update examples

case_studies/Covid_RNA-Seq/Nextflow/README.md

@@ -20,6 +20,8 @@ To install the reference data and build Salmon index, run [this file](https://gi
 
 `bash prepare_data.sh`
 
+The salmon index must be in `./human_data/salmon_index` or specify path to salmon index in the `run_quant.nf` file.
+
 ### Execute using Nextflow
 
 `nextflow run run_quant.nf`

case_studies/Covid_RNA-Seq/Nextflow/runids.txt

@@ -0,0 +1,3 @@
+SRR12850397
+SRR12850398
+SRR12850399

case_studies/Covid_RNA-Seq/Nextflow/scripts/merge.py

@@ -0,0 +1,39 @@
+import sys
+import pandas as pd
+import os
+
+input=sys.argv[1].split(',')
+for f in input:
+    print ('this f',f)
+
+DIR=sys.argv[-1]
+
+with open(input[0]) as f:
+    thisdata=f.read().splitlines()
+thisdata.pop(0)
+
+names=[]
+txids=[]
+geneids=[]
+for l in thisdata:
+    thistx=l.split('\t')[0].split('|')[0]
+    thisgene=l.split('\t')[0].split('|')[1]
+    txids.append(thistx)
+    geneids.append(thisgene)
+df=pd.DataFrame({'TranscriptID':txids,'GeneID':geneids})
+
+#read files in memory
+for qf in input:
+    name=qf.split('/')[-3]
+    names.append(name)
+    thisdata=pd.read_csv(qf,sep='\t',usecols=[3],skiprows=0)
+    df[name]=thisdata['TPM']
+
+#transcript counts
+df_tx=df[['TranscriptID']+names].copy()
+#write to file
+df_tx.to_csv(DIR+'/results_TPM_tx.tsv',sep='\t',index=False)
+#gene counts
+df_gene=df[['GeneID']+names].copy()
+df_gene = df_gene.groupby(['GeneID'],as_index = False).sum()
+df_gene.to_csv(DIR+'/results_TPM_gene.tsv',sep='\t',index=False)