1 /* The MIT License
2
3 Copyright (c) 2015 Adrian Tan <atks@umich.edu>
4
5 Permission is hereby granted, free of charge, to any person obtaining a copy
6 of this software and associated documentation files (the "Software"), to deal
7 in the Software without restriction, including without limitation the rights
8 to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 copies of the Software, and to permit persons to whom the Software is
10 furnished to do so, subject to the following conditions:
11
12 The above copyright notice and this permission notice shall be included in
13 all copies or substantial portions of the Software.
14
15 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
21 THE SOFTWARE.
22 */
23
24 #include "consolidate_vntrs.h"
25
26 namespace
27 {
28
29 class Igor : Program
30 {
31 public:
32
33 ///////////
34 //options//
35 ///////////
36 std::string input_vcf_file;
37 std::string output_vcf_file;
38 std::string ref_fasta_file;
39 std::vector<GenomeInterval> intervals;
40 bool debug;
41
42 /////////
43 //tools//
44 /////////
45 VariantManip *vm;
46 VNTRConsolidator *vc;
47
Igor(int argc,char ** argv)48 Igor(int argc, char **argv)
49 {
50 version = "0.57";
51
52 //////////////////////////
53 //options initialization//
54 //////////////////////////
55 try
56 {
57 std::string desc = "Consolidates VNTRs by\n"
58 " 1. removing overlapping VNTRs and leaving behind the most complete VNTR\n"
59 " 2. resolves adjacent VNTRs\n"
60 " 3. marking VNTRs that are \n"
61 " 4. Adds INFO fields indicating the number of variants that overlap with this variant";
62
63 TCLAP::CmdLine cmd(desc, ' ', version);
64 VTOutput my;
65 cmd.setOutput(&my);
66 TCLAP::ValueArg<std::string> arg_intervals("i", "i", "intervals []", false, "", "str", cmd);
67 TCLAP::ValueArg<std::string> arg_interval_list("I", "I", "file containing list of intervals []", false, "", "file", cmd);
68 TCLAP::ValueArg<std::string> arg_ref_fasta_file("r", "r", "reference sequence fasta file []", true, "", "str", cmd);
69 TCLAP::ValueArg<std::string> arg_output_vcf_file("o", "o", "output VCF file [-]", false, "-", "str", cmd);
70 TCLAP::SwitchArg arg_debug("d", "d", "debug [false]", cmd, false);
71 TCLAP::UnlabeledValueArg<std::string> arg_input_vcf_file("<in.vcf>", "input VCF file", true, "","file", cmd);
72
73 cmd.parse(argc, argv);
74
75 input_vcf_file = arg_input_vcf_file.getValue();
76 output_vcf_file = arg_output_vcf_file.getValue();
77 ref_fasta_file = arg_ref_fasta_file.getValue();
78 debug = arg_debug.getValue();
79 parse_intervals(intervals, arg_interval_list.getValue(), arg_intervals.getValue());
80 }
81 catch (TCLAP::ArgException &e)
82 {
83 std::cerr << "error: " << e.error() << " for arg " << e.argId() << "\n";
84 abort();
85 }
86 };
87
initialize()88 void initialize()
89 {
90 ////////////////////////
91 //tools initialization//
92 ////////////////////////
93 vc = new VNTRConsolidator(input_vcf_file, intervals, output_vcf_file, ref_fasta_file, debug);
94 vm = new VariantManip();
95 }
96
consolidate_vntrs()97 void consolidate_vntrs()
98 {
99 bcf1_t *v = vc->odw->get_bcf1_from_pool();
100 bcf_hdr_t *h = vc->odr->hdr;
101
102 Variant* variant;
103 while (vc->odr->read(v))
104 {
105 bcf_print_liten(h,v);
106
107 variant = new Variant(vc->odw->hdr, v);
108 vc->flush_variant_buffer(variant);
109 vc->insert_variant_record_into_buffer(variant);
110 v = vc->odw->get_bcf1_from_pool();
111
112 ++vc->no_total_variants;
113 }
114
115 vc->flush_variant_buffer();
116 vc->close();
117 };
118
print_options()119 void print_options()
120 {
121 std::clog << "consolidate_vntrs v" << version << "\n\n";
122
123 std::clog << "options: input VCF file " << input_vcf_file << "\n";
124 std::clog << " [o] output VCF file " << output_vcf_file << "\n";
125 print_int_op(" [i] intervals ", intervals);
126 std::clog << "\n";
127 }
128
print_stats()129 void print_stats()
130 {
131 std::clog << "\n";
132 std::clog << " Variants observed\n";
133 std::clog << " No. of SNPs " << vc->no_snps << "\n";
134 std::clog << " No. of Indels " << vc->no_indels << "\n";
135 std::clog << " No. of VNTRs " << vc->no_vntrs << "\n";
136 std::clog << " No. of other variant types " << vc->no_other_variants << "\n";
137 std::clog << "\n";
138 std::clog << " No. of isolated VNTRs " << vc->no_isolated_vntrs << "\n";
139 std::clog << " No. of clustered VNTRs\n";
140 std::clog << " consistent RUs " << vc->no_clustered_consistent_ru_vntrs << " (" << vc->no_merged_consistent_ru_vntrs << ")\n";
141 std::clog << " consistent bases " << vc->no_clustered_consistent_basis_vntrs << " (" << vc->no_merged_consistent_basis_vntrs << ")\n";
142 std::clog << " inconsistent RUs and bases " << vc->no_clustered_inconsistent_ru_basis_vntrs << "\n";
143
144 std::clog << "\n";
145 };
146
~Igor()147 ~Igor() {};
148
149 private:
150 };
151
152 }
153
consolidate_vntrs(int argc,char ** argv)154 void consolidate_vntrs(int argc, char ** argv)
155 {
156 Igor igor(argc, argv);
157 igor.print_options();
158 igor.initialize();
159 igor.consolidate_vntrs();
160 igor.print_stats();
161 };
162