From 93baa3687e8f77cedace221019fa36058640bc75 Mon Sep 17 00:00:00 2001 From: Yamato Matsuoka Date: Tue, 29 Oct 2024 21:35:14 -0400 Subject: [PATCH] Update minimap2 --- bio.json.gz | 4 ++-- bio/bash | 2 +- bio/fish | 2 +- bio/json/minimap2.json | 2 +- bio/yaml/minimap2.yaml | 16 ++++++++++++---- bio/zsh | 2 +- 6 files changed, 18 insertions(+), 10 deletions(-) diff --git a/bio.json.gz b/bio.json.gz index a07feca2..ff38bc75 100644 --- a/bio.json.gz +++ b/bio.json.gz @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2c671f0e569eea7b683f70d419046f4e340cee6e6cd52de8065f54039c93ba38 -size 1073683 +oid sha256:fc490c4342d29ca00d83234f1a44598d85acda09695bfeaad28179501151c4ca +size 1073766 diff --git a/bio/bash b/bio/bash index a3ee44c1..0a65ffff 160000 --- a/bio/bash +++ b/bio/bash @@ -1 +1 @@ -Subproject commit a3ee44c1b14a3b93f18d7efc03f2b4dda3b6c40a +Subproject commit 0a65fffff5f135ce81a7673dc1cc71117a6befe9 diff --git a/bio/fish b/bio/fish index 6480614a..6f099438 160000 --- a/bio/fish +++ b/bio/fish @@ -1 +1 @@ -Subproject commit 6480614af7263770ec3efb9ed35318746400db26 +Subproject commit 6f099438b93ae0a373e617944b675f19d057fa7f diff --git a/bio/json/minimap2.json b/bio/json/minimap2.json index 66207d50..bec847f2 100644 --- a/bio/json/minimap2.json +++ b/bio/json/minimap2.json @@ -1 +1 @@ -{"name":"minimap2","description":"minimap2","usage":"minimap2 [options] | [query.fa] [...]","options":[{"names":["-x"],"argument":"{map-pb|map_ont|map-hifi|ava-pb|ava-ont|asm5|asm10|asm20|splice|splice:hg|sr}","description":"preset (always applied before other options; see minimap2.1 for details) []"},{"names":["-H"],"argument":"","description":"use homopolymer-compressed k-mer (preferrable for PacBio)"},{"names":["-k"],"argument":"INT","description":"k-mer size (no larger than 28) [15]"},{"names":["-w"],"argument":"INT","description":"minimizer window size [10]"},{"names":["-I"],"argument":"NUM","description":"split index for every ~NUM input bases [4G]"},{"names":["-d"],"argument":"FILE","description":"dump index to FILE []"},{"names":["-f"],"argument":"FLOAT","description":"filter out top FLOAT fraction of repetitive minimizers [0.0002]"},{"names":["-g"],"argument":"NUM","description":"stop chain enlongation if there are no minimizers in INT-bp [5000]"},{"names":["-G"],"argument":"NUM","description":"max intron length (effective with -xsplice; changing -r) [200k]"},{"names":["-F"],"argument":"NUM","description":"max fragment length (effective with -xsr or in the fragment mode) [800]"},{"names":["-r"],"argument":"NUM[,NUM]","description":"chaining/alignment bandwidth and long-join bandwidth [500,20000]"},{"names":["-n"],"argument":"INT","description":"minimal number of minimizers on a chain [3]"},{"names":["-m"],"argument":"INT","description":"minimal chaining score (matching bases minus log gap penalty) [40]"},{"names":["-X"],"argument":"","description":"skip self and dual mappings (for the all-vs-all mode)"},{"names":["-p"],"argument":"FLOAT","description":"min secondary-to-primary score ratio [0.8]"},{"names":["-N"],"argument":"INT","description":"retain at most INT secondary alignments [5]"},{"names":["-A"],"argument":"INT","description":"matching score [2]"},{"names":["-B"],"argument":"INT","description":"mismatch penalty [4]"},{"names":["-O"],"argument":"INT[,INT]","description":"gap open penalty [4,24]"},{"names":["-E"],"argument":"INT[,INT]","description":"gap extension penalty; a k-long gap costs min{O1+k*E1,O2+k*E2} [2,1]"},{"names":["-z"],"argument":"INT[,INT]","description":"Z-drop score and inversion Z-drop score [400,200]"},{"names":["-s"],"argument":"INT","description":"minimal peak DP alignment score [80]"},{"names":["-u"],"argument":"CHAR","description":"how to find GT-AG. f:transcript strand, b:both strands, n:don't match GT-AG [n]"},{"names":["-a"],"argument":"","description":"output in the SAM format (PAF by default)"},{"names":["-o"],"argument":"FILE","description":"output alignments to FILE [stdout]"},{"names":["-L"],"argument":"","description":"write CIGAR with >65535 ops at the CG tag"},{"names":["-R"],"argument":"STR","description":"SAM read group line in a format like '@RG\\tID:foo\\tSM:bar' []"},{"names":["-c"],"argument":"","description":"output CIGAR in PAF"},{"names":["--cs"],"argument":"[=STR]","description":"output the cs tag; STR is 'short' (if absent) or 'long' [none]"},{"names":["--MD"],"argument":"","description":"output the MD tag"},{"names":["--eqx"],"argument":"","description":"write =/X CIGAR operators"},{"names":["-Y"],"argument":"","description":"use soft clipping for supplementary alignments"},{"names":["-t"],"argument":"INT","description":"number of threads [3]"},{"names":["-K"],"argument":"NUM","description":"minibatch size for mapping [500M]"},{"names":["--version"],"argument":"","description":"show version number"}],"version":"2.24-r1122","tldr":"> Map and align between collections of DNA sequences.\n> More information: .\n\n- Get alignment in SAM format\n\n`minimap2 -a {{ref.fa}} {{query.fq}} > {{alignment.sam}}`\n\n- Map long noisy genomic reads (PacBio):\n\n`minimap2 -ax map-pb {{ref.fa}} {{pacbio-reads.fq}} > {{aln.sam}}`\n\n- Map long cDNA-seq reads (Oxford Nanopore):\n\n`minimap2 -ax splice {{ref.fa}} {{nanopore-cdna.fa}} > {{aln.sam}}`\n\n- Find overlaps between long reads (Oxford Nanopore):\n\n`minimap2 -x ava-ont {{reads.fq}} {{reads.fq}} > {{ovlp.paf}}`\n\n- Map short accurate paired-end genomic reads:\n\n`minimap2 -ax sr {{ref.fa}} {{read1.fq}} {{read2.fq}} > s{{aln.sam}}`\n\n- Full genome/assembly alignment:\n\n`minimap2 -ax asm5 {{ref.fa}} {{asm.fa}} > {{aln.sam}}`\n"} +{"name":"minimap2","description":"minimap2","usage":"minimap2 [options] | [query.fa] [...]","options":[{"names":["-x"],"argument":"{map-ont|lr:hq|map-hifi|map-pb|map-iclr|asm5|asm10|asm20|splice|splice:hg|sr|ava-pb|ava-ont}","description":"preset (always applied before other options; see minimap2.1 for details) []"},{"names":["-H"],"argument":"","description":"use homopolymer-compressed k-mer (preferrable for PacBio)"},{"names":["-k"],"argument":"INT","description":"k-mer size (no larger than 28) [15]"},{"names":["-w"],"argument":"INT","description":"minimizer window size [10]"},{"names":["-I"],"argument":"NUM","description":"split index for every ~NUM input bases [8G]"},{"names":["-d"],"argument":"FILE","description":"dump index to FILE []"},{"names":["-f"],"argument":"FLOAT","description":"filter out top FLOAT fraction of repetitive minimizers [0.0002]"},{"names":["-g"],"argument":"NUM","description":"stop chain enlongation if there are no minimizers in INT-bp [5000]"},{"names":["-G"],"argument":"NUM","description":"max intron length (effective with -xsplice; changing -r) [200k]"},{"names":["-F"],"argument":"NUM","description":"max fragment length (effective with -xsr or in the fragment mode) [800]"},{"names":["-r"],"argument":"NUM[,NUM]","description":"chaining/alignment bandwidth and long-join bandwidth [500,20000]"},{"names":["-n"],"argument":"INT","description":"minimal number of minimizers on a chain [3]"},{"names":["-m"],"argument":"INT","description":"minimal chaining score (matching bases minus log gap penalty) [40]"},{"names":["-X"],"argument":"","description":"skip self and dual mappings (for the all-vs-all mode)"},{"names":["-p"],"argument":"FLOAT","description":"min secondary-to-primary score ratio [0.8]"},{"names":["-N"],"argument":"INT","description":"retain at most INT secondary alignments [5]"},{"names":["-A"],"argument":"INT","description":"matching score [2]"},{"names":["-B"],"argument":"INT","description":"mismatch penalty (larger value for lower divergence) [4]"},{"names":["-O"],"argument":"INT[,INT]","description":"gap open penalty [4,24]"},{"names":["-E"],"argument":"INT[,INT]","description":"gap extension penalty; a k-long gap costs min{O1+k*E1,O2+k*E2} [2,1]"},{"names":["-z"],"argument":"INT[,INT]","description":"Z-drop score and inversion Z-drop score [400,200]"},{"names":["-s"],"argument":"INT","description":"minimal peak DP alignment score [80]"},{"names":["-u"],"argument":"CHAR","description":"how to find GT-AG. f:transcript strand, b:both strands, n:don't match GT-AG [n]"},{"names":["-J"],"argument":"INT","description":"splice mode. 0: original minimap2 model; 1: miniprot model [1]"},{"names":["-a"],"argument":"","description":"output in the SAM format (PAF by default)"},{"names":["-o"],"argument":"FILE","description":"output alignments to FILE [stdout]"},{"names":["-L"],"argument":"","description":"write CIGAR with >65535 ops at the CG tag"},{"names":["-R"],"argument":"STR","description":"SAM read group line in a format like '@RG\\tID:foo\\tSM:bar' []"},{"names":["-c"],"argument":"","description":"output CIGAR in PAF"},{"names":["--cs"],"argument":"[=STR]","description":"output the cs tag; STR is 'short' (if absent) or 'long' [none]"},{"names":["--ds"],"argument":"","description":"output the ds tag, which is an extension to cs"},{"names":["--MD"],"argument":"","description":"output the MD tag"},{"names":["--eqx"],"argument":"","description":"write =/X CIGAR operators"},{"names":["-Y"],"argument":"","description":"use soft clipping for supplementary alignments"},{"names":["-t"],"argument":"INT","description":"number of threads [3]"},{"names":["-K"],"argument":"NUM","description":"minibatch size for mapping [500M]"},{"names":["--version"],"argument":"","description":"show version number"}],"version":"2.28-r1209","tldr":"> Map and align between collections of DNA sequences.\n> More information: .\n\n- Get alignment in SAM format\n\n`minimap2 -a {{ref.fa}} {{query.fq}} > {{alignment.sam}}`\n\n- Map long noisy genomic reads (PacBio):\n\n`minimap2 -ax map-pb {{ref.fa}} {{pacbio-reads.fq}} > {{aln.sam}}`\n\n- Map long cDNA-seq reads (Oxford Nanopore):\n\n`minimap2 -ax splice {{ref.fa}} {{nanopore-cdna.fa}} > {{aln.sam}}`\n\n- Find overlaps between long reads (Oxford Nanopore):\n\n`minimap2 -x ava-ont {{reads.fq}} {{reads.fq}} > {{ovlp.paf}}`\n\n- Map short accurate paired-end genomic reads:\n\n`minimap2 -ax sr {{ref.fa}} {{read1.fq}} {{read2.fq}} > s{{aln.sam}}`\n\n- Full genome/assembly alignment:\n\n`minimap2 -ax asm5 {{ref.fa}} {{asm.fa}} > {{aln.sam}}`\n"} diff --git a/bio/yaml/minimap2.yaml b/bio/yaml/minimap2.yaml index c9b00408..959e7611 100644 --- a/bio/yaml/minimap2.yaml +++ b/bio/yaml/minimap2.yaml @@ -4,7 +4,7 @@ usage: minimap2 [options] | [query.fa] [...] options: - names: - -x - argument: '{map-pb|map_ont|map-hifi|ava-pb|ava-ont|asm5|asm10|asm20|splice|splice:hg|sr}' + argument: '{map-ont|lr:hq|map-hifi|map-pb|map-iclr|asm5|asm10|asm20|splice|splice:hg|sr|ava-pb|ava-ont}' description: preset (always applied before other options; see minimap2.1 for details) [] - names: - -H @@ -21,7 +21,7 @@ options: - names: - -I argument: NUM - description: split index for every ~NUM input bases [4G] + description: split index for every ~NUM input bases [8G] - names: - -d argument: FILE @@ -73,7 +73,7 @@ options: - names: - -B argument: INT - description: mismatch penalty [4] + description: mismatch penalty (larger value for lower divergence) [4] - names: - -O argument: INT[,INT] @@ -94,6 +94,10 @@ options: - -u argument: CHAR description: how to find GT-AG. f:transcript strand, b:both strands, n:don't match GT-AG [n] + - names: + - -J + argument: INT + description: 'splice mode. 0: original minimap2 model; 1: miniprot model [1]' - names: - -a argument: "" @@ -118,6 +122,10 @@ options: - --cs argument: '[=STR]' description: output the cs tag; STR is 'short' (if absent) or 'long' [none] + - names: + - --ds + argument: "" + description: output the ds tag, which is an extension to cs - names: - --MD argument: "" @@ -142,7 +150,7 @@ options: - --version argument: "" description: show version number -version: 2.24-r1122 +version: 2.28-r1209 tldr: | > Map and align between collections of DNA sequences. > More information: . diff --git a/bio/zsh b/bio/zsh index e1e301be..cc921fef 160000 --- a/bio/zsh +++ b/bio/zsh @@ -1 +1 @@ -Subproject commit e1e301beed5423e8b2ed2a83af80224efe0e8552 +Subproject commit cc921fef6fcba6f65464e24a1b474b3a5d152f34