viral_seq 1.1.0 → 1.2.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +16 -3
- data/README.md +99 -12
- data/bin/tcs +54 -10
- data/bin/tcs_log +20 -1
- data/bin/tcs_sdrm +409 -0
- data/docs/assets/img/cover.jpg +0 -0
- data/{doc → docs}/dr.json +0 -1
- data/docs/sample_miseq_data/hivdr_control/r1.fastq.gz +0 -0
- data/docs/sample_miseq_data/hivdr_control/r2.fastq.gz +0 -0
- data/lib/viral_seq.rb +5 -1
- data/lib/viral_seq/constant.rb +41 -4
- data/lib/viral_seq/hivdr.rb +1 -1
- data/lib/viral_seq/muscle.rb +3 -2
- data/lib/viral_seq/recency.rb +52 -0
- data/lib/viral_seq/sdrm.rb +101 -35
- data/lib/viral_seq/seq_hash.rb +24 -4
- data/lib/viral_seq/sequence.rb +1 -84
- data/lib/viral_seq/tcs_dr.rb +71 -0
- data/lib/viral_seq/version.rb +2 -2
- data/viral_seq.gemspec +11 -0
- metadata +72 -5
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a235cae95121a8522a47620eb9f8c05a3e2e416084743cd23df43aff7870a2c4
|
4
|
+
data.tar.gz: f0ce3a9412774eed703b0b0b663e7bb2dccf340f3f558cffdca85e920291794d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: b97f98e40b8257281bd29cee40942d16084cf175933fc8357838ebb2a9eede1ab93ba323dbf315afb300f0a7852b2c6d939235831124710fc6f16f109e3eafc5
|
7
|
+
data.tar.gz: 4d660da22c69ce1ff929ed7f67d2b03aad662bb0237e9a93d9a8ea6bd1866d8544ad108db9ab8a11eee2df992395e41b68ffc43a8d1dbb132cc1f83a897676ef
|
data/Gemfile.lock
CHANGED
@@ -1,16 +1,27 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
viral_seq (1.
|
5
|
-
colorize (
|
6
|
-
|
4
|
+
viral_seq (1.1.1)
|
5
|
+
colorize (>= 0.1)
|
6
|
+
combine_pdf (>= 1.0.0)
|
7
|
+
muscle_bio (>= 0.4)
|
8
|
+
prawn (>= 2.3.0)
|
9
|
+
prawn-table (>= 0.2.0)
|
7
10
|
|
8
11
|
GEM
|
9
12
|
remote: https://rubygems.org/
|
10
13
|
specs:
|
11
14
|
colorize (0.8.1)
|
15
|
+
combine_pdf (1.0.21)
|
16
|
+
ruby-rc4 (>= 0.1.5)
|
12
17
|
diff-lcs (1.3)
|
13
18
|
muscle_bio (0.4.0)
|
19
|
+
pdf-core (0.9.0)
|
20
|
+
prawn (2.4.0)
|
21
|
+
pdf-core (~> 0.9.0)
|
22
|
+
ttfunk (~> 1.7)
|
23
|
+
prawn-table (0.2.2)
|
24
|
+
prawn (>= 1.3.0, < 3.0.0)
|
14
25
|
rake (13.0.1)
|
15
26
|
rspec (3.8.0)
|
16
27
|
rspec-core (~> 3.8.0)
|
@@ -25,6 +36,8 @@ GEM
|
|
25
36
|
diff-lcs (>= 1.2.0, < 2.0)
|
26
37
|
rspec-support (~> 3.8.0)
|
27
38
|
rspec-support (3.8.0)
|
39
|
+
ruby-rc4 (0.1.5)
|
40
|
+
ttfunk (1.7.0)
|
28
41
|
|
29
42
|
PLATFORMS
|
30
43
|
ruby
|
data/README.md
CHANGED
@@ -1,5 +1,11 @@
|
|
1
1
|
# ViralSeq
|
2
2
|
|
3
|
+
[![Gem Version](https://img.shields.io/gem/v/viral_seq?color=%2300e673&style=flat-square)](https://rubygems.org/gems/viral_seq)
|
4
|
+
![GitHub](https://img.shields.io/github/license/viralseq/viral_seq)
|
5
|
+
![Gem](https://img.shields.io/gem/dt/viral_seq?color=%23E9967A)
|
6
|
+
![GitHub last commit](https://img.shields.io/github/last-commit/viralseq/viral_seq?color=%2300BFFF)
|
7
|
+
[![Join the chat at https://gitter.im/viral_seq/community](https://badges.gitter.im/viral_seq/community.svg)](https://gitter.im/viral_seq/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
|
8
|
+
|
3
9
|
A Ruby Gem containing bioinformatics tools for processing viral NGS data.
|
4
10
|
|
5
11
|
Specifically for Primer ID sequencing and HIV drug resistance analysis.
|
@@ -7,11 +13,12 @@ Specifically for Primer ID sequencing and HIV drug resistance analysis.
|
|
7
13
|
## Illustration for the Primer ID Sequencing
|
8
14
|
|
9
15
|
|
10
|
-
![Primer ID Sequencing](
|
16
|
+
![Primer ID Sequencing](./docs/assets/img/cover.jpg)
|
11
17
|
|
12
18
|
### Reference readings on the Primer ID sequencing
|
13
|
-
[Primer ID
|
14
|
-
[Primer ID MiSeq protocol](https://doi.org/10.1128/JVI.00522-15)
|
19
|
+
[Explantion of Primer ID sequencing](https://doi.org/10.21769/BioProtoc.3938)
|
20
|
+
[Primer ID MiSeq protocol](https://doi.org/10.1128/JVI.00522-15)
|
21
|
+
[Application of Primer ID sequencing in COVID-19 research](https://doi.org/10.1126/scitranslmed.abb5883)
|
15
22
|
|
16
23
|
## Install
|
17
24
|
|
@@ -24,14 +31,23 @@ Specifically for Primer ID sequencing and HIV drug resistance analysis.
|
|
24
31
|
### Excutables
|
25
32
|
|
26
33
|
### `tcs`
|
27
|
-
Use executable `tcs` pipeline to process **Primer ID MiSeq sequencing** data.
|
34
|
+
Use executable `tcs` pipeline (v2.3.2) to process **Primer ID MiSeq sequencing** data.
|
28
35
|
|
29
36
|
Example commands:
|
30
37
|
```bash
|
31
38
|
$ tcs -p params.json # run TCS pipeline with params.json
|
39
|
+
$ tcs -p params.json -i DIRECTORY
|
40
|
+
# run TCS pipeline with params.json and DIRECTORY
|
41
|
+
# if DIRECTORY is not defined in params.json
|
42
|
+
$ tcs -dr -i DIRECTORY
|
43
|
+
# run tcs-dr (MPID HIV drug resistance sequencing) pipeline
|
44
|
+
# DIRECTORY needs to be given.
|
32
45
|
$ tcs -j # CLI to generate params.json
|
33
46
|
$ tcs -h # print out the help
|
34
47
|
```
|
48
|
+
|
49
|
+
[sample params.json for the tcs-dr pipeline](./docs/dr.json)
|
50
|
+
|
35
51
|
---
|
36
52
|
### `tcs_log`
|
37
53
|
|
@@ -53,6 +69,44 @@ Example command:
|
|
53
69
|
$ tcs_log batch_tcs_jobs
|
54
70
|
```
|
55
71
|
|
72
|
+
---
|
73
|
+
### `tcs_sdrm`
|
74
|
+
|
75
|
+
Use `tcs_sdrm` pipeline for HIV-1 drug resistance mutation and recency.
|
76
|
+
|
77
|
+
Example command:
|
78
|
+
```bash
|
79
|
+
$ tcs_sdrm libs_dir
|
80
|
+
```
|
81
|
+
|
82
|
+
lib_dir file structure:
|
83
|
+
```
|
84
|
+
libs_dir/
|
85
|
+
├── lib1
|
86
|
+
├── lib1_RT
|
87
|
+
├── lib1_PR
|
88
|
+
├── lib1_IN
|
89
|
+
├── lib1_V1V3
|
90
|
+
├── lib2
|
91
|
+
├── lib1_RT
|
92
|
+
├── lib1_PR
|
93
|
+
├── lib1_IN
|
94
|
+
├── lib1_V1V3
|
95
|
+
├── ...
|
96
|
+
```
|
97
|
+
|
98
|
+
Output data in a new dir as 'libs_dir_SDRM'
|
99
|
+
|
100
|
+
|
101
|
+
**Note: [R](https://www.r-project.org/) and the following R libraries are required:**
|
102
|
+
- phangorn
|
103
|
+
- ape
|
104
|
+
- scales
|
105
|
+
- ggforce
|
106
|
+
- cowplot
|
107
|
+
- magrittr
|
108
|
+
- gridExtra
|
109
|
+
|
56
110
|
---
|
57
111
|
|
58
112
|
### `locator`
|
@@ -93,7 +147,7 @@ qc_seqhash = aligned_seqhash.hiv_seq_qc(2253, 2549, false, :HXB2)
|
|
93
147
|
Further filter out sequences with Apobec3g/f hypermutations
|
94
148
|
|
95
149
|
```ruby
|
96
|
-
qc_seqhash = qc_seqhash.a3g
|
150
|
+
qc_seqhash = qc_seqhash.a3g[:filtered_seq]
|
97
151
|
```
|
98
152
|
|
99
153
|
Calculate nucleotide diveristy π
|
@@ -121,15 +175,48 @@ qc_seqhash.sdrm_hiv_pr(cut_off)
|
|
121
175
|
|
122
176
|
## Updates
|
123
177
|
|
178
|
+
### Version 1.2.2-05272021
|
179
|
+
|
180
|
+
1. Fixed a bug in the `tcs` pipeline that sometimes causes `SystemStackError`.
|
181
|
+
`tcs` pipeline upgraded to v2.3.2
|
182
|
+
|
183
|
+
### Version 1.2.1-05172021
|
184
|
+
|
185
|
+
1. Added a function in R to check and install missing R packages for `tcs_sdrm` pipeline.
|
186
|
+
|
187
|
+
### Version 1.2.0-05102021
|
188
|
+
|
189
|
+
1. Added `tcs_sdrm` pipeline as an excutable.
|
190
|
+
`tcs_sdrm` processes `tcs`-processed HIV MPID-NGS data for drug resistance mutations, recency and phylogentic analysis.
|
191
|
+
|
192
|
+
2. Added function ViralSeq::SeqHash#sample.
|
193
|
+
|
194
|
+
3. Added recency determining function `ViralSeq::Recency::define`
|
195
|
+
|
196
|
+
4. Fixed a few bugs related to `tcs_sdrm`.
|
197
|
+
|
198
|
+
### Version 1.1.2-04262021
|
199
|
+
|
200
|
+
1. Added function `ViralSeq::DRMs.sdrm_json` to export SDRM as json object.
|
201
|
+
2. Added a random string to the temp file names for `muscle_bio` to avoid issues when running scripts in parallel.
|
202
|
+
3. Added `--keep-original` flag to the `tcs` pipeline.
|
203
|
+
|
204
|
+
### Version 1.1.1-04012021
|
205
|
+
|
206
|
+
1. Added warning when paired_raw_sequence less than 0.1% of total_raw_sequence.
|
207
|
+
2. Added option `-i WORKING_DIRECTORY` to the `tcs` script.
|
208
|
+
If the `params.json` file does not contain the path to the working directory, it will append path to the run params.
|
209
|
+
3. Added option `-dr` to the `tcs` script.
|
210
|
+
|
124
211
|
### Version 1.1.0-03252021
|
125
212
|
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
|
213
|
+
1. Optimized the algorithm of end-join.
|
214
|
+
2. Fixed a bug in the `tcs` pipeline that sometimes combined tcs files are not saved.
|
215
|
+
3. Added `tcs_log` command to pool run logs and tcs files from one batch of tcs jobs.
|
216
|
+
4. Added the preset of MPID-HIVDR params file [***dr.json***](./docs/dr.json) in /docs.
|
217
|
+
5. Add `platform_format` option in the json generator of the `tcs` Pipeline.
|
218
|
+
Users can choose from 3 MiSeq platforms for processing their sequencing data.
|
219
|
+
MiSeq 300x7x300 is the default option.
|
133
220
|
|
134
221
|
### Version 1.0.14-03052021
|
135
222
|
|
data/bin/tcs
CHANGED
@@ -46,11 +46,23 @@ OptionParser.new do |opts|
|
|
46
46
|
options[:params_json] = p
|
47
47
|
end
|
48
48
|
|
49
|
+
opts.on("-i", "--input PATH_TO_WORKING_DIRECTORY", "Path to the working directory") do |p|
|
50
|
+
options[:input] = p
|
51
|
+
end
|
52
|
+
|
53
|
+
opts.on("-dr", "--dr_pipeline", "HIV drug resistance MPID pipeline") do |p|
|
54
|
+
options[:dr] = true
|
55
|
+
end
|
56
|
+
|
49
57
|
opts.on("-h", "--help", "Prints this help") do
|
50
58
|
puts opts
|
51
59
|
exit
|
52
60
|
end
|
53
61
|
|
62
|
+
opts.on("--keep-original", "keep raw sequence files") do
|
63
|
+
options[:keep] = true
|
64
|
+
end
|
65
|
+
|
54
66
|
opts.on("-v", "--version", "Version info") do
|
55
67
|
puts "tcs version: " + ViralSeq::TCS_VERSION.red.bold
|
56
68
|
puts "viral_seq version: " + ViralSeq::VERSION.red.bold
|
@@ -64,15 +76,21 @@ end.parse!
|
|
64
76
|
|
65
77
|
if options[:json_generator]
|
66
78
|
params = ViralSeq::TcsJson.generate
|
79
|
+
elsif options[:dr]
|
80
|
+
params = ViralSeq::TcsDr::PARAMS
|
67
81
|
elsif (options[:params_json] && File.exist?(options[:params_json]))
|
68
82
|
params = JSON.parse(File.read(options[:params_json]), symbolize_names: true)
|
69
83
|
else
|
70
84
|
abort "No params JSON file found. Script terminated.".red
|
71
85
|
end
|
72
86
|
|
73
|
-
|
87
|
+
if options[:input]
|
88
|
+
indir = options[:input]
|
89
|
+
else
|
90
|
+
indir = params[:raw_sequence_dir]
|
91
|
+
end
|
74
92
|
|
75
|
-
unless File.exist?(indir)
|
93
|
+
unless indir and File.exist?(indir)
|
76
94
|
abort "No input sequence directory found. Script terminated.".red.bold
|
77
95
|
end
|
78
96
|
|
@@ -129,6 +147,7 @@ end
|
|
129
147
|
|
130
148
|
primers.each do |primer|
|
131
149
|
summary_json = {}
|
150
|
+
summary_json[:warnings] = []
|
132
151
|
summary_json[:tcs_version] = ViralSeq::TCS_VERSION
|
133
152
|
summary_json[:viralseq_version] = ViralSeq::VERSION
|
134
153
|
summary_json[:runtime] = Time.now.to_s
|
@@ -140,6 +159,7 @@ primers.each do |primer|
|
|
140
159
|
forward_primer = primer[:forward]
|
141
160
|
|
142
161
|
export_raw = primer[:export_raw]
|
162
|
+
limit_raw = primer[:limit_raw]
|
143
163
|
|
144
164
|
unless cdna_primer
|
145
165
|
log.puts Time.now.to_s + "\t" + region + " does not have cDNA primer sequence. #{region} skipped."
|
@@ -181,6 +201,10 @@ primers.each do |primer|
|
|
181
201
|
paired_seq_number = common_keys.size
|
182
202
|
log.puts Time.now.to_s + "\t" + "Paired raw sequences are : #{paired_seq_number.to_s}"
|
183
203
|
summary_json[:paired_raw_sequence] = paired_seq_number
|
204
|
+
if paired_seq_number < raw_sequence_number * 0.001
|
205
|
+
summary_json[:warnings] <<
|
206
|
+
"WARNING: Filtered raw sequneces less than 0.1% of the total raw sequences. Possible contamination."
|
207
|
+
end
|
184
208
|
|
185
209
|
common_keys.each do |seqtag|
|
186
210
|
r1_seq = r1_passed_seq[seqtag]
|
@@ -242,7 +266,13 @@ primers.each do |primer|
|
|
242
266
|
raw_r1_f = File.open(outfile_raw_r1, 'w')
|
243
267
|
raw_r2_f = File.open(outfile_raw_r2, 'w')
|
244
268
|
|
245
|
-
|
269
|
+
if limit_raw
|
270
|
+
raw_keys = bio_r1.keys.sample(limit_raw.to_i)
|
271
|
+
else
|
272
|
+
raw_keys = bio_r1.keys
|
273
|
+
end
|
274
|
+
|
275
|
+
raw_keys.each do |k|
|
246
276
|
raw_r1_f.puts k + "_r1"
|
247
277
|
raw_r2_f.puts k + "_r2"
|
248
278
|
raw_r1_f.puts bio_r1[k]
|
@@ -341,9 +371,21 @@ primers.each do |primer|
|
|
341
371
|
# Primer ID distribution in .json file
|
342
372
|
out_pid_json = File.join(out_dir_set, 'primer_id.json')
|
343
373
|
pid_json = {}
|
344
|
-
pid_json[:primer_id_in_use] =
|
345
|
-
|
346
|
-
|
374
|
+
pid_json[:primer_id_in_use] = {}
|
375
|
+
primer_id_in_use.sort_by {|k, v| [-v,k]}.each do |k,v|
|
376
|
+
pid_json[:primer_id_in_use][k] = v
|
377
|
+
end
|
378
|
+
|
379
|
+
pid_json[:primer_id_distribution] = {}
|
380
|
+
primer_id_dis.sort_by{|k,v| k}.each do |k,v|
|
381
|
+
pid_json[:primer_id_distribution][k] = v
|
382
|
+
end
|
383
|
+
|
384
|
+
pid_json[:primer_id_frequency] = {}
|
385
|
+
primer_id_count.sort_by {|k,v| [-v,k]}.each do |k,v|
|
386
|
+
pid_json[:primer_id_frequency][k] = v
|
387
|
+
end
|
388
|
+
|
347
389
|
File.open(out_pid_json, 'w') do |f|
|
348
390
|
f.puts JSON.pretty_generate(pid_json)
|
349
391
|
end
|
@@ -455,9 +497,11 @@ primers.each do |primer|
|
|
455
497
|
end
|
456
498
|
end
|
457
499
|
|
458
|
-
|
459
|
-
|
460
|
-
File.unlink(
|
461
|
-
|
500
|
+
unless options[:keep]
|
501
|
+
log.puts Time.now.to_s + "\t" + "Removing raw sequence files..."
|
502
|
+
File.unlink(r1_f)
|
503
|
+
File.unlink(r2_f)
|
504
|
+
end
|
505
|
+
log.puts Time.now.to_s + "\t" + "TCS pipeline successfuly executed."
|
462
506
|
log.close
|
463
507
|
puts "DONE!"
|
data/bin/tcs_log
CHANGED
@@ -37,8 +37,26 @@ Dir.mkdir(outdir4) unless File.directory?(outdir4)
|
|
37
37
|
|
38
38
|
log_file = File.join(tcs_dir,"log.csv")
|
39
39
|
log = File.open(log_file,'w')
|
40
|
-
log.puts "lib name,Region,Raw Sequences per barcode,R1 Raw,R2 Raw,Paired Raw,Cutoff,PID Length,Consensus1,Consensus2,Distinct to Raw,Resampling index,Combined TCS,Combined TCS after QC"
|
41
40
|
|
41
|
+
header = %w{
|
42
|
+
lib_name
|
43
|
+
Region
|
44
|
+
Raw_Sequences_per_barcode
|
45
|
+
R1_Raw
|
46
|
+
R2_Raw
|
47
|
+
Paired_Raw
|
48
|
+
Cutoff
|
49
|
+
PID_Length
|
50
|
+
Consensus1
|
51
|
+
Consensus2
|
52
|
+
Distinct_to_Raw
|
53
|
+
Resampling_index
|
54
|
+
Combined_TCS
|
55
|
+
Combined_TCS_after_QC
|
56
|
+
WARNINGS
|
57
|
+
}
|
58
|
+
|
59
|
+
log.puts header.join(',')
|
42
60
|
libs.each do |lib|
|
43
61
|
Dir.mkdir(File.join(outdir2, lib)) unless File.directory?(File.join(outdir2, lib))
|
44
62
|
fasta_files = []
|
@@ -77,6 +95,7 @@ libs.each do |lib|
|
|
77
95
|
json_log[:resampling_param],
|
78
96
|
json_log[:combined_tcs],
|
79
97
|
json_log[:combined_tcs_after_qc],
|
98
|
+
json_log[:warnings],
|
80
99
|
].join(',') + "\n"
|
81
100
|
end
|
82
101
|
end
|
data/bin/tcs_sdrm
ADDED
@@ -0,0 +1,409 @@
|
|
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
|
+
begin
|
36
|
+
r_version = `R --version`.split("\n")[0]
|
37
|
+
r_check = `R -e '#{ViralSeq::R_SCRIPT_CHECK_PACKAGES}' > /dev/null 2>&1`
|
38
|
+
rescue Errno::ENOENT
|
39
|
+
abort '"R" is not installed. Install R at https://www.r-project.org/' +
|
40
|
+
"\n`tcs_sdrm` pipeline aborted."
|
41
|
+
end
|
42
|
+
|
43
|
+
def abstract_line(data)
|
44
|
+
return_data = data[3] + data[2] + data[4] + ":" +
|
45
|
+
(data[6].to_f * 100).round(2).to_s + "(" +
|
46
|
+
(data[7].to_f * 100).round(2).to_s + "-" +
|
47
|
+
(data[8].to_f * 100).round(2).to_s + "); "
|
48
|
+
end
|
49
|
+
|
50
|
+
# run params
|
51
|
+
log = []
|
52
|
+
|
53
|
+
log << { time: Time.now }
|
54
|
+
log << { viral_seq_version: ViralSeq::VERSION }
|
55
|
+
log << { tcs_version: ViralSeq::TCS_VERSION }
|
56
|
+
log << { R_version: r_version}
|
57
|
+
sdrm_list = {}
|
58
|
+
sdrm_list[:nrti] = ViralSeq::DRMs.sdrm_json(:nrti)
|
59
|
+
sdrm_list[:nnrti] = ViralSeq::DRMs.sdrm_json(:nnrti)
|
60
|
+
sdrm_list[:hiv_pr] = ViralSeq::DRMs.sdrm_json(:hiv_pr)
|
61
|
+
sdrm_list[:hiv_in] = ViralSeq::DRMs.sdrm_json(:hiv_in)
|
62
|
+
log << { sdrm_list: sdrm_list }
|
63
|
+
|
64
|
+
# input dir
|
65
|
+
indir = ARGV[0]
|
66
|
+
libs = Dir[indir + "/*"]
|
67
|
+
log << { processed_libs: libs }
|
68
|
+
|
69
|
+
#output dir
|
70
|
+
outdir = indir + "_SDRM"
|
71
|
+
Dir.mkdir(outdir) unless File.directory?(outdir)
|
72
|
+
|
73
|
+
libs.each do |lib|
|
74
|
+
|
75
|
+
r_script = ViralSeq::R_SCRIPT.dup
|
76
|
+
|
77
|
+
next unless File.directory?(lib)
|
78
|
+
|
79
|
+
lib_name = File.basename(lib)
|
80
|
+
out_lib_dir = File.join(outdir, lib_name)
|
81
|
+
Dir.mkdir(out_lib_dir) unless File.directory?(out_lib_dir)
|
82
|
+
|
83
|
+
sub_seq_files = Dir[lib + "/*"]
|
84
|
+
|
85
|
+
seq_summary_file = File.join(out_lib_dir, (lib_name + "_summary.csv"))
|
86
|
+
seq_summary_out = File.open(seq_summary_file, "w")
|
87
|
+
seq_summary_out.puts 'Region,TCS,TCS with A3G/F hypermutation,TCS with stop codon,' +
|
88
|
+
'TCS w/o hypermutation and stop codon,' +
|
89
|
+
'Poisson cutoff for minority mutation (>=),Pi,Dist20'
|
90
|
+
|
91
|
+
point_mutation_file = File.join(out_lib_dir, (lib_name + "_substitution.csv"))
|
92
|
+
point_mutation_out = File.open(point_mutation_file, "w")
|
93
|
+
point_mutation_out.puts "region,TCS,AA position,wild type,mutation," +
|
94
|
+
"number,percentage,95% CI low, 95% CI high, notes"
|
95
|
+
|
96
|
+
linkage_file = File.join(out_lib_dir, (lib_name + "_linkage.csv"))
|
97
|
+
linkage_out = File.open(linkage_file, "w")
|
98
|
+
linkage_out.puts "region,TCS,mutation linkage,number," +
|
99
|
+
"percentage,95% CI low, 95% CI high, notes"
|
100
|
+
|
101
|
+
aa_report_file = File.join(out_lib_dir, (lib_name + "_aa.csv"))
|
102
|
+
aa_report_out = File.open(aa_report_file, "w")
|
103
|
+
aa_report_out.puts "region,ref.aa.positions,TCS.number," +
|
104
|
+
ViralSeq::AMINO_ACID_LIST.join(",")
|
105
|
+
|
106
|
+
summary_json_file = File.join(out_lib_dir, (lib_name + "_summary.json"))
|
107
|
+
summary_json_out = File.open(summary_json_file,"w")
|
108
|
+
|
109
|
+
filtered_seq_dir = File.join(out_lib_dir, (lib_name + "_filtered_seq"))
|
110
|
+
Dir.mkdir(filtered_seq_dir) unless File.directory?(filtered_seq_dir)
|
111
|
+
|
112
|
+
aln_seq_dir = File.join(out_lib_dir, (lib_name + "_aln_seq"))
|
113
|
+
Dir.mkdir(aln_seq_dir) unless File.directory?(aln_seq_dir)
|
114
|
+
|
115
|
+
point_mutation_list = []
|
116
|
+
linkage_list = []
|
117
|
+
aa_report_list = []
|
118
|
+
summary_hash = {}
|
119
|
+
|
120
|
+
sub_seq_files.each do |sub_seq|
|
121
|
+
seq_basename = File.basename(sub_seq)
|
122
|
+
seqs = ViralSeq::SeqHash.fa(sub_seq)
|
123
|
+
next if seqs.size < 3
|
124
|
+
if seq_basename =~ /V1V3/i
|
125
|
+
summary_hash[:V1V3] = "#{seqs.size.to_s},NA,NA,NA,NA"
|
126
|
+
FileUtils.cp(sub_seq, filtered_seq_dir)
|
127
|
+
elsif seq_basename =~ /PR/i
|
128
|
+
a3g_check = seqs.a3g
|
129
|
+
a3g_seqs = a3g_check[:a3g_seq]
|
130
|
+
a3g_filtered_seqs = a3g_check[:filtered_seq]
|
131
|
+
stop_codon_check = a3g_filtered_seqs.stop_codon
|
132
|
+
stop_codon_seqs = stop_codon_check[:with_stop_codon]
|
133
|
+
filtered_seqs = stop_codon_check[:without_stop_codon]
|
134
|
+
poisson_minority_cutoff = filtered_seqs.pm
|
135
|
+
summary_hash[:PR] = [
|
136
|
+
seqs.size.to_s,
|
137
|
+
a3g_seqs.size.to_s,
|
138
|
+
stop_codon_seqs.size.to_s,
|
139
|
+
filtered_seqs.size.to_s,
|
140
|
+
poisson_minority_cutoff.to_s
|
141
|
+
].join(',')
|
142
|
+
next if filtered_seqs.size < 3
|
143
|
+
filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
|
144
|
+
|
145
|
+
sdrm = filtered_seqs.sdrm_hiv_pr(poisson_minority_cutoff)
|
146
|
+
point_mutation_list += sdrm[0]
|
147
|
+
linkage_list += sdrm[1]
|
148
|
+
aa_report_list += sdrm[2]
|
149
|
+
|
150
|
+
elsif seq_basename =~/IN/i
|
151
|
+
a3g_check = seqs.a3g
|
152
|
+
a3g_seqs = a3g_check[:a3g_seq]
|
153
|
+
a3g_filtered_seqs = a3g_check[:filtered_seq]
|
154
|
+
stop_codon_check = a3g_filtered_seqs.stop_codon(2)
|
155
|
+
stop_codon_seqs = stop_codon_check[:with_stop_codon]
|
156
|
+
filtered_seqs = stop_codon_check[:without_stop_codon]
|
157
|
+
poisson_minority_cutoff = filtered_seqs.pm
|
158
|
+
summary_hash[:IN] = [
|
159
|
+
seqs.size.to_s,
|
160
|
+
a3g_seqs.size.to_s,
|
161
|
+
stop_codon_seqs.size.to_s,
|
162
|
+
filtered_seqs.size.to_s,
|
163
|
+
poisson_minority_cutoff.to_s
|
164
|
+
].join(',')
|
165
|
+
next if filtered_seqs.size < 3
|
166
|
+
filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
|
167
|
+
|
168
|
+
sdrm = filtered_seqs.sdrm_hiv_in(poisson_minority_cutoff)
|
169
|
+
point_mutation_list += sdrm[0]
|
170
|
+
linkage_list += sdrm[1]
|
171
|
+
aa_report_list += sdrm[2]
|
172
|
+
|
173
|
+
elsif seq_basename =~/RT/i
|
174
|
+
rt_seq1 = {}
|
175
|
+
rt_seq2 = {}
|
176
|
+
seqs.dna_hash.each do |k,v|
|
177
|
+
rt_seq1[k] = v[0,267]
|
178
|
+
rt_seq2[k] = v[267..-1]
|
179
|
+
end
|
180
|
+
rt1 = ViralSeq::SeqHash.new(rt_seq1)
|
181
|
+
rt2 = ViralSeq::SeqHash.new(rt_seq2)
|
182
|
+
rt1_a3g = rt1.a3g
|
183
|
+
rt2_a3g = rt2.a3g
|
184
|
+
hypermut_seq_rt1 = rt1_a3g[:a3g_seq]
|
185
|
+
hypermut_seq_rt2 = rt2_a3g[:a3g_seq]
|
186
|
+
rt1_stop_codon = rt1.stop_codon(1)[:with_stop_codon]
|
187
|
+
rt2_stop_codon = rt2.stop_codon(2)[:with_stop_codon]
|
188
|
+
hypermut_seq_keys = (hypermut_seq_rt1.dna_hash.keys | hypermut_seq_rt2.dna_hash.keys)
|
189
|
+
stop_codon_seq_keys = (rt1_stop_codon.dna_hash.keys | rt2_stop_codon.dna_hash.keys)
|
190
|
+
reject_keys = (hypermut_seq_keys | stop_codon_seq_keys)
|
191
|
+
filtered_seqs = ViralSeq::SeqHash.new(seqs.dna_hash.reject {|k,v| reject_keys.include?(k) })
|
192
|
+
poisson_minority_cutoff = filtered_seqs.pm
|
193
|
+
summary_hash[:RT] = [
|
194
|
+
seqs.size.to_s,
|
195
|
+
hypermut_seq_keys.size.to_s,
|
196
|
+
stop_codon_seq_keys.size.to_s,
|
197
|
+
filtered_seqs.size.to_s,
|
198
|
+
poisson_minority_cutoff.to_s
|
199
|
+
].join(',')
|
200
|
+
next if filtered_seqs.size < 3
|
201
|
+
filtered_seqs.write_nt_fa(File.join(filtered_seq_dir,seq_basename))
|
202
|
+
|
203
|
+
sdrm = filtered_seqs.sdrm_hiv_rt(poisson_minority_cutoff)
|
204
|
+
point_mutation_list += sdrm[0]
|
205
|
+
linkage_list += sdrm[1]
|
206
|
+
aa_report_list += sdrm[2]
|
207
|
+
end
|
208
|
+
end
|
209
|
+
|
210
|
+
point_mutation_list.each do |record|
|
211
|
+
point_mutation_out.puts record.join(",")
|
212
|
+
end
|
213
|
+
linkage_list.each do |record|
|
214
|
+
linkage_out.puts record.join(",")
|
215
|
+
end
|
216
|
+
aa_report_list.each do |record|
|
217
|
+
aa_report_out.puts record.join(",")
|
218
|
+
end
|
219
|
+
|
220
|
+
filtered_seq_files = Dir[filtered_seq_dir + "/*"]
|
221
|
+
|
222
|
+
out_r_csv = File.join(out_lib_dir, (lib_name + "_pi.csv"))
|
223
|
+
out_r_pdf = File.join(out_lib_dir, (lib_name + "_pi.pdf"))
|
224
|
+
|
225
|
+
if filtered_seq_files.size > 0
|
226
|
+
filtered_seq_files.each do |seq_file|
|
227
|
+
filtered_sh = ViralSeq::SeqHash.fa(seq_file)
|
228
|
+
next if filtered_sh.size < 3
|
229
|
+
aligned_sh = filtered_sh.random_select(1000).align
|
230
|
+
aligned_sh.write_nt_fa(File.join(aln_seq_dir, File.basename(seq_file)))
|
231
|
+
end
|
232
|
+
|
233
|
+
r_script.gsub!(/PATH_TO_FASTA/,aln_seq_dir)
|
234
|
+
File.unlink(out_r_csv) if File.exist?(out_r_csv)
|
235
|
+
File.unlink(out_r_pdf) if File.exist?(out_r_pdf)
|
236
|
+
r_script.gsub!(/OUTPUT_CSV/,out_r_csv)
|
237
|
+
r_script.gsub!(/OUTPUT_PDF/,out_r_pdf)
|
238
|
+
r_script_file = File.join(out_lib_dir, "/pi.R")
|
239
|
+
File.open(r_script_file,"w") {|line| line.puts r_script}
|
240
|
+
print `Rscript #{r_script_file} 1> /dev/null 2> /dev/null`
|
241
|
+
if File.exist?(out_r_csv)
|
242
|
+
pi_csv = File.readlines(out_r_csv)
|
243
|
+
pi_csv.each do |line|
|
244
|
+
line.chomp!
|
245
|
+
data = line.split(",")
|
246
|
+
tag = data[0].split("_")[-1].gsub(/\W/,"").to_sym
|
247
|
+
summary_hash[tag] += "," + data[1].to_f.round(4).to_s + "," + data[2].to_f.round(4).to_s
|
248
|
+
end
|
249
|
+
[:PR, :RT, :IN, :V1V3].each do |regions|
|
250
|
+
next unless summary_hash[regions]
|
251
|
+
seq_summary_out.puts regions.to_s + "," + summary_hash[regions]
|
252
|
+
end
|
253
|
+
File.unlink(out_r_csv)
|
254
|
+
end
|
255
|
+
File.unlink(r_script_file)
|
256
|
+
end
|
257
|
+
|
258
|
+
seq_summary_out.close
|
259
|
+
point_mutation_out.close
|
260
|
+
linkage_out.close
|
261
|
+
aa_report_out.close
|
262
|
+
|
263
|
+
summary_lines = File.readlines(seq_summary_file)
|
264
|
+
summary_lines.shift
|
265
|
+
|
266
|
+
tcs_PR = 0
|
267
|
+
tcs_RT = 0
|
268
|
+
tcs_IN = 0
|
269
|
+
tcs_V1V3 = 0
|
270
|
+
pi_RT = 0.0
|
271
|
+
pi_V1V3 = 0.0
|
272
|
+
dist20_RT = 0.0
|
273
|
+
dist20_V1V3 = 0.0
|
274
|
+
summary_lines.each do |line|
|
275
|
+
data = line.chomp.split(",")
|
276
|
+
if data[0] == "PR"
|
277
|
+
tcs_PR = data[4].to_i
|
278
|
+
elsif data[0] == "RT"
|
279
|
+
tcs_RT = data[4].to_i
|
280
|
+
pi_RT = data[6].to_f
|
281
|
+
dist20_RT = data[7].to_f
|
282
|
+
elsif data[0] == "IN"
|
283
|
+
tcs_IN = data[4].to_i
|
284
|
+
elsif data[0] == "V1V3"
|
285
|
+
tcs_V1V3 = data[1].to_i
|
286
|
+
pi_V1V3 = data[6].to_f
|
287
|
+
dist20_V1V3 = data[7].to_f
|
288
|
+
end
|
289
|
+
end
|
290
|
+
|
291
|
+
recency = ViralSeq::Recency.define(
|
292
|
+
tcs_RT: tcs_RT,
|
293
|
+
tcs_V1V3: tcs_V1V3,
|
294
|
+
pi_RT: pi_RT,
|
295
|
+
dist20_RT: dist20_RT,
|
296
|
+
pi_V1V3: pi_V1V3,
|
297
|
+
dist20_V1V3: dist20_V1V3
|
298
|
+
)
|
299
|
+
|
300
|
+
sdrm_lines = File.readlines(point_mutation_file)
|
301
|
+
sdrm_lines.shift
|
302
|
+
sdrm_PR = ""
|
303
|
+
sdrm_RT = ""
|
304
|
+
sdrm_IN = ""
|
305
|
+
sdrm_lines.each do |line|
|
306
|
+
data = line.chomp.split(",")
|
307
|
+
next if data[-1] == "*"
|
308
|
+
if data[0] == "PR"
|
309
|
+
sdrm_PR += abstract_line(data)
|
310
|
+
elsif data[0] =~ /NRTI/
|
311
|
+
sdrm_RT += abstract_line(data)
|
312
|
+
elsif data[0] == "IN"
|
313
|
+
sdrm_IN += abstract_line(data)
|
314
|
+
end
|
315
|
+
end
|
316
|
+
|
317
|
+
summary_json = [
|
318
|
+
sample_id: lib_name,
|
319
|
+
tcs_PR: tcs_PR,
|
320
|
+
tcs_RT: tcs_RT,
|
321
|
+
tcs_IN: tcs_IN,
|
322
|
+
tcs_V1V3: tcs_V1V3,
|
323
|
+
pi_RT: pi_RT,
|
324
|
+
dist20_RT: dist20_RT,
|
325
|
+
dist20_V1V3: dist20_V1V3,
|
326
|
+
recency: recency,
|
327
|
+
sdrm_PR: sdrm_PR,
|
328
|
+
sdrm_RT: sdrm_RT,
|
329
|
+
sdrm_IN: sdrm_IN
|
330
|
+
]
|
331
|
+
|
332
|
+
summary_json_out.puts JSON.pretty_generate(summary_json)
|
333
|
+
summary_json_out.close
|
334
|
+
|
335
|
+
csvs = [
|
336
|
+
{
|
337
|
+
name: "summary",
|
338
|
+
title: "Summary",
|
339
|
+
file: seq_summary_file,
|
340
|
+
newPDF: "",
|
341
|
+
table_width: [65,55,110,110,110,110,60,60],
|
342
|
+
extra_text: ""
|
343
|
+
},
|
344
|
+
{
|
345
|
+
name: "substitution",
|
346
|
+
title: "Surveillance Drug Resistance Mutations",
|
347
|
+
file: point_mutation_file,
|
348
|
+
newPDF: "",
|
349
|
+
table_width: [65,55,85,80,60,65,85,85,85,45],
|
350
|
+
extra_text: "* Mutation below Poisson cut-off for minority mutations"
|
351
|
+
},
|
352
|
+
{
|
353
|
+
name: "linkage",
|
354
|
+
title: "Mutation Linkage",
|
355
|
+
file: linkage_file,
|
356
|
+
newPDF: "",
|
357
|
+
table_width: [55,50,250,60,80,80,80,45],
|
358
|
+
extra_text: "* Mutation below Poisson cut-off for minority mutations"
|
359
|
+
}
|
360
|
+
]
|
361
|
+
|
362
|
+
csvs.each do |csv|
|
363
|
+
file_name = File.join(out_lib_dir, (csv[:name] + ".pdf"))
|
364
|
+
next unless File.exist? csv[:file]
|
365
|
+
Prawn::Document.generate(file_name, :page_layout => :landscape) do |pdf|
|
366
|
+
pdf.text((File.basename(lib, ".*") + ': ' + csv[:title]),
|
367
|
+
:size => 20,
|
368
|
+
:align => :center,
|
369
|
+
:style => :bold)
|
370
|
+
pdf.move_down 20
|
371
|
+
table_data = CSV.open(csv[:file]).to_a
|
372
|
+
header = table_data.first
|
373
|
+
pdf.table(table_data,
|
374
|
+
:header => header,
|
375
|
+
:position => :center,
|
376
|
+
:column_widths => csv[:table_width],
|
377
|
+
:row_colors => ["B6B6B6", "FFFFFF"],
|
378
|
+
:cell_style => {:align => :center, :size => 10}) do |table|
|
379
|
+
table.row(0).style :font_style => :bold, :size => 12 #, :background_color => 'ff00ff'
|
380
|
+
end
|
381
|
+
pdf.move_down 5
|
382
|
+
pdf.text(csv[:extra_text], :size => 8, :align => :justify,)
|
383
|
+
end
|
384
|
+
csv[:newPDF] = file_name
|
385
|
+
end
|
386
|
+
|
387
|
+
pdf = CombinePDF.new
|
388
|
+
csvs.each do |csv|
|
389
|
+
pdf << CombinePDF.load(csv[:newPDF]) if File.exist?(csv[:newPDF])
|
390
|
+
end
|
391
|
+
pdf << CombinePDF.load(out_r_pdf) if File.exist?(out_r_pdf)
|
392
|
+
|
393
|
+
pdf.number_pages location: [:bottom_right],
|
394
|
+
number_format: "Swanstrom\'s lab HIV SDRM Pipeline, version #{$sdrm_version_number} by S.Z. and M.U.C. Page %s",
|
395
|
+
font_size: 6,
|
396
|
+
opacity: 0.5
|
397
|
+
|
398
|
+
pdf.save File.join(out_lib_dir, (lib_name + ".pdf"))
|
399
|
+
|
400
|
+
csvs.each do |csv|
|
401
|
+
File.unlink csv[:newPDF]
|
402
|
+
end
|
403
|
+
end
|
404
|
+
|
405
|
+
log_file = File.join(File.dirname(indir), "sdrm_log.json")
|
406
|
+
|
407
|
+
File.open(log_file, 'w') { |f| f.puts JSON.pretty_generate(log) }
|
408
|
+
|
409
|
+
FileUtils.touch(File.join(outdir, ".done"))
|