Merge pull request #95 from alan-jarmusch/master

update to example code and ReDU logo

examples/Fig1d_ChemicalEnrichment/20190805_ReDU_ChemicalEnrichment.R

@@ -47,7 +47,7 @@ plot <- ggplot(df_plot,aes(x=as.factor(sample), as.numeric(proportion*100)))+
         legend.title=element_text(colour="black", size=6),
         legend.text=element_text(colour="black", size=6) ) +
  # labs(x="", y="Annotated in Proportion of Files", title = chemical)
-  labs(x="", y="Annotated in Human Files (%)")
+  labs(x="", y="Annotated in Files (%)")
 print(plot)  
 ggsave(plot, file=paste0("Manuscript/Figures/Source_Material/ReDU_ChemicalEnrichment_",chemical,".pdf"), 
        width = 1, height = 1.15, units = "in", useDingbats=FALSE)

examples/Fig1d_ChemicalEnrichment/20190805_ReDU_ChemicalEnrichment_Bacteria.R

@@ -0,0 +1,52 @@
+library(data.table)
+library(dplyr)
+library(tidyr)
+library(ggplot2)
+setwd("~/Research/Projects/ReDU_MS2")
+
+df <- fread("Manuscript/Data/ReDU_chemical_enrichment_bacteria.txt", sep="\t", header=TRUE)
+
+df[1:5,1:7]
+colnames(df) <- c("Chemical",
+                  "# 1423|Bacillus subtilis (n=89)","1423|Bacillus subtilis (n=89)",
+                  "# 1280|Staphylococcus aureus (n=49)","1280|Staphylococcus aureus (n=49)",
+                  "# 1883|Streptomyces (n=7)","1883|Streptomyces (n=7)"
+                  #"# of G4","Proportion of G4",
+                  #"# of G5","Proportion of G5",
+                  #"# of G6","Proportion of G6",
+                  )
+
+df <- df[,c(1,3,5,7)]
+
+df_gather <- gather(data=df, sample, proportion, 2:length(df))
+
+#chemical <- "Surfactin_C14"
+chemical <- "Spectral Match to Cholic acid from NIST14"
+
+df_plot <- subset(df_gather, df_gather$Chemical == chemical)
+
+plot <- ggplot(df_plot,aes(x=as.factor(sample), as.numeric(proportion*100)))+
+                 geom_bar(aes(fill=sample), stat="identity", width=0.75)+
+  #facet_wrap(~Comparison, ncol=3)+
+  scale_fill_manual(values = c("#e41a1c","#377eb8","#fdbf6f"))+
+  theme_minimal()+
+  theme(panel.grid.major.x=element_blank(),
+        panel.grid.major.y=element_line(colour="grey90",size=0.5, linetype="dashed"),
+        panel.grid.minor=element_blank(),
+        axis.ticks=element_line(colour ="black",size=0.5, linetype="solid"),
+        axis.text=element_text(colour="black",size=6),
+        axis.text.x=element_text(colour="black", size=6),
+        axis.line=element_line(colour="black",size=0.5, linetype="solid"),                  
+        axis.title=element_text(colour="black",size=6),
+        strip.text.x=element_text(colour="black",size=6),
+        aspect.ratio=2,
+        title=element_text(colour="black", size=6),
+        legend.position="none",
+        legend.title=element_text(colour="black", size=6),
+        legend.text=element_text(colour="black", size=6) ) +
+ # labs(x="", y="Annotated in Proportion of Files", title = chemical)
+  labs(x="", y="Annotated in Files (%)")
+print(plot)  
+ggsave(plot, file=paste0("Manuscript/Figures/Source_Material/ReDU_ChemicalEnrichment_",chemical,".pdf"), 
+       width = 1, height = 1.15, units = "in", useDingbats=FALSE)
+

examples/MS2_library_information/20190805_ReDU_LibraryInformation.R

@@ -0,0 +1,18 @@
+library(data.table)
+library(dplyr)
+library(ggplot2)
+setwd("~/Research/Projects/ReDU_MS2")
+
+df <- fread("Manuscript/Data/ReDU_all_identifications.tsv", sep="\t", header=TRUE)
+
+library_GNPS <- df %>% group_by(Organism,Compound_Name) %>% summarise(Unique = n_distinct(full_CCMS_path))
+library_GNPS[1:10,1:3]
+
+library_GNPSinfo <- library_GNPS %>% group_by(Organism) %>% summarise(total_hits = sum(Unique))
+colnames(library_GNPSinfo)[1] <- "library_name"
+
+library_size <- fread("Manuscript/Data/GNPS_library_annotation_info/LIVING-DATA-SEARCH-ba6a5b6a-production_library_sizes-main.tsv", sep="\t", header=TRUE)
+
+library_GNPSinfo_final <- library_GNPSinfo %>% left_join(library_size, by="library_name") %>% mutate(proportion = total_hits/number_spectra)
+
+write.csv(library_GNPSinfo_final, "Manuscript/Figures/Source_Material/ReDUSummary_libraryinfo.csv", row.names=FALSE)

examples/MS2_library_information/LIVING-DATA-SEARCH-ba6a5b6a-production_library_sizes-main.tsv

@@ -0,0 +1,33 @@
+library_name	number_spectra
+GNPS-COLLECTIONS-MISC	46
+MMV_NEGATIVE	47
+GNPS-COLLECTIONS-PESTICIDES-NEGATIVE	76
+LDB_POSITIVE	83
+MMV_POSITIVE	110
+GNPS-FAULKNERLEGACY	127
+GNPS-PRESTWICKPHYTOCHEM	143
+MIADB	172
+BILELIB19	177
+GNPS-NIH-CLINICALCOLLECTION2	195
+LDB_NEGATIVE	226
+GNPS-NIH-CLINICALCOLLECTION1	377
+DEREPLICATOR_IDENTIFIED_LIBRARY	379
+CASMI	568
+GNPS-EMBL-MCF	585
+GNPS-COLLECTIONS-PESTICIDES-POSITIVE	653
+GNPS-SELLECKCHEM-FDA-PART2	656
+SUMNER	904
+GNPS-NIH-NATURALPRODUCTSLIBRARY	1267
+GNPS-NIH-SMALLMOLECULEPHARMACOLOGICALLYACTIVE	1460
+MASSBANKEU	1492
+GNPS-NIH-NATURALPRODUCTSLIBRARY_ROUND2_NEGATIVE	1863
+HMDB	2235
+GNPS-SELLECKCHEM-FDA-PART1	2388
+GNPS-LIBRARY	4697
+GNPS-NIST14-MATCHES	5763
+GNPS-NIH-NATURALPRODUCTSLIBRARY_ROUND2_POSITIVE	5796
+RESPECT	7112
+MASSBANK	11999
+PNNL-LIPIDS-NEGATIVE	16142
+PNNL-LIPIDS-POSITIVE	30582
+MONA	49241

examples/MS2_library_information/ReDUSummary_libraryinfo.csv

@@ -0,0 +1,32 @@
+"library_name","total_hits","number_spectra","proportion"
+"BILELIB19",25392,177,143.457627118644
+"CASMI",9164,568,16.1338028169014
+"DEREPLICATOR_IDENTIFIED_LIBRARY",4840,379,12.7704485488127
+"GNPS-COLLECTIONS-MISC",5757,46,125.152173913043
+"GNPS-COLLECTIONS-PESTICIDES-NEGATIVE",9,76,0.118421052631579
+"GNPS-COLLECTIONS-PESTICIDES-POSITIVE",2707,653,4.14548238897397
+"GNPS-EMBL-MCF",31082,585,53.1316239316239
+"GNPS-FAULKNERLEGACY",1322,127,10.4094488188976
+"GNPS-LIBRARY",150457,4697,32.0325739833937
+"GNPS-NIH-CLINICALCOLLECTION1",3512,377,9.31564986737401
+"GNPS-NIH-CLINICALCOLLECTION2",671,195,3.44102564102564
+"GNPS-NIH-NATURALPRODUCTSLIBRARY",4474,1267,3.53117600631413
+"GNPS-NIH-NATURALPRODUCTSLIBRARY_ROUND2_NEGATIVE",1667,1863,0.894793344068706
+"GNPS-NIH-NATURALPRODUCTSLIBRARY_ROUND2_POSITIVE",194438,5796,33.5469289164941
+"GNPS-NIH-SMALLMOLECULEPHARMACOLOGICALLYACTIVE",4625,1460,3.16780821917808
+"GNPS-NIST14-MATCHES",944273,5763,163.85094568801
+"GNPS-PRESTWICKPHYTOCHEM",689,143,4.81818181818182
+"GNPS-SELLECKCHEM-FDA-PART1",12760,2388,5.34338358458962
+"GNPS-SELLECKCHEM-FDA-PART2",5050,656,7.69817073170732
+"HMDB",16827,2235,7.52885906040268
+"LDB_NEGATIVE",2632,226,11.646017699115
+"LDB_POSITIVE",745,83,8.97590361445783
+"MASSBANK",110935,11999,9.24535377948162
+"MASSBANKEU",9239,1492,6.19235924932976
+"MIADB",571,172,3.31976744186047
+"MMV_POSITIVE",585,110,5.31818181818182
+"MONA",278184,49241,5.64943847606669
+"PNNL-LIPIDS-NEGATIVE",3126,16142,0.193656300334531
+"PNNL-LIPIDS-POSITIVE",298000,30582,9.74429402916748
+"RESPECT",33684,7112,4.73622047244094
+"SUMNER",2742,904,3.03318584070796

examples/MS2_library_information/params.xml

@@ -0,0 +1,18 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<parameters>
+<parameter name="RUN_CLUSTER">NO</parameter>
+<parameter name="RUN_CONVERT">NO</parameter>
+<parameter name="RUN_DEREPLICATOR">NO</parameter>
+<parameter name="RUN_GLOBALNETWORK">NO</parameter>
+<parameter name="RUN_LIBRARY_FILES_CREATION">YES</parameter>
+<parameter name="RUN_MOLECULEEXPLORER">NO</parameter>
+<parameter name="RUN_REPORTER">NO</parameter>
+<parameter name="RUN_SEARCH">NO</parameter>
+<parameter name="desc">Test Library Creation [9]</parameter>
+<parameter name="email">[email protected]</parameter>
+<parameter name="task">ba6a5b6a1c0946b3a641c67ad59fb2df</parameter>
+<parameter name="user">mwang87</parameter>
+<parameter name="uuid">1E14A8E2-5075-0001-3D8A-6940F0501B9D</parameter>
+<parameter name="workflow">LIVING-DATA-SEARCH</parameter>
+<parameter name="workflow_version">1.2.5</parameter>
+</parameters>