comparison scripts/strike-ambigs.bf @ 0:f304c108aa1f draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hyphy/ commit 00684bab4c9e740cfa6a39abc444380e6818fd97"
author iuc
date Wed, 09 Jun 2021 07:03:54 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:f304c108aa1f
1 RequireVersion ("2.5.20");
2
3 LoadFunctionLibrary ("libv3/tasks/alignments.bf");
4 LoadFunctionLibrary ("libv3/tasks/trees.bf");
5 LoadFunctionLibrary ("libv3/UtilityFunctions.bf");
6 LoadFunctionLibrary ("libv3/IOFunctions.bf");
7 LoadFunctionLibrary ("libv3/convenience/math.bf");
8
9
10
11 filter.analysis_description = {terms.io.info :
12 "
13 Read an alignment of coding sequences and replace any ambiguous codons with ---. Write results to a new file in FASTA format, and report changed sequences to stdout
14 ",
15 terms.io.version : "0.1",
16 terms.io.reference : "TBD",
17 terms.io.authors : "Sergei L Kosakovsky Pond",
18 terms.io.contact : "spond@temple.edu",
19 terms.io.requirements : "An MSA"
20 };
21
22
23 io.DisplayAnalysisBanner (filter.analysis_description);
24
25 utility.SetEnvVariable ("NORMALIZE_SEQUENCE_NAMES", FALSE);
26
27 KeywordArgument ("code", "Which genetic code should be used", "Universal");
28 KeywordArgument ("alignment", "An in-frame codon alignment in one of the formats supported by HyPhy");
29
30 filter.in = alignments.PromptForGeneticCodeAndAlignment ("filter.dataset", "filter.input");
31
32 KeywordArgument ("output", ".fasta for compressed data", None);
33 filter.out = io.PromptUserForFilePath(".fasta for filtered data");
34 fprintf (filter.out, CLEAR_FILE, KEEP_OPEN);
35
36 GetDataInfo (filter.site_patterns, filter.input);
37
38 filter.patter2site = {};
39
40
41 for (i,j,v; in; filter.site_patterns) {
42 index = i+j;
43 if (filter.patter2site / v == FALSE ) {
44 filter.patter2site [v] = {};
45 }
46 filter.patter2site [v] + index;
47 }
48
49 GET_DATA_INFO_RETURNS_ONLY_THE_INDEX = TRUE;
50 COUNT_GAPS_IN_FREQUENCIES = FALSE;
51 filter.unique_patterns = utility.Array1D (filter.input.site_freqs);
52
53 for (seq = 0; seq < filter.input.species; seq += 1) {
54 io.ReportProgressBar ("filter","Processing sequence " + (1+seq));
55 codons = {1, filter.input.sites};
56 codons [0] = "";
57 GetString (seq_name, filter.input, seq);
58 GetDataInfo (seq_chars, filter.input, seq);
59
60 filter.ambigs = 0;
61
62 for (pattern = 0; pattern < filter.unique_patterns; pattern += 1) {
63 GetDataInfo (pattern_info, filter.input, seq, pattern);
64 if (pattern_info >= 0) {
65 codon_start = (filter.patter2site[pattern])[0] * 3;
66 codon = seq_chars [codon_start][codon_start+2];
67 } else {
68 codon = "---";
69 filter.ambigs += Abs (filter.patter2site [pattern])
70 }
71 for (c; in; filter.patter2site [pattern] ) {
72 codons[c] = codon;
73 }
74 }
75 if (filter.ambigs > 0) {
76 fprintf (stdout, "\nStriking ", filter.ambigs, " codons that are incompletely resolved from " + seq_name + "\n");
77 }
78 fprintf (filter.out,">",seq_name,"\n",Join ("", codons), "\n");
79 }
80
81 fprintf (filter.out,CLOSE_FILE);
82
83