Paper_2024-Genomic_Hotspots/domains-012-python-sourceids at main · 000generic/Paper_2024-Genomic_Hotspots · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
#! python

input_idswapper = open( 'input/map-giganticid-to-sourceid', 'r' )
input_annotations = open( 'output/9-list-parsed-interproscan-files', 'r' )

giganticids_sourceids = {}
coreids_giganticids = {}
giganticids_locids = {}

for next_line in input_idswapper:
    info = next_line[ :-1 ].split( '\t' )
    species = info[ 0 ]
    giganticid = info[ 1 ]
    coreid = giganticid.split( '-' )[ -1 ]
    sourceid = info[ 3 ]
    locid = info[ -1 ]

    giganticids_sourceids[ giganticid ] = sourceid
    coreids_giganticids[ coreid ] = giganticid

    if locid != 'NA':
        giganticids_locids[ giganticid ] = locid

# output/8-Acanthopleura_seqids-CDD_annotationids_X_global-counts-all-species
for next_anno_file in input_annotations:
    input_path = next_anno_file[ :-1 ]
    input_name = next_anno_file[ :-1 ].split( '/' )[ -1 ]
    input_core_name = '-'.join( input_name.split( '-' )[ 1: ] )
    analysis_type = ''
    if input_name[ 0 ] == '7':
        analysis_type = 'software'
    if input_name[ 0 ] == '8':
        analysis_type = 'species'
    output_path = 'output/10-' + analysis_type + '/' + '10-' + analysis_type + '-' + input_core_name + '.tsv'
    input_file = open( input_path, 'r' )
    output_file = open( output_path, 'w' )

    for next_line in input_file:

        info = next_line[ :-1 ].split( '\t' )
        keeper = False
        counter = -1
        counter_keeper = ''
        for next_item in info:

            counter = counter + 1

            if next_item in giganticids_sourceids.keys():

                keeper = True
                incoming = next_item
                outgoing = giganticids_sourceids[ incoming ]
                if incoming in giganticids_locids.keys():
                    outgoing = giganticids_locids[ incoming ]
                counter_keeper = counter
            elif next_item in coreids_giganticids:

                keeper = True
                incoming = coreids_giganticids[ next_item ]
                outgoing = giganticids_sourceids[ incoming ]
                if incoming in giganticids_locids.keys():
                    outgoing = giganticids_locids[ incoming ]
                counter_keeper = counter
            else:
                pass

        if keeper == True:
            info[ counter_keeper ] = outgoing

        output = '\t'.join( info ) + '\n'
        output_file.write( output )

    input_file.close()
    output_file.close()

input_idswapper.close()
input_annotations.close()