Mercurial > repos > rliterman > csp2
comparison CSP2/docker/Makefile @ 39:93393808f415
"planemo upload"
author | rliterman |
---|---|
date | Thu, 12 Dec 2024 13:53:15 -0500 |
parents | 01431fa12065 |
children |
comparison
equal
deleted
inserted
replaced
38:ee512a230a1e | 39:93393808f415 |
---|---|
1 .PHONY: | |
2 | |
3 .ONESHELL: | |
4 | |
5 | |
6 | |
7 usage: ## Show this menu | |
8 @grep -E '^[a-zA-Z_-]+:.*?##.*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?##"}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | |
9 | |
10 version: ## Show version and branch | |
11 @echo "CSP2 v$${CSP2_VER}/$${CSP2_BRANCH}" | |
12 | |
13 # ENV CSP2_VER=${CSP2_VER} | |
14 # ENV BEDTOOLS_VER=${BEDTOOLS_VER} | |
15 # ENV MIUMMER_VER=${MUMMER_VER} | |
16 # ENV SKESA_VER=${SKESA_VER} | |
17 # ENV MASH_VER=${MASH_VER} | |
18 # ENV BBMAP_VER=${BBMAP_VER} | |
19 # ENV PYTHON_VER=${PYTHON_VER} | |
20 | |
21 versions: version ## Show versions of key installed depedencies | |
22 @echo `nextflow -v` | |
23 @echo `python3 --version` " (container says ${PYTHON_VER})" | |
24 @echo `bedtools --version` " (container says ${BEDTOOLS_VER})" | |
25 @echo "mummer " `mummer --version` " (container says ${MUMMER_VER})" | |
26 @echo `skesa --version 2>&1` " (container says ${SKESA_VER})" | |
27 @echo "mash " `mash --version` " (container says ${MASH_VER})" | |
28 @echo `bbmap.sh --version 2>&1` " (container says ${BBMAP_VER})" | |
29 | |
30 help: ## Show help | |
31 @echo "Citation: CFSAN SNP Pipeline 2, v$${CSP2_VER}, Literman et al. 2024" | |
32 @echo | |
33 @echo "CSP2 is a Nextflow pipeline for rapid, accurate SNP distance estimation" | |
34 @echo "from assembly data." | |
35 @echo | |
36 @echo "Please see: https://github.com/CFSAN-Biostatistics/CSP2" | |
37 @echo | |
38 @echo "CSP2 runs are managed via Nextflow, providing the user with an array of" | |
39 @echo "customizations while also facilitating module development and additions in" | |
40 @echo "future releases." | |
41 @echo | |
42 @echo "Important Note: The software continues to be focused on the analysis of" | |
43 @echo "groups of bacterial genomes with limited evolutionary differences (<1000" | |
44 @echo "SNPs). Testing is underway to determine how the underlying cluster" | |
45 @echo "diversity impacts distances estimates." | |
46 @echo | |
47 @echo "CSP2 has two main run modes:" | |
48 @echo "1) "Screening Mode" (screen): Used to determine whether query isolates are" | |
49 @echo "close to a set of reference isolates (e.g., lab control strains, strains" | |
50 @echo "related to an outbreak, etc.) Given one or more user-provided reference" | |
51 @echo "isolates (--ref_reads; --ref_fasta), get alignment statistics and SNP" | |
52 @echo "distances between all reference and query isolates (--reads; --fasta)" | |
53 @echo | |
54 @echo "2) "SNP Pipeline Mode" (snp): Used to generate pairwise distances and" | |
55 @echo "alignments for a set of query isolates Generate pairwise SNP distances and" | |
56 @echo "alignments for 2+ isolates (--reads; --fasta) based on comparisons to:" | |
57 @echo | |
58 @echo "One or more user-provided references (--ref_reads; --ref_fasta), or One or" | |
59 @echo "more reference isolates selected by RefChooser (--n_ref)" | |
60 @echo | |
61 @echo "Usage: screen [options] {--fasta PATH {--reads=PATH | --forward=STR --reverse=STR} --out=PATH}" | |
62 @echo " or snp [options] {--fasta {--reads=PATH | --forward=STR --reverse=STR} --out=PATH}" | |
63 @echo | |
64 @echo "Options:" | |
65 @echo " --outroot=PATH\tBase directory to create output folder [default=$CWD] " | |
66 @echo " --out=PATH\t\tName of the output folder to create (must not exist)" | |
67 @echo "\t\t\t [default=CSP2_<current_datetime>]" | |
68 @echo " --forward=STR\t\tFull file extension for forward/left reads of query" | |
69 @echo "\t\t\t [default='_1.fastq.gz']" | |
70 @echo " --reverse=STR\t\tFull file extension for reverse/right reads of reference" | |
71 @echo "\t\t\t [default='_2.fastq.gz']" | |
72 @echo " --ref_forward=STR\tFull file extension for forward/left reads of reference" | |
73 @echo "\t\t\t [default='_1.fastq.gz']" | |
74 @echo " --ref_reverse=STR\tFull file extension for reverse/right reads of reference" | |
75 @echo "\t\t\t [default='_2.fastq.gz']" | |
76 @echo " --readext=STR\t\tExtension for single-end reads for query [default='fastq.gz']" | |
77 @echo " --ref_readext=STR\tExtension for single-end reads for reference" | |
78 @echo "\t\t\t [default='fastq.gz']" | |
79 @echo " --min_cov=NUM\t\tDo not analyze queries that cover less than <min_cov>% of the" | |
80 @echo "\t\t\treference assembly [default=85]" | |
81 @echo " --min_iden=NUM\tOnly consider alignments where the percent identity is at least" | |
82 @echo "\t\t\t <min_iden> [default=99]" | |
83 @echo " --min_len=NUM\t\tOnly consider alignments that span at least <min_len> in bp" | |
84 @echo "\t\t\t [default=500]" | |
85 @echo " --dwin=LIST\t\tA comma-separated list of windows to check SNP densities" | |
86 @echo "\t\t\t [default=1000,125,15]" | |
87 @echo " --wsnps=LIST\t\tThe maximum number of SNPs allowed in the corresponding window from" | |
88 @echo "\t\t\t --dwin [default=3,2,1]" | |
89 @echo " --query_edge=NUM\tOnly consider SNPs that occur within <query_edge>bp of the end" | |
90 @echo "\t\t\t of a query contig [default=250]" | |
91 @echo " --ref_edge=NUM\tOnly consider SNPs that occur within <query_edge>bp of the end" | |
92 @echo "\t\t\t of a reference contig [default=250]" | |
93 @echo " --n_ref=NUM\t\tThe number of RefChooser reference isolates to consider (only" | |
94 @echo "\t\t\t applied if using RefChooser) [default=3]" | |
95 @echo " --reads=PATH\t\tLocation of query read data (Path to directory, or path to file with" | |
96 @echo "\t\t\t multiple directories)" | |
97 @echo " --fasta=PATH\t\tLocation of query assembly data (Path to directory containing" | |
98 @echo "\t\t\t FASTAs, path to FASTA, path to multiple FASTAs)" | |
99 @echo " --ref_reads=PATH\tLocation of reference read data (Path to directory, or path to" | |
100 @echo "\t\t\t file with multiple directories)" | |
101 @echo " --ref_fasta=PATH\tLocation of reference assembly data (Path to directory" | |
102 @echo "\t\t\t containing FASTAs, path to FASTA, path to multiple FASTAs)" | |
103 @echo " --trim_name=STR\tA string in assembly file names that you want to remove from" | |
104 @echo "\t\t\t sample IDs (e.g., _contigs_skesa)" | |
105 | |
106 config: | |
107 @cat <<- EOF | |
108 profiles { | |
109 standard { | |
110 process.executor = 'local' | |
111 params.cores = `nproc --all` | |
112 } | |
113 } | |
114 EOF > ~/.nextflow/config | |
115 | |
116 | |
117 ifeq (screen, $(firstword $(MAKECMDGOALS))) | |
118 runargs := $(wordlist 2, $(words $(MAKECMDGOALS)), $(MAKECMDGOALS)) | |
119 $(eval $(runargs):;@true) | |
120 endif | |
121 | |
122 ifeq (snp, $(firstword $(MAKECMDGOALS))) | |
123 runargs := $(wordlist 2, $(words $(MAKECMDGOALS)), $(MAKECMDGOALS)) | |
124 $(eval $(runargs):;@true) | |
125 endif | |
126 | |
127 screen: config ## determine whether query isolates are close to a reference | |
128 nextflow run CSP2.nf -profile standard --runmode screen $(runargs) | |
129 | |
130 snp: config ## generate pairwise distances for a set of query isolates | |
131 nextflow run CSP2.nf -profile standard --runmode snp $(runargs) | |
132 | |
133 snpdiffs: config | |
134 | |
135 test_screen: | |
136 nextflow run CSP2.nf -profile standard --runmode screen --fasta assets/Screen/Assembly/Week_42_Assembly.fasta --reads assets/Screen/Reads/ --ref_fasta assets/Screen/Assembly/Lab_Control.fasta --out ./CSP2_Test_Screen --readext fq.gz --forward _1.fq.gz --reverse _2.fq.gz | |
137 | |
138 test_snp: | |
139 nextflow run CSP2.nf -profile standard --runmode snp --fasta assets/SNP/ --n_ref 3 --out ./CSP2_Test_SNP --max_missing 50 | |
140 | |
141 test: config test_screen test_snp | |
142 ls -lah assets/Screen/Output/Contamination_Screen/ | |
143 diff -bur ./CSP2_Test_SNP/snpdiffs assets/SNP/Output/Soil_Analysis/snpdiffs |