In [ ]:

    

import pandas as pd
from os import path


    

In [ ]:

    

sra = pd.read_table("SraRunTable.txt")

# Fix sample names to use '_', not '.'
sra.Sample_Name_s = sra.Sample_Name_s.str.replace('.', '_')


    

In [ ]:

    

# Create mapping of sample names to SRRs
name2run = {}
for run in sra.itertuples():
    name2run[run.Sample_Name_s] = run.Run_s


    

In [ ]:

    

def make_srr_list(name_set):
    outfile = path.splitext(name_set)[0] + '.srr.txt'
    with open(name_set) as infp, open(outfile, 'w') as outfp:
        for name in (line.rstrip() for line in infp):
            if name:
                print(name2run[name], file=outfp)


    

In [ ]:

    

make_srr_list("field-expt.txt")
make_srr_list("greenhouse.txt")
make_srr_list("timecourse_ghdavis.txt")


    

In [ ]:

    

with open("sra2name.tab", 'w') as fh:
    print("runid", "name", sep='\t', file=fh)
    for name, run in name2run.items():
        print(run, name, sep='\t', file=fh)