Paper_2024-Genomic_Hotspots/domains-005-python-interproscan-parser 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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
#! python

input_files = open( 'output/4-list-interproscan-tsvs', 'r' )
input_fastas = open( 'output/1-list-fastas', 'r' )

apps_redundant = [ ]
seqids_gos = {}

# Metazoa-Mollusca-Gastropoda-Aplysiida-Aplysiidae-Aplysia-californica-gigantic20220627164247_seq0006145488aa     84f1ffb9a864616ec3aa0e37433b6487        1152    PANTHER PTHR15377       TRANSCRIPTION ELONGATION REGULATOR 1    238     1123    8.0E-256   T       14-12-2022      IPR045148       Transcription elongation regulator 1-like       GO:0003712|GO:0070063

seq_app_id = {}

# read into dictionary all interproscan species annotations
for next_file in input_files:

    input_file = open( next_file[ :-1 ], 'r' )

    for next_line in input_file:
        info = next_line[ :-1 ].split( '\t' )
        seqid = info[ 0 ]
        app = info [ 3 ]
        apps_redundant.append( app )
        identifier = info[ 4 ]
        start = info[ 6 ]
        if len( start ) == 0:
            start = 'NA'
        stop = info[ 7 ]
        if len( stop ) == 0:
            stop = 'NA'

        app_id = app + '_' + identifier + '_' + start + '_' + stop
        if seqid in seq_app_id.keys():
            seq_app_id[ seqid ].append( app_id )
        else:
            seq_app_id[ seqid ] = []
            seq_app_id[ seqid ].append( app_id )

        gos = info[ -1 ]
        go_test = gos.split( 'O:' )
        if len( go_test ) > 1:
            go_info = gos.split( '|' )
            for next_go in go_info:
                go_details = next_go + '_' + start + '_' + stop
                if seqid in seqids_gos.keys():
                    seqids_gos[ seqid ].append( go_details )
                else:
                    seqids_gos[ seqid ] = []
                    seqids_gos[ seqid ].append( go_details )

for next_seqid in seqids_gos.keys():
    seqids_gos[ next_seqid ] = list( set( seqids_gos[ next_seqid ] ) )

apps = list( set( apps_redundant ) )

# collect seqids for all species and check for interproscan annotations
for next_fasta in input_fastas:

    # create filehandles for input and output
    # ../../species16/proteomes/USEME-species16-pep-fastas/ACal.pep
    input_fasta = open( next_fasta[ :-1 ], 'r' )

    file_name = next_fasta.split( '/' )[ -1 ]
    core_name = file_name.split( '.' )[ 0 ]
    new_file = 'output/5-interproscan5-app-id-annotations-' + core_name
    output_info = open( new_file, 'w' )

    # provide file structure details
    output = '[ Sequence Identifier ]' + '\t'
    for next_app in sorted( apps ):
        output = output + '[ InterProScan ' + next_app + ' ]\t'
    output = output + '[ InterProScan GO ]' + '\n'
    output_info.write( output )

    # process fasta file
    for next_line in input_fasta:
        if next_line[ 0 ] == '>': # check if its a header
            seqid = next_line[ 1:-1 ]
            output = seqid + '\t' # output interproscan annotations for the sequence

            if seqid in seq_app_id.keys(): # check if sequence has inteproscan annotation

                for next_app in sorted( apps ): # go through apps of interest
                    annotations = []
                    for next_annotation in seq_app_id[ seqid ]: # check if app annotated the sequence
                        info_annotation = next_annotation.split( '_' )
                        if info_annotation[ 0 ] == next_app:
                            annotations.append( next_annotation )
                        else:
                            pass

                    if len( annotations ) == 0:
                        output = output + 'None' +  '\t'
                    else:
                        app_annotations = ', '.join( annotations )
                        output = output + app_annotations + '\t'

                if seqid in seqids_gos.keys():
                    gos_list = seqids_gos[ seqid ]
                    gos = ', '.join( gos_list )
                    output = output + gos + '\n'
                else:
                    output = output + 'None' + '\n'
                output_info.write( output )

            else:
                for next_app in apps:
                    output = output + 'None' + '\t'
                if seqid in seqids_gos.keys():
                    gos_list = seqids_gos[ seqid ]
                    gos = ', '.join( gos_list )
                    output = output + gos + '\n'
                else:
                    output = output + 'None' + '\n'
                output_info.write( output )
        else:
            pass
    input_fasta.close()
    output_info.close()
input_files.close()
input_fastas.close()