viral_seq 1.1.2 → 1.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/README.md +13 -2
- data/bin/tcs_sdrm +402 -0
- data/lib/viral_seq.rb +1 -0
- data/lib/viral_seq/recency.rb +52 -0
- data/lib/viral_seq/sdrm.rb +2 -2
- data/lib/viral_seq/seq_hash.rb +24 -4
- data/lib/viral_seq/version.rb +1 -1
- metadata +5 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: dbcddd0679b712b28592875aa18e38269ccbac5b85113f53873d4cedc5572b04
|
4
|
+
data.tar.gz: 7268e596a2c40f7cdd2c815ccf5cdb40663c096c709aba6ee2e0dc4bc9a07542
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a689ed94201b19ee258fb07f73dd89ed2c8fd297b9580ba720d85ef2a16c5a38fdfed326dbdcc987f0913b4c9ab2aa060683a770df48baa4b1d657d63de35152
|
7
|
+
data.tar.gz: 0b8065ae813f66b88fda3d7788c20718aa0db1a4f723d6831e948157b682a81fd1ae44a1d9043ebfb046df91c072bbc16db41ddd42e272d3f6c74a13fa473836
|
data/README.md
CHANGED
@@ -109,7 +109,7 @@ qc_seqhash = aligned_seqhash.hiv_seq_qc(2253, 2549, false, :HXB2)
|
|
109
109
|
Further filter out sequences with Apobec3g/f hypermutations
|
110
110
|
|
111
111
|
```ruby
|
112
|
-
qc_seqhash = qc_seqhash.a3g
|
112
|
+
qc_seqhash = qc_seqhash.a3g[:filtered_seq]
|
113
113
|
```
|
114
114
|
|
115
115
|
Calculate nucleotide diveristy π
|
@@ -137,11 +137,22 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
|
|
137
137
|
|
138
138
|
## Updates
|
139
139
|
|
140
|
+
### Version 1.2.0-05102021
|
141
|
+
|
142
|
+
1. Added `tcs_sdrm` pipeline as an excutable.
|
143
|
+
`tcs_sdrm` processes `tcs`-processed HIV MPID-NGS data for drug resistance mutations, recency and phylogentic analysis.
|
144
|
+
|
145
|
+
2. Added function ViralSeq::SeqHash#sample.
|
146
|
+
|
147
|
+
3. Added recency determining function `ViralSeq::Recency::define`
|
148
|
+
|
149
|
+
4. Fixed a few bugs related to `tcs_sdrm`.
|
150
|
+
|
140
151
|
### Version 1.1.2-04262021
|
141
152
|
|
142
153
|
1. Added function `ViralSeq::DRMs.sdrm_json` to export SDRM as json object.
|
143
154
|
2. Added a random string to the temp file names for `muscle_bio` to avoid issues when running scripts in parallel.
|
144
|
-
3. Added `--keep-original` flag to the `tcs` pipeline.
|
155
|
+
3. Added `--keep-original` flag to the `tcs` pipeline.
|
145
156
|
|
146
157
|
### Version 1.1.1-04012021
|
147
158
|
|
data/bin/tcs_sdrm
ADDED
@@ -0,0 +1,402 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
# tcs/sdrm pipeline for HIV-1 drug resistance mutation and recency
|
3
|
+
#
|
4
|
+
# command example:
|
5
|
+
# $ tcs_sdrm libs_dir
|
6
|
+
#
|
7
|
+
# lib_dir file structure:
|
8
|
+
# libs_dir
|
9
|
+
# ├── lib1
|
10
|
+
# ├── lib1_RT
|
11
|
+
# ├── lib1_PR
|
12
|
+
# ├── lib1_IN
|
13
|
+
# ├── lib1_V1V3
|
14
|
+
# ├── lib2
|
15
|
+
# ├── lib1_RT
|
16
|
+
# ├── lib1_PR
|
17
|
+
# ├── lib1_IN
|
18
|
+
# ├── lib1_V1V3
|
19
|
+
# ├── ...
|
20
|
+
#
|
21
|
+
# output data in a new dir as 'libs_dir_SDRM'
|
22
|
+
|
23
|
+
require 'viral_seq'
|
24
|
+
require 'json'
|
25
|
+
require 'csv'
|
26
|
+
require 'fileutils'
|
27
|
+
require 'prawn'
|
28
|
+
require 'prawn/table'
|
29
|
+
require 'combine_pdf'
|
30
|
+
|
31
|
+
unless ARGV[0] && File.directory?(ARGV[0])
|
32
|
+
abort "No sequence data provided. `tcs_sdrm` pipeline aborted. "
|
33
|
+
end
|
34
|
+
|
35
|
+
def abstract_line(data)
|
36
|
+
return_data = data[3] + data[2] + data[4] + ":" +
|
37
|
+
(data[6].to_f * 100).round(2).to_s + "(" +
|
38
|
+
(data[7].to_f * 100).round(2).to_s + "-" +
|
39
|
+
(data[8].to_f * 100).round(2).to_s + "); "
|
40
|
+
end
|
41
|
+
|
42
|
+
# run params
|
43
|
+
log = []
|
44
|
+
|
45
|
+
log << { time: Time.now }
|
46
|
+
log << { viral_seq_version: ViralSeq::VERSION }
|
47
|
+
log << { tcs_version: ViralSeq::TCS_VERSION }
|
48
|
+
r_version = `R --version`.split("\n")[0]
|
49
|
+
log << { R_version: r_version}
|
50
|
+
sdrm_list = {}
|
51
|
+
sdrm_list[:nrti] = ViralSeq::DRMs.sdrm_json(:nrti)
|
52
|
+
sdrm_list[:nnrti] = ViralSeq::DRMs.sdrm_json(:nnrti)
|
53
|
+
sdrm_list[:hiv_pr] = ViralSeq::DRMs.sdrm_json(:hiv_pr)
|
54
|
+
sdrm_list[:hiv_in] = ViralSeq::DRMs.sdrm_json(:hiv_in)
|
55
|
+
log << { sdrm_list: sdrm_list }
|
56
|
+
|
57
|
+
# input dir
|
58
|
+
indir = ARGV[0]
|
59
|
+
libs = Dir[indir + "/*"]
|
60
|
+
log << { processed_libs: libs }
|
61
|
+
|
62
|
+
#output dir
|
63
|
+
outdir = indir + "_SDRM"
|
64
|
+
Dir.mkdir(outdir) unless File.directory?(outdir)
|
65
|
+
|
66
|
+
libs.each do |lib|
|
67
|
+
|
68
|
+
r_script = ViralSeq::R_SCRIPT.dup
|
69
|
+
|
70
|
+
next unless File.directory?(lib)
|
71
|
+
|
72
|
+
lib_name = File.basename(lib)
|
73
|
+
out_lib_dir = File.join(outdir, lib_name)
|
74
|
+
Dir.mkdir(out_lib_dir) unless File.directory?(out_lib_dir)
|
75
|
+
|
76
|
+
sub_seq_files = Dir[lib + "/*"]
|
77
|
+
|
78
|
+
seq_summary_file = File.join(out_lib_dir, (lib_name + "_summary.csv"))
|
79
|
+
seq_summary_out = File.open(seq_summary_file, "w")
|
80
|
+
seq_summary_out.puts 'Region,TCS,TCS with A3G/F hypermutation,TCS with stop codon,' +
|
81
|
+
'TCS w/o hypermutation and stop codon,' +
|
82
|
+
'Poisson cutoff for minority mutation (>=),Pi,Dist20'
|
83
|
+
|
84
|
+
point_mutation_file = File.join(out_lib_dir, (lib_name + "_substitution.csv"))
|
85
|
+
point_mutation_out = File.open(point_mutation_file, "w")
|
86
|
+
point_mutation_out.puts "region,TCS,AA position,wild type,mutation," +
|
87
|
+
"number,percentage,95% CI low, 95% CI high, notes"
|
88
|
+
|
89
|
+
linkage_file = File.join(out_lib_dir, (lib_name + "_linkage.csv"))
|
90
|
+
linkage_out = File.open(linkage_file, "w")
|
91
|
+
linkage_out.puts "region,TCS,mutation linkage,number," +
|
92
|
+
"percentage,95% CI low, 95% CI high, notes"
|
93
|
+
|
94
|
+
aa_report_file = File.join(out_lib_dir, (lib_name + "_aa.csv"))
|
95
|
+
aa_report_out = File.open(aa_report_file, "w")
|
96
|
+
aa_report_out.puts "region,ref.aa.positions,TCS.number," +
|
97
|
+
ViralSeq::AMINO_ACID_LIST.join(",")
|
98
|
+
|
99
|
+
summary_json_file = File.join(out_lib_dir, (lib_name + "_summary.json"))
|
100
|
+
summary_json_out = File.open(summary_json_file,"w")
|
101
|
+
|
102
|
+
filtered_seq_dir = File.join(out_lib_dir, (lib_name + "_filtered_seq"))
|
103
|
+
Dir.mkdir(filtered_seq_dir) unless File.directory?(filtered_seq_dir)
|
104
|
+
|
105
|
+
aln_seq_dir = File.join(out_lib_dir, (lib_name + "_aln_seq"))
|
106
|
+
Dir.mkdir(aln_seq_dir) unless File.directory?(aln_seq_dir)
|
107
|
+
|
108
|
+
point_mutation_list = []
|
109
|
+
linkage_list = []
|
110
|
+
aa_report_list = []
|
111
|
+
summary_hash = {}
|
112
|
+
|
113
|
+
sub_seq_files.each do |sub_seq|
|
114
|
+
seq_basename = File.basename(sub_seq)
|
115
|
+
seqs = ViralSeq::SeqHash.fa(sub_seq)
|
116
|
+
next if seqs.size < 3
|
117
|
+
if seq_basename =~ /V1V3/i
|
118
|
+
summary_hash[:V1V3] = "#{seqs.size.to_s},NA,NA,NA,NA"
|
119
|
+
FileUtils.cp(sub_seq, filtered_seq_dir)
|
120
|
+
elsif seq_basename =~ /PR/i
|
121
|
+
a3g_check = seqs.a3g
|
122
|
+
a3g_seqs = a3g_check[:a3g_seq]
|
123
|
+
a3g_filtered_seqs = a3g_check[:filtered_seq]
|
124
|
+
stop_codon_check = a3g_filtered_seqs.stop_codon
|
125
|
+
stop_codon_seqs = stop_codon_check[:with_stop_codon]
|
126
|
+
filtered_seqs = stop_codon_check[:without_stop_codon]
|
127
|
+
poisson_minority_cutoff = filtered_seqs.pm
|
128
|
+
summary_hash[:PR] = [
|
129
|
+
seqs.size.to_s,
|
130
|
+
a3g_seqs.size.to_s,
|
131
|
+
stop_codon_seqs.size.to_s,
|
132
|
+
filtered_seqs.size.to_s,
|
133
|
+
poisson_minority_cutoff.to_s
|
134
|
+
].join(',')
|
135
|
+
next if filtered_seqs.size < 3
|
136
|
+
filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
|
137
|
+
|
138
|
+
sdrm = filtered_seqs.sdrm_hiv_pr(poisson_minority_cutoff)
|
139
|
+
point_mutation_list += sdrm[0]
|
140
|
+
linkage_list += sdrm[1]
|
141
|
+
aa_report_list += sdrm[2]
|
142
|
+
|
143
|
+
elsif seq_basename =~/IN/i
|
144
|
+
a3g_check = seqs.a3g
|
145
|
+
a3g_seqs = a3g_check[:a3g_seq]
|
146
|
+
a3g_filtered_seqs = a3g_check[:filtered_seq]
|
147
|
+
stop_codon_check = a3g_filtered_seqs.stop_codon(2)
|
148
|
+
stop_codon_seqs = stop_codon_check[:with_stop_codon]
|
149
|
+
filtered_seqs = stop_codon_check[:without_stop_codon]
|
150
|
+
poisson_minority_cutoff = filtered_seqs.pm
|
151
|
+
summary_hash[:IN] = [
|
152
|
+
seqs.size.to_s,
|
153
|
+
a3g_seqs.size.to_s,
|
154
|
+
stop_codon_seqs.size.to_s,
|
155
|
+
filtered_seqs.size.to_s,
|
156
|
+
poisson_minority_cutoff.to_s
|
157
|
+
].join(',')
|
158
|
+
next if filtered_seqs.size < 3
|
159
|
+
filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
|
160
|
+
|
161
|
+
sdrm = filtered_seqs.sdrm_hiv_in(poisson_minority_cutoff)
|
162
|
+
point_mutation_list += sdrm[0]
|
163
|
+
linkage_list += sdrm[1]
|
164
|
+
aa_report_list += sdrm[2]
|
165
|
+
|
166
|
+
elsif seq_basename =~/RT/i
|
167
|
+
rt_seq1 = {}
|
168
|
+
rt_seq2 = {}
|
169
|
+
seqs.dna_hash.each do |k,v|
|
170
|
+
rt_seq1[k] = v[0,267]
|
171
|
+
rt_seq2[k] = v[267..-1]
|
172
|
+
end
|
173
|
+
rt1 = ViralSeq::SeqHash.new(rt_seq1)
|
174
|
+
rt2 = ViralSeq::SeqHash.new(rt_seq2)
|
175
|
+
rt1_a3g = rt1.a3g
|
176
|
+
rt2_a3g = rt2.a3g
|
177
|
+
hypermut_seq_rt1 = rt1_a3g[:a3g_seq]
|
178
|
+
hypermut_seq_rt2 = rt2_a3g[:a3g_seq]
|
179
|
+
rt1_stop_codon = rt1.stop_codon(1)[:with_stop_codon]
|
180
|
+
rt2_stop_codon = rt2.stop_codon(2)[:with_stop_codon]
|
181
|
+
hypermut_seq_keys = (hypermut_seq_rt1.dna_hash.keys | hypermut_seq_rt2.dna_hash.keys)
|
182
|
+
stop_codon_seq_keys = (rt1_stop_codon.dna_hash.keys | rt2_stop_codon.dna_hash.keys)
|
183
|
+
reject_keys = (hypermut_seq_keys | stop_codon_seq_keys)
|
184
|
+
filtered_seqs = ViralSeq::SeqHash.new(seqs.dna_hash.reject {|k,v| reject_keys.include?(k) })
|
185
|
+
poisson_minority_cutoff = filtered_seqs.pm
|
186
|
+
summary_hash[:RT] = [
|
187
|
+
seqs.size.to_s,
|
188
|
+
hypermut_seq_keys.size.to_s,
|
189
|
+
stop_codon_seq_keys.size.to_s,
|
190
|
+
filtered_seqs.size.to_s,
|
191
|
+
poisson_minority_cutoff.to_s
|
192
|
+
].join(',')
|
193
|
+
next if filtered_seqs.size < 3
|
194
|
+
filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
|
195
|
+
|
196
|
+
sdrm = filtered_seqs.sdrm_hiv_rt(poisson_minority_cutoff)
|
197
|
+
point_mutation_list += sdrm[0]
|
198
|
+
linkage_list += sdrm[1]
|
199
|
+
aa_report_list += sdrm[2]
|
200
|
+
end
|
201
|
+
end
|
202
|
+
|
203
|
+
point_mutation_list.each do |record|
|
204
|
+
point_mutation_out.puts record.join(",")
|
205
|
+
end
|
206
|
+
linkage_list.each do |record|
|
207
|
+
linkage_out.puts record.join(",")
|
208
|
+
end
|
209
|
+
aa_report_list.each do |record|
|
210
|
+
aa_report_out.puts record.join(",")
|
211
|
+
end
|
212
|
+
|
213
|
+
filtered_seq_files = Dir[filtered_seq_dir + "/*"]
|
214
|
+
|
215
|
+
out_r_csv = File.join(out_lib_dir, (lib_name + "_pi.csv"))
|
216
|
+
out_r_pdf = File.join(out_lib_dir, (lib_name + "_pi.pdf"))
|
217
|
+
|
218
|
+
if filtered_seq_files.size > 0
|
219
|
+
filtered_seq_files.each do |seq_file|
|
220
|
+
filtered_sh = ViralSeq::SeqHash.fa(seq_file)
|
221
|
+
next if filtered_sh.size < 3
|
222
|
+
aligned_sh = filtered_sh.random_select(1000).align
|
223
|
+
aligned_sh.write_nt_fa(File.join(aln_seq_dir, File.basename(seq_file)))
|
224
|
+
end
|
225
|
+
|
226
|
+
r_script.gsub!(/PATH_TO_FASTA/,aln_seq_dir)
|
227
|
+
File.unlink(out_r_csv) if File.exist?(out_r_csv)
|
228
|
+
File.unlink(out_r_pdf) if File.exist?(out_r_pdf)
|
229
|
+
r_script.gsub!(/OUTPUT_CSV/,out_r_csv)
|
230
|
+
r_script.gsub!(/OUTPUT_PDF/,out_r_pdf)
|
231
|
+
r_script_file = File.join(out_lib_dir, "/pi.R")
|
232
|
+
File.open(r_script_file,"w") {|line| line.puts r_script}
|
233
|
+
print `Rscript #{r_script_file} 1> /dev/null 2> /dev/null`
|
234
|
+
if File.exist?(out_r_csv)
|
235
|
+
pi_csv = File.readlines(out_r_csv)
|
236
|
+
pi_csv.each do |line|
|
237
|
+
line.chomp!
|
238
|
+
data = line.split(",")
|
239
|
+
tag = data[0].split("_")[-1].gsub(/\W/,"").to_sym
|
240
|
+
summary_hash[tag] += "," + data[1].to_f.round(4).to_s + "," + data[2].to_f.round(4).to_s
|
241
|
+
end
|
242
|
+
[:PR, :RT, :IN, :V1V3].each do |regions|
|
243
|
+
next unless summary_hash[regions]
|
244
|
+
seq_summary_out.puts regions.to_s + "," + summary_hash[regions]
|
245
|
+
end
|
246
|
+
File.unlink(out_r_csv)
|
247
|
+
end
|
248
|
+
File.unlink(r_script_file)
|
249
|
+
end
|
250
|
+
|
251
|
+
seq_summary_out.close
|
252
|
+
point_mutation_out.close
|
253
|
+
linkage_out.close
|
254
|
+
aa_report_out.close
|
255
|
+
|
256
|
+
summary_lines = File.readlines(seq_summary_file)
|
257
|
+
summary_lines.shift
|
258
|
+
|
259
|
+
tcs_PR = 0
|
260
|
+
tcs_RT = 0
|
261
|
+
tcs_IN = 0
|
262
|
+
tcs_V1V3 = 0
|
263
|
+
pi_RT = 0.0
|
264
|
+
pi_V1V3 = 0.0
|
265
|
+
dist20_RT = 0.0
|
266
|
+
dist20_V1V3 = 0.0
|
267
|
+
summary_lines.each do |line|
|
268
|
+
data = line.chomp.split(",")
|
269
|
+
if data[0] == "PR"
|
270
|
+
tcs_PR = data[4].to_i
|
271
|
+
elsif data[0] == "RT"
|
272
|
+
tcs_RT = data[4].to_i
|
273
|
+
pi_RT = data[6].to_f
|
274
|
+
dist20_RT = data[7].to_f
|
275
|
+
elsif data[0] == "IN"
|
276
|
+
tcs_IN = data[4].to_i
|
277
|
+
elsif data[0] == "V1V3"
|
278
|
+
tcs_V1V3 = data[1].to_i
|
279
|
+
pi_V1V3 = data[6].to_f
|
280
|
+
dist20_V1V3 = data[7].to_f
|
281
|
+
end
|
282
|
+
end
|
283
|
+
|
284
|
+
recency = ViralSeq::Recency.define(
|
285
|
+
tcs_RT: tcs_RT,
|
286
|
+
tcs_V1V3: tcs_V1V3,
|
287
|
+
pi_RT: pi_RT,
|
288
|
+
dist20_RT: dist20_RT,
|
289
|
+
pi_V1V3: pi_V1V3,
|
290
|
+
dist20_V1V3: dist20_V1V3
|
291
|
+
)
|
292
|
+
|
293
|
+
sdrm_lines = File.readlines(point_mutation_file)
|
294
|
+
sdrm_lines.shift
|
295
|
+
sdrm_PR = ""
|
296
|
+
sdrm_RT = ""
|
297
|
+
sdrm_IN = ""
|
298
|
+
sdrm_lines.each do |line|
|
299
|
+
data = line.chomp.split(",")
|
300
|
+
next if data[-1] == "*"
|
301
|
+
if data[0] == "PR"
|
302
|
+
sdrm_PR += abstract_line(data)
|
303
|
+
elsif data[0] =~ /NRTI/
|
304
|
+
sdrm_RT += abstract_line(data)
|
305
|
+
elsif data[0] == "IN"
|
306
|
+
sdrm_IN += abstract_line(data)
|
307
|
+
end
|
308
|
+
end
|
309
|
+
|
310
|
+
summary_json = [
|
311
|
+
sample_id: lib_name,
|
312
|
+
tcs_PR: tcs_PR,
|
313
|
+
tcs_RT: tcs_RT,
|
314
|
+
tcs_IN: tcs_IN,
|
315
|
+
tcs_V1V3: tcs_V1V3,
|
316
|
+
pi_RT: pi_RT,
|
317
|
+
dist20_RT: dist20_RT,
|
318
|
+
dist20_V1V3: dist20_V1V3,
|
319
|
+
recency: recency,
|
320
|
+
sdrm_PR: sdrm_PR,
|
321
|
+
sdrm_RT: sdrm_RT,
|
322
|
+
sdrm_IN: sdrm_IN
|
323
|
+
]
|
324
|
+
|
325
|
+
summary_json_out.puts JSON.pretty_generate(summary_json)
|
326
|
+
summary_json_out.close
|
327
|
+
|
328
|
+
csvs = [
|
329
|
+
{
|
330
|
+
name: "summary",
|
331
|
+
title: "Summary",
|
332
|
+
file: seq_summary_file,
|
333
|
+
newPDF: "",
|
334
|
+
table_width: [65,55,110,110,110,110,60,60],
|
335
|
+
extra_text: ""
|
336
|
+
},
|
337
|
+
{
|
338
|
+
name: "substitution",
|
339
|
+
title: "Surveillance Drug Resistance Mutations",
|
340
|
+
file: point_mutation_file,
|
341
|
+
newPDF: "",
|
342
|
+
table_width: [65,55,85,80,60,65,85,85,85,45],
|
343
|
+
extra_text: "* Mutation below Poisson cut-off for minority mutations"
|
344
|
+
},
|
345
|
+
{
|
346
|
+
name: "linkage",
|
347
|
+
title: "Mutation Linkage",
|
348
|
+
file: linkage_file,
|
349
|
+
newPDF: "",
|
350
|
+
table_width: [55,50,250,60,80,80,80,45],
|
351
|
+
extra_text: "* Mutation below Poisson cut-off for minority mutations"
|
352
|
+
}
|
353
|
+
]
|
354
|
+
|
355
|
+
csvs.each do |csv|
|
356
|
+
file_name = File.join(out_lib_dir, (csv[:name] + ".pdf"))
|
357
|
+
next unless File.exist? csv[:file]
|
358
|
+
Prawn::Document.generate(file_name, :page_layout => :landscape) do |pdf|
|
359
|
+
pdf.text((File.basename(lib, ".*") + ': ' + csv[:title]),
|
360
|
+
:size => 20,
|
361
|
+
:align => :center,
|
362
|
+
:style => :bold)
|
363
|
+
pdf.move_down 20
|
364
|
+
table_data = CSV.open(csv[:file]).to_a
|
365
|
+
header = table_data.first
|
366
|
+
pdf.table(table_data,
|
367
|
+
:header => header,
|
368
|
+
:position => :center,
|
369
|
+
:column_widths => csv[:table_width],
|
370
|
+
:row_colors => ["B6B6B6", "FFFFFF"],
|
371
|
+
:cell_style => {:align => :center, :size => 10}) do |table|
|
372
|
+
table.row(0).style :font_style => :bold, :size => 12 #, :background_color => 'ff00ff'
|
373
|
+
end
|
374
|
+
pdf.move_down 5
|
375
|
+
pdf.text(csv[:extra_text], :size => 8, :align => :justify,)
|
376
|
+
end
|
377
|
+
csv[:newPDF] = file_name
|
378
|
+
end
|
379
|
+
|
380
|
+
pdf = CombinePDF.new
|
381
|
+
csvs.each do |csv|
|
382
|
+
pdf << CombinePDF.load(csv[:newPDF]) if File.exist?(csv[:newPDF])
|
383
|
+
end
|
384
|
+
pdf << CombinePDF.load(out_r_pdf) if File.exist?(out_r_pdf)
|
385
|
+
|
386
|
+
pdf.number_pages location: [:bottom_right],
|
387
|
+
number_format: "Swanstrom\'s lab HIV SDRM Pipeline, version #{$sdrm_version_number} by S.Z. and M.U.C. Page %s",
|
388
|
+
font_size: 6,
|
389
|
+
opacity: 0.5
|
390
|
+
|
391
|
+
pdf.save File.join(out_lib_dir, (lib_name + ".pdf"))
|
392
|
+
|
393
|
+
csvs.each do |csv|
|
394
|
+
File.unlink csv[:newPDF]
|
395
|
+
end
|
396
|
+
end
|
397
|
+
|
398
|
+
log_file = indir + "_sdrm_log.json"
|
399
|
+
|
400
|
+
File.open(log_file, 'w') { |f| f.puts JSON.pretty_generate(log) }
|
401
|
+
|
402
|
+
FileUtils.touch(File.join(outdir, ".done"))
|
data/lib/viral_seq.rb
CHANGED
@@ -0,0 +1,52 @@
|
|
1
|
+
module ViralSeq
|
2
|
+
|
3
|
+
# recency prediction function based on HIV MPID-NGS
|
4
|
+
# @see https://pubmed.ncbi.nlm.nih.gov/32663847 Ref: Zhou et al. J Infect Dis. 2021
|
5
|
+
|
6
|
+
module Recency
|
7
|
+
|
8
|
+
# @params tcs_RT [Integer] number of TCS at the RT region
|
9
|
+
# @params tcs_V1V3 [Integer] number of TCS at the V1V3 region
|
10
|
+
# @params pi_RT [Float] pairwise diversity at the RT region
|
11
|
+
# @params pi_V1V3 [Float] pairwise diversity at the V1V3 region
|
12
|
+
# @params dist20_RT [Float] dist20 at the RT region
|
13
|
+
# @params dist20_V1V3 [Float] dist20 at the V1V3 region
|
14
|
+
# @return [String] determination of the recency
|
15
|
+
|
16
|
+
def self.define(tcs_RT: nil,
|
17
|
+
tcs_V1V3: nil,
|
18
|
+
pi_RT: nil,
|
19
|
+
dist20_RT: nil,
|
20
|
+
pi_V1V3: nil,
|
21
|
+
dist20_V1V3: nil)
|
22
|
+
tcs_RT ||= 0
|
23
|
+
tcs_V1V3 ||= 0
|
24
|
+
if (tcs_RT >= 3 && pi_RT) and (tcs_V1V3 >= 3 && pi_V1V3)
|
25
|
+
if (pi_RT + pi_V1V3) < 0.0103
|
26
|
+
recency = "recent"
|
27
|
+
elsif (pi_RT + pi_V1V3) >= 0.0103 and (dist20_RT + dist20_V1V3) >= 0.006
|
28
|
+
recency = "chronic"
|
29
|
+
else
|
30
|
+
recency = "indeterminant"
|
31
|
+
end
|
32
|
+
elsif (tcs_RT >= 3 && pi_RT) and tcs_V1V3 < 3
|
33
|
+
if pi_RT < 0.0021
|
34
|
+
recency = "recent"
|
35
|
+
elsif pi_RT >= 0.0021 and dist20_RT >= 0.001
|
36
|
+
recency = "chronic"
|
37
|
+
else
|
38
|
+
recency = "indeterminant"
|
39
|
+
end
|
40
|
+
elsif (tcs_V1V3 >= 3 && pi_V1V3)
|
41
|
+
if pi_V1V3 >= 0.0103 and dist20_V1V3 >= 0.006
|
42
|
+
recency = "chronic"
|
43
|
+
else
|
44
|
+
recency = "insufficient data"
|
45
|
+
end
|
46
|
+
else
|
47
|
+
recency = "insufficient data"
|
48
|
+
end
|
49
|
+
return recency
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
data/lib/viral_seq/sdrm.rb
CHANGED
@@ -90,7 +90,7 @@ module ViralSeq
|
|
90
90
|
|
91
91
|
# function to export SDRM positions as json object
|
92
92
|
# @param (see #sdrm_hash)
|
93
|
-
# @return [
|
93
|
+
# @return [Array] json Array of SDRM positions
|
94
94
|
|
95
95
|
def sdrm_json(options)
|
96
96
|
sdrm = ViralSeq::DRMs.sdrm_hash(options)
|
@@ -102,7 +102,7 @@ module ViralSeq
|
|
102
102
|
mutation[:mutationCodons] = muts[1]
|
103
103
|
json_array << mutation
|
104
104
|
end
|
105
|
-
|
105
|
+
return json_array
|
106
106
|
end
|
107
107
|
end
|
108
108
|
end
|
data/lib/viral_seq/seq_hash.rb
CHANGED
@@ -11,7 +11,7 @@ module ViralSeq
|
|
11
11
|
# # filter nt sequences with the reference coordinates
|
12
12
|
# filtered_seqhash = aligned_pr_seqhash.stop_codon[:without_stop_codon]
|
13
13
|
# # return a new ViralSeq::SeqHash object without stop codons
|
14
|
-
# filtered_seqhash = filtered_seqhash.a3g[
|
14
|
+
# filtered_seqhash = filtered_seqhash.a3g[:filtered_seq]
|
15
15
|
# # further filter out sequences with A3G hypermutations
|
16
16
|
# filtered_seqhash.pi
|
17
17
|
# # return pairwise diveristy π
|
@@ -187,6 +187,25 @@ module ViralSeq
|
|
187
187
|
return new_seqhash
|
188
188
|
end
|
189
189
|
|
190
|
+
# sample a certain number of sequences from a SeqHash object
|
191
|
+
# @param n [Integer] number of sequences to sample
|
192
|
+
# @return [ViralSeq::SeqHash] sampled SeqHash
|
193
|
+
|
194
|
+
def sample(n = 1)
|
195
|
+
keys = self.dna_hash.keys
|
196
|
+
sampled_keys = keys.sample(n)
|
197
|
+
sampled_nt = {}
|
198
|
+
sampled_aa = {}
|
199
|
+
sampled_qc = {}
|
200
|
+
sampled_title = self.title + "_sampled_" + n.to_s
|
201
|
+
sampled_keys.each do |k|
|
202
|
+
sampled_nt[k] = self.dna_hash[k]
|
203
|
+
sampled_aa[k] = self.aa_hash[k]
|
204
|
+
sampled_qc[k] = self.qc_hash[k]
|
205
|
+
end
|
206
|
+
return ViralSeq::SeqHash.new(sampled_nt, sampled_aa, sampled_qc, sampled_title, self.file)
|
207
|
+
end
|
208
|
+
|
190
209
|
# write the nt sequences to a FASTA format file
|
191
210
|
# @param file [String] path to the FASTA output file
|
192
211
|
# @return [NilClass]
|
@@ -582,8 +601,8 @@ module ViralSeq
|
|
582
601
|
temp_dir=File.dirname($0)
|
583
602
|
end
|
584
603
|
|
585
|
-
temp_file = temp_dir
|
586
|
-
temp_aln = temp_dir
|
604
|
+
temp_file = File.join(temp_dir, "_temp_muscle_in")
|
605
|
+
temp_aln = File.join(temp_dir, "_temp_muscle_aln")
|
587
606
|
File.open(temp_file, 'w'){|f| seq_hash.each {|k,v| f.puts k; f.puts v}}
|
588
607
|
if path_to_muscle
|
589
608
|
unless ViralSeq.check_muscle?(path_to_muscle)
|
@@ -808,7 +827,7 @@ module ViralSeq
|
|
808
827
|
end # end of locator
|
809
828
|
alias_method :loc, :sequence_locator
|
810
829
|
|
811
|
-
# Remove
|
830
|
+
# Remove sequences with residual offspring Primer IDs.
|
812
831
|
# Compare PID with sequences which have identical sequences.
|
813
832
|
# PIDs differ by 1 base will be recognized. If PID1 is x time (cutoff) greater than PID2, PID2 will be disgarded.
|
814
833
|
# each sequence tag starting with ">" and the Primer ID sequence
|
@@ -1155,6 +1174,7 @@ module ViralSeq
|
|
1155
1174
|
new_sh.aa_hash[k] = aa_hash[k]
|
1156
1175
|
new_sh.qc_hash[k] = qc_hash[k]
|
1157
1176
|
end
|
1177
|
+
new_sh.file = self.file
|
1158
1178
|
new_sh.title = self.title + "_" + n.to_s
|
1159
1179
|
return new_sh
|
1160
1180
|
end
|
data/lib/viral_seq/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: viral_seq
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Shuntai Zhou
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2021-
|
12
|
+
date: 2021-05-11 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bundler
|
@@ -151,6 +151,7 @@ executables:
|
|
151
151
|
- locator
|
152
152
|
- tcs
|
153
153
|
- tcs_log
|
154
|
+
- tcs_sdrm
|
154
155
|
extensions: []
|
155
156
|
extra_rdoc_files: []
|
156
157
|
files:
|
@@ -166,6 +167,7 @@ files:
|
|
166
167
|
- bin/locator
|
167
168
|
- bin/tcs
|
168
169
|
- bin/tcs_log
|
170
|
+
- bin/tcs_sdrm
|
169
171
|
- docs/assets/img/cover.jpg
|
170
172
|
- docs/dr.json
|
171
173
|
- docs/sample_miseq_data/hivdr_control/r1.fastq.gz
|
@@ -178,6 +180,7 @@ files:
|
|
178
180
|
- lib/viral_seq/math.rb
|
179
181
|
- lib/viral_seq/muscle.rb
|
180
182
|
- lib/viral_seq/pid.rb
|
183
|
+
- lib/viral_seq/recency.rb
|
181
184
|
- lib/viral_seq/ref_seq.rb
|
182
185
|
- lib/viral_seq/rubystats.rb
|
183
186
|
- lib/viral_seq/sdrm.rb
|