ich habe folgende Eingabe Datei:
Code: Alles auswählen
G|G0024s00480|s_24|G0024s00480.1|438189|438579|-1
G|G0024s00240|s_24|G0024s00240.1|14401|16599|1
G|G0022s00500|s_22|G0022s00500.1|990172|990304|1
G|G0023s00620|s_23|G0023s00620.1|708242|709405|-1
Code: Alles auswählen
{ 's_22': {'G0022s00500.1': ['990172', '990304', '1']},
's_23': {'G0023s00620.1': ['708242', '709405', '-1']},
's_24': {'G0024s00240.1': ['14401', '16599', '1']}}
Code: Alles auswählen
{ 's_22': {'G0022s00500.1': ['990172', '990304', '1']},
's_23': {'G0023s00620.1': ['708242', '709405', '-1']},
's_24': {'G0024s00240.1': ['14401', '16599', '1']},
'G0024s00480.1': ['438189','438579','-1']}}
Code: Alles auswählen
import pprint
def retrieveIds():
f = open("a.txt","r")
linkageGroups = {}
while True:
line = f.readline().rstrip()
if not line:
break
line = line.split("|")
#G|G0024s00480|s_24|G0024s00480.1|438189|438579|-1
#0 1 2 3 4 5 6
linkageId = line[2] # s_24
gId = line[3] # G0024s00240.1
start = line[4] # 14401
end = line[5] # 16599
strand = line[6] # -1
aGroup = {gId:[start, end, strand]}
linkageGroups[linkageId] = aGroup
pp = pprint.PrettyPrinter(indent=2)
pp.pprint(linkageGroups)
if __name__ == '__main__':
seqLen = 0
firstSeqRead = False
setNewLine = False
retrieveIds()
Viele Grüße