1"use strict";(self.webpackChunkuniprot_website=self.webpackChunkuniprot_website||[]).push([[9838],{26523(e,t,n){n.r(t),n.d(t,{default:()=>ie}),n(67622),n(38660),n(73748);var o=n(36371),r=n(66532),s=n(87912),a=n(65297),i=n(78375),l=n(68823),c=n(18088),p=n(34821),m=n(52871),d=n(69429);const u=e=>{let t;const n=e.taxonomy.scientificName,o=e.taxonomy.commonName;return t=n&&o?`${n} (${o})`:n||o||e.taxonomy.taxonId,t};n.dn(u),n(23132),n(75438),n(39828),n(84156),n(29462),n(8415),n(39490),n(18208),n(86100),n(40106),n(26572),n(35534),n(25833),n(85459),n(16137),n(67148);var x=n(71763),h=n(84026),g=(n(80746),n(85399)),y=n(61151),f=n(12249),j=n(51153),b=n(5968),A=n(61540),$=n(72695),w=n(96820);const _=(e,t)=>`(${(Array.isArray(t)?t:[t]).map(t=>{return`proteomecomponent:"${n=`${e}:${t}`,n.replace(/\\/g,"\\\\").replace(/"/g,'\\"')}"`;var n}).sort().join(" OR ")})`;var P=n(79523),C=n(75655),v=n(91987);const k=(0,C.A)(()=>Promise.all([n.e(4814),n.e(2887),n.e(6652),n.e(4374),n.e(8332),n.e(7660)]).then(n.bind(n,33806))),R={method:"HEAD"},I=({id:e,proteinCount:t,components:n,selectedEntries:a,proteomeType:i,proteomeStatistics:l})=>{const[c,u]=(0,x.useState)(!1),{pathname:y}=(0,r.zy)(),f=(0,x.useCallback)((e,t)=>{u(n=>(n?(0,P.a8)(e,t):(0,P.iJ)("results_download"),!n))},[]),j=(0,w.c)(i),b=(0,x.useMemo)(()=>0!==a.length&&a.length!==n?.length?_(e,a):`(proteome:${e})`,[e,n?.length,a]),{headers:$}=(0,m.A)(c&&a.length?(0,A.fI)(p.A.search.searchPrefix(j?d.g$.uniparc:d.g$.uniprotkb),{query:b,size:"0"}):null,R),C=Number($?.["x-total-results"]||0);return n?.length?(0,v.jsxs)(v.Fragment,{children:[c&&(0,v.jsx)(x.Suspense,{fallback:null,children:(0,v.jsx)(o.LT,{title:(0,v.jsx)("span",{"data-article-id":"downloads",children:"Download"}),position:"left",onClose:f,pathname:y,children:(0,v.jsx)(h.A,{children:(0,v.jsx)(k,{query:`(proteome:${e})`,selectedEntries:a,selectedQuery:b,totalNumberResults:t,numberSelectedEntries:C,onClose:f,proteomeStatistics:l,isUniparcSearch:j})})})}),(0,v.jsxs)("div",{className:"button-group",children:[(0,v.jsxs)(o.$n,{variant:"tertiary",onPointerOver:k.preload,onFocus:k.preload,onClick:()=>f("toggle"),children:[(0,v.jsx)(o.s3,{}),"Download"]}),(0,v.jsx)(g.N_,{className:"button tertiary",to:{pathname:s.qg[j?s.aZ.UniParcResults:s.aZ.UniProtKBResults],search:(0,A._b)({query:b})},children:"View proteins"})]})]}):null},T=({name:e})=>e,S=({components:e,id:t,proteinCount:n,proteomeType:r,taxonomy:a,proteomeStatistics:i})=>{const[l,c]=(0,b.A)(),p=(0,j.A)(),m=(0,x.useMemo)(()=>{const e=(0,w.c)(r),n=s.qg[e?s.aZ.UniParcResults:s.aZ.UniProtKBResults];return[{label:"Component name",name:"component_name",render:({name:e})=>e},{label:"Genome accession(s)",name:"genome_accession",render:({proteomeCrossReferences:e,genomeAnnotation:t})=>e?.filter(e=>Boolean(e.id)&&"GenomeAccession"===e.database).map(({id:e},n)=>{let o=null;switch(t.source){case"Refseq":case"RefSeq":o=(0,$.X5)(p,"GenBank",{ProteinId:e},"ProteinId");break;case"ENA/EMBL":o=(0,$.X5)(p,"EMBL",{id:e});break;case"Ensembl":o=f.A.EnsemblComponent(a.taxonId,e)}return(0,v.jsxs)(x.Fragment,{children:[n?", ":"",(0,v.jsx)(y.A,{url:o,children:e},e)]},e)})},{label:"Protein count",name:"proteins",render:({proteinCount:e,name:r})=>e?(0,v.jsx)(g.N_,{to:{pathname:n,search:(0,A._b)({query:_(t,r)})},children:(0,v.jsx)(o.Ig,{children:e})}):0}]},[p,t,r,a.taxonId]);return e?.length?(0,v.jsxs)(o.Zp,{header:(0,v.jsx)("h2",{children:"Components"}),children:[(0,v.jsx)(I,{components:e,selectedEntries:l,id:t,proteinCount:n,proteomeType:r,proteomeStatistics:i}),(0,v.jsx)(o.bQ,{getIdKey:T,density:"compact",columns:m,data:e,onSelectionChange:c})]}):null},N=({children:e})=>(0,v.jsxs)(o.Zp,{header:(0,v.jsx)("h2",{children:"Description"}),children:[(0,v.jsx)(l.A,{children:(0,v.jsx)("meta",{name:"description",content:e})}),e]});var F=n(85429),D=n(35590);const E=e=>(0,v.jsx)(D.Ay,{data:e,headingLevel:"h3",linkToEntry:!0,className:"CHImv"}),M=(0,F.X)(d.g$.citations),U=({citations:e})=>{const t=(0,x.useMemo)(()=>e?.map(e=>({citation:e})),[e]);return t?.length?(0,v.jsx)(o.Zp,{header:(0,v.jsx)("h2",{children:"Publications"}),children:(0,v.jsx)(o.Tr,{getIdKey:M,data:t,dataRenderer:E})}):null};var q=n(51799);const L="proteome_similarity",z=({proteomeId:e})=>e,Z=[{label:"Proteome",name:"proteome_id",render:({proteomeId:e,proteomeType:t})=>(0,v.jsx)(q.A,{id:e,namespace:d.g$.proteomes,entryType:t})},{label:"Organism",name:"organism",render:({taxonomy:e,scientificName:t})=>(0,v.jsx)(a.Ay,{data:{taxonId:e.taxonId,scientificName:t}})},{label:"Proteome similarity",name:"similarity",render:({similarity:e})=>`${(100*e).toFixed(1)}%`}],B=({exclusionReasons:e})=>(0,v.jsxs)("p",{children:["No similar proteomes are available because this proteome has been"," ",(0,v.jsx)("span",{"data-article-id":"proteome_exclusion_reasons",children:"excluded"}),e?.length?(0,v.jsxs)(v.Fragment,{children:[" (",e.join(", "),")"]}):null,"."]}),G=()=>(0,v.jsx)("p",{"data-article-id":L,children:"No similar proteome is available for this proteome. This is typically because the proteome is the only one for its species, or because no other reference proteome is similar enough to be listed here."}),K=()=>(0,v.jsx)("p",{"data-article-id":`${L}#what-proteomes-have-a-similarity-score`,children:"No similar proteome is available for this proteome."}),O=({relatedProteomes:e,proteomeType:t,exclusionReasons:n})=>{const r=(0,x.useMemo)(()=>e?.slice().sort((e,t)=>
1t.similarity-e.similarity),[e]);let s;return s=r?.length?(0,v.jsx)("div",{className:"t8JTa",children:(0,v.jsx)(o.bQ,{getIdKey:z,density:"compact",columns:Z,data:r})}):"Excluded"===t?(0,v.jsx)(B,{exclusionReasons:n}):"Reference proteome"===t?(0,v.jsx)(G,{}):(0,v.jsx)(K,{}),(0,v.jsx)(o.Zp,{header:(0,v.jsxs)("h2",{children:[(0,v.jsx)("span",{"data-article-id":L,children:"Similarity to reference proteomes"})," ",(0,v.jsx)(o.vu,{compact:!0,children:"New"})]}),children:s})};var H=function(e){return e.Description="description",e.SimilarProteomes="similar_proteomes",e.Components="components",e.Publications="publications",e}(H||{});const Q=H,X=[{id:Q.Description,sectionContent:e=>e.description?(0,v.jsx)(N,{children:e.description}):null},{id:Q.Components,sectionContent:({components:e,id:t,proteinCount:n,proteomeType:o,taxonomy:r,proteomeStatistics:s})=>(0,v.jsx)(S,{components:e,id:t,proteinCount:n,proteomeType:o,taxonomy:r,proteomeStatistics:s})},{id:Q.Publications,sectionContent:({citations:e})=>(0,v.jsx)(U,{citations:e})},{id:Q.SimilarProteomes,sectionContent:({relatedProteomes:e,proteomeType:t,exclusionReasons:n})=>(0,v.jsx)(O,{relatedProteomes:e,proteomeType:t,exclusionReasons:n})}],J=({transformedData:e})=>(0,v.jsx)(v.Fragment,{children:X.map(({id:t,sectionContent:n})=>(0,v.jsx)("section",{id:t,children:(0,v.jsx)(x.Suspense,{fallback:(0,v.jsx)(o.aH,{}),children:(0,v.jsx)(h.A,{children:n(e)})})},t))}),V=(0,x.memo)(J);n(29690);var W=n(13197),Y=n(54790),ee=n(34949),te=n(62900),ne=n(52851),oe=n(6398),re=n(85822);n(34059);const se=({panproteomeTaxon:e,taxonLineage:t,taxonomy:n})=>{const r=t.find(t=>"species"===t.rank&&t.taxonId===e.taxonId)??n,s=r.taxonId&&Y.Ay.panProteomesFolder(r.taxonId),{scientificName:a}=r;return a&&s&&(0,v.jsxs)(v.Fragment,{children:["This proteome is part of the ",(0,v.jsxs)(o.Gr,{url:s,children:[(0,v.jsx)("i",{children:a})," pan proteome"]})]})},ae=({data:e})=>{const t=(0,te.A)((0,w.c)(e.proteomeType)&&e.proteinCount?e.id:void 0),n=t=>{const n=ne.Ay.get(t);return n?.render(e)||null};let r,{proteomeType:s}=e;s.toLowerCase().includes("representative")&&(s="Reference proteome"),e.genomeAssembly?.assemblyId&&(r=(0,v.jsxs)(v.Fragment,{children:[e.genomeAssembly.assemblyId,e.genomeAssembly.source?` from ${e.genomeAssembly.source}`:""]}));const i=[{title:(0,v.jsx)("span",{"data-article-id":"proteome_id",children:"Proteome ID"}),content:e.id},{title:(0,v.jsx)("span",{"data-article-id":"proteome_terminology#proteome-status",children:"Status"}),content:(0,v.jsxs)(v.Fragment,{children:[(0,v.jsx)(W.Ay,{entryType:e.proteomeType}),"Non Reference proteome"===s?"Non-reference proteome":s,e.exclusionReasons?.length?(0,v.jsxs)("span",{"data-article-id":"proteome_exclusion_reasons",children:[" ","(",e.exclusionReasons.join(", "),")"]}):null,e.relatedProteomes?.length?(0,v.jsxs)(v.Fragment,{children:[" (",(0,v.jsx)("a",{href:`#${Q.SimilarProteomes}`,children:"Reference proteome"===s?"view similar reference proteomes":"view similarity to reference proteomes"}),")"]}):null]})},{title:(0,v.jsx)("span",{"data-article-id":"proteome_terminology#number-of-entries",children:"Number of entries"}),content:(0,v.jsxs)(v.Fragment,{children:[n(ne.$n.proteinCount),t>0?(0,v.jsxs)(v.Fragment,{children:[" ",(0,v.jsx)("a",{href:ee.A.precomputedProteomeAnnotations(e.id,{stream:!0,compressed:!0,download:!0}),children:"Download predicted annotations"})]}):null]})},{title:(0,v.jsx)("span",{"data-article-id":"proteome_terminology#gene-count",children:"Gene count"}),content:e.geneCount?(0,v.jsxs)(v.Fragment,{children:[(0,v.jsx)(o.Ig,{children:e.geneCount}),e.geneCount&&e.superkingdom&&e.taxonomy.taxonId?(0,v.jsxs)(v.Fragment,{children:[" ",(0,v.jsx)("a",{href:Y.Ay.referenceProteomes(e.id,e.superkingdom,e.taxonomy.taxonId),children:"Download one protein sequence per gene (FASTA)"})]}):null]}):null},{title:"Taxonomy"+(e.strain?" | Strain":""),content:(e.taxonomy.taxonId||e.taxonomy.scientificName)&&(0,v.jsxs)(v.Fragment,{children:[(0,v.jsx)(a.Ay,{data:e.taxonomy}),e.strain&&` | ${e.strain}`]})},{title:"Taxon ID",content:(0,v.jsx)(a.Ay,{data:e.taxonomy,displayOnlyID:!0})},{title:(0,v.jsx)("span",{"data-article-id":"proteome_terminology#genome-assembly",children:"Genome assembly and annotation"}),content:e.genomeAssembly?.assemblyId&&(0,v.jsx)(y.A,{url:e.genomeAssembly.genomeAssemblyUrl||null,children:r})},{title:"Genome representation",content:n(ne.$n.genomeRepresentation)},{title:(0,v.jsx)("span",{"data-article-id":"pan_proteomes",children:"Pan proteome"}),content:e.panproteomeTaxon&&(0,v.jsx)(se,{panproteomeTaxon:e.panproteomeTaxon,taxonLineage:e.taxonLineage,taxonomy:e.taxonomy})},{title:(0,v.jsx)("span",{"data-article-id":"assessing_proteomes#complete-proteome-detector-cpd",children:"Completeness (CPD)"}),content:n(ne.$n.cpd)},{title:(0,v.jsx)("span",{"data-article-id":"assessing_proteomes#benchmarking-universal-single-copy-orthologs-busco",children:"BUSCO"}),content:e.proteomeCompletenessReport?.buscoReport&&(0,v.jsxs)("div",{className:"busco",children:[(0,v.jsx)("div",{className:"busco__legend",children:(0,v.jsx)(oe.A,{})}),(0,v.jsx)(re.A,{report:e.proteomeCompletenessReport?.buscoReport})]})}];return(0,v.jsx)(o.f9,{columns:!0,infoData:i})},ie=()=>{const e=(0,r.W5)(s.qg[s.aZ.ProteomesEntry]),t=e?.params.accession,n=(0,m.A)(p.A.entry.entry(t,d.g$.proteomes)),x=n.data?.relatedProteomes,h=(0,m.A)(x?.length?p.A.search.search({namespace:d.g$.proteomes,query:x.map(({proteomeId:e})=>`upid:${e}`).join(" OR "),size:x.length,facets:null}):null);if(n.loading||h.loading)return(0,v.jsx)(o.aH,{progress:n.progress||h.progress});if(n.error||!t||!n.data)return(0,v.jsx)(i.A,{status:n.status,error:n.error,fullPage:!0});const g=((e,t)=>{const n=new Map(t?.map(e=>[e.id,e]));return{...e,relatedProteomes:e.relatedProteomes?.map(e=>{const t=n.get(e.proteomeId);return{...e,scientificName:t?.taxonomy?.scientificName,proteomeType:t?.proteomeType}})}})(n.data,h.data?.results);return(0,v.jsxs)(c.j,{className:"entry-page",children:[(0,v.jsx)(l.A,{title:[u(g),d.zK[d.g$.proteomes]]}),(0,v.jsxs)("h1",{children:[d.zK[d.g$.proteomes]," · ",(0,v.jsx)(a.Ay,{data:n.data.taxonomy,noLink:!0})]}),(0,v.jsx)(ae,{data:g}),(0,v.jsx)(V,{transformedData:g})]})}}
1,54790(e,t,n){n(29690),n(67622),n(38660),n(23132),n(75438),n(29833),n(36967),n(91482),n(11207),n(84160),n(31511),n(19675),n(39828),n(84156),n(29462),n(8415),n(39490),n(18208),n(86100),n(40106),n(26572),n(35534),n(25833),n(85459),n(16137),n(67148),n(87870),n(21862),n(64636),n(69516),n(80329),n(61284),n(37930),n(99453),n(50906),n(79747),n(3731),n(14357),n(99469),n(36411),n(43462),n(69992),n(98660),n(68907),n(20206);var o=n(41766),r=n(74547),s=n(69429),a=n(38335);const i="https://ftp.uniprot.org/pub/databases/uniprot/",l=`${i}current_release/knowledgebase/pan_proteomes`,c={uniprot:i,uniprotkb:(0,r.A)(i,"knowledgebase/complete"),uniprotkbReviewed:(0,r.A)(i,"knowledgebase/complete/uniprot_sprot"),uniprotkbUnreviewed:(0,r.A)(i,"knowledgebase/complete/uniprot_trembl"),referenceProteomes:(e,t,n)=>(0,r.A)(i,"/current_release/knowledgebase/reference_proteomes/"+(e&&t&&n?`${(0,o.A)(t)}/${e}/${e}_${n}.fasta.gz`:"")),panProteomes:e=>e?`${l}/pp${e}/pp${e}.fa.gz`:l,panProteomesFolder:e=>`${l}/pp${e}/`,embeddings:(0,r.A)(i,"current_release/knowledgebase/embeddings"),uniref:(0,r.A)(i,"uniref"),uniparc:(0,r.A)(i,"current_release/uniparc"),idmapping:(0,r.A)(i,"/current_release/knowledgebase/idmapping/")},p=new Map([[s.g$.uniprotkb,c.uniprotkb],[s.g$.uniref,c.uniref],[s.g$.uniparc,c.uniparc]]),m=new Map([[a.o.fastaRepresentative,"fasta"],[a.o.fastaCanonical,"fasta"],[a.o.text,"dat"],[a.o.xml,"xml"]]),d=new Map([[s.g$.uniprotkb,new Set([a.o.fastaCanonical,a.o.text,a.o.xml,a.o.embeddings])],[s.g$.uniref,new Set([a.o.fastaRepresentative])],[s.g$.uniparc,new Set([a.o.fasta,a.o.xml])]]),u=new Map([[s.g$.uniparc,new Map([["*",[]]])],[s.g$.uniref,new Map([["*",["uniref50/uniref50","uniref90/uniref90","uniref100/uniref100"]],["identity:1.0",["uniref100/uniref100"]],["identity:0.9",["uniref90/uniref90"]],["identity:0.5",["uniref50/uniref50"]]])],[s.g$.uniprotkb,new Map([["reviewed:true",["uniprot_sprot"]],["reviewed:false",["uniprot_trembl"]],["*",["uniprot_sprot","uniprot_trembl"]],["proteome:up000006548",["UP000006548_3702/per-protein.h5"]],["proteome:up000001940",["UP000001940_6239/per-protein.h5"]],["proteome:up000000625",["UP000000625_83333/per-protein.h5"]],["proteome:up000005640",["UP000005640_9606/per-protein.h5"]],["proteome:up000000589",["UP000000589_10090/per-protein.h5"]],["proteome:up000002494",["UP000002494_10116/per-protein.h5"]],["proteome:up000464024",["UP000464024_2697049/per-protein.h5"]]])]]),x=new Map([[[/^\(*\*\)*$/],"*"],[[/^\(*identity:(?<identity>0.5|0.9|1.0)\)*\)?$/,/^\(*identity:(?<identity>0.5|0.9|1.0)\)*(?:\s+and\s+\(*\*\)*)?$/,/^(?:\(*\*\)*\s+and\s+)?\(*identity:(?<identity>0.5|0.9|1.0)\)*$/],"identity:$<identity>"],[[/^\(*reviewed:(?<bool>false|true)\)*(?:\s+and\s+\(*\*\)*)?$/,/^(?:\(*\*\)*\s+and\s+)?\(*reviewed:(?<bool>false|true)\)*$/],"reviewed:$<bool>"],[[/^\(*proteome:(?<upid>up\d+)\)*$/,/^(?:\(*\*\)*\s+and\s+)?\(*proteome:(?<upid>up\d+)\)*$/],"proteome:$<upid>"]]),h=c;n.d(t,["Ay",0,h,"rD",0,(e,t,n)=>{if(!d.get(e)?.has(n))return null;const o=p.get(e);if(!o)return null;const i=new URLSearchParams(t).get("query");if(!i)return null;const l=(e=>{const t=e.trim().toLowerCase();for(const[e,n]of x)for(const o of e){const e=t.match(o);if(e){const t=Object.entries(e.groups||{});if(0===t.length)return n;if(1===t.length){const[e,o]=t[0];return n.replace(`$<${e}>`,o)}}}return null})(i);if(!l)return null;const h=u.get(e)?.get(l);if(!h)return null;if(e===s.g$.uniparc){const e=n===a.o.fasta?"/fasta/active/":n===a.o.xml&&"/xml/all/";return e?[{filename:e,url:(0,r.A)(o,e)}]:null}if(n===a.o.embeddings&&1===h.length)return"uniprot_sprot"===h[0]&&(h[0]+="/per-protein.h5"),[{filename:h[0],url:(0,r.A)(c.embeddings,h[0])}];const g=m.get(n);return!g||l.includes("proteome")?null:h.map(e=>{const t=`${e}.${g}.gz`;return{filename:t,url:(0,r.A)(o,t)}})}])},5968(e,t,n){n(67622),n(80746),n(38660),n(29833),n(36967),n(91482),n(11207),n(84160),n(31511),n(19675),n(87870),n(21862),n(64636),n(69516),n(80329),n(61284),n(37930),n(99453),n(50906),n(79747),n(3731),n(14357),n(99469),n(36411),n(43462),n(69992);var o=n(71763),r=n(66532),s=n(91981),a=n(97657);n.d(t,["A",0,e=>{const[t,n]=(0,a.A)([]),i=(0,r.zy)(),l=(0,o.useRef)(new Set([])),c=(0,o.useRef)(!1),p=(0,o.useCallback)(()=>{c.current=!1,n(Array.from(l.current))},[n]),m=(0,o.useCallback)(e=>{if(e.target instanceof HTMLInputElement&&e.target.dataset.id){const{id:t}=e.target.dataset,{checked:n}=e.target;l.current[n?"add":"delete"](t),c.current||(c.current=!0,(0,s._)().then(()=>{p()}))}},[p]);return(0,o.useEffect)(()=>{e||n(e=>{const t=new Set(Array.from(document.querySelectorAll('td > input[type="checkbox"]:checked')).map(e=>e.dataset.id));
1return l.current=new Set(e.filter(e=>t.has(e))),Array.from(l.current)})},[e,i,n]),[t,m,n]}])},62900(e,t,n){var o=n(52871),r=n(34949);const s={method:"HEAD"};n.d(t,["A",0,e=>{const{headers:t}=(0,o.A)(e?r.A.precomputedProteomeAnnotations(e,{size:0}):null,s),n=+(t?.["x-total-results"]||0);return Number.isFinite(n)?n:0}])},73748(){}}]); 2//# sourceMappingURL=modern.proteomes-entry.68a6b4.js.map
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.