From fe5092fc7022c9356dc675ddaa1bccb00c979dd1 Mon Sep 17 00:00:00 2001 From: Yamato Matsuoka Date: Mon, 27 Nov 2023 00:22:55 -0500 Subject: [PATCH] Add ntedit --- bio.json.gz | 4 +- bio.txt | 1 + bio/bash | 2 +- bio/fish | 2 +- bio/json/ntedit.json | 1 + bio/yaml/ntedit.yaml | 89 ++++++++++++++++++++++++++++++++++++++++++++ bio/zsh | 2 +- 7 files changed, 96 insertions(+), 5 deletions(-) create mode 100644 bio/json/ntedit.json create mode 100644 bio/yaml/ntedit.yaml diff --git a/bio.json.gz b/bio.json.gz index 7930e14c..6369ff15 100644 --- a/bio.json.gz +++ b/bio.json.gz @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:358b881acfafd0079547f818f98414619d6637192ce6c000e8ac23504aafd641 -size 1034380 +oid sha256:4477d80b47cb8d9f1b2a8601e74d3f827982dd8225b0ec806f084cd9e3c7f97e +size 1035128 diff --git a/bio.txt b/bio.txt index fc84ca23..3ec3c517 100644 --- a/bio.txt +++ b/bio.txt @@ -379,6 +379,7 @@ nhmmscan normalize-by-median.py normalize-iHS nquire +ntedit nucmer nullarbor.pl octopus diff --git a/bio/bash b/bio/bash index 174abf20..96222396 160000 --- a/bio/bash +++ b/bio/bash @@ -1 +1 @@ -Subproject commit 174abf20158e56266582bc74327743c2550d7542 +Subproject commit 962223961fc8a7d6a7c6c63d3ea5652e76077299 diff --git a/bio/fish b/bio/fish index e3e5a7db..b73066b6 160000 --- a/bio/fish +++ b/bio/fish @@ -1 +1 @@ -Subproject commit e3e5a7dbc9129a485f9affdbaf6c4e38a6ea5381 +Subproject commit b73066b6e23f62f635a2cab2040c99dd60345521 diff --git a/bio/json/ntedit.json b/bio/json/ntedit.json new file mode 100644 index 00000000..22f1f83e --- /dev/null +++ b/bio/json/ntedit.json @@ -0,0 +1 @@ +{"name":"ntedit","description":"Fast, lightweight, scalable genome sequence polishing and SNV detection & annotation","usage":"","options":[{"names":["-t"],"argument":"NUM","description":"number of threads [default=1]"},{"names":["-f"],"argument":"FILE","description":"draft genome assembly (FASTA, Multi-FASTA, and/or gzipped compatible), REQUIRED"},{"names":["-r"],"argument":"FILE","description":"Bloom filter file (generated from ntHits), REQUIRED"},{"names":["-e"],"argument":"FILE","description":"secondary Bloom filter with k-mers to reject (generated from ntHits), OPTIONAL"},{"names":["-b"],"argument":"STR","description":"output file prefix, OPTIONAL"},{"names":["-z"],"argument":"NUM","description":"minimum contig length [default=100]"},{"names":["-i"],"argument":"NUM","description":"maximum number of insertion bases to try, range 0-5, [default=5]"},{"names":["-d"],"argument":"NUM","description":"maximum number of deletions bases to try, range 0-10, [default=5]"},{"names":["-x"],"argument":"NUM","description":"k/x ratio for the number of k-mers that should be missing, [default=5.000]"},{"names":["-y"],"argument":"NUM","description":"k/y ratio for the number of edited k-mers that should be present, [default=9.000]"},{"names":["-X"],"argument":"NUM","description":"ratio of number of k-mers in the k subset that should be missing in order to attempt fix (higher=stringent), [default=0.5]"},{"names":["-Y"],"argument":"NUM","description":"ratio of number of k-mers in the k subset that should be present to accept an edit (higher=stringent), [default=0.5]"},{"names":["-c"],"argument":"NUM","description":"cap for the number of base insertions that can be made at one position, [default=k*1.5]"},{"names":["-j"],"argument":"NUM","description":"controls size of k-mer subset. When checking subset of k-mers, check every jth k-mer, [default=3]"},{"names":["-m"],"argument":"{0,1,2}","description":"mode of editing, range 0-2, [default=0] 0: best substitution, or first good indel 1: best substitution, or best indel 2: best edit overall (suggestion that you reduce i and d for performance)"},{"names":["-s"],"argument":"{0,1}","description":"SNV mode. Overrides draft k-mer checks, forcing reassessment at each position (-s 1 = yes, default = 0, no)"},{"names":["-l"],"argument":"FILE","description":"input VCF file with annotated variants (e.g., clinvar.vcf), OPTIONAL"},{"names":["-a"],"argument":"{0,1}","description":"soft masks missing k-mer positions having no fix (-v 1 = yes, default = 0, no)"},{"names":["-v"],"argument":"{0,1}","description":"verbose mode (-v 1 = yes, default = 0, no)"},{"names":["--help"],"argument":"","description":"display this message and exit"},{"names":["--version"],"argument":"","description":"output version information and exit"}],"version":"ntEdit v1.4.3"} diff --git a/bio/yaml/ntedit.yaml b/bio/yaml/ntedit.yaml new file mode 100644 index 00000000..cb239491 --- /dev/null +++ b/bio/yaml/ntedit.yaml @@ -0,0 +1,89 @@ +name: ntedit +description: Fast, lightweight, scalable genome sequence polishing and SNV detection & annotation +usage: "" +options: + - names: + - -t + argument: NUM + description: number of threads [default=1] + - names: + - -f + argument: FILE + description: draft genome assembly (FASTA, Multi-FASTA, and/or gzipped compatible), REQUIRED + - names: + - -r + argument: FILE + description: Bloom filter file (generated from ntHits), REQUIRED + - names: + - -e + argument: FILE + description: secondary Bloom filter with k-mers to reject (generated from ntHits), OPTIONAL + - names: + - -b + argument: STR + description: output file prefix, OPTIONAL + - names: + - -z + argument: NUM + description: minimum contig length [default=100] + - names: + - -i + argument: NUM + description: maximum number of insertion bases to try, range 0-5, [default=5] + - names: + - -d + argument: NUM + description: maximum number of deletions bases to try, range 0-10, [default=5] + - names: + - -x + argument: NUM + description: k/x ratio for the number of k-mers that should be missing, [default=5.000] + - names: + - -y + argument: NUM + description: k/y ratio for the number of edited k-mers that should be present, [default=9.000] + - names: + - -X + argument: NUM + description: ratio of number of k-mers in the k subset that should be missing in order to attempt fix (higher=stringent), [default=0.5] + - names: + - -Y + argument: NUM + description: ratio of number of k-mers in the k subset that should be present to accept an edit (higher=stringent), [default=0.5] + - names: + - -c + argument: NUM + description: cap for the number of base insertions that can be made at one position, [default=k*1.5] + - names: + - -j + argument: NUM + description: controls size of k-mer subset. When checking subset of k-mers, check every jth k-mer, [default=3] + - names: + - -m + argument: '{0,1,2}' + description: 'mode of editing, range 0-2, [default=0] 0: best substitution, or first good indel 1: best substitution, or best indel 2: best edit overall (suggestion that you reduce i and d for performance)' + - names: + - -s + argument: "{0,1}" + description: SNV mode. Overrides draft k-mer checks, forcing reassessment at each position (-s 1 = yes, default = 0, no) + - names: + - -l + argument: FILE + description: input VCF file with annotated variants (e.g., clinvar.vcf), OPTIONAL + - names: + - -a + argument: '{0,1}' + description: soft masks missing k-mer positions having no fix (-v 1 = yes, default = 0, no) + - names: + - -v + argument: '{0,1}' + description: verbose mode (-v 1 = yes, default = 0, no) + - names: + - --help + argument: "" + description: display this message and exit + - names: + - --version + argument: "" + description: output version information and exit +version: ntEdit v1.4.3 \ No newline at end of file diff --git a/bio/zsh b/bio/zsh index d97b55c7..9b23c066 160000 --- a/bio/zsh +++ b/bio/zsh @@ -1 +1 @@ -Subproject commit d97b55c7a20bf303cc77ed0a499e0c53f65e8938 +Subproject commit 9b23c066dade960d4e5ea574357207ee093dd6e8