diff --git a/docs/build/.doctrees/environment.pickle b/docs/build/.doctrees/environment.pickle index 8e17b35..2636e81 100644 Binary files a/docs/build/.doctrees/environment.pickle and b/docs/build/.doctrees/environment.pickle differ diff --git a/docs/build/.doctrees/minimap.doctree b/docs/build/.doctrees/minimap.doctree index b2f594c..40d1d36 100644 Binary files a/docs/build/.doctrees/minimap.doctree and b/docs/build/.doctrees/minimap.doctree differ diff --git a/docs/build/_modules/ensembl/tools/anno/transcriptomic_annotation/minimap.html b/docs/build/_modules/ensembl/tools/anno/transcriptomic_annotation/minimap.html index 371a316..cdb2b48 100644 --- a/docs/build/_modules/ensembl/tools/anno/transcriptomic_annotation/minimap.html +++ b/docs/build/_modules/ensembl/tools/anno/transcriptomic_annotation/minimap.html @@ -88,20 +88,21 @@

Source code for ensembl.tools.anno.transcriptomic_annotation.minimap

""" Run Minimap2 to align long read data against genome file. Default Minimap set for PacBio data. - :param output_dir: Working directory path. - :type output_dir: Path - :param long_read_fastq_dir: Long read directory path. - :type long_read_fastq_dir: Path - :param genome_file: Genome file path. - :type genome_file: Path - :param minimap2_bin: Software path. - :type minimap2_bin: Path, default minimap2 - :param paftools_bin: Software path. - :type paftools_bin: Path, default paftools.js - :param max_intron_length: The maximum intron size for alignments. Defaults to 100000. - :type max_intron_length: int, default 100000 - :param num_threads: Number of available threads. - :type num_threads: int, default 1 + + :param output_dir: Working directory path. + :type output_dir: Path + :param long_read_fastq_dir: Long read directory path. + :type long_read_fastq_dir: Path + :param genome_file: Genome file path. + :type genome_file: Path + :param minimap2_bin: Software path. + :type minimap2_bin: Path, default minimap2 + :param paftools_bin: Software path. + :type paftools_bin: Path, default paftools.js + :param max_intron_length: The maximum intron size for alignments. Defaults to 100000. + :type max_intron_length: int, default 100000 + :param num_threads: Number of available threads. + :type num_threads: int, default 1 :return: None :rtype: None diff --git a/docs/build/minimap.html b/docs/build/minimap.html index 1bec9cb..bbf542d 100644 --- a/docs/build/minimap.html +++ b/docs/build/minimap.html @@ -54,7 +54,6 @@

Run Minimap2 to align long read data against genome file. Default Minimap set for PacBio data.

-
param output_dir:

Working directory path.

@@ -98,9 +97,6 @@
type num_threads:

int, default 1

-
-
-
return:

None

diff --git a/docs/build/searchindex.js b/docs/build/searchindex.js index 721f442..962945b 100644 --- a/docs/build/searchindex.js +++ b/docs/build/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["cpg", "dust", "eponine", "genblast", "index", "install", "license", "minimap", "red", "repeatmasker", "scallop", "star", "stringtie", "trf", "trnascan"], "filenames": ["cpg.rst", "dust.rst", "eponine.rst", "genblast.rst", "index.rst", "install.rst", "license.rst", "minimap.rst", "red.rst", "repeatmasker.rst", "scallop.rst", "star.rst", "stringtie.rst", "trf.rst", "trnascan.rst"], "titles": ["CpG Module Documentation", "DustMasker Module Documentation", "Eponine Module Documentation", "Genblast Module Documentation", "Ensembl-anno", "API Setup and installation", "License", "Minimap2 Module Documentation", "Red Module Documentation", "Repeatmasker Module Documentation", "Scallop Module Documentation", "STAR Module Documentation", "Stringtie Module Documentation", "TRF Module Documentation", "tRNAscan-SE Module Documentation"], "terms": {"set": [0, 7, 14], "discrimin": 0, "function": [0, 3], "can": 0, "recogn": 0, "structur": [0, 10], "composit": 0, "featur": [0, 3], "island": 0, "promot": 0, "region": 0, "first": [0, 8], "splice": [0, 11, 12], "donor": 0, "site": [0, 2], "davuluri": 0, "rv": 0, "gross": 0, "i": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 12, 13], "zhang": 0, "mq": 0, "comput": [0, 2, 6], "identif": [0, 6], "exon": 0, "human": 0, "genom": [0, 1, 2, 3, 7, 8, 9, 11, 13, 14], "nat": [0, 10], "genet": 0, "2001": 0, "29": [0, 11], "4": [0, 9], "412": 0, "417": 0, "pmid": [0, 2, 10, 14], "11726928": 0, "ensembl": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14], "tool": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 12, 13, 14], "anno": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "simple_feature_annot": [0, 2], "run_cpg": 0, "genome_fil": [0, 1, 2, 7, 8, 9, 11, 13, 14], "pathlik": [0, 1, 2, 9, 13, 14], "output_dir": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "path": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "cpg_bin": 0, "posixpath": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "cpg_lh": 0, "cpg_min_length": 0, "int": [0, 1, 2, 3, 7, 9, 10, 11, 12, 13, 14], "400": 0, "cpg_min_gc_cont": 0, "50": [0, 6], "cpg_min_o": 0, "float": [0, 2], "0": [0, 2, 6, 9, 11], "6": [0, 5], "num_thread": [0, 1, 2, 3, 7, 9, 11, 12, 13, 14], "1": [0, 1, 2, 3, 5, 6, 7, 9, 11, 12, 13, 14], "none": [0, 1, 2, 3, 7, 9, 10, 11, 12, 13, 14], "sourc": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 12, 13, 14], "run": [0, 1, 2, 7, 8, 10, 11], "slice": [0, 1, 2, 3, 9, 13, 14], "param": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "file": [0, 1, 2, 3, 6, 7, 8, 9, 11, 13, 14], "work": [0, 1, 2, 3, 6, 7, 8, 10, 11, 12, 13, 14], "directori": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "softwar": [0, 1, 2, 3, 6, 7, 8, 10, 11, 12, 13, 14], "min": 0, "length": [0, 3, 12], "gc": 0, "frequenc": 0, "percentag": 0, "ratio": 0, "observ": 0, "expect": 0, "number": [0, 1, 2, 3, 7, 9, 11, 12, 13, 14], "cpgo": 0, "e": 0, "thread": [0, 1, 2, 3, 7, 9, 11, 12, 13, 14], "program": [1, 9, 13, 14], "identifi": [1, 3, 6, 14], "mask": [1, 3, 8], "out": [1, 4, 6], "low": [1, 9, 14], "complex": [1, 9], "part": [1, 3, 6], "us": [1, 3, 6, 7, 11, 12], "new": 1, "improv": [1, 6, 12, 14], "dust": 1, "algorithm": [1, 7, 10, 12], "morguli": 1, "A": [1, 6, 11], "gertz": 1, "em": 1, "schaffer": 1, "aa": 1, "agarwala": 1, "r": [1, 3, 9], "fast": [1, 12], "symmetr": 1, "implement": 1, "dna": [1, 2, 9, 13, 14], "sequenc": [1, 2, 3, 7, 9, 13, 14], "repeat_annot": [1, 8, 9, 13], "run_dust": 1, "dust_bin": 1, "mutiprocess": 1, "probabilist": 2, "method": 2, "detect": [2, 8, 14], "transcript": [2, 10, 11, 12], "start": 2, "tss": 2, "mammalian": 2, "good": 2, "specif": [2, 6], "excel": 2, "posit": [2, 14], "accuraci": 2, "down": 2, "ta": 2, "hubbard": 2, "tj": 2, "locat": [2, 13], "re": [2, 3, 13, 14], "2002": 2, "mar": 2, "12": [2, 10], "3": [2, 5, 10], "458": 2, "61": 2, "doi": [2, 8, 10, 11, 12, 13], "10": [2, 8, 10, 11, 12, 13], "1101": 2, "gr": 2, "216102": 2, "11875034": 2, "pmcid": [2, 10], "pmc155284": 2, "run_eponin": 2, "java_bin": 2, "java": 2, "eponine_bin": 2, "hp": 2, "user": 2, "ensw": 2, "c8": 2, "mar21": 2, "sandybridg": 2, "linuxbrew": 2, "opt": 2, "libexec": 2, "scan": 2, "jar": 2, "eponine_threshold": 2, "999": 2, "homolog": 3, "gene": [3, 10, 12, 14], "databas": 3, "One": 3, "kei": 3, "its": [3, 6, 8], "flexibl": 3, "handl": [3, 10], "compar": [3, 7], "task": 3, "accur": [3, 8, 10], "even": [3, 6], "when": 3, "have": [3, 6], "undergon": 3, "signific": 3, "evolutionari": 3, "chang": [3, 6, 12], "thi": [3, 6], "capabl": [3, 8, 10], "make": [3, 6, 10], "valuabl": [3, 10], "resourc": [3, 10], "research": [3, 11], "studi": [3, 10], "evolut": 3, "famili": 3, "across": 3, "divers": 3, "speci": [3, 9], "ha": [3, 6], "been": [3, 6], "wide": [3, 11], "variou": 3, "analys": 3, "avail": [3, 6, 7, 11, 12], "standalon": 3, "command": [3, 10], "line": 3, "differ": [3, 6], "bioinformat": [3, 7, 8, 11], "pipelin": 3, "field": [3, 6], "analysi": [3, 5, 10], "often": 3, "reli": 3, "perform": [3, 6, 10], "sensit": 3, "homologi": 3, "search": [3, 4], "obtain": [3, 6], "insight": 3, "relationship": 3, "conserv": 3, "organ": 3, "she": 3, "chu": 3, "j": [3, 7], "": [3, 6, 10], "uyar": 3, "b": [3, 5], "wang": 3, "k": 3, "chen": 3, "n": 3, "2011": 3, "genblasta": 3, "enabl": [3, 12], "blast": 3, "21": [3, 11], "5": [3, 8, 13, 14], "936": 3, "949": 3, "protein_annot": 3, "run_genblast": 3, "masked_genom": 3, "protein_dataset": 3, "max_intron_length": [3, 7, 11], "genblast_timeout_sec": 3, "10800": 3, "genblast_bin": 3, "convert2blastmask_bin": 3, "convert2blastmask": 3, "makeblastdb_bin": 3, "makeblastdb": 3, "protein_set": 3, "str": [3, 8, 9], "uniprot": 3, "orthodb": 3, "execut": [3, 6, 9, 13, 14], "protein": 3, "dataset": 3, "time": 3, "timeout": 3, "sec": 3, "maximum": [3, 7, 11, 13], "intron": [3, 7, 11], "genblast_timeout": 3, "second": 3, "kit": 4, "check": 4, "instal": 4, "section": [4, 6], "further": 4, "inform": [4, 6], "how": [4, 6], "project": 4, "api": 4, "setup": 4, "requir": 6, "licens": 4, "cpg": 4, "modul": 4, "document": [4, 6], "dustmask": 4, "eponin": 4, "genblast": 4, "minimap2": 4, "run_minimap2": 7, "red": 4, "run_r": 8, "repeatmask": 4, "run_repeatmask": 9, "scallop": 4, "run_scallop": 10, "star": [4, 10], "run_star": 11, "subsample_transcriptomic_data": 11, "stringti": [4, 10], "run_stringti": 12, "trf": 4, "run_trf": 13, "trnascan": 4, "se": 4, "run_trnascan": 14, "page": [4, 6], "an": [5, 6, 8, 12], "checkout": 5, "includ": [5, 6], "product": [5, 6], "dev": 5, "hive_mast": 5, "branch": 5, "taxonomi": 5, "orm": 5, "8": 5, "bioperl": 5, "9": [5, 6], "argschema": 5, "directli": 5, "from": [5, 6, 12], "github": 5, "git": 5, "clone": 5, "http": [5, 6, 8], "com": 5, "experiment": 5, "gbiab": 5, "hive": 5, "apach": 6, "version": 6, "2": [6, 11, 13], "januari": 6, "2004": 6, "www": 6, "org": [6, 8], "definit": 6, "shall": 6, "mean": 6, "term": 6, "condit": 6, "reproduct": 6, "distribut": 6, "defin": 6, "through": [6, 10], "licensor": 6, "copyright": 6, "owner": 6, "entiti": 6, "author": 6, "grant": 6, "legal": 6, "union": 6, "act": 6, "all": 6, "other": [6, 7], "control": 6, "ar": 6, "under": 6, "common": 6, "For": 6, "purpos": 6, "power": 6, "direct": 6, "indirect": 6, "caus": 6, "manag": 6, "whether": 6, "contract": 6, "otherwis": 6, "ii": 6, "ownership": 6, "fifti": 6, "percent": 6, "more": 6, "outstand": 6, "share": 6, "iii": 6, "benefici": 6, "you": 6, "your": 6, "individu": 6, "exercis": 6, "permiss": 6, "form": 6, "prefer": 6, "modif": 6, "limit": [6, 10], "code": 6, "configur": 6, "object": 6, "ani": 6, "result": 6, "mechan": 6, "transform": 6, "translat": 6, "compil": 6, "gener": 6, "convers": 6, "media": 6, "type": [0, 1, 3, 6, 7, 8, 9, 10, 11, 12, 13, 14], "authorship": 6, "made": 6, "indic": 6, "notic": 6, "attach": 6, "exampl": 6, "provid": [6, 10], "appendix": 6, "below": 6, "deriv": 6, "base": 6, "which": 6, "editori": 6, "revis": 6, "annot": [6, 9], "elabor": 6, "repres": [6, 12], "whole": [6, 13], "origin": [6, 11], "remain": 6, "separ": 6, "mere": 6, "link": 6, "bind": 6, "name": [6, 9], "interfac": 6, "thereof": 6, "contribut": 6, "addit": 6, "intention": 6, "submit": 6, "inclus": 6, "behalf": 6, "electron": 6, "verbal": 6, "written": 6, "commun": 6, "sent": 6, "mail": 6, "list": [6, 11], "system": 6, "issu": 6, "track": 6, "discuss": 6, "exclud": 6, "conspicu": 6, "mark": 6, "design": [6, 7, 10], "write": 6, "Not": 6, "contributor": 6, "whom": 6, "receiv": 6, "subsequ": 6, "incorpor": 6, "within": 6, "subject": 6, "each": [6, 12], "herebi": 6, "perpetu": 6, "worldwid": 6, "non": 6, "exclus": 6, "charg": 6, "royalti": 6, "free": 6, "irrevoc": 6, "reproduc": 6, "prepar": 6, "publicli": 6, "displai": [6, 13], "sublicens": 6, "patent": 6, "except": 6, "state": 6, "offer": 6, "sell": 6, "import": 6, "transfer": [6, 14], "where": 6, "appli": 6, "onli": 6, "those": 6, "claim": 6, "necessarili": 6, "infring": 6, "alon": 6, "combin": 6, "wa": 6, "If": 6, "institut": 6, "litig": 6, "against": [6, 7], "cross": 6, "counterclaim": 6, "lawsuit": 6, "alleg": 6, "constitut": 6, "contributori": 6, "termin": 6, "date": 6, "redistribut": 6, "mai": 6, "copi": 6, "medium": 6, "without": 6, "meet": 6, "follow": 6, "must": 6, "give": [6, 14], "recipi": 6, "modifi": 6, "carri": 6, "promin": 6, "retain": 6, "trademark": 6, "attribut": 6, "do": 6, "pertain": 6, "text": 6, "readabl": 6, "contain": 6, "least": 6, "one": [6, 14], "place": 6, "along": 6, "wherev": 6, "third": 6, "parti": 6, "normal": 6, "appear": 6, "The": [6, 7, 11], "content": 6, "add": 6, "own": 6, "alongsid": 6, "addendum": 6, "cannot": 6, "constru": 6, "statement": 6, "compli": 6, "submiss": 6, "unless": 6, "explicitli": 6, "notwithstand": 6, "abov": 6, "noth": 6, "herein": 6, "supersed": 6, "agreement": 6, "regard": 6, "doe": 6, "trade": 6, "servic": 6, "reason": 6, "customari": 6, "describ": 6, "disclaim": 6, "warranti": 6, "applic": 6, "law": 6, "agre": 6, "AS": 6, "basi": 6, "OR": 6, "OF": 6, "kind": 6, "either": 6, "express": [6, 10], "impli": 6, "titl": 6, "merchant": 6, "fit": 6, "FOR": 6, "particular": 6, "sole": 6, "respons": 6, "determin": 6, "appropri": 6, "assum": 6, "risk": 6, "associ": 6, "liabil": 6, "In": 6, "event": 6, "theori": 6, "tort": 6, "neglig": 6, "deliber": 6, "grossli": 6, "liabl": 6, "damag": 6, "special": 6, "incident": 6, "consequenti": 6, "charact": 6, "aris": 6, "inabl": 6, "loss": 6, "goodwil": 6, "stoppag": 6, "failur": 6, "malfunct": 6, "commerci": 6, "advis": 6, "possibl": 6, "accept": 6, "while": [6, 10, 14], "choos": 6, "fee": 6, "support": 6, "indemn": 6, "oblig": 6, "right": 6, "consist": 6, "howev": 6, "indemnifi": 6, "defend": 6, "hold": 6, "harmless": 6, "incur": 6, "assert": 6, "end": 6, "AND": 6, "To": 6, "boilerpl": 6, "enclos": 6, "bracket": 6, "replac": 6, "don": 6, "t": 6, "should": 6, "comment": 6, "syntax": 6, "format": 6, "we": 6, "also": 6, "recommend": 6, "class": 6, "descript": 6, "same": 6, "print": 6, "easier": 6, "archiv": 6, "yyyi": 6, "complianc": 6, "see": 6, "languag": 6, "govern": 6, "pairwis": 7, "align": [7, 10, 11, 12, 13], "effici": [7, 10, 12], "nucleotid": 7, "versatil": 7, "index": 7, "strategi": 7, "quickli": 7, "find": 7, "approxim": 7, "match": [7, 13], "between": 7, "allow": [7, 10], "long": 7, "refer": [7, 11], "li": 7, "h": [7, 8], "2018": 7, "34": 7, "18": 7, "3094": 7, "3100": 7, "transcriptomic_annot": [7, 10, 11, 12], "minimap": 7, "long_read_fastq_dir": 7, "minimap2_bin": 7, "paftools_bin": 7, "paftool": 7, "100000": [7, 11], "read": [7, 10, 11, 12], "data": [7, 8, 10, 11, 12], "default": [1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "pacbio": 7, "size": [7, 11, 13], "repeat": [8, 9, 13], "label": 8, "train": 8, "itself": 8, "automat": 8, "entir": 8, "girgi": 8, "z": 8, "intellig": 8, "rapid": 8, "de": [8, 12], "novo": [8, 12], "scale": [8, 10], "bmc": 8, "16": 8, "227": 8, "2015": [8, 12], "1186": 8, "s12859": 8, "015": 8, "0654": 8, "red_bin": 8, "paramet": 11, "return": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "screen": 9, "interspers": 9, "smit": 9, "afa": 9, "hublei": 9, "green": 9, "p": 9, "open": 9, "repeatmasker_bin": 9, "librari": 9, "repeatmasker_engin": 9, "rmblast": 9, "store": 9, "final": 9, "gtf": 9, "repeatmasker_output": 9, "repeatmasker_path": [], "custom": 9, "output": 9, "high": 10, "quantif": 10, "transcriptom": [10, 12], "assembli": [10, 12], "It": [10, 12], "larg": 10, "precis": 10, "estim": 10, "abund": 10, "approach": 10, "reconstruct": [10, 12], "quantifi": 10, "level": 10, "shao": 10, "m": [10, 12], "kingsford": 10, "c": 10, "phase": 10, "preserv": 10, "graph": 10, "decomposit": 10, "biotechnol": 10, "2017": 10, "dec": 10, "35": 10, "1167": 10, "1169": 10, "1038": [10, 12], "nbt": [10, 12], "4020": 10, "epub": 10, "nov": 10, "13": 10, "29131147": 10, "pmc5722698": 10, "scallop_bin": 10, "prlimit_bin": 10, "prlimit": 10, "stringtie_bin": [10, 12], "memory_limit": 10, "42949672960": 10, "assembl": [10, 12], "short": [10, 11, 12], "after": [10, 11], "memori": 10, "40": [10, 13], "1024": 10, "rna": [11, 12, 14], "seq": [11, 12], "dobin": 11, "davi": 11, "ca": 11, "schlesing": 11, "f": 11, "et": 11, "al": 11, "ultrafast": 11, "univers": 11, "2013": 11, "15": [11, 14], "1093": [11, 13], "bts635": 11, "short_read_fastq_dir": 11, "delete_pre_trim_fastq": 11, "bool": 11, "fals": [11, 14], "trim_fastq": 11, "max_reads_per_sampl": 11, "star_bin": 11, "samtools_bin": 11, "samtool": 11, "trim_galore_bin": 11, "trim_galor": 11, "delet": 11, "fastq": 11, "trim": 11, "trimgalor": 11, "max": 11, "per": [11, 14], "sampl": 11, "unlimit": 11, "fastq_file_list": 11, "subsampl": 11, "pair": 11, "process": 11, "highli": 12, "potenti": 12, "novel": 12, "network": 12, "flow": 12, "well": 12, "option": 12, "step": 12, "quantit": 12, "full": 12, "multipl": 12, "variant": 12, "locu": 12, "pertea": 12, "gm": 12, "antonescu": 12, "cm": 12, "tc": 12, "mendel": 12, "jt": 12, "salzberg": 12, "sl": 12, "natur": 12, "biotechnologi": 12, "3122": 12, "tandem": 13, "finder": 13, "benson": 13, "g": 13, "analyz": 13, "nucleic": [13, 14], "acid": [13, 14], "1999": 13, "27": 13, "573": 13, "580": 13, "nar": 13, "trf_bin": 13, "match_scor": 13, "mismatch_scor": 13, "delta": 13, "7": 13, "pm": 13, "80": 13, "pi": 13, "minscor": 13, "maxperiod": 13, "500": 13, "weight": 13, "mismatch": 13, "penalti": 13, "indel": 13, "probabl": 13, "minimum": 13, "score": 13, "report": 13, "period": 13, "99": 14, "100": 14, "less": 14, "than": 14, "gigabas": 14, "tm": 14, "eddi": 14, "sr": 14, "1997": 14, "25": 14, "955": 14, "64": 14, "9023104": 14, "snc_rna_annot": 14, "trnascan_bin": 14, "trnascan_filt": 14, "eukhighconfidencefilt": 14, "filter": 14, "rtype": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "engin": 9, "boolean": 11}, "objects": {"ensembl.tools.anno.protein_annotation": [[3, 0, 0, "-", "genblast"]], "ensembl.tools.anno.protein_annotation.genblast": [[3, 1, 1, "", "run_genblast"]], "ensembl.tools.anno.repeat_annotation": [[1, 0, 0, "-", "dust"], [8, 0, 0, "-", "red"], [9, 0, 0, "-", "repeatmasker"], [13, 0, 0, "-", "trf"]], "ensembl.tools.anno.repeat_annotation.dust": [[1, 1, 1, "", "run_dust"]], "ensembl.tools.anno.repeat_annotation.red": [[8, 1, 1, "", "run_red"]], "ensembl.tools.anno.repeat_annotation.repeatmasker": [[9, 1, 1, "", "run_repeatmasker"]], "ensembl.tools.anno.repeat_annotation.trf": [[13, 1, 1, "", "run_trf"]], "ensembl.tools.anno.simple_feature_annotation": [[0, 0, 0, "-", "cpg"], [2, 0, 0, "-", "eponine"]], "ensembl.tools.anno.simple_feature_annotation.cpg": [[0, 1, 1, "", "run_cpg"]], "ensembl.tools.anno.simple_feature_annotation.eponine": [[2, 1, 1, "", "run_eponine"]], "ensembl.tools.anno.snc_rna_annotation": [[14, 0, 0, "-", "trnascan"]], "ensembl.tools.anno.snc_rna_annotation.trnascan": [[14, 1, 1, "", "run_trnascan"]], "ensembl.tools.anno.transcriptomic_annotation": [[7, 0, 0, "-", "minimap"], [10, 0, 0, "-", "scallop"], [11, 0, 0, "-", "star"], [12, 0, 0, "-", "stringtie"]], "ensembl.tools.anno.transcriptomic_annotation.minimap": [[7, 1, 1, "", "run_minimap2"]], "ensembl.tools.anno.transcriptomic_annotation.scallop": [[10, 1, 1, "", "run_scallop"]], "ensembl.tools.anno.transcriptomic_annotation.star": [[11, 1, 1, "", "run_star"], [11, 1, 1, "", "subsample_transcriptomic_data"]], "ensembl.tools.anno.transcriptomic_annotation.stringtie": [[12, 1, 1, "", "run_stringtie"]]}, "objtypes": {"0": "py:module", "1": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"]}, "titleterms": {"cpg": 0, "modul": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14], "document": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "dustmask": 1, "eponin": 2, "genblast": 3, "content": 4, "index": 4, "indic": 4, "tabl": 4, "api": 5, "setup": 5, "instal": 5, "requir": 5, "softwar": 5, "python": 5, "licens": 6, "minimap2": 7, "red": 8, "repeatmask": 9, "scallop": 10, "star": 11, "stringti": 12, "trf": 13, "trnascan": 14, "se": 14, "ensembl": 4, "anno": 4}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx": 60}, "alltitles": {"API Setup and installation": [[5, "api-setup-and-installation"]], "Requirements": [[5, "requirements"]], "Software": [[5, "software"]], "Python Modules": [[5, "python-modules"]], "Installation": [[5, "installation"]], "License": [[6, "license"]], "Ensembl-anno": [[4, "ensembl-anno"]], "Contents": [[4, "contents"]], "Index": [[4, null]], "Indices and tables": [[4, "indices-and-tables"]], "CpG Module Documentation": [[0, "module-ensembl.tools.anno.simple_feature_annotation.cpg"]], "DustMasker Module Documentation": [[1, "module-ensembl.tools.anno.repeat_annotation.dust"]], "Eponine Module Documentation": [[2, "module-ensembl.tools.anno.simple_feature_annotation.eponine"]], "Red Module Documentation": [[8, "module-ensembl.tools.anno.repeat_annotation.red"]], "Repeatmasker Module Documentation": [[9, "module-ensembl.tools.anno.repeat_annotation.repeatmasker"]], "Scallop Module Documentation": [[10, "module-ensembl.tools.anno.transcriptomic_annotation.scallop"]], "STAR Module Documentation": [[11, "module-ensembl.tools.anno.transcriptomic_annotation.star"]], "Stringtie Module Documentation": [[12, "module-ensembl.tools.anno.transcriptomic_annotation.stringtie"]], "TRF Module Documentation": [[13, "module-ensembl.tools.anno.repeat_annotation.trf"]], "tRNAscan-SE Module Documentation": [[14, "module-ensembl.tools.anno.snc_rna_annotation.trnascan"]], "Minimap2 Module Documentation": [[7, "module-ensembl.tools.anno.transcriptomic_annotation.minimap"]], "Genblast Module Documentation": [[3, "module-ensembl.tools.anno.protein_annotation.genblast"]]}, "indexentries": {"ensembl.tools.anno.protein_annotation.genblast": [[3, "module-ensembl.tools.anno.protein_annotation.genblast"]], "module": [[3, "module-ensembl.tools.anno.protein_annotation.genblast"]], "run_genblast() (in module ensembl.tools.anno.protein_annotation.genblast)": [[3, "ensembl.tools.anno.protein_annotation.genblast.run_genblast"]]}}) \ No newline at end of file +Search.setIndex({"docnames": ["cpg", "dust", "eponine", "genblast", "index", "install", "license", "minimap", "red", "repeatmasker", "scallop", "star", "stringtie", "trf", "trnascan"], "filenames": ["cpg.rst", "dust.rst", "eponine.rst", "genblast.rst", "index.rst", "install.rst", "license.rst", "minimap.rst", "red.rst", "repeatmasker.rst", "scallop.rst", "star.rst", "stringtie.rst", "trf.rst", "trnascan.rst"], "titles": ["CpG Module Documentation", "DustMasker Module Documentation", "Eponine Module Documentation", "Genblast Module Documentation", "Ensembl-anno", "API Setup and installation", "License", "Minimap2 Module Documentation", "Red Module Documentation", "Repeatmasker Module Documentation", "Scallop Module Documentation", "STAR Module Documentation", "Stringtie Module Documentation", "TRF Module Documentation", "tRNAscan-SE Module Documentation"], "terms": {"set": [0, 7, 14], "discrimin": 0, "function": [0, 3], "can": 0, "recogn": 0, "structur": [0, 10], "composit": 0, "featur": [0, 3], "island": 0, "promot": 0, "region": 0, "first": [0, 8], "splice": [0, 11, 12], "donor": 0, "site": [0, 2], "davuluri": 0, "rv": 0, "gross": 0, "i": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 12, 13], "zhang": 0, "mq": 0, "comput": [0, 2, 6], "identif": [0, 6], "exon": 0, "human": 0, "genom": [0, 1, 2, 3, 7, 8, 9, 11, 13, 14], "nat": [0, 10], "genet": 0, "2001": 0, "29": [0, 11], "4": [0, 9], "412": 0, "417": 0, "pmid": [0, 2, 10, 14], "11726928": 0, "ensembl": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14], "tool": [0, 1, 2, 3, 4, 7, 8, 9, 10, 11, 12, 13, 14], "anno": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "simple_feature_annot": [0, 2], "run_cpg": 0, "genome_fil": [0, 1, 2, 7, 8, 9, 11, 13, 14], "pathlik": [0, 1, 2, 9, 13, 14], "output_dir": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "path": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "cpg_bin": 0, "posixpath": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "cpg_lh": 0, "cpg_min_length": 0, "int": [0, 1, 2, 3, 7, 9, 10, 11, 12, 13, 14], "400": 0, "cpg_min_gc_cont": 0, "50": [0, 6], "cpg_min_o": 0, "float": [0, 2], "0": [0, 2, 6, 9, 11], "6": [0, 5], "num_thread": [0, 1, 2, 3, 7, 9, 11, 12, 13, 14], "1": [0, 1, 2, 3, 5, 6, 7, 9, 11, 12, 13, 14], "none": [0, 1, 2, 3, 7, 9, 10, 11, 12, 13, 14], "sourc": [0, 1, 2, 3, 6, 7, 8, 9, 10, 11, 12, 13, 14], "run": [0, 1, 2, 7, 8, 10, 11], "slice": [0, 1, 2, 3, 9, 13, 14], "param": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "file": [0, 1, 2, 3, 6, 7, 8, 9, 11, 13, 14], "work": [0, 1, 2, 3, 6, 7, 8, 10, 11, 12, 13, 14], "directori": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "softwar": [0, 1, 2, 3, 6, 7, 8, 10, 11, 12, 13, 14], "min": 0, "length": [0, 3, 12], "gc": 0, "frequenc": 0, "percentag": 0, "ratio": 0, "observ": 0, "expect": 0, "number": [0, 1, 2, 3, 7, 9, 11, 12, 13, 14], "cpgo": 0, "e": 0, "thread": [0, 1, 2, 3, 7, 9, 11, 12, 13, 14], "program": [1, 9, 13, 14], "identifi": [1, 3, 6, 14], "mask": [1, 3, 8], "out": [1, 4, 6], "low": [1, 9, 14], "complex": [1, 9], "part": [1, 3, 6], "us": [1, 3, 6, 7, 11, 12], "new": 1, "improv": [1, 6, 12, 14], "dust": 1, "algorithm": [1, 7, 10, 12], "morguli": 1, "A": [1, 6, 11], "gertz": 1, "em": 1, "schaffer": 1, "aa": 1, "agarwala": 1, "r": [1, 3, 9], "fast": [1, 12], "symmetr": 1, "implement": 1, "dna": [1, 2, 9, 13, 14], "sequenc": [1, 2, 3, 7, 9, 13, 14], "repeat_annot": [1, 8, 9, 13], "run_dust": 1, "dust_bin": 1, "mutiprocess": 1, "probabilist": 2, "method": 2, "detect": [2, 8, 14], "transcript": [2, 10, 11, 12], "start": 2, "tss": 2, "mammalian": 2, "good": 2, "specif": [2, 6], "excel": 2, "posit": [2, 14], "accuraci": 2, "down": 2, "ta": 2, "hubbard": 2, "tj": 2, "locat": [2, 13], "re": [2, 3, 13, 14], "2002": 2, "mar": 2, "12": [2, 10], "3": [2, 5, 10], "458": 2, "61": 2, "doi": [2, 8, 10, 11, 12, 13], "10": [2, 8, 10, 11, 12, 13], "1101": 2, "gr": 2, "216102": 2, "11875034": 2, "pmcid": [2, 10], "pmc155284": 2, "run_eponin": 2, "java_bin": 2, "java": 2, "eponine_bin": 2, "hp": 2, "user": 2, "ensw": 2, "c8": 2, "mar21": 2, "sandybridg": 2, "linuxbrew": 2, "opt": 2, "libexec": 2, "scan": 2, "jar": 2, "eponine_threshold": 2, "999": 2, "homolog": 3, "gene": [3, 10, 12, 14], "databas": 3, "One": 3, "kei": 3, "its": [3, 6, 8], "flexibl": 3, "handl": [3, 10], "compar": [3, 7], "task": 3, "accur": [3, 8, 10], "even": [3, 6], "when": 3, "have": [3, 6], "undergon": 3, "signific": 3, "evolutionari": 3, "chang": [3, 6, 12], "thi": [3, 6], "capabl": [3, 8, 10], "make": [3, 6, 10], "valuabl": [3, 10], "resourc": [3, 10], "research": [3, 11], "studi": [3, 10], "evolut": 3, "famili": 3, "across": 3, "divers": 3, "speci": [3, 9], "ha": [3, 6], "been": [3, 6], "wide": [3, 11], "variou": 3, "analys": 3, "avail": [3, 6, 7, 11, 12], "standalon": 3, "command": [3, 10], "line": 3, "differ": [3, 6], "bioinformat": [3, 7, 8, 11], "pipelin": 3, "field": [3, 6], "analysi": [3, 5, 10], "often": 3, "reli": 3, "perform": [3, 6, 10], "sensit": 3, "homologi": 3, "search": [3, 4], "obtain": [3, 6], "insight": 3, "relationship": 3, "conserv": 3, "organ": 3, "she": 3, "chu": 3, "j": [3, 7], "": [3, 6, 10], "uyar": 3, "b": [3, 5], "wang": 3, "k": 3, "chen": 3, "n": 3, "2011": 3, "genblasta": 3, "enabl": [3, 12], "blast": 3, "21": [3, 11], "5": [3, 8, 13, 14], "936": 3, "949": 3, "protein_annot": 3, "run_genblast": 3, "masked_genom": 3, "protein_dataset": 3, "max_intron_length": [3, 7, 11], "genblast_timeout_sec": 3, "10800": 3, "genblast_bin": 3, "convert2blastmask_bin": 3, "convert2blastmask": 3, "makeblastdb_bin": 3, "makeblastdb": 3, "protein_set": 3, "str": [3, 8, 9], "uniprot": 3, "orthodb": 3, "execut": [3, 6, 9, 13, 14], "protein": 3, "dataset": 3, "time": 3, "timeout": 3, "sec": 3, "maximum": [3, 7, 11, 13], "intron": [3, 7, 11], "genblast_timeout": 3, "second": 3, "kit": 4, "check": 4, "instal": 4, "section": [4, 6], "further": 4, "inform": [4, 6], "how": [4, 6], "project": 4, "api": 4, "setup": 4, "requir": 6, "licens": 4, "cpg": 4, "modul": 4, "document": [4, 6], "dustmask": 4, "eponin": 4, "genblast": 4, "minimap2": 4, "run_minimap2": 7, "red": 4, "run_r": 8, "repeatmask": 4, "run_repeatmask": 9, "scallop": 4, "run_scallop": 10, "star": [4, 10], "run_star": 11, "subsample_transcriptomic_data": 11, "stringti": [4, 10], "run_stringti": 12, "trf": 4, "run_trf": 13, "trnascan": 4, "se": 4, "run_trnascan": 14, "page": [4, 6], "an": [5, 6, 8, 12], "checkout": 5, "includ": [5, 6], "product": [5, 6], "dev": 5, "hive_mast": 5, "branch": 5, "taxonomi": 5, "orm": 5, "8": 5, "bioperl": 5, "9": [5, 6], "argschema": 5, "directli": 5, "from": [5, 6, 12], "github": 5, "git": 5, "clone": 5, "http": [5, 6, 8], "com": 5, "experiment": 5, "gbiab": 5, "hive": 5, "apach": 6, "version": 6, "2": [6, 11, 13], "januari": 6, "2004": 6, "www": 6, "org": [6, 8], "definit": 6, "shall": 6, "mean": 6, "term": 6, "condit": 6, "reproduct": 6, "distribut": 6, "defin": 6, "through": [6, 10], "licensor": 6, "copyright": 6, "owner": 6, "entiti": 6, "author": 6, "grant": 6, "legal": 6, "union": 6, "act": 6, "all": 6, "other": [6, 7], "control": 6, "ar": 6, "under": 6, "common": 6, "For": 6, "purpos": 6, "power": 6, "direct": 6, "indirect": 6, "caus": 6, "manag": 6, "whether": 6, "contract": 6, "otherwis": 6, "ii": 6, "ownership": 6, "fifti": 6, "percent": 6, "more": 6, "outstand": 6, "share": 6, "iii": 6, "benefici": 6, "you": 6, "your": 6, "individu": 6, "exercis": 6, "permiss": 6, "form": 6, "prefer": 6, "modif": 6, "limit": [6, 10], "code": 6, "configur": 6, "object": 6, "ani": 6, "result": 6, "mechan": 6, "transform": 6, "translat": 6, "compil": 6, "gener": 6, "convers": 6, "media": 6, "type": [0, 1, 3, 6, 7, 8, 9, 10, 11, 12, 13, 14], "authorship": 6, "made": 6, "indic": 6, "notic": 6, "attach": 6, "exampl": 6, "provid": [6, 10], "appendix": 6, "below": 6, "deriv": 6, "base": 6, "which": 6, "editori": 6, "revis": 6, "annot": [6, 9], "elabor": 6, "repres": [6, 12], "whole": [6, 13], "origin": [6, 11], "remain": 6, "separ": 6, "mere": 6, "link": 6, "bind": 6, "name": [6, 9], "interfac": 6, "thereof": 6, "contribut": 6, "addit": 6, "intention": 6, "submit": 6, "inclus": 6, "behalf": 6, "electron": 6, "verbal": 6, "written": 6, "commun": 6, "sent": 6, "mail": 6, "list": [6, 11], "system": 6, "issu": 6, "track": 6, "discuss": 6, "exclud": 6, "conspicu": 6, "mark": 6, "design": [6, 7, 10], "write": 6, "Not": 6, "contributor": 6, "whom": 6, "receiv": 6, "subsequ": 6, "incorpor": 6, "within": 6, "subject": 6, "each": [6, 12], "herebi": 6, "perpetu": 6, "worldwid": 6, "non": 6, "exclus": 6, "charg": 6, "royalti": 6, "free": 6, "irrevoc": 6, "reproduc": 6, "prepar": 6, "publicli": 6, "displai": [6, 13], "sublicens": 6, "patent": 6, "except": 6, "state": 6, "offer": 6, "sell": 6, "import": 6, "transfer": [6, 14], "where": 6, "appli": 6, "onli": 6, "those": 6, "claim": 6, "necessarili": 6, "infring": 6, "alon": 6, "combin": 6, "wa": 6, "If": 6, "institut": 6, "litig": 6, "against": [6, 7], "cross": 6, "counterclaim": 6, "lawsuit": 6, "alleg": 6, "constitut": 6, "contributori": 6, "termin": 6, "date": 6, "redistribut": 6, "mai": 6, "copi": 6, "medium": 6, "without": 6, "meet": 6, "follow": 6, "must": 6, "give": [6, 14], "recipi": 6, "modifi": 6, "carri": 6, "promin": 6, "retain": 6, "trademark": 6, "attribut": 6, "do": 6, "pertain": 6, "text": 6, "readabl": 6, "contain": 6, "least": 6, "one": [6, 14], "place": 6, "along": 6, "wherev": 6, "third": 6, "parti": 6, "normal": 6, "appear": 6, "The": [6, 7, 11], "content": 6, "add": 6, "own": 6, "alongsid": 6, "addendum": 6, "cannot": 6, "constru": 6, "statement": 6, "compli": 6, "submiss": 6, "unless": 6, "explicitli": 6, "notwithstand": 6, "abov": 6, "noth": 6, "herein": 6, "supersed": 6, "agreement": 6, "regard": 6, "doe": 6, "trade": 6, "servic": 6, "reason": 6, "customari": 6, "describ": 6, "disclaim": 6, "warranti": 6, "applic": 6, "law": 6, "agre": 6, "AS": 6, "basi": 6, "OR": 6, "OF": 6, "kind": 6, "either": 6, "express": [6, 10], "impli": 6, "titl": 6, "merchant": 6, "fit": 6, "FOR": 6, "particular": 6, "sole": 6, "respons": 6, "determin": 6, "appropri": 6, "assum": 6, "risk": 6, "associ": 6, "liabil": 6, "In": 6, "event": 6, "theori": 6, "tort": 6, "neglig": 6, "deliber": 6, "grossli": 6, "liabl": 6, "damag": 6, "special": 6, "incident": 6, "consequenti": 6, "charact": 6, "aris": 6, "inabl": 6, "loss": 6, "goodwil": 6, "stoppag": 6, "failur": 6, "malfunct": 6, "commerci": 6, "advis": 6, "possibl": 6, "accept": 6, "while": [6, 10, 14], "choos": 6, "fee": 6, "support": 6, "indemn": 6, "oblig": 6, "right": 6, "consist": 6, "howev": 6, "indemnifi": 6, "defend": 6, "hold": 6, "harmless": 6, "incur": 6, "assert": 6, "end": 6, "AND": 6, "To": 6, "boilerpl": 6, "enclos": 6, "bracket": 6, "replac": 6, "don": 6, "t": 6, "should": 6, "comment": 6, "syntax": 6, "format": 6, "we": 6, "also": 6, "recommend": 6, "class": 6, "descript": 6, "same": 6, "print": 6, "easier": 6, "archiv": 6, "yyyi": 6, "complianc": 6, "see": 6, "languag": 6, "govern": 6, "pairwis": 7, "align": [7, 10, 11, 12, 13], "effici": [7, 10, 12], "nucleotid": 7, "versatil": 7, "index": 7, "strategi": 7, "quickli": 7, "find": 7, "approxim": 7, "match": [7, 13], "between": 7, "allow": [7, 10], "long": 7, "refer": [7, 11], "li": 7, "h": [7, 8], "2018": 7, "34": 7, "18": 7, "3094": 7, "3100": 7, "transcriptomic_annot": [7, 10, 11, 12], "minimap": 7, "long_read_fastq_dir": 7, "minimap2_bin": 7, "paftools_bin": 7, "paftool": 7, "100000": [7, 11], "read": [7, 10, 11, 12], "data": [7, 8, 10, 11, 12], "default": [1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "pacbio": 7, "size": [7, 11, 13], "repeat": [8, 9, 13], "label": 8, "train": 8, "itself": 8, "automat": 8, "entir": 8, "girgi": 8, "z": 8, "intellig": 8, "rapid": 8, "de": [8, 12], "novo": [8, 12], "scale": [8, 10], "bmc": 8, "16": 8, "227": 8, "2015": [8, 12], "1186": 8, "s12859": 8, "015": 8, "0654": 8, "red_bin": 8, "paramet": 11, "return": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "screen": 9, "interspers": 9, "smit": 9, "afa": 9, "hublei": 9, "green": 9, "p": 9, "open": 9, "repeatmasker_bin": 9, "librari": 9, "repeatmasker_engin": 9, "rmblast": 9, "store": 9, "final": 9, "gtf": 9, "repeatmasker_output": 9, "repeatmasker_path": [], "custom": 9, "output": 9, "high": 10, "quantif": 10, "transcriptom": [10, 12], "assembli": [10, 12], "It": [10, 12], "larg": 10, "precis": 10, "estim": 10, "abund": 10, "approach": 10, "reconstruct": [10, 12], "quantifi": 10, "level": 10, "shao": 10, "m": [10, 12], "kingsford": 10, "c": 10, "phase": 10, "preserv": 10, "graph": 10, "decomposit": 10, "biotechnol": 10, "2017": 10, "dec": 10, "35": 10, "1167": 10, "1169": 10, "1038": [10, 12], "nbt": [10, 12], "4020": 10, "epub": 10, "nov": 10, "13": 10, "29131147": 10, "pmc5722698": 10, "scallop_bin": 10, "prlimit_bin": 10, "prlimit": 10, "stringtie_bin": [10, 12], "memory_limit": 10, "42949672960": 10, "assembl": [10, 12], "short": [10, 11, 12], "after": [10, 11], "memori": 10, "40": [10, 13], "1024": 10, "rna": [11, 12, 14], "seq": [11, 12], "dobin": 11, "davi": 11, "ca": 11, "schlesing": 11, "f": 11, "et": 11, "al": 11, "ultrafast": 11, "univers": 11, "2013": 11, "15": [11, 14], "1093": [11, 13], "bts635": 11, "short_read_fastq_dir": 11, "delete_pre_trim_fastq": 11, "bool": 11, "fals": [11, 14], "trim_fastq": 11, "max_reads_per_sampl": 11, "star_bin": 11, "samtools_bin": 11, "samtool": 11, "trim_galore_bin": 11, "trim_galor": 11, "delet": 11, "fastq": 11, "trim": 11, "trimgalor": 11, "max": 11, "per": [11, 14], "sampl": 11, "unlimit": 11, "fastq_file_list": 11, "subsampl": 11, "pair": 11, "process": 11, "highli": 12, "potenti": 12, "novel": 12, "network": 12, "flow": 12, "well": 12, "option": 12, "step": 12, "quantit": 12, "full": 12, "multipl": 12, "variant": 12, "locu": 12, "pertea": 12, "gm": 12, "antonescu": 12, "cm": 12, "tc": 12, "mendel": 12, "jt": 12, "salzberg": 12, "sl": 12, "natur": 12, "biotechnologi": 12, "3122": 12, "tandem": 13, "finder": 13, "benson": 13, "g": 13, "analyz": 13, "nucleic": [13, 14], "acid": [13, 14], "1999": 13, "27": 13, "573": 13, "580": 13, "nar": 13, "trf_bin": 13, "match_scor": 13, "mismatch_scor": 13, "delta": 13, "7": 13, "pm": 13, "80": 13, "pi": 13, "minscor": 13, "maxperiod": 13, "500": 13, "weight": 13, "mismatch": 13, "penalti": 13, "indel": 13, "probabl": 13, "minimum": 13, "score": 13, "report": 13, "period": 13, "99": 14, "100": 14, "less": 14, "than": 14, "gigabas": 14, "tm": 14, "eddi": 14, "sr": 14, "1997": 14, "25": 14, "955": 14, "64": 14, "9023104": 14, "snc_rna_annot": 14, "trnascan_bin": 14, "trnascan_filt": 14, "eukhighconfidencefilt": 14, "filter": 14, "rtype": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "engin": 9, "boolean": 11}, "objects": {"ensembl.tools.anno.protein_annotation": [[3, 0, 0, "-", "genblast"]], "ensembl.tools.anno.protein_annotation.genblast": [[3, 1, 1, "", "run_genblast"]], "ensembl.tools.anno.repeat_annotation": [[1, 0, 0, "-", "dust"], [8, 0, 0, "-", "red"], [9, 0, 0, "-", "repeatmasker"], [13, 0, 0, "-", "trf"]], "ensembl.tools.anno.repeat_annotation.dust": [[1, 1, 1, "", "run_dust"]], "ensembl.tools.anno.repeat_annotation.red": [[8, 1, 1, "", "run_red"]], "ensembl.tools.anno.repeat_annotation.repeatmasker": [[9, 1, 1, "", "run_repeatmasker"]], "ensembl.tools.anno.repeat_annotation.trf": [[13, 1, 1, "", "run_trf"]], "ensembl.tools.anno.simple_feature_annotation": [[0, 0, 0, "-", "cpg"], [2, 0, 0, "-", "eponine"]], "ensembl.tools.anno.simple_feature_annotation.cpg": [[0, 1, 1, "", "run_cpg"]], "ensembl.tools.anno.simple_feature_annotation.eponine": [[2, 1, 1, "", "run_eponine"]], "ensembl.tools.anno.snc_rna_annotation": [[14, 0, 0, "-", "trnascan"]], "ensembl.tools.anno.snc_rna_annotation.trnascan": [[14, 1, 1, "", "run_trnascan"]], "ensembl.tools.anno.transcriptomic_annotation": [[7, 0, 0, "-", "minimap"], [10, 0, 0, "-", "scallop"], [11, 0, 0, "-", "star"], [12, 0, 0, "-", "stringtie"]], "ensembl.tools.anno.transcriptomic_annotation.minimap": [[7, 1, 1, "", "run_minimap2"]], "ensembl.tools.anno.transcriptomic_annotation.scallop": [[10, 1, 1, "", "run_scallop"]], "ensembl.tools.anno.transcriptomic_annotation.star": [[11, 1, 1, "", "run_star"], [11, 1, 1, "", "subsample_transcriptomic_data"]], "ensembl.tools.anno.transcriptomic_annotation.stringtie": [[12, 1, 1, "", "run_stringtie"]]}, "objtypes": {"0": "py:module", "1": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "function", "Python function"]}, "titleterms": {"cpg": 0, "modul": [0, 1, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 14], "document": [0, 1, 2, 3, 7, 8, 9, 10, 11, 12, 13, 14], "dustmask": 1, "eponin": 2, "genblast": 3, "content": 4, "index": 4, "indic": 4, "tabl": 4, "api": 5, "setup": 5, "instal": 5, "requir": 5, "softwar": 5, "python": 5, "licens": 6, "minimap2": 7, "red": 8, "repeatmask": 9, "scallop": 10, "star": 11, "stringti": 12, "trf": 13, "trnascan": 14, "se": 14, "ensembl": 4, "anno": 4}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.viewcode": 1, "sphinx": 60}, "alltitles": {"API Setup and installation": [[5, "api-setup-and-installation"]], "Requirements": [[5, "requirements"]], "Software": [[5, "software"]], "Python Modules": [[5, "python-modules"]], "Installation": [[5, "installation"]], "License": [[6, "license"]], "Ensembl-anno": [[4, "ensembl-anno"]], "Contents": [[4, "contents"]], "Index": [[4, null]], "Indices and tables": [[4, "indices-and-tables"]], "CpG Module Documentation": [[0, "module-ensembl.tools.anno.simple_feature_annotation.cpg"]], "DustMasker Module Documentation": [[1, "module-ensembl.tools.anno.repeat_annotation.dust"]], "Eponine Module Documentation": [[2, "module-ensembl.tools.anno.simple_feature_annotation.eponine"]], "Red Module Documentation": [[8, "module-ensembl.tools.anno.repeat_annotation.red"]], "Repeatmasker Module Documentation": [[9, "module-ensembl.tools.anno.repeat_annotation.repeatmasker"]], "Scallop Module Documentation": [[10, "module-ensembl.tools.anno.transcriptomic_annotation.scallop"]], "STAR Module Documentation": [[11, "module-ensembl.tools.anno.transcriptomic_annotation.star"]], "Stringtie Module Documentation": [[12, "module-ensembl.tools.anno.transcriptomic_annotation.stringtie"]], "TRF Module Documentation": [[13, "module-ensembl.tools.anno.repeat_annotation.trf"]], "tRNAscan-SE Module Documentation": [[14, "module-ensembl.tools.anno.snc_rna_annotation.trnascan"]], "Genblast Module Documentation": [[3, "module-ensembl.tools.anno.protein_annotation.genblast"]], "Minimap2 Module Documentation": [[7, "module-ensembl.tools.anno.transcriptomic_annotation.minimap"]]}, "indexentries": {"ensembl.tools.anno.transcriptomic_annotation.minimap": [[7, "module-ensembl.tools.anno.transcriptomic_annotation.minimap"]], "module": [[7, "module-ensembl.tools.anno.transcriptomic_annotation.minimap"]], "run_minimap2() (in module ensembl.tools.anno.transcriptomic_annotation.minimap)": [[7, "ensembl.tools.anno.transcriptomic_annotation.minimap.run_minimap2"]]}}) \ No newline at end of file diff --git a/src/python/ensembl/tools/anno/transcriptomic_annotation/minimap.py b/src/python/ensembl/tools/anno/transcriptomic_annotation/minimap.py index 9e51d10..6b874a5 100644 --- a/src/python/ensembl/tools/anno/transcriptomic_annotation/minimap.py +++ b/src/python/ensembl/tools/anno/transcriptomic_annotation/minimap.py @@ -48,20 +48,21 @@ def run_minimap2( """ Run Minimap2 to align long read data against genome file. Default Minimap set for PacBio data. - :param output_dir: Working directory path. - :type output_dir: Path - :param long_read_fastq_dir: Long read directory path. - :type long_read_fastq_dir: Path - :param genome_file: Genome file path. - :type genome_file: Path - :param minimap2_bin: Software path. - :type minimap2_bin: Path, default minimap2 - :param paftools_bin: Software path. - :type paftools_bin: Path, default paftools.js - :param max_intron_length: The maximum intron size for alignments. Defaults to 100000. - :type max_intron_length: int, default 100000 - :param num_threads: Number of available threads. - :type num_threads: int, default 1 + + :param output_dir: Working directory path. + :type output_dir: Path + :param long_read_fastq_dir: Long read directory path. + :type long_read_fastq_dir: Path + :param genome_file: Genome file path. + :type genome_file: Path + :param minimap2_bin: Software path. + :type minimap2_bin: Path, default minimap2 + :param paftools_bin: Software path. + :type paftools_bin: Path, default paftools.js + :param max_intron_length: The maximum intron size for alignments. Defaults to 100000. + :type max_intron_length: int, default 100000 + :param num_threads: Number of available threads. + :type num_threads: int, default 1 :return: None :rtype: None