python dependencies

README.md

@@ -9,6 +9,13 @@ Code and comments to [https://r3.pages.uni.lu/biocuration/resources/biohackathon
 - R
 - zip utility
 
+Python needs to have packages decribed in `associations/requirement.txt` which can be installed
+via
+
+```commandline
+pip3 install -r associations/requirement.txt
+```
+
 If the pipeline is run at clean Linux installation you might need to install the following libraries 
 (`sudo apt-get install` on Ubuntu) prior to running the code:
 - libcurl

assemble.sh

@@ -8,8 +8,8 @@ DISGENET_CNT_THRESHOLD=50
 DISGENET_ASSOCIATION_SCORE_THRESHOLD=0
 OPENTARGETS_CNT_THRESHOLD=50
 OPENTARGETS_ASSOCIATION_SCORE_THRESHOLD=0.2
-BUILD_MAP_GENERATOR=0 #1 for building it
-STOP_AFTER_STAGE=-1
+BUILD_MAP_GENERATOR=1 #0 for building it
+STOP_AFTER_STAGE=1
 # ------------------------- PARAMETERS TO SET -------------------------
 
 ASSOCIATIONS_DIR=associations/
@@ -19,20 +19,23 @@ ENRICHMENT_DIR=enrichment/
 ENRICHMENT_CONFIG=${ENRICHMENT_DIR}/config.txt
 MAP_GENERATOR_DIR=map_generator/
 PYTHON_BIN=python3
+PIP_BIN=pip3
 
 ORPHANET_IDS_UNDERSCORE=${ORPHANET_IDS//,/_}
 
 mkdir $RES_DIR
 
-# -------------- 1. Extract genes and variants associated with a disease --------------
+# Get associations from DisGeNET
 disgenet_out_path=${RES_DIR}/01-disgenet-id_${ORPHANET_IDS_UNDERSCORE}-n_${DISGENET_CNT_THRESHOLD}-s_${DISGENET_ASSOCIATION_SCORE_THRESHOLD}.json
 $PYTHON_BIN $ASSOCIATIONS_DIR/disgenet.py -o ${ORPHANET_IDS} -n ${DISGENET_CNT_THRESHOLD} -s ${DISGENET_ASSOCIATION_SCORE_THRESHOLD} > ${disgenet_out_path}
 echo "Disgenet gene and variant associations stored in ${disgenet_out_path}"
 
+# Get associations from OpenTargets
 opentargets_out_path=${RES_DIR}/01-opentargets-id_${ORPHANET_IDS_UNDERSCORE}-n_${DISGENET_CNT_THRESHOLD}-s_${DISGENET_ASSOCIATION_SCORE_THRESHOLD}.json
 $PYTHON_BIN $ASSOCIATIONS_DIR/opentargets.py -o ${ORPHANET_IDS} -n ${OPENTARGETS_CNT_THRESHOLD} -s ${OPENTARGETS_ASSOCIATION_SCORE_THRESHOLD} > ${opentargets_out_path}
 echo "Opentargets gene and variant associations stored in ${opentargets_out_path}"
 
+# Merge with ClinVar
 genes_variants_out_path=${RES_DIR}/02-genes_variants-id_${ORPHANET_IDS_UNDERSCORE}.log
 $PYTHON_BIN $ASSOCIATIONS_DIR/merge_with_clinvar.py -v $disgenet_out_path,$opentargets_out_path -c ${ASSOCIATIONS_DATA_DIR}/OrphaHPO_clinvar_variants_summary.tsv -oid ${ORPHANET_IDS} > ${genes_variants_out_path}
 echo "Integration with ClinVar stored in ${genes_variants_out_path}"