issues fixed

corefuns/fdrsampleperm.py

@@ -124,8 +124,8 @@ def fdrsampleperm(ssmFile, BPMindFile, pcut, minpath, N, genesetname=None):
 
     # calling calculate_fdr() function to compute FDRs
     fdrBPM1, fdrBPM2 = calculate_fdr(bpmdf, bpm_cols, bpm_pvdf, bpm_pv_cols, pcut, N, 'bpm')
-    fdrWPM1, fdrWPM2 = calculate_fdr(wpmdf, wpm_cols, wpm_pvdf, wpm_pv_cols, pcut, N, 'wpm')
-    fdrPATH1, fdrPATH2 = calculate_fdr(pathdf, path_cols, path_pvdf, path_pv_cols, pcut, N, 'path')
+    fdrWPM1, fdrWPM2 = calculate_fdr(wpmdf, wpm_cols, wpm_pvdf, wpm_pv_cols, 0.05, N, 'wpm')
+    fdrPATH1, fdrPATH2 = calculate_fdr(pathdf, path_cols, path_pvdf, path_pv_cols, 0.05, N, 'path')
 
     bpm_ranksum = bpmdf[bpm_cols[0:1]]
     bpm_ranksum.columns = ['bpm_ranksum']

corefuns/pathway_map.py

@@ -5,14 +5,15 @@
 import networkx as nx
 import matplotlib.pyplot as plt
 from matplotlib.lines import Line2D
+from matplotlib import rcParams
 from classes import fdrresultsclass
 from corefuns import check_BPM_WPM_redundancy as cbwr
 from networkx.drawing.nx_agraph import to_agraph
 from matplotlib.backends.backend_pdf import PdfPages
 
 
 def draw_map(project_dir,fdrcut,resultsfile,BPM_group_tmp,WPM_group_tmp,PATH_group_tmp,bpm_limit=20):
-
+	rcParams['font.family'] = 'sans-serif'
 	# load results file(FDRs)
 	#fdr_file = project_dir + '/' + resultsfile
 	pklin = open(resultsfile,'rb')
@@ -217,8 +218,8 @@ def draw_map(project_dir,fdrcut,resultsfile,BPM_group_tmp,WPM_group_tmp,PATH_gro
 			if val == 1:
 				p1 = used_pathways[i]
 				p2 = used_pathways[j]
-				G.add_edge(inds[p1],inds[p2],color='yellow')
-				G.add_edge(inds[p2],inds[p1],color='yellow')
+				G.add_edge(inds[p1],inds[p2],color='orange')
+				G.add_edge(inds[p2],inds[p1],color='orange')
 			elif val == -1:
 				p1 = used_pathways[i]
 				p2 = used_pathways[j]
@@ -244,7 +245,7 @@ def draw_map(project_dir,fdrcut,resultsfile,BPM_group_tmp,WPM_group_tmp,PATH_gro
 	legend_elements = [Line2D([0], [0], marker='o', color='w', label='pathway',markerfacecolor='lightblue', markersize=15)]
 	#legend_elements.append(Line2D([0], [0], marker='o', color='w', label='protective PATH pwathway',markerfacecolor='yellow', markersize=15))
 	#legend_elements.append(Line2D([0], [0], marker='o', color='w', label='risk PATH pwathway',markerfacecolor='blue', markersize=15))
-	legend_elements.append(Line2D([0], [0], color='yellow', lw=4, label='protective interaction'))
+	legend_elements.append(Line2D([0], [0], color='orange', lw=4, label='protective interaction'))
 	legend_elements.append(Line2D([0], [0], color='blue', lw=4, label='risk interaction'))
 	legend_elements.append(Line2D([0], [0], marker='o', color='w', label='self loops indicate WPM interactions',markerfacecolor='w', markersize=1))
 	plt.legend(handles=legend_elements, loc='lower left')

scripts/data_checkpopulation.sh

@@ -102,9 +102,9 @@ grep -w ASW ${popIDFile} | awk '{print $1 "\t" $2}' >> intermediate/sublist.tmp
 grep -w YRI ${popIDFile} | awk '{print $1 "\t" $2}' >> intermediate/sublist.tmp
 
 # add ${prj1000Pop} if it's not in CEU, CHB, YRI and ASW 
-if [[ ! "${prj1000Pop}" =~ ^(CEU|CHB|ASW|YRI)$ ]]; then 
-     grep -w ${prj1000Pop} ${popIDFile} | awk '{print $1 "\t" $2}' >> intermediate/sublist.tmp
-fi
+#if [[ ! "${prj1000Pop}" =~ ^(CEU|CHB|ASW|YRI)$ ]]; then 
+#     grep -w ${prj1000Pop} ${popIDFile} | awk '{print $1 "\t" $2}' >> intermediate/sublist.tmp
+#fi
 
 for pop in "${prj1000Pop[@]}"; do
     if [[ ! "${pop}" =~ ^(CEU|CHB|ASW|YRI)$ ]]; then 
@@ -122,13 +122,13 @@ plink --bfile intermediate/prj1000_tmp1 --keep intermediate/sublist.tmp --allow-
 plink --bfile intermediate/prj1000_tmp2 --biallelic-only strict --allow-no-sex --make-bed --out intermediate/prj1000_tmp3 > /dev/null
 
 # merge 1000 project data with study data
-plink --bfile intermediate/prj1000_tmp3 --bmerge raw/${plinkFile} --allow-no-sex --make-bed --out intermediate/allpop_tmp > /dev/null
+plink --bfile intermediate/prj1000_tmp3 --bmerge raw/${plinkFile} --allow-no-sex --make-bed --out intermediate/allpop_tmp > /dev/null 2> /dev/null
 
 # if any SNPs in two datasets have different alleles, there will be error "variants with 3+ alleles present"
 if [ -f "allpop_tmp-merge.missnp" ]; then
   plink --bfile intermediate/prj1000_tmp3 --exclude intermediate/allpop_tmp-merge.missnp --allow-no-sex --make-bed --out intermediate/prj1000_tmp4 > /dev/null
   plink --bfile raw/${plinkFile} --exclude intermediate/allpop_tmp-merge.missnp --allow-no-sex --make-bed --out  intermediate/${plinkFile}_tmp1 > /dev/null
-  plink --bfile intermediate/prj1000_tmp4 --bmerge intermediate/${plinkFile}_tmp1 --allow-no-sex --make-bed --out intermediate/allpop_tmp > /dev/null
+  plink --bfile intermediate/prj1000_tmp4 --bmerge intermediate/${plinkFile}_tmp1 --allow-no-sex --make-bed --out intermediate/allpop_tmp > /dev/null 2> /dev/null
 fi
 
 
@@ -149,21 +149,21 @@ z=0
 #echo `echo CEU CHB ASW YRI ${prj1000Pop} | xargs -n1 | sort -u | xargs` StudyPop > intermediate/allpopid.txt
 
 valid_values=("CEU" "CHB" "ASW" "YRI")
-pop_values=("${valid_values[@]}" ${prj1000Pop[@]})
+pop_values=("${valid_values[@]}" "${prj1000Pop[@]}")
 
-for i in $(printf '%s\n' "${pop_values[*]}" | sort -u); do
+for i in $(printf '%s\n' "${pop_values[*]}"); do
   z+=" 0"
 done
 
-echo $(printf '%s\n' "${pop_values[*]}" | sort -u) StudyPop > intermediate/allpopid.txt
+echo $(printf '%s\n' "${pop_values[@]}") StudyPop > intermediate/allpopid.txt
 
 
 num_columns=$(( ${#pop_values[@]} + 1 ))
 while read -r line; do
   pattern=$(echo "$line" | awk '{print $1 " " $2}')
   pop=$(grep -w "$pattern" "$popIDFile" | awk '{print $3}')
 
-  if [[ "${pop_values[@]}" =~ "$pop" ]]; then
+  if [[ -n "$pop" ]]  && [[ "${pop_values[@]}" =~ "$pop" ]]; then
     idx=$(printf '%s\n' "${pop_values[@]}" | awk -v p="$pop" 'BEGIN{ORS="\n";NR=0}$1==p{print NR}')
     echo "$pattern $(echo "$z" | awk -v i="$idx" '{ $i=1; print }')"
   else

scripts/plotmds.py

@@ -2,6 +2,7 @@
 import pandas as pd
 import seaborn as sns
 import matplotlib.pyplot as plt
+from matplotlib import rcParams
 import sys
 
 
@@ -27,6 +28,7 @@
 
 
 if __name__ == '__main__':
+	rcParams['font.family'] = 'sans-serif'
 	mds_file = sys.argv[1]
 	pop_id_file = sys.argv[2]
 	prj1000Pop = sys.argv[3]