1(self.webpackChunk_N_E=self.webpackChunk_N_E||[]).push([[627],{8855:function(s,e,r){(window.__NEXT_P=window.__NEXT_P||[]).push(["/workflow",function(){return r(7934)}])},7934:function(s,e,r){"use strict";r.r(e),r.d(e,{__toc:function(){return i}});var n=r(1527),t=r(918),l=r(7271);r(9418);let i=[{depth:2,value:"Software",id:"software"},{depth:2,value:"Data preparation",id:"data-preparation"},{depth:2,value:"Workflow",id:"workflow"},{depth:3,value:"Constructing reference panels",id:"constructing-reference-panels"},{depth:3,value:"Constructing target database",id:"constructing-target-database"},{depth:3,value:"Preprocessing and genotyping",id:"preprocessing-and-genotyping"},{depth:3,value:"Reformatting results",id:"reformatting-results"}];function o(s){let e=Object.assign({h2:"h2",p:"p",pre:"pre",code:"code",span:"span",a:"a",h3:"h3",em:"em"},(0,l.a)(),s.components);return(0,n.jsxs)(n.Fragment,{children:[(0,n.jsx)(e.h2,{id:"software",children:"Software"}),"\n",(0,n.jsx)(e.p,{children:"Clone Locityper to access additional scripts:"}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"git"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"clone"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"https://github.com/tprodanov/locityper"})]})})}),"\n",(0,n.jsxs)(e.p,{children:["Install additional dependencies (not necessarily via ",(0,n.jsx)(e.code,{children:"conda"}),"):"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"conda"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"install"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"agc"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"seqtk"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"brotli"})]})})}),"\n",(0,n.jsx)(e.h2,{id:"data-preparation",children:"Data preparation"}),"\n",(0,n.jsxs)(e.p,{children:["Download test data from ",(0,n.jsx)(e.a,{href:"https://zenodo.org/records/21903460",children:"Zenodo"})," (107 Mb) and decompress it:"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"xz"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"data.tar.xz"})]})})}),"\n",(0,n.jsxs)(e.p,{children:["Please, also download ",(0,n.jsx)(e.a,{href:"https://github.com/refresh-bio/agc",children:"AGC"}),"-compressed HPRC2 assemblies ",(0,n.jsx)(e.a,{href:"https://s3-us-west-2.amazonaws.com/human-pangenomics/submissions/B4174A5F-F20E-4DCF-8470-F8A907B640BC--HPRCv2_0.6.1_pr_agc_submission/HPRC_r2_assemblies_0.6.1.agc",children:"here (3.1 Gb)"}),"."]}),"\n",(0,n.jsxs)(e.p,{children:["Download ",(0,n.jsx)(e.a,{href:"https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/analysis_set/chm13v2.0.fa.gz",children:"(936 Mb)"})," or copy CHM13 reference genome into the working directory:"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsxs)(e.code,{"data-language":"bash","data-theme":"default",children:[(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"wget"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"https://s3-us-west-2.amazonaws.com/human-pangenomics/T2T/CHM13/assemblies/analysis_set/chm13v2.0.fa.gz"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"gzip"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"chm13v2.0.fa.gz"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"mv"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"chm13v2.0.fa"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"samtools"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"faidx"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"jellyfish"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"count"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--canonical"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--lower-count"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-constant)"},children:"2"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--out-counter-len"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-constant)"},children:"2"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--mer-len"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-constant)"},children:"25"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" \\"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--threads"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-constant)"},children:"8"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--size"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-constant)"},children:"3"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"G"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--output"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.jf"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"})]})]})}),"\n",(0,n.jsx)(e.h2,{id:"workflow",children:"Workflow"}),"\n",(0,n.jsx)(e.h3,{id:"constructing-reference-panels",children:"Constructing reference panels"}),"\n",(0,n.jsxs)(e.p,{children:["While it is possible to extract target haplotypes from a Minigraph-cactus VCF file (",(0,n.jsx)(e.a,{href:"/target#vcf",children:"see instructions"}),"), we recommend extracting haplotypes directly from the assemblies since some variation may be missing from the VCF file. Please run"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsxs)(e.code,{"data-language":"bash","data-theme":"default",children:[(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper/extra/extract-targets.sh"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" \\"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-i"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-i"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"HPRC_r2_assemblies_0.6.1.agc"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" \\"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-n"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"data/assembly_aliases.txt"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" \\"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-c"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"data/targets.CHM13.bed"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-r"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" \\"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-o"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"haplotypes"})]})]})}),"\n",(0,n.jsxs)(e.p,{children:["The script will map extract target sequences (",(0,n.jsx)(e.code,{children:"-c <BED file>"}),") from the corresponding reference genome (",(0,n.jsx)(e.code,{children:"-r <FASTA>"}),"); and map them to each of the assemblies (",(0,n.jsx)(e.code,{children:"-i"}),"). In this case, it's the CHM13 reference genome and the assemblies from the HPRC2 AGC file. To speed things up, we only specified GRCh38 and two other assemblies in the ",(0,n.jsx)(e.code,{children:"-n data/assembly_aliases.txt"}),", setting others to ",(0,n.jsx)(e.code,{children:"skip"}),". On a server, you can run multiple instances of this command at the same time, as they will automatically process different assemblies. In total, this process will take around 2-3 minutes per assembly. You can find more information about the output files ",(0,n.jsx)(e.a,{href:"/target#extract",children:"here"}),"."]}),"\n",(0,n.jsx)(e.h3,{id:"constructing-target-database",children:"Constructing target database"}),"\n",(0,n.jsx)(e.p,{children:"Now we need to construct Locityper target database on top of the extracted haplotypes."}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"target"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-r"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-j"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.jf"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-L"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"haplotypes/targets.bed"})]})})}),"\n",(0,n.jsxs)(e.p,{children:["We also provided local haplotypes for all HPRC2 and HGSVC3 assemblies in ",(0,n.jsx)(e.code,{children:"data/panels"}),". Let's rerun database construction:"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"target"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-r"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-j"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.jf"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),
1(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-L"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"data/panels/targets.bed"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--force"})]})})}),"\n",(0,n.jsxs)(e.p,{children:["Next step is recommended, but not required: we ",(0,n.jsx)(e.a,{href:"/target#augment",children:"augment"})," the database with pairwise haplotype alignments:"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"augment"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db"})]})})}),"\n",(0,n.jsxs)(e.p,{children:["If necessary, you can ",(0,n.jsx)(e.a,{href:"/target#augment",children:"prune"})," the database to remove very similar haplotypes up to a divergence threshold (",(0,n.jsx)(e.code,{children:"-t"}),") or to retain some number of haplotypes (",(0,n.jsx)(e.code,{children:"-n"}),"):"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"prune"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-o"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db-pruned"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-t"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-constant)"},children:"0.0002"})]})})}),"\n",(0,n.jsx)(e.h3,{id:"preprocessing-and-genotyping",children:"Preprocessing and genotyping"}),"\n",(0,n.jsxs)(e.p,{children:["First, we need to preprocess WGS data (you can find more information ",(0,n.jsx)(e.a,{href:"/preproc",children:"here"}),"):"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsxs)(e.code,{"data-language":"bash","data-theme":"default",children:[(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"mkdir"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"preproc"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"preproc"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-i"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"data/HG00733.*.fastq.gz"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-o"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"preproc/HG00733"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-r"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.fa"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-j"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"CHM13.jf"})]})]})}),"\n",(0,n.jsxs)(e.p,{children:["Afterwards, we genotype the data (more information ",(0,n.jsx)(e.a,{href:"/genotype",children:"here"}),"):"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsxs)(e.code,{"data-language":"bash","data-theme":"default",children:[(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"mkdir"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"gt"})]}),"\n",(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"genotype"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-i"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"data/HG00733.*.fastq.gz"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-p"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"preproc/HG00733"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-o"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"gt/HG00733"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"--leave-out"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"HG00733"})]})]})}),"\n",(0,n.jsxs)(e.p,{children:["In this example we added ",(0,n.jsx)(e.code,{children:"--leave-out HG00733"}
1)," because this sample is already present in the Locityper database."]}),"\n",(0,n.jsx)(e.h3,{id:"reformatting-results",children:"Reformatting results"}),"\n",(0,n.jsxs)(e.p,{children:["Locityper has written results into ",(0,n.jsx)(e.code,{children:"gt/HG00733/loci/{locus}/res.json.gz"}),". We can summarize them with"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper/extra/into_csv.py"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-i"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"gt/*"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-o"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"summary.csv"})]})})}),"\n",(0,n.jsxs)(e.p,{children:["Results may differ due to different versions and non-deterministic nature of Locityper. In our case, results look like this (explanations can be found ",(0,n.jsx)(e.a,{href:"/genotype#output",children:"here"}),"):"]}),"\n",(0,n.jsx)(e.pre,{"data-language":"text","data-theme":"default",hasCopyCode:!0,children:(0,n.jsxs)(e.code,{"data-language":"text","data-theme":"default",children:[(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"sample locus genotype quality total_reads unexpl_reads weight_dist warnings"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFA6 NA20762.1,HG01784.2 14.5 3231 0 0.03476 *"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFB1 HG00099.2,HG00731.2 29.8 3103 0 0.00209 *"})})]})}),"\n",(0,n.jsx)(e.p,{children:"Finally, since this sample is taken from the pangenome, we can evaluate the genotyping accuracy with"}),"\n",(0,n.jsx)(e.pre,{"data-language":"bash","data-theme":"default",hasCopyCode:!0,children:(0,n.jsx)(e.code,{"data-language":"bash","data-theme":"default",children:(0,n.jsxs)(e.span,{className:"line",children:[(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-function)"},children:"locityper/extra/eval_accuracy.py"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-i"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"summary.csv"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-d"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"db"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"-o"}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:" "}),(0,n.jsx)(e.span,{style:{color:"var(--shiki-token-string)"},children:"eval.csv"})]})})}),"\n",(0,n.jsx)(e.p,{children:"which in our case generated"}),"\n",(0,n.jsx)(e.pre,{"data-language":"text","data-theme":"default",hasCopyCode:!0,children:(0,n.jsxs)(e.code,{"data-language":"text","data-theme":"default",children:[(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"sample locus genotype quality total_reads unexpl_reads weight_dist warnings query_type edit size div qv"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFA6 NA20762.1,HG01784.2 14.5 3231 0 0.03476 * hap 0 25226 0.000000000 inf"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFA6 NA20762.1,HG01784.2 14.5 3231 0 0.03476 * hap 1 25252 0.000039601 44.022957807"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFA6 NA20762.1,HG01784.2 14.5 3231 0 0.03476 * gt 1 50478 0.000019811 47.031021393"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFB1 HG00099.2,HG00731.2 29.8 3103 0 0.00209 * hap 0 25589 0.000000000 inf"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFB1 HG00099.2,HG00731.2 29.8 3103 0 0.00209 * hap 0 25589 0.000000000 inf"})}),"\n",(0,n.jsx)(e.span,{className:"line",children:(0,n.jsx)(e.span,{style:{color:"var(--shiki-color-text)"},children:"HG00733 NDUFB1 HG00099.2,HG00731.2 29.8 3103 0 0.00209 * gt 0 51178 0.000000000 inf"})})]})}),"\n",(0,n.jsxs)(e.p,{children:["The output shows that the sample was genotyped almost perfectly: one of the haplotypes in ",(0,n.jsx)(e.em,{children:"NDUFA6"})," had edit distance of 1 to the true haplotype; all other haplotypes were predicted perfectly."]})]})}
1e.default=(0,t.j)({MDXContent:function(){let s=arguments.length>0&&void 0!==arguments[0]?arguments[0]:{},{wrapper:e}=Object.assign({},(0,l.a)(),s.components);return e?(0,n.jsx)(e,{...s,children:(0,n.jsx)(o,{...s})}):o(s)},pageOpts:{filePath:"pages/workflow.mdx",route:"/workflow",timestamp:1786538071e3,title:"Workflow",headings:i},pageNextRoute:"/workflow"})}},function(s){s.O(0,[918,888,774,179],function(){return s(s.s=8855)}),_N_E=s.O()}]);
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.