Add the cNF organoid dataset: drugs and experiments

coderbuild/cnf/build_drugs.sh

@@ -0,0 +1,20 @@
+#!/usr/bin/env bash
+# build_drugs.sh - wraps 03-drugs-cnf.py per coderdata convention.
+#
+# Usage:
+#   build_drugs.sh <existing_drug_files>
+#
+# <existing_drug_files> is a comma-delimited list of drug TSV files from
+# previous datasets in the build sequence. Their improve_drug_id values
+# get reused when the canonical SMILES match.
+
+set -euo pipefail
+
+PREV_DRUGS="${1:-}"
+
+python 03-drugs-cnf.py \
+    --prev_drugs "$PREV_DRUGS" \
+    --out_drugs /tmp/cnf_drugs.tsv \
+    --out_desc  /tmp/cnf_drug_descriptors.tsv
+
+python build_drug_desc.py --drugtable /tmp/cnf_drugs.tsv --desctable /tmp/cnf_drug_descriptors.tsv.gz

coderbuild/cnf/build_exp.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+# build_exp.sh - wraps 04-experiments-cnf.py per coderdata convention.
+#
+# Usage:
+#   build_exp.sh <samples_file> <drugs_file>
+
+set -euo pipefail
+
+SAMPLES="${1:?Usage: build_exp.sh <cnf_samples.csv> <cnf_drugs.tsv>}"
+DRUGS="${2:?Usage: build_exp.sh <cnf_samples.csv> <cnf_drugs.tsv>}"
+
+python 04-experiments-cnf.py "$SAMPLES" "$DRUGS" --output /tmp/cnf_experiments.tsv

coderbuild/mpnst/00_sample_gen.R

@@ -1,3 +1,4 @@
+# 00_sample_gen.R
 # This script generate a new sample table based on previous dataset's sample file (taking the max improve_sample_id)
 # Load required libraries
 library(data.table)
@@ -26,9 +27,14 @@ synapser::synLogin(authToken=synapse_token)
 manifest<-synapser::synTableQuery("select * from syn53503360")$asDataFrame()|>
                                                              as.data.frame()
 
-#Drop contaminated sample JH-2-009
+#Drop contaminated sample JH-2-009 and others with issues
 manifest <- manifest %>% 
-  filter(Sample != "JH-2-009")
+  filter(Sample != "JH-2-009") %>%
+  filter(Sample != "WU-545") %>%
+  filter(Sample != "WU-536") %>%
+  filter(Sample != "WU-505") %>%
+  filter(Sample != "MN-1") %>%
+  filter(Sample != "MN-3")
 
 
 ###sample file has a strict schema
@@ -56,7 +62,7 @@ sampTable<-manifest|>
 
 ##third, generate a sample for the MTs if they were generated
 pdxmt<-subset(sampTable,!is.na(MicroTissueDrugFolder))
-pdxmt$model_type=rep('xenograft derived organoid',nrow(pdxmt))
+pdxmt$model_type=rep('3D-MEDS',nrow(pdxmt))
 print(pdxmt)
 
 main<-rbind(sampTable,pdxmt)|>