-
Notifications
You must be signed in to change notification settings - Fork 1
/
snakemake
184 lines (121 loc) · 5.61 KB
/
snakemake
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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
import re
import subprocess
from pytools.persistent_dict import PersistentDict
storage = PersistentDict("mystorage")
#Parameters
#ONT reads path (.fq)
input_reads=""
#Flye path
flye_path=""
#Conda envs path (i.e "~/miniconda3/envs/")
conda_path=""
#Strainy path
strainy_path=""
#Clair model path (r1041_e82_400bps_sup_v420 is recomended)
clair_model_path=""
rule all:
input: "output/qa_bins","output/coverage_list.lst","output/qa_transformed_bins" #bestbins
rule flye_build_assembly:
input:input_reads
output:"output/flye_output/assembly.fasta",dir=directory("output/flye_output")
threads: 30
shell:"python {flye_path} --nano-hq {input} --out-dir {output.dir} --threads 30 --meta --keep-haplotypes"
rule strainy_split_unitigs:
input:"output/flye_output"
output:"output/strainy_split/preprocessing_data/long_unitigs_split.bam", "output/strainy_split/preprocessing_data/long_unitigs_split.gfa","output/strainy_split/preprocessing_data/gfa_converted.fasta"
conda:conda_path+"strainy"
threads: 30
shell:"python3 {strainy_path} -g {input}/assembly_graph.gfa -q {input_reads} --unitig-split-length 50 -o output/strainy_split -b none.bam -t 30 -m nano --only_split True"
rule binning:
input: "output/strainy_split/preprocessing_data/gfa_converted.fasta"
output: dir=directory("output/bins")
threads: 30
shell: "metabat2 -i {input} output/strainy_split/preprocessing_data/long_unitigs_split.bam -o {output.dir}/bin -t 30"
rule mag_qa:
input: "output/bins"
output: outdir=directory("output/qa_bins"),report="output/qa_bins/quality_report.tsv"
threads: 30
conda: conda_path+"checkm2"
shell: "checkm2 predict -x .fa -i {input} -o {output.outdir} -t 30"
rule unitig_per_bin:
input: "output/bins"
output: "output/unitigs/bin.{bin}.lst"
shell: "cat output/bins/bin.{wildcards.bin}.fa | grep '>' | cut -c 2- > {output}"
rule subset_bam:
input: l="output/unitigs_connected/{bin}.lst", bam="output/strainy_split/preprocessing_data/long_unitigs_split.bam"
output: "output/bams/{bin}.bam"
conda: conda_path+"strainy"
threads: 30
shell: "python3 split_bam.py -bam {input.bam} -list {input.l} -o {output}"
rule index_bam:
input:"output/bams/{bin}.bam"
output: "output/bams/{bin}.bam.bai"
conda: conda_path+"strainy"
shell: "samtools index {input} "
rule make_split_fa:
input: "output/strainy_split/preprocessing_data/long_unitigs_split.gfa"
output: "output/gfa_splitted.fasta"
conda: conda_path+"strainy"
shell:"""
awk '//^S{{print ">"$2"\\n"$3}}' {input} | fold > {output}
"""
rule index_fa:
input: "output/strainy_split/preprocessing_data/gfa_converted.fasta"
output: "output/strainy_split/preprocessing_data/gfa_converted.fasta.fai"
conda: conda_path+"strainy"
shell:"samtools faidx {input}"
rule call_snp:
input:b="output/bams/{bin}.bam",bai="output/bams/{bin}.bam.bai",fai="output/strainy_split/preprocessing_data/gfa_converted.fasta.fai",fa="output/strainy_split/preprocessing_data/gfa_converted.fasta"
threads: 30
output: "output/clair/{bin}/merge_output.vcf.gz"
conda: conda_path+"clair3"
shell: "run_clair3.sh --bam_fn={input.b} --ref_fn={input.fa} --output=output/clair/{wildcards.bin} --threads=30 --platform=ont --include_all_ctgs --model_path={clair_model_path} --chunk_size=50000 --snp_min_af=0.15 --no_phasing_for_fa"
rule unzip_snp:
input: "output/clair/{bin}/merge_output.vcf.gz"
output: "output/clair/{bin}/snp.vcf"
shell: "gunzip -c {input} > {output}"
rule connect_unitigs:
input: g="output/strainy_split/preprocessing_data/long_unitigs_split.gfa", l="output/unitigs/{bin}.lst"
output: "output/unitigs_connected/{bin}.lst"
conda: conda_path+"strainy"
shell: "python3 connect_bin.py {input.l} output/unitigs/ {input.g} {output}"
rule subset_gfa:
input: g="output/strainy_split/preprocessing_data/long_unitigs_split.gfa", l="output/unitigs_connected/{bin}.lst"
output: "output/gfa_sub/{bin}.gfa"
conda: conda_path+"strainy"
shell: "python3 split_gfa.py -g {input.g} -l {input.l} -outfile {output}"
rule strainy:
input: snp="output/clair/{bin}/snp.vcf", b="output/bams/{bin}.bam",bai="output/bams/{bin}.bam.bai", gfa="output/gfa_sub/{bin}.gfa"
output: "output/strainy_final/{bin}/strainy_final.gfa"
conda: conda_path+"strainy"
threads: 30
shell: "python3 {strainy_path} -g {input.gfa} -q {input_reads} -o output/strainy_final/{wildcards.bin} -b {input.b} -t 30 -m nano --snp {input.snp} --unitig-split-length 0" #Add af abd base quality
rule bin_transform:
input:"output/strainy_final/{bin}/strainy_final.gfa"
output: "output/transformed_bins/{bin}.fa"
shell:"""awk '/^S/{{print ">"$2"\\n"$3}}' output/strainy_final/{wildcards.bin}/strainy_final.gfa > {output}"""
rule run_filter_best:
input: "output/qa_bins/quality_report.tsv"
output: "best_res"
run:
from filter import get_best
storage.store("myvar",get_best())
shell("touch best_res")
rule count_MAG_coverage:
input: "best_res", storage.fetch("myvar")
output: "output/coverage_list.lst"
conda:conda_path+"strainy"
shell:"python3 calc_cov.py > output/coverage_list.lst"
rule run_filter_cov:
input: "output/coverage_list.lst"
output: "cov_res"
run:
from filter import cov_filtered
storage.store("myvar",cov_filtered("output/coverage_list.lst"))
shell("touch cov_res")
rule mag_transformed_qa:
input: "cov_res",storage.fetch("myvar")
output: directory("output/qa_transformed_bins")
conda:
conda_path+"checkm2"
shell: "checkm2 predict -x .fa -i output/transformed_bins -o {output} -t 30"