updated expression docker and FSES headings

FSES data said 'environment' not 'environmental',. enrichR package was removed from CRAN so expression data was not being built

data/README.md

@@ -1,9 +1,30 @@
 ## Data directory
 This directory contains existing data and references files to be added to the SRP analytics database. These data are not private in any way, but mainly serve as reference files for the broader repository.
 
+### Data Schema file
+Incoming data requires a pre-defined schema so we can validate things
+BEFORE they are going to be processed by our pipeline. This schema
+also enables an easy way to check if a file CAN be processed before
+adding it to the list.
+
+### Data file manifest
+The data file manifest contains a link to all the other data files,
+including those referenced in this document. This file can be found
+[here](./srp_build_files.csv). 
+
 ### Chemical reference information
 
+Many of the build files are actual reference information. 
+
+#### Chemical id file
+#### Chemical classification file
+#### compTox file
+
 ### Environmental sample information
 
+#### Sample id file
+
 ### Existing Zebrafish data
 
+
+####

data/fses/FSES_indoor_outdoor_study.csv

@@ -1,4 +1,4 @@
-"","SampleNumber","date_sampled","date_sample_start","sample_matrix","technology","Sample_ID","zf_lims_id","cas_number","ClientName","SampleName","LocationLat","LocationLon","LocationName","LocationAlternateDescription","AlternateName","Chemical_ID","measurement_value","measurement_value_qualifier","measurement_value_unit","measurement_value_molar","measurement_value_molar_unit","environment_concentration","environment_concentration_qualifier","environment_concentration_unit","environment_concentration_molar","environment_concentration_molar_unit","parentSampleNumber","childSampleNumber","projectName","projectLink"
+"","SampleNumber","date_sampled","date_sample_start","sample_matrix","technology","Sample_ID","zf_lims_id","cas_number","ClientName","SampleName","LocationLat","LocationLon","LocationName","LocationAlternateDescription","AlternateName","Chemical_ID","measurement_value","measurement_value_qualifier","measurement_value_unit","measurement_value_molar","measurement_value_molar_unit","environmental_concentration","environmental_concentration_qualifier","environmental_concentration_unit","environmental_concentration_molar","environmental_concentration_molar_unit","parentSampleNumber","childSampleNumber","projectName","projectLink"
 "1","A181010","2018-09-30 11:43:00","2018-09-05 00:00:00","PSD-Air","GC-MS - RTL DRS Screening - MASV15",NA,NA,"120-82-1","FSES Laboratory","La Pine, OR Outdoor",43.6704,121.5036,"LaPine, OR",NA,NA,NA,"<50 J","U","pg/uL","<276 J","pmol/mL",NA,NA,NA,NA,NA,NA,NA,"Forest Fire Citizen Science 2018 (Pilot)","http://fses.oregonstate.edu/research/indoor-outdoor-air-quality"
 "2","A181010","2018-09-30 11:43:00","2018-09-05 00:00:00","PSD-Air","GC-MS - RTL DRS Screening - MASV15",NA,NA,"96-12-8","FSES Laboratory","La Pine, OR Outdoor",43.6704,121.5036,"LaPine, OR",NA,NA,NA,"<100 J","U","pg/uL","<423 J","pmol/mL",NA,NA,NA,NA,NA,NA,NA,"Forest Fire Citizen Science 2018 (Pilot)","http://fses.oregonstate.edu/research/indoor-outdoor-air-quality"
 "3","A181010","2018-09-30 11:43:00","2018-09-05 00:00:00","PSD-Air","GC-MS - RTL DRS Screening - MASV15",NA,NA,"95-50-1","FSES Laboratory","La Pine, OR Outdoor",43.6704,121.5036,"LaPine, OR",NA,NA,NA,"<50 J","U","pg/uL","<340 J","pmol/mL",NA,NA,NA,NA,NA,NA,NA,"Forest Fire Citizen Science 2018 (Pilot)","http://fses.oregonstate.edu/research/indoor-outdoor-air-quality"

data/fses/fses_data_for_pnnl_4-27-2021.csv

@@ -1,4 +1,4 @@
-SampleNumber,date_sampled,sample_matrix,technology,Sample_ID,zf_lims_id,cas_number,ClientName,SampleName,LocationLat,LocationLon,LocationName,LocationAlternateDescription,AlternateName,Chemical_ID,measurement_value,measurement_value_qualifier,measurement_value_unit,measurement_value_molar,measurement_value_molar_unit,environment_concentration,environment_concentration_qualifier,environment_concentration_unit,environment_concentration_molar,environment_concentration_molar_unit,parentSampleNumber,childSampleNumber,projectName,date_sample_start,projectLink
+enSampleNumber,date_sampled,sample_matrix,technology,Sample_ID,zf_lims_id,cas_number,ClientName,SampleName,LocationLat,LocationLon,LocationName,LocationAlternateDescription,AlternateName,Chemical_ID,measurement_value,measurement_value_qualifier,measurement_value_unit,measurement_value_molar,measurement_value_molar_unit,environmental_concentration,environmental_concentration_qualifier,environmental_concentration_unit,environmental_concentration_molar,environmental_concentration_molar_unit,parentSampleNumber,childSampleNumber,projectName,date_sample_start,projectLink
 10JUL11-01-007,2010-07-07 8:00:00,PSD-Water,LFT - Spiked,NULL,10JUL11-01-015,120-12-7,NULL,LA-LFT-W-SPK,29.2611,-89.2611,"Grand Isle, Louisiana",NULL,"Grand Isle, LA",0,0,NULL,pg/uL,0,pmol/mL,BDL,NULL,ng/L,nc:BDL,nmol/L,NULL,A100078,NA,NA,NA
 10JUL11-01-007,2010-07-07 8:00:00,PSD-Water,LFT - Spiked,NULL,10JUL11-01-015,129-00-0,NULL,LA-LFT-W-SPK,29.2611,-89.2611,"Grand Isle, Louisiana",NULL,"Grand Isle, LA",0,32200,NULL,pg/uL,159208,pmol/mL,14.8,NULL,ng/L,0.0731765,nmol/L,NULL,A100078,NA,NA,NA
 10JUL11-01-007,2010-07-07 8:00:00,PSD-Water,LFT - Spiked,NULL,10JUL11-01-015,132-65-0,NULL,LA-LFT-W-SPK,29.2611,-89.2611,"Grand Isle, Louisiana",NULL,"Grand Isle, LA",0,309,NULL,pg/uL,1677.01,pmol/mL,0.462,NULL,ng/L,0.00250737,nmol/L,NULL,A100078,NA,NA,NA

sampleChemMapping/mapSamplesToChems.R

@@ -5,7 +5,7 @@ require(rio)
 require(argparse)
 require(xml2)
 library(tidyr)
-##The data release will be comprised of 9 files (note change from v1!)
+##The data release will be comprised of 9 files (note change fro v1!)
 #' 1- list of environmental samples and the chemical composition (curated sample data)
 #' 2- ZF summary statistics for chemicals (and no chemical metadata)
 #' 3- ZF points to plot for chemicals
@@ -27,13 +27,13 @@ required_sample_columns<-c("ClientName","SampleNumber","date_sampled","sample_ma
                            "AlternateName","cas_number","date_sample_start",
                            "measurement_value","measurement_value_qualifier","measurement_value_unit",
                            "measurement_value_molar","measurement_value_molar_unit",
-                           'environment_concentration','environment_concentration_qualifier','environment_concentration_unit',
-                           'environment_concentration_molar','environment_concentration_molar_unit')
+                           'environmental_concentration','environmental_concentration_qualifier','environmental_concentration_unit',
+                           'environmental_concentration_molar','environmental_concentration_molar_unit')
 
 #we need to rename the water columns
-#new_sample_columns=c(environment_concentration="water_concentration",environment_concentration_qualifier='water_concentration_qualifier',
-#                        environment_concentration_unit='water_concentration_unit',environment_concentration_molar='water_concentration_molar',
-#                        environment_concentration_molar_unit='water_concentration_molar_unit')
+#new_sample_columns=c(environmental_concentration="water_concentration",environmental_concentration_qualifier='water_concentration_qualifier',
+#                        environmental_concentration_unit='water_concentration_unit',environmental_concentration_molar='water_concentration_molar',
+#                        environmental_concentration_molar_unit='water_concentration_molar_unit')
 
 ##required for comptox-derived mapping files
 required_comptox_columns <- c("INPUT","DTXSID","PREFERRED_NAME","INCHIKEY","SMILES","MOLECULAR_FORMULA",
@@ -43,8 +43,8 @@ required_comptox_columns <- c("INPUT","DTXSID","PREFERRED_NAME","INCHIKEY","SMIL
 ##output tables
 sample_chem_columns <-c('Sample_ID','Chemical_ID',"measurement_value","measurement_value_qualifier","measurement_value_unit",
                            "measurement_value_molar","measurement_value_molar_unit",
-                           "environment_concentration","environment_concentration_qualifier","environment_concentration_unit",
-                           "environment_concentration_molar","environment_concentration_molar_unit")
+                           "environmental_concentration","environmental_concentration_qualifier","environmental_concentration_unit",
+                           "environmental_concentration_molar","environmental_concentration_molar_unit")
 
 samp_columns <-c("Sample_ID","ClientName","SampleNumber","date_sampled","sample_matrix","technology",
                 "projectName","SampleName","LocationLat","projectLink",
@@ -325,10 +325,10 @@ buildSampleData<-function(fses_files, #files from barton that contain sample inf
 #            dplyr::rename(new_sample_columns)|>  ##REMOVE this once we have new names
             subset(SampleNumber!='None')%>%
             subset(cas_number!='NULL')%>%
-            mutate(environment_concentration_molar=stringr::str_replace_all(environment_concentration_molar,'BLOD|NULL|nc:BDL',"0"))%>%
+            mutate(environmental_concentration_molar=stringr::str_replace_all(environmental_concentration_molar,'BLOD|NULL|nc:BDL',"0"))%>%
             mutate(measurement_value_molar=stringr::str_replace_all(measurement_value_molar,'BLOD|NULL|BDL',"0"))%>%
-            mutate(environment_concentration=stringr::str_replace_all(environment_concentration,'BLOD|NULL|BDL',"0"))%>%
-                                        # subset(environment_concentration_molar!='0.0')%>%
+            mutate(environmental_concentration=stringr::str_replace_all(environmental_concentration,'BLOD|NULL|BDL',"0"))%>%
+                                        # subset(environmental_concentration_molar!='0.0')%>%
             subset(!measurement_value_molar%in%c('0'))%>%
             subset(!measurement_value%in%c("0","NULL",""))#%>%
 #        select(-c(Sample_ID))#,Chemical_ID)) ##These two are added in the 4/27 version of the file

zfExp/Dockerfile

@@ -4,7 +4,7 @@ FROM r-base:4.4.1
 
 RUN apt-get update --allow-insecure-repositories
 RUN apt-get install -y --allow-unauthenticated --fix-missing  python3-pip python3-setuptools python3-dev python3-venv libcurl4-openssl-dev libglpk-dev libxml2-dev libpq-dev
-
+RUN apt-get install -y libmariadb-dev-compat libmariadb-dev
 
 RUN python3 -m venv /opt/venv
 
@@ -26,7 +26,9 @@ RUN Rscript -e "install.packages('readxl',dependencies=TRUE, repos='http://cran.
 RUN Rscript -e "install.packages('dplyr',dependencies=TRUE, repos='http://cran.rstudio.com')"
 RUN Rscript -e "install.packages('tidyr',dependencies=TRUE, repos='http://cran.rstudio.com')"
 RUN Rscript -e "install.packages('rio',dependencies=TRUE, repos='http://cran.rstudio.com')"
-RUN Rscript -e "install.packages('enrichR', dependencies=TRUE, repos='http://cran.rstudio.com')"
+RUN Rscript -e "install.packages('rjson',dependencies=TRUE, repos='http://cran.rstudio.com')"
+RUN Rscript -e "install.packages('WriteXLS',dependencies=TRUE, repos='http://cran.rstudio.com')"
+RUN Rscript -e "install.packages('https://cran.r-project.org/src/contrib/Archive/enrichR/enrichR_3.2.tar.gz', dependencies=TRUE, source=TRUE)"
 RUN Rscript -e "install.packages('argparse',dependencies=TRUE,repos='http://cran.rstudio.com')"
 
 RUN pip3 install --upgrade pip