00       396        HHS   \n",
       "2780    NIH  2014-02-28T00:00:00  2009-04-06T00:00:00       839        HHS   \n",
       "2781    NIH  2014-06-30T00:00:00  2012-07-20T00:00:00       396        HHS   \n",
       "2782    NIH  2014-04-30T00:00:00  2012-05-15T00:00:00       394        HHS   \n",
       "2783    NIH  2014-03-31T00:00:00  2012-04-01T00:00:00       395        HHS   \n",
       "2784    NIH  2014-02-28T00:00:00  2012-03-01T00:00:00       394        HHS   \n",
       "2785    NIH  2017-08-31T00:00:00  2012-09-18T00:00:00       398        HHS   \n",
       "2786    NIH  2013-08-31T00:00:00  2003-08-05T00:00:00       397        HHS   \n",
       "2787    NIH  2013-08-31T00:00:00                 None      None        HHS   \n",
       "2788    NIH  2013-08-31T00:00:00                 None      None        HHS   \n",
       "2789    NIH  2013-08-31T00:00:00                 None      None        HHS   \n",
       "2790    NIH  2014-12-31T00:00:00  2010-02-05T00:00:00       242        HHS   \n",
       "2791    NIH  2015-01-31T00:00:00  2010-02-09T00:00:00       396        HHS   \n",
       "2792    NIH  2015-12-31T00:00:00  2011-02-01T00:00:00       395        HHS   \n",
       "2793    NIH  2012-02-29T00:00:00  2009-03-01T00:00:00       839        HHS   \n",
       "2794    NIH  2014-02-28T00:00:00  2009-05-01T00:00:00       393        HHS   \n",
       "2795    NIH  2014-04-30T00:00:00  2011-07-01T00:00:00       393        HHS   \n",
       "2796    NIH  2016-06-30T00:00:00  2011-07-01T00:00:00       398        HHS   \n",
       "2797    NIH  2013-07-31T00:00:00  2011-08-18T00:00:00       394        HHS   \n",
       "2798    NIH  2015-11-30T00:00:00  2010-12-03T00:00:00       396        HHS   \n",
       "2799    NIH  2015-01-31T00:00:00  2010-03-01T00:00:00       396        HHS   \n",
       "2800    NIH  2013-03-31T00:00:00  2010-04-01T00:00:00       393        HHS   \n",
       "2801    NIH  2013-02-28T00:00:00  2001-12-01T00:00:00       395        HHS   \n",
       "2802    NIH  2015-01-31T00:00:00  2010-04-01T00:00:00       396        HHS   \n",
       "\n",
       "      Fiscal Year                                          Key Words  \\\n",
       "0            2012   Acer; Address; Area; Bacteria; Bacteriophages...   \n",
       "1            2012   base; Base Sequence; Biological Models; Biolo...   \n",
       "2            2012   base; Biological; Clinic; Collaborations; col...   \n",
       "3            2012   Accounting; Affect; Africa South of the Sahar...   \n",
       "4            2012   Address; Adopted; Advisory Committees; Animal...   \n",
       "5            2012   Actinobacteria class; Anabolism; analog; Anti...   \n",
       "6            2012   Adoption; Appointment; Base Pairing; Base Seq...   \n",
       "7            2012   Acute Myelocytic Leukemia; Address; Affect; B...   \n",
       "8            2012   Address; Adopted; Advisory Committees; Animal...   \n",
       "9            2012   abstracting; Alu Elements; Award; Beryllium; ...   \n",
       "10           2012   Address; Allelotyping; Automation; base; Bioi...   \n",
       "11           2012   Adopted; anticancer research; Automobile Driv...   \n",
       "12           2012   Algorithms; analytical method; base; biodefen...   \n",
       "13           2012   Algorithms; analytical method; base; biodefen...   \n",
       "14           2012   Address; Algorithms; base; Behavior; Binding;...   \n",
       "15           2009   Achievement; Bacteria; base; Bioinformatics; ...   \n",
       "16           2009   Actinium; Address; Bioinformatics; Collection...   \n",
       "17           2011   Address; Animals; Area; Award; base; Biodiver...   \n",
       "18           2011   Address; Animals; Area; Award; base; Biodiver...   \n",
       "19           2011   Area; Basic Science; Biotechnology; Computing...   \n",
       "20           2009   Address; Anodes; Area; base; Base Pairing; Ba...   \n",
       "21           2009   Address; Algorithms; Area; Attention; base; B...   \n",
       "22           2009   Accounting; Adult; Affect; African American; ...   \n",
       "23           2009   Algorithms; American; anticancer research; At...   \n",
       "24           2010   Address; Anodes; Area; base; Base Pairing; Ba...   \n",
       "25           2010   Address; Area; base; Behavior; Biological Ass...   \n",
       "26           2010   Arts; base; Biological; Clinic; Collaboration...   \n",
       "27           2010   Address; Algorithms; Area; Attention; base; B...   \n",
       "28           2010   Algorithms; American; anticancer research; At...   \n",
       "29           2010   Accounting; Adult; Affect; African American; ...   \n",
       "...           ...                                                ...   \n",
       "2773         2012   Acute Myelocytic Leukemia; Adverse event; AMD...   \n",
       "2774         2012   1-Phosphatidylinositol 3-Kinase; Acute Myeloc...   \n",
       "2775         2012   Acute leukemia; Adult; adult leukemia; Cell C...   \n",
       "2776         2012   Acute; Acute leukemia; Acute Lymphocytic Leuk...   \n",
       "2777         2012   Acute leukemia; Acute Promyelocytic Leukemia;...   \n",
       "2778         2012   Accounting; adult leukemia; Age; aged; Antige...   \n",
       "2779         2012   Accounting; Acute Lymphocytic Leukemia; Acute...   \n",
       "2780         2012   Acute leukemia; Adhesions; Apoptosis; base; b...   \n",
       "2781         2012   Accounting; Address; Adult; Animals; Biologic...   \n",
       "2782         2012   Abnormal Cell; Acute Myelocytic Leukemia; Aff...   \n",
       "2783         2012   Ablation; Acute Myelocytic Leukemia; addictio...   \n",
       "2784         2012   Acute; Acute leukemia; Acute Lymphocytic Leuk...   \n",
       "2785         2012   Acceleration; Activator Appliances; Acute leu...   \n",
       "2786         2012   abstracting; Acute Myelocytic Leukemia; Area;...   \n",
       "2787         2012   Adoptive Cell Transfers; Affinity; Agonist; A...   \n",
       "2788         2012   Acute Myelocytic Leukemia; Affinity; Aftercar...   \n",
       "2789         2012   3-Dimensional; abstracting; Achievement; acti...   \n",
       "2790         2011   8 year old; Acute; Acute Lymphocytic Leukemia...   \n",
       "2791         2011   1-Phosphatidylinositol 3-Kinase; Acute Myeloc...   \n",
       "2792         2011   Acute Lymphocytic Leukemia; Address; Affect; ...   \n",
       "2793         2011   Address; Blood; CD34 gene; Cell Differentiati...   \n",
       "2794         2011   Address; Affinity; Aliquot; Alleles; Antibodi...   \n",
       "2795         2011   Accounting; Acute Lymphocytic Leukemia; Afric...   \n",
       "2796         2011   Acute leukemia; Acute Myelocytic Leukemia; Ad...   \n",
       "2797         2011   Accident and Emergency department; Acute leuk...   \n",
       "2798         2011   Accounting; Acute T Cell Leukemia; Address; A...   \n",
       "2799         2011   11q23; Acute leukemia; Acute Lymphocytic Leuk...   \n",
       "2800         2011   Address; adult leukemia; Affect; Attention; b...   \n",
       "2801         2011   4-ethoxymethylene-2-phenyl-2-oxazoline-5-one;...   \n",
       "2802         2011   Acute; Acute T Cell Leukemia; Address; Adhesi...   \n",
       "\n",
       "       Latitude   Longitude Organization City    ...     Organization State  \\\n",
       "0     42.787172  -86.101102           HOLLAND    ...                     MI   \n",
       "1     42.334978  -71.105987            BOSTON    ...                     MA   \n",
       "2     44.055948  -92.525906         ROCHESTER    ...                     MN   \n",
       "3     41.302711  -72.931986         NEW HAVEN    ...                     CT   \n",
       "4     35.366248  -79.429394       CHAPEL HILL    ...                     NC   \n",
       "5     37.240049 -119.503236          LA JOLLA    ...                     CA   \n",
       "6     39.298737  -76.594342         BALTIMORE    ...                     MD   \n",
       "7     38.648424  -90.309068       SAINT LOUIS    ...                     MO   \n",
       "8     35.366248  -79.429394       CHAPEL HILL    ...                     NC   \n",
       "9     40.481906  -74.457066        PISCATAWAY    ...                     NJ   \n",
       "10    42.748478  -84.483276      EAST LANSING    ...                     MI   \n",
       "11    38.648424  -90.309068       SAINT LOUIS    ...                     MO   \n",
       "12    40.092617  -88.247723         CHAMPAIGN    ...                     IL   \n",
       "13    33.968143 -117.335853         RIVERSIDE    ...                     CA   \n",
       "14    42.336250  -71.070668            BOSTON    ...                     MA   \n",
       "15    30.605842  -96.368935   COLLEGE STATION    ...                     TX   \n",
       "16    40.477702  -74.425495     NEW BRUNSWICK    ...                     NJ   \n",
       "17    41.808431  -72.249523            STORRS    ...                     CT   \n",
       "18    42.317789  -72.635903       NORTHAMPTON    ...                     MA   \n",
       "19    32.832811 -117.271272          LA JOLLA    ...                     CA   \n",
       "20    29.673047  -95.413789           HOUSTON    ...                     TX   \n",
       "21    42.335814  -71.105033            BOSTON    ...                     MA   \n",
       "22    29.703025  -95.403303           HOUSTON    ...                     TX   \n",
       "23    42.337854  -71.108326            BOSTON    ...                     MA   \n",
       "24    29.673047  -95.413789           HOUSTON    ...                     TX   \n",
       "25    37.430351 -122.178210          STANFORD    ...                     CA   \n",
       "26    44.055948  -92.525906         ROCHESTER    ...                     MN   \n",
       "27    42.335814  -71.105033            BOSTON    ...                     MA   \n",
       "28    42.337854  -71.108326            BOSTON    ...                     MA   \n",
       "29    29.703025  -95.403303           HOUSTON    ...                     TX   \n",
       "...         ...         ...               ...    ...                    ...   \n",
       "2773  38.648424  -90.309068       SAINT LOUIS    ...                     MO   \n",
       "2774  39.952982  -75.192768      PHILADELPHIA    ...                     PA   \n",
       "2775  45.670519 -111.065608           BOZEMAN    ...                     MT   \n",
       "2776  36.059402  -80.321981     WINSTON-SALEM    ...                     NC   \n",
       "2777  29.681814  -82.345358       GAINESVILLE    ...                     FL   \n",
       "2778  40.066768  -75.092750      PHILADELPHIA    ...                     PA   \n",
       "2779  40.841253  -73.940404          NEW YORK    ...                     NY   \n",
       "2780  39.140663  -84.501007        CINCINNATI    ...                     OH   \n",
       "2781  40.444095  -79.956899        PITTSBURGH    ...                     PA   \n",
       "2782  41.502739  -81.607334         CLEVELAND    ...                     OH   \n",
       "2783  40.764910  -73.955055          NEW YORK    ...                     NY   \n",
       "2784  47.628707 -122.330795           SEATTLE    ...                     WA   \n",
       "2785  34.065915 -118.196446       LOS ANGELES    ...                     CA   \n",
       "2786  29.706319  -95.397195           HOUSTON    ...                     TX   \n",
       "2787  29.706319  -95.397195           HOUSTON    ...                     TX   \n",
       "2788  29.706319  -95.397195           HOUSTON    ...                     TX   \n",
       "2789  29.706319  -95.397195           HOUSTON    ...                     TX   \n",
       "2790  35.150278  -90.041851           MEMPHIS    ...                     TN   \n",
       "2791  32.635016  -86.809379        BIRMINGHAM    ...                     AL   \n",
       "2792  29.706319  -95.397195           HOUSTON    ...                     TX   \n",
       "2793  41.302711  -72.931986         NEW HAVEN    ...                     CT   \n",
       "2794  44.055948  -92.525906         ROCHESTER    ...                     MN   \n",
       "2795  37.786097 -122.448391     SAN FRANCISCO    ...                     CA   \n",
       "2796  42.336891  -71.105371            BOSTON    ...                     MA   \n",
       "2797  37.870295 -122.268133          BERKELEY    ...                     CA   \n",
       "2798  40.841253  -73.940404          NEW YORK    ...                     NY   \n",
       "2799  42.336891  -71.105371            BOSTON    ...                     MA   \n",
       "2800  44.055948  -92.525906         ROCHESTER    ...                     MN   \n",
       "2801  40.790552  -73.953850          NEW YORK    ...                     NY   \n",
       "2802  40.745221  -73.978294          NEW YORK    ...                     NY   \n",
       "\n",
       "     Organization ZIP        Principal Investigator  \\\n",
       "0          49422-9000                 BEST, AARON A   \n",
       "1           021156110            GOESSLING, WOLFRAM   \n",
       "2           559050001      WEINSHILBOUM, RICHARD M.   \n",
       "3           065208327             CACCONE, ADALGISA   \n",
       "4           275990001          MARZLUFF, WILLIAM F.   \n",
       "5           920930934              BERNHARDT, PETER   \n",
       "6           212051832  YEGNASUBRAMANIAN, SRINIVASAN   \n",
       "7           631304862              MARDIS, ELAINE R   \n",
       "8           275990001          MARZLUFF, WILLIAM F.   \n",
       "9           088543925                XING, JINCHUAN   \n",
       "10          488242600               BROWN, C. TITUS   \n",
       "11          631304862          MAHER, CHRISTOPHER A   \n",
       "12         61820-7473                      MA, PING   \n",
       "13         92521-1000                  CUI, XINPING   \n",
       "14          021182340         JOHNSON, WILLIAM EVAN   \n",
       "15         77845-0000             DICKMAN, MARTIN B   \n",
       "16         08901-8559                DOONER, HUGO K   \n",
       "17         06269-1133             MCMANUS, GEORGE B   \n",
       "18         01063-6304                 KATZ, LAURA A   \n",
       "19         92093-0210           BARTLETT, DOUGLAS H   \n",
       "20          770545029                 GAO, XIAOLIAN   \n",
       "21          021156027                 PARK, PETER J   \n",
       "22              77030              HIXSON, JAMES E.   \n",
       "23          022155450          MEYERSON, MATTHEW L.   \n",
       "24          770545029                 GAO, XIAOLIAN   \n",
       "25          943041222                  JI, HANLEE P   \n",
       "26          559050001      WEINSHILBOUM, RICHARD M.   \n",
       "27          021156027                 PARK, PETER J   \n",
       "28          022155450          MEYERSON, MATTHEW L.   \n",
       "29              77030              HIXSON, JAMES E.   \n",
       "...               ...                           ...   \n",
       "2773        631304862                UY, GEOFFREY L   \n",
       "2774        191046205            PERL, ALEXANDER E.   \n",
       "2775       59718-4012                   NAGY, JON O   \n",
       "2776        271570001        ORNELLES, DAVID ARNOLD   \n",
       "2777        326115500                      LI, YING   \n",
       "2778        191112434               HAYAKAWA, KYOKO   \n",
       "2779        100323702           FERRANDO, ADOLFO A.   \n",
       "2780        452293039              CANCELAS, JOSE A   \n",
       "2781        152132303                  WANG, QINGDE   \n",
       "2782        441061712    JACOBBERGER, JAMES WILLIAM   \n",
       "2783        100654805              GUZMAN, MONICA L   \n",
       "2784        981094433              BEDALOV, ANTONIO   \n",
       "2785        900339263                MERCHANT, AKIL   \n",
       "2786        770304009             KANTARJIAN, HAGOP   \n",
       "2787        770304009           MOLLDREM, JEFFREY J   \n",
       "2788        770304009             ANDREEFF, MICHAEL   \n",
       "2789        770304009           PLUNKETT, WILLIAM K   \n",
       "2790        381053678                KRULL, KEVIN R   \n",
       "2791        352940001           KLUG, CHRISTOPHER A   \n",
       "2792        770304009           KONOPLEVA, MARINA Y   \n",
       "2793        065208327                   NOLDE, MONA   \n",
       "2794        559050001              JELINEK, DIANE F   \n",
       "2795        941186215           WIEMELS, JOSEPH LEO   \n",
       "2796        021155724                  NEFF, TOBIAS   \n",
       "2797        947045940                 SOHN, LYDIA L   \n",
       "2798        100323702           FERRANDO, ADOLFO A.   \n",
       "2799        021155724            ARMSTRONG, SCOTT A   \n",
       "2800        559050001              SLAGER, SUSAN L.   \n",
       "2801        100296574                 JING, YONGKUI   \n",
       "2802        100165802              AIFANTIS, IANNIS   \n",
       "\n",
       "                                       Project Abstract     Project End Date  \\\n",
       "0     Advances in sequencing technology have dramati...  2015-08-31T00:00:00   \n",
       "1     DESCRIPTION (provided by applicant): The power...  2016-08-31T00:00:00   \n",
       "2     OVERALL SUMMARY AND SPECIFIC AIMS: NETWORK RES...                 None   \n",
       "3     DESCRIPTION (provided by applicant): Human Afr...  2013-10-31T00:00:00   \n",
       "4     Next Generation Sequencing and Genotyping Core...                 None   \n",
       "5     DESCRIPTION (provided by applicant): Actinomyc...  2012-03-05T00:00:00   \n",
       "6     To maintain and build on the Sidney Kimmel Com...  2017-04-30T00:00:00   \n",
       "7     Pharmacogenomics began with a focus on the fun...  2015-06-30T00:00:00   \n",
       "8     Next Generation Sequencing and Genotyping Core...                 None   \n",
       "9     Project Summary/Abstract Mobile DNA elements a...  2015-02-28T00:00:00   \n",
       "10    DESCRIPTION (provided by applicant): Modern bi...  2013-08-31T00:00:00   \n",
       "11    PROJECT SUMMARY/ABSTRACT The impact of high-th...  2014-08-31T00:00:00   \n",
       "12    Recently, the emerging new field of metagenomi...  2016-07-31T00:00:00   \n",
       "13    Recently, the emerging new field of metagenomi...  2016-07-31T00:00:00   \n",
       "14    DESCRIPTION (provided by applicant): Next-gene...  2015-02-28T00:00:00   \n",
       "15    During the past 10 years, there has been a maj...  2012-08-31T00:00:00   \n",
       "16    PI: Hugo K. Dooner (Rutgers University)<br/>Co...  2012-08-31T00:00:00   \n",
       "17    The Ocean's biomass and diversity are predomin...  2014-08-31T00:00:00   \n",
       "18    The Ocean's biomass and diversity are predomin...  2014-08-31T00:00:00   \n",
       "19    This grant will support a workshop focused on ...  2011-09-30T00:00:00   \n",
       "20      DESCRIPTION (provided by applicant):  This p...  2011-07-31T00:00:00   \n",
       "21      DESCRIPTION (provided by applicant):  This a...  2011-06-30T00:00:00   \n",
       "22      DESCRIPTION (provided by applicant):  This p...  2011-08-31T00:00:00   \n",
       "23      DESCRIPTION (provided by applicant): Our goa...  2011-08-31T00:00:00   \n",
       "24      DESCRIPTION (provided by applicant):  This p...  2012-07-31T00:00:00   \n",
       "25      DESCRIPTION (provided by applicant): Creatin...  2012-07-31T00:00:00   \n",
       "26    OVERALL SUMMARY AND SPECIFIC AIMS: NETWORK RES...  2015-06-30T00:00:00   \n",
       "27      DESCRIPTION (provided by applicant):  This a...  2012-06-30T00:00:00   \n",
       "28      DESCRIPTION (provided by applicant): Our goa...  2012-08-31T00:00:00   \n",
       "29      DESCRIPTION (provided by applicant):  This p...  2012-08-31T00:00:00   \n",
       "...                                                 ...                  ...   \n",
       "2773  DESCRIPTION (provided by applicant): This care...  2014-06-30T00:00:00   \n",
       "2774  DESCRIPTION (provided by applicant): AML is a ...  2015-08-31T00:00:00   \n",
       "2775  This Small Business Innovation Research (SBIR)...  2012-12-31T00:00:00   \n",
       "2776  DESCRIPTION (provided by applicant): Acute leu...  2014-01-31T00:00:00   \n",
       "2777  DESCRIPTION (provided by applicant): Today, mi...  2014-02-28T00:00:00   \n",
       "2778  SummaryB CLL (B cell chronic lymphocytic leuke...  2013-12-31T00:00:00   \n",
       "2779  The role of AKT signaling in NOTCH1-induced le...  2014-01-31T00:00:00   \n",
       "2780  DESCRIPTION (provided by applicant): Rac GTPas...  2014-02-28T00:00:00   \n",
       "2781  DESCRIPTION (provided by applicant): This proj...  2014-06-30T00:00:00   \n",
       "2782  DESCRIPTION (provided by applicant): The long ...  2014-04-30T00:00:00   \n",
       "2783  DESCRIPTION (provided by applicant): Acute mye...  2014-03-31T00:00:00   \n",
       "2784  DESCRIPTION (provided by applicant): The goal ...  2014-02-28T00:00:00   \n",
       "2785  DESCRIPTION (provided by applicant): This prop...  2017-08-31T00:00:00   \n",
       "2786  DESCRIPTION (provided by applicant): The Unive...  2013-08-31T00:00:00   \n",
       "2787  There is increasing evidence that lymphocytes ...  2013-08-31T00:00:00   \n",
       "2788  The main therapeutic challenge in the treatmen...  2013-08-31T00:00:00   \n",
       "2789  Effective therapies for acute leukemias have b...  2013-08-31T00:00:00   \n",
       "2790    DESCRIPTION (provided by applicant):  Surviv...  2014-12-31T00:00:00   \n",
       "2791    DESCRIPTION (provided by applicant): Constit...  2015-01-31T00:00:00   \n",
       "2792    DESCRIPTION (provided by applicant): The mai...  2015-12-31T00:00:00   \n",
       "2793    DESCRIPTION (provided by applicant): The lon...  2012-02-29T00:00:00   \n",
       "2794    DESCRIPTION (provided by applicant): B cell ...  2014-02-28T00:00:00   \n",
       "2795    DESCRIPTION (provided by applicant): Althoug...  2014-04-30T00:00:00   \n",
       "2796    DESCRIPTION (provided by applicant): Increas...  2016-06-30T00:00:00   \n",
       "2797    DESCRIPTION (provided by applicant): We prop...  2013-07-31T00:00:00   \n",
       "2798    DESCRIPTION (provided by applicant): This pr...  2015-11-30T00:00:00   \n",
       "2799    DESCRIPTION (provided by applicant): Acute l...  2015-01-31T00:00:00   \n",
       "2800  DESCRIPTION (provided by applicant):  Chronic ...  2013-03-31T00:00:00   \n",
       "2801    DESCRIPTION (provided by applicant): The out...  2013-02-28T00:00:00   \n",
       "2802    DESCRIPTION (provided by applicant): T cell ...  2015-01-31T00:00:00   \n",
       "\n",
       "                Project Number   Project Start Date  \\\n",
       "0                      1229585  2012-09-01T00:00:00   \n",
       "1              1R01DK095721-01  2012-09-21T00:00:00   \n",
       "2       5U19GM061388-13 (7593)                 None   \n",
       "3              5R21AI094615-02  2011-08-15T00:00:00   \n",
       "4       5P30CA016086-36 (8778)                 None   \n",
       "5              5F32GM096711-02  2011-02-01T00:00:00   \n",
       "6       2P30CA006973-49 (5858)  2012-08-09T00:00:00   \n",
       "7              5U01GM097119-03  2010-07-15T00:00:00   \n",
       "8     3P30CA016086-36S1 (8778)                 None   \n",
       "9              4R00HG005846-03  2010-09-26T00:00:00   \n",
       "10             5R25HG006243-02  2011-08-23T00:00:00   \n",
       "11             5R00CA149182-04  2011-09-01T00:00:00   \n",
       "12                     1222718  2012-08-15T00:00:00   \n",
       "13                     1223107  2012-08-15T00:00:00   \n",
       "14             7R01HG005692-03  2010-06-01T00:00:00   \n",
       "15                     0923502  2009-09-01T00:00:00   \n",
       "16                     0923950  2009-09-01T00:00:00   \n",
       "17                     1130033  2011-09-01T00:00:00   \n",
       "18                     1129734  2011-09-01T00:00:00   \n",
       "19                     1068643  2010-10-15T00:00:00   \n",
       "20             1R41DA029169-01  2009-08-01T00:00:00   \n",
       "21             1RC1HG005482-01  2009-09-22T00:00:00   \n",
       "22             1RC2HG005697-01  2009-09-30T00:00:00   \n",
       "23             1RC2CA148317-01  2009-09-30T00:00:00   \n",
       "24             5R41DA029169-02  2009-08-01T00:00:00   \n",
       "25           1R21CA140089-01A1  2010-08-19T00:00:00   \n",
       "26      2U19GM061388-11 (7593)  2010-07-01T00:00:00   \n",
       "27             5RC1HG005482-02  2009-09-22T00:00:00   \n",
       "28             5RC2CA148317-02  2009-09-30T00:00:00   \n",
       "29             5RC2HG005697-02  2009-09-30T00:00:00   \n",
       "...                        ...                  ...   \n",
       "2773           5K23CA140707-04  2009-09-14T00:00:00   \n",
       "2774           5K23CA141054-03  2010-09-03T00:00:00   \n",
       "2775                   1143342  2012-01-01T00:00:00   \n",
       "2776           5R01CA127621-04  2009-04-20T00:00:00   \n",
       "2777           5R01CA129311-05  2008-05-01T00:00:00   \n",
       "2778           5R01CA129330-04  2009-01-01T00:00:00   \n",
       "2779           5R01CA129382-05  2008-04-01T00:00:00   \n",
       "2780           5R01HL087159-04  2009-04-06T00:00:00   \n",
       "2781         1R21CA158650-01A1  2012-07-20T00:00:00   \n",
       "2782         1R21CA158659-01A1  2012-05-15T00:00:00   \n",
       "2783         1R21CA158728-01A1  2012-04-01T00:00:00   \n",
       "2784           1R21CA164545-01  2012-03-01T00:00:00   \n",
       "2785         1K08CA154975-01A1  2012-09-18T00:00:00   \n",
       "2786           5P50CA100632-10  2003-08-05T00:00:00   \n",
       "2787    5P50CA100632-10 (0002)                 None   \n",
       "2788    5P50CA100632-10 (0003)                 None   \n",
       "2789    5P50CA100632-10 (0005)                 None   \n",
       "2790           5R01MH085849-02  2010-02-05T00:00:00   \n",
       "2791           5R01CA144248-02  2010-02-09T00:00:00   \n",
       "2792           1R01CA155056-01  2011-02-01T00:00:00   \n",
       "2793           5F32HL095308-03  2009-03-01T00:00:00   \n",
       "2794           5R01CA136591-03  2009-05-01T00:00:00   \n",
       "2795           1R01CA155461-01  2011-07-01T00:00:00   \n",
       "2796           1K08CA154777-01  2011-07-01T00:00:00   \n",
       "2797           1R21CA156139-01  2011-08-18T00:00:00   \n",
       "2798           1R01CA155743-01  2010-12-03T00:00:00   \n",
       "2799           5R01CA140575-02  2010-03-01T00:00:00   \n",
       "2800           5R01CA148690-02  2010-04-01T00:00:00   \n",
       "2801           5R01CA093533-08  2001-12-01T00:00:00   \n",
       "2802           5R01CA149655-02  2010-04-01T00:00:00   \n",
       "\n",
       "                                          Project Title  \\\n",
       "0     MRI: ACQUISITION OF A BENCHTOP NEXT GENERATION...   \n",
       "1     MUTANT MAPPING AND IDENTIFICATION IN ZEBRAFISH...   \n",
       "2       NEXT GENERATION DNA SEQUENCING NETWORK RESOURCE   \n",
       "3     NEXT GENERATION SEQUENCING OF EAST AFRICAN TRY...   \n",
       "4     NEXT GENERATION SEQUENCING AND GENOTYPING CORE...   \n",
       "5     NEXT-GENERATION SEQUENCING AS A PLATFORM FOR A...   \n",
       "6                            NEXT GENERATION SEQUENCING   \n",
       "7     NEXT GENERATION SEQUENCING ADD-ON-PHARMACOGENO...   \n",
       "8     NEXT GENERATION SEQUENCING AND GENOTYPING CORE...   \n",
       "9     HIGH-THROUGHPUT MOBILE ELEMENT GENOTYPING USIN...   \n",
       "10            ANALYZING NEXT-GENERATION SEQUENCING DATA   \n",
       "11    CHARACTERIZATION OF CANCER TRANSCRIPTOMES USIN...   \n",
       "12    COLLABORATIVE RESEARCH: ATD: INTEGRATED STATIS...   \n",
       "13    COLLABORATIVE RESEARCH: ATD: INTEGRATED STATIS...   \n",
       "14    STATISTICAL TOOLS AND METHODS FOR NEXT-GENERAT...   \n",
       "15    MRI: ACQUISITION OF A ROCHE 454 FLX PYROSEQUEN...   \n",
       "16    FACILE PRODUCTION AND EFFICIENT INDEXING OF TR...   \n",
       "17    COLLABORATIVE RESEARCH: DIVERSITY AND DYNAMICS...   \n",
       "18    COLLABORATIVE RESEARCH: DIVERSITY AND DYNAMICS...   \n",
       "19    US-EC WORKSHOP ON MARINE GENOMICS: NEXT GENERA...   \n",
       "20    LONG READ NEXT GENERATION SEQUENCING TECHNOLOG...   \n",
       "21    STATISTICAL METHODS FOR ESTIMATION OF COPY NUM...   \n",
       "22    NEXT-GENERATION MEDICAL RESEQUENCING OF GOUT D...   \n",
       "23    AN INFRASTRUCTURE FOR CANCER VIRUS DISCOVERY F...   \n",
       "24    LONG READ NEXT GENERATION SEQUENCING TECHNOLOG...   \n",
       "25    MUTATION ANALYSIS OF PARAFFIN-EMBEDDED TUMORS ...   \n",
       "26      NEXT GENERATION DNA SEQUENCING NETWORK RESOURCE   \n",
       "27    STATISTICAL METHODS FOR ESTIMATION OF COPY NUM...   \n",
       "28    AN INFRASTRUCTURE FOR CANCER VIRUS DISCOVERY F...   \n",
       "29    NEXT-GENERATION MEDICAL RESEQUENCING OF GOUT D...   \n",
       "...                                                 ...   \n",
       "2773     TARGETING LEUKEMIA STROMAL INTERACTIONS IN AML   \n",
       "2774  MTOR INHIBITION AS A THERAPEUTIC STRATEGY FOR ...   \n",
       "2775  SBIR PHASE I: TARGETED NANOPARTICLE DELIVERY A...   \n",
       "2776  PRENATAL ADENOVIRUS INFECTION, INHIBITION OF D...   \n",
       "2777  APTAMER BASED TECHNOLOGY FOR MOLECULAR ANALYSI...   \n",
       "2778    ORIGIN OF CD5+ B CELL LYMPHOMA/LEUKEMIA IN MICE   \n",
       "2779  THE ROLE OF AKT SIGNALING IN NOTCH1 INDUCED LE...   \n",
       "2780  RAC GTPASE INHIBITION IN CHRONIC MYELOGENOUS L...   \n",
       "2781  FUNCTION OF ADAR1 IN HEMATOPOIETIC AND LEUKEMI...   \n",
       "2782             CELL SIGNALING AS A LEUKEMIA BIOMARKER   \n",
       "2783  A ROLE FOR ELEVATED AUTOPHAGY IN SURVIVAL AND ...   \n",
       "2784  PROTEIN BIOMARKERS IN CHILDHOOD ACUTE MYELOID ...   \n",
       "2785  THE ROLE OF HEDGEHOG/GLI IN NORMAL HEMATOPOIES...   \n",
       "2786  UNIVERSITY OF TEXAS M.D. ANDERSON CANCER CENTE...   \n",
       "2787     ADOPTIVE CELLULAR THERAPY FOR MYELOID LEUKEMIA   \n",
       "2788  P53 ACTIVATION AS NOVEL THERAPEUTIC STRATGEY F...   \n",
       "2789   DEVELOPMENT OF SAPACITABINE THERAPY IN LEUKEMIAS   \n",
       "2790  RISK FOR PSYCHOPATHOLOGY AND NEUROCOGNITIVE IM...   \n",
       "2791  ROLE OF NF-KB IN HEMATOPOIETIC STEM CELLS AND ...   \n",
       "2792  TARGETING HYPOXIC MICROENVIRONMENT IN ACUTE LY...   \n",
       "2793  THE ROLE OF MAMMALIAN PIWI PROTEINS AND PIRNAS...   \n",
       "2794  ROLE OF THE BCR IN B CELL CHRONIC LYMPHOCYTIC ...   \n",
       "2795  GENOME-WIDE ASSOCIATION STUDY OF CHILDHOOD LEU...   \n",
       "2796    EZH2 IN MLL-AF9 MEDIATED ACUTE MYELOID LEUKEMIA   \n",
       "2797  RAPID LABEL-FREE DETECTION OF ACUTE PROMYELOCY...   \n",
       "2798  THE ROLE OF PHF6 IN T-CELL ACUTE LYMPHOBLASTIC...   \n",
       "2799        MOLECULAR PATHOGENESIS OF MLL-AF4 LEUKEMIAS   \n",
       "2800  POOLING AND EXPANSION OF CHRONIC LYMPHOCYTIC L...   \n",
       "2801        ARSENIC TRIOXIDE AND ACUTE MYELOID LEUKEMIA   \n",
       "2802  MECHANISMS OF T CELL LEUKEMIA INDUCTION AND MA...   \n",
       "\n",
       "                       Seed Term Total Cost  \n",
       "0     next+generation+sequencing   171877.0  \n",
       "1     next+generation+sequencing   530443.0  \n",
       "2     next+generation+sequencing   482387.0  \n",
       "3     next+generation+sequencing   209013.0  \n",
       "4     next+generation+sequencing   270636.0  \n",
       "5     next+generation+sequencing     8124.0  \n",
       "6     next+generation+sequencing   229477.0  \n",
       "7     next+generation+sequencing   572671.0  \n",
       "8     next+generation+sequencing     2552.0  \n",
       "9     next+generation+sequencing   249000.0  \n",
       "10    next+generation+sequencing    53653.0  \n",
       "11    next+generation+sequencing   231830.0  \n",
       "12    next+generation+sequencing   372098.0  \n",
       "13    next+generation+sequencing   532114.0  \n",
       "14    next+generation+sequencing   336105.0  \n",
       "15    next+generation+sequencing   612019.0  \n",
       "16    next+generation+sequencing  1242967.0  \n",
       "17    next+generation+sequencing   408830.0  \n",
       "18    next+generation+sequencing   421638.0  \n",
       "19    next+generation+sequencing    25000.0  \n",
       "20    next+generation+sequencing   277737.0  \n",
       "21    next+generation+sequencing   397116.0  \n",
       "22    next+generation+sequencing  1317671.0  \n",
       "23    next+generation+sequencing   765137.0  \n",
       "24    next+generation+sequencing   294692.0  \n",
       "25    next+generation+sequencing   208800.0  \n",
       "26    next+generation+sequencing   519037.0  \n",
       "27    next+generation+sequencing   376168.0  \n",
       "28    next+generation+sequencing   786413.0  \n",
       "29    next+generation+sequencing  1448896.0  \n",
       "...                          ...        ...  \n",
       "2773                    leukemia   158853.0  \n",
       "2774                    leukemia   172368.0  \n",
       "2775                    leukemia   164848.0  \n",
       "2776                    leukemia   409936.0  \n",
       "2777                    leukemia   294868.0  \n",
       "2778                    leukemia   351225.0  \n",
       "2779                    leukemia   324613.0  \n",
       "2780                    leukemia   371250.0  \n",
       "2781                    leukemia   196729.0  \n",
       "2782                    leukemia   204885.0  \n",
       "2783                    leukemia   220545.0  \n",
       "2784                    leukemia   245687.0  \n",
       "2785                    leukemia   175824.0  \n",
       "2786                    leukemia  2300000.0  \n",
       "2787                    leukemia   234003.0  \n",
       "2788                    leukemia   221325.0  \n",
       "2789                    leukemia   188182.0  \n",
       "2790                    leukemia   499368.0  \n",
       "2791                    leukemia   294868.0  \n",
       "2792                    leukemia   341354.0  \n",
       "2793                    leukemia    54734.0  \n",
       "2794                    leukemia   304127.0  \n",
       "2795                    leukemia  1566078.0  \n",
       "2796                    leukemia   146016.0  \n",
       "2797                    leukemia   162098.0  \n",
       "2798                    leukemia   333211.0  \n",
       "2799                    leukemia   347535.0  \n",
       "2800                    leukemia   547062.0  \n",
       "2801                    leukemia   247445.0  \n",
       "2802                    leukemia   340155.0  \n",
       "\n",
       "[2803 rows x 22 columns]"
      ]
     },
     "execution_count": 111,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# store in DataFrame\n",
    "NIH_dict = {\n",
    "    \"Seed Term\": seed_term,\n",
    "    \"Key Words\": key_words,\n",
    "    \"Project Abstract\": project_abstract,\n",
    "    \"Project Title\": project_title,\n",
    "    \"Project Number\": project_number,\n",
    "    \"Project Start Date\": project_start_date,\n",
    "    \"Project End Date\": project_end_date,\n",
    "    \"Department\": department,\n",
    "    \"Agency\": agency,\n",
    "    \"Principal Investigator\": PI,\n",
    "    \"Latitude\": latitude,\n",
    "    \"Longitude\":longitude,\n",
    "    \"Organization Name\": org_name,\n",
    "    \"Organization City\": org_city,\n",
    "    \"Organization State\": org_state,\n",
    "    \"Organization ZIP\": org_zip,\n",
    "    \"Organization Country\": org_country,\n",
    "    \"Budget Start Date\": budget_start_date,\n",
    "    \"Budget End Date\": budget_end_date,\n",
    "    \"CFDA code\": CFDA_code,\n",
    "    \"Fiscal Year\": fiscal_year,\n",
    "    \"Total Cost\": total_cost\n",
    "}\n",
    "NIH_data = pd.DataFrame(NIH_dict)\n",
    "NIH_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 114,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# save DF to a csv\n",
    "NIH_data.to_csv(\"FedReporter.csv\", encoding=\"utf-8\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 115,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "NIH_data.to_excel(\"FedReporter.xlsx\", encoding=\"utf-8\", index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}