CINXE.COM
RPs [PIR - Protein Information Resource]
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <HTML> <HEAD> <TITLE>RPs [PIR - Protein Information Resource]</TITLE><!-- ##### page dependent--> <LINK href="/pirwww/stylesheet/styles.css" type="text/css" rel="stylesheet"> <SCRIPT language=JavaScript src="/pirwww/scripts/progress_bar.js" type="text/javascript"></SCRIPT> <style type="text/css"> a:active { color:#336699; text-decoration:underline} a:link { color:#336699; text-decoration:underline} a:visited { color:#996666; text-decoration:underline } a:hover { color: #FFAA00; text-decoration: underline} a.nounderline{text-decoration:none} </style> <!-- Global site tag (gtag.js) - Google Analytics --> <script async src="https://www.googletagmanager.com/gtag/js?id=UA-4232355-1"></script> <script> window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag('js', new Date()); gtag('config', 'UA-4232355-1'); </script> </HEAD> <BODY bgColor="#cccccc" background="/pirwww/images/temp/bg02.gif" leftMargin="0" topMargin="0" marginwidth="0" marginheight="0" > <table border="0" cellspacing="0" cellpadding="0" width=100%><tr><td> <MAP NAME="PIRBanner_Map"> <AREA SHAPE="rect" alt="home" COORDS="16,16,110,60" HREF="/" TARGET="_top"> <AREA SHAPE="rect" alt="uniprot" COORDS="140,36,178,50" HREF="http://www.uniprot.org/" TARGET="_blank"> </MAP> <TABLE cellSpacing=0 cellPadding=0 width="100%" border=0 height=80> <TR> <TD><img alt='' src="/pirwww/images/temp/PIRBanner.png" border="0" usemap="#PIRBanner_Map"></TD> <TD width="99%" nowrap height=1 background="/pirwww/images/temp/blueSpacer.png"> <img alt='' src="/pirwww/images/spacer.gif" width="1" height="1" border=0> </TD> <td align=right vAlign=top height="80" width="400" background="/pirwww/images/temp/gradientHome6.png"> <table border=0 cellpadding=0 cellspacing=0 width="400" height=80> <form action="/cgi-bin/textsearch.pl" id="textSearch" method="get" name="textSearchForm" style="MARGIN: 0px"> <tr> <td width=400 colspan=7><img alt='' src="/pirwww/images/spacer.gif" width=400 height="30"></td> </tr> <tr> <td><img alt='' src="/pirwww/images/spacer.gif" width="40" height="1"></td> <td align=right nowrap class=searchLable></td> <td><img alt='' src="/pirwww/images/spacer.gif" width="8" height="1"></td> <td align=right></td> <td><img alt='' src="/pirwww/images/spacer.gif" width="2" height="1"></td> <td align=right></td> <td><img alt='' src="/pirwww/images/spacer.gif" width="26" height="1"></td> </tr> <input type=hidden name=field0 value=ALL> <input type=hidden name=search value=1> </form> </table> </td> </TR> </TABLE> <style> <!-- .radio1 { font-size:4px; background-color:transparent; border:1px; border-color:transparent; border:transparent; } .searchBannerBox { font-family: Verdana, Tahoma, Arial, Helvetica, sans-serif; font-size: 11px; WIDTH: 180px; HEIGHT:18px } td.searchLable { color:#ffffff; font-family:Verdana,Arial, Helvetica, sans-serif; font-size:10px; font-weight:bold } table.result { color:#000000; background-color:#ffffff; border:1px solid #333333; } th.result { color:#ffffff; background-color:#eeeeee; padding-bottom:5px; } tr.resultEvenRow { background-color:#eeeeee; padding-bottom:5px; } td.result { color:#000000; background-color:#FFFFFF; } td.tableHead{ color:#000000; background-color:#c1d0df; text-align:left; font-weight:bold; } .hide2 { position:absolute; visibility:hidden; } .show2 { position:absolute; visibility:visible; } --> </style> <TABLE cellSpacing=0 cellPadding=0 width=100% bgColor=#333333 border=0><tr> <TD><img src='/pirwww/images/temp/leftSearch.png'></TD><!-- ############### group dependent--> <td class=sml01 width=99% background='/pirwww/images/temp/bgcolor.png'> </td> <noscript> <td> <table bgcolor="#4a4a4a" width="100%" height="21" border="0" cellspacing="0" cellpadding="0"> <tr> <td class="nrm02" nowrap> <a href="/" class="m"><font face=verdana size="2pt" color="white">Home</font></a> <a href="/pirwww/about/" class="m"><font face=verdana size="2pt" color="white">About PIR</font></a> <a href="/pirwww/dbinfo/" class="m"><font face=verdana size="2pt" color="white">Databases</font></a> <a href="/pirwww/search/" class="m"><font face=verdana size="2pt" color="white">Search/Retrieval</font></a> <a href="/pirwww/download/" class="m"><font face=verdana size="2pt" color="white">Download</font></a> <a href="/pirwww/support/" class="m"><font face=verdana size="2pt" color="white">Support</font></a> </td> </tr> </table> </td> </noscript> </tr></table> <TABLE cellSpacing=0 cellPadding=0 width=100% bgColor=#ffffff border=0> <TR vAlign=top> <TD background="/pirwww/images/temp/bg02.gif"><img src="/pirwww/images/spacer.gif" width="94" height="1" alt=''></TD> <TD><img width=8 height=400 src="/pirwww/images/spacer.gif" border="0" alt=''></TD> <TD align=left nowrap bgcolor='#ffffff' width=678> <!-- The closing half of the body frame is in half_frame_close.inc--> <table border="0" cellspacing="0" cellpadding="0" class=docTitle><tr> <td width="10" rowspan=2><IMG height=40 src="/pirwww/images/spacer.gif" width=10 alt=""></td> <td> <table border=0 cellpadding=0 cellspacing=0 width="8" height=20> <tr> <td bgcolor="#336699"><img height=20 src="/pirwww/images/spacer.gif" width=8 alt=""></td> </tr> </table> </td> <td width="10"><IMG height=20 src="/pirwww/images/spacer.gif" width=10 alt=""></td> <td> <a href="/pirwww/" class='titleLink'><b>HOME</b></a> / <b>Reference Proteomes</b><!-- ############### page dependent--> </td></tr><tr><td height=2></td></tr> </table> <!-- ############## page dependent block--> <!-- ############## page dependent block--> <TABLE cellSpacing=0 cellPadding=9 border=0 width=1000 bgcolor='#ffffff' class=nrm02> <TR> <td><table width="100%" bgcolor="#ffffff" cellpadding="8" cellspacing="0" width=100% class=boxTable> <tr width=100%> <th class="right" align=left width=99%>Reference Proteomes (RP)</th> <th class=rightHelp align=center><A href="/pirwww/support/help.shtml#42"><img src="/pirwww/images/temp/question11.gif" border=0"></A></th> </tr> <tr> <td colspan=2> <!-- ######### MAIN content --> <table width=100% cellpadding=15 border=0> <tr><td class=nrm02 width=100%> <p align=justify> <center><b>A stable, scalable and unbiased proteome set for sequence analysis<br> and functional annotation</b><br></center><br> <!--<center><b>A stable and unbiased set of proteomes ideal for functional annotation <br>and protein classification efforts</b><br></center><br> --> </p> <p><center>Release <a href="data/current/release_note.txt">2024_04</a>, July 24, 2024 </p> </center> <table width=100% cellpadding=4 cellspacing=0 border=0 class=nrm02> <tr> <td align=justify>Reference Proteomes (RPs) (algorithmically determined), are proteomes that are selected from Representative Proteome Groups (RPGs) containing similar proteomes calculated based on co-membership in UniRef50 clusters. Reference Proteome is the proteome that can best represent all the proteomes in its group in terms of the majority of the sequence space and information. RPs at 75%, 55%, 35% and 15% co-membership threshold are provided to allow users to decrease or increase the granularity of the sequence space based on their requirements (<a href="http://dx.plos.org/10.1371/journal.pone.0018910">Chen et al., 2011</a>). <!-- Representative genomes (RGs) are also constructed based on the corresponding RPs. --> </td> <tr> <tr><td align=justify> <p> The RP set is updated every four weeks (synchronized with UniProtKB release) and the data is available for browsing, downloading and BLAST search. </td></tr></table> <br> <!-- <p><font size=-1 color="red">Starting from 2014_09 release, we have used UniProt Proteome identifiers as Reference Proteome identifiers instead of NCBI Taxonomy identifiers. For those using the RPG files below, the first column now contains UniProt Proteome identifiers. Previously, it contains NCBI Taxonomy identifiers.</font></p> <p> <p><font size=-1 color="red">Starting from 2015_12 release, we have renamed "Representative Proteomes" to "Reference Proteomes" (algorithmically determined) to be consistent with the changes already made at the UniProt site.</font></p> <br/> --> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="/rps/rp_stats.shtml">Release Statistics</a> </b> </p> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="/rps/blast_rp.shtml">BLAST sequence search</a> </b> </p> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="/cgi-bin/rps_tree.pl">Browse RPs database</a> </b> </p> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="ftp://ftp.proteininformationresource.org/databases/rps/">Download RPs files</a> </b> <br><br> <table border=0 align=center> <tr align=right><td> <font size=-2>(<a href="data/current/completeProteomeSet-seqs.fasta.gz">download the complete proteome set</a>, #Proteomes: 30218) </font> </td></tr> <tr align=center><td> <table border=1 class=nrm02 align="center" cellpadding="8" cellspacing="0"> <th> <th>RPG file<th>Seq file*<th>#RPGs <tr><td>75% cut-off<td><a href="data/current/75/rpg-75.txt">rpg-75.txt</a> <td><a href="data/current/75/rp-seqs-75.fasta.gz">rp-seqs-75.fasta.gz</a><td>18367 <tr><td>55% cut-off<td><a href="data/current/55/rpg-55.txt">rpg-55.txt</a> <td><a href="data/current/55/rp-seqs-55.fasta.gz">rp-seqs-55.fasta.gz</a><td>11753 <tr><td>35% cut-off <td><a href="data/current/35/rpg-35.txt">rpg-35.txt</a><td><a href="data/current/35/rp-seqs-35.fasta.gz">rp-seqs-35.fasta.gz</a><td>5942 <tr><td>15% cut-off<td><a href="data/current/15/rpg-15.txt">rpg-15.txt</a> <td><a href="data/current/15/rp-seqs-15.fasta.gz">rp-seqs-15.fasta.gz</a><td>1906 </table> </td></tr> </table> <center><font size=-2>* Seq files for each cut-off include the sequences from <a href="http://www.geneontology.org/GO.refgenome.shtml">model organisms with complete proteomes</a >. <br/>All sequence files have been filtered to contain one-protein-per-gene. </font> </center> </p> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="/rps/mk_rp.shtml">Make your own RP sequence file</a> </b><br/> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="/rps/pp.shtml">Pan Proteomes (PPs)</a> </b><br/></p> <!-- <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="ftp://ftp.proteininformationresource.org/databases/rps/archive/current/rg">Download RG files</a></b> <br>Representative genomes (RGs) are constructed based on the corresponding RPs. UniProt taxonomy ids are mapped to NCBI genome project ids and RefSeq project ids. The RefSeq ids can be used to retrieve corresponding genomes and proteomes from NCBI. </b><br/> <br/> --> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="/rps/viruses">Viral Reference Proteomes (Viral RPs)</a> </b><br/> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10>Representative Genome (RG) files</b> <p>Users can retrieve the genomic sequences of the RPs from UniProt or NCBI.</p> <p><b>UniProt</b>: UniProt provides genomics sequences of bacterial and archaeal RPs at 55% cut-off and eukaryotic RPs at 75% cutoff (ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/reference_proteomes/).</p> <p> <b>NCBI</b>: NCBI provides refseq-genbank.csv. file which has mappings of Genome project id, RefSeq project id and taxonomy id (ftp://ftp.ncbi.nlm.nih.gov/bioproject/). The taxonomy id mappings available at http://pir.georgetown.edu/rps/data/current/75/rpg-75.txt can be used to get the Genome project id or RefSeq project id from refseq-genbank.csv, which then can be used to retrieve the genomic sequence or CDS using NCBI e-utils.</p> <p> <b><IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><a href="ftp://ftp.proteininformationresource.org/databases/rps/archive">Previous Releases</a> </b><br/> <br/> <IMG src="/pirwww/images/temp/orangeDot.gif" width=10 height=10><b>Publication</b><br/> Chen C, Natale DA, Finn RD, Huang H, Zhang J, Wu CH, Mazumder R.<br/> <a href="http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0018910">Representative proteomes: a stable, scalable and unbiased proteome set for sequence analysis and functional annotation.</a> <br/><i>PLoS One</i>. 2011 Apr 27;6(4):e18910. PubMed PMID: <a href="http://www.ncbi.nlm.nih.gov/pubmed/21556138">21556138</a>; PubMed Central PMCID: <a href="http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3083393/">PMC3083393</a>. </td></tr> </table> <!-- ######### end of MAIN content --> </td> </tr> </table> </TD> </TR> </TABLE> <br><br> <!-- ############## end of page dependent block--> <!-- ############## end of page dependent block--> <!-- This is a second half of body frame. The first half is in half_frame_close.inc"--> </TD> <TD width=100% background="/pirwww/images/temp/bg02.gif" align=right bgcolor='#ffffff'><img src="/pirwww/images/spacer.gif" width="1" height="1" alt=''></TD> </TR> </TABLE> <!-- FOOTER --> <TABLE cellspacing=0 cellpadding=0 width="100%" bgcolor="#eeeeee" border=0 class=nrm02> <TBODY> <TR> <TD align="center" valign="middle" nowrap bgcolor=#71a1cf> <img src="/pirwww/images/pirlogo2.png" alt="PIR"> </TD> <TD align="left" valign="top"> <TABLE background="/pirwww/images/spacer.gif" width="686" border=0 cellPadding=3 cellSpacing=0 class=nrm02> <TBODY> <TR> <TD align="left" valign=bottom nowrap> <a href="/" class='footerMenu'>Home</a> | <a href="/pirwww/about/" class='footerMenu'>About PIR</a> | <a href="/pirwww/dbinfo" class='footerMenu'>Databases</a> | <a href="/pirwww/search/" class='footerMenu'>Search/Analysis</a> | <a href="/pirwww/download/" class='footerMenu'>Download</a> | <a href="/pirwww/support/" class='footerMenu'>Support</a> </TD> <TD align="right" valign=bottom nowrap class=nrm01> <a href="/pirwww/support/sitemap.shtml" class='footer'>SITE MAP</a> | <a href="/pirwww/about/linkpir.shtml" class='footer'>TERMS OF USE</a> </TD> </TR> <TR> <TD colspan="2" align="center" nowrap class="footer3"><span class=nrm10><FONT color=#999999> ©2018</FONT></sapn> <img src="/pirwww/images/spacer.gif" alt="" width=20 height=1> <b><a href="/" >Protein Information Resource</a></b> <img src="/pirwww/images/spacer.gif" alt="" width=105 height=1></TD> </TR> <TR><TD colspan="2" nowrap><table border=0 cellPadding=2 cellSpacing=0 class=nrm02 width=100%> <tr><td><img src="/pirwww/images/spacer.gif" alt="" width=50 height=1></td> <TD nowrap align="center" class=footer><a href='http://bioinformatics.udel.edu' target="_blank"><FONT color=#999999>University of Delaware</font></a> <br><FONT color=#999999>590 Avenue 1743, Suite 147 <br>Newark, DE 19711, USA</FONT></TD> <td><img src="/pirwww/images/spacer.gif" alt="" width=20 height=1></td> <TD nowrap align="center" class=footer><a href='http://gumc.georgetown.edu' target="_blank" ><FONT color=#999999>Georgetown University Medical Center</font></a> <br><FONT color=#999999>2115 Wisconsin Ave NW, G1 level, Suite 040A <br>Washington, DC 20007, USA</FONT></TD> </tr></table></td> </TR> </TBODY> </TABLE></TD> <TD width="99%" > </TD> </TR> </TBODY> </TABLE> </td></tr></table> </body> <!-- Menu Related --> <!-- <LINK href="/pirwww/menu/milo.css" type=text/css rel=stylesheet> --> <SCRIPT language=javascript src="/pirwww/menu/milonic_src.js" type="text/javascript"></SCRIPT> <SCRIPT language=javascript> if(ns4) _d.write("<scr"+"ipt language=JavaScript src=/pirwww/menu/mmenuns4.js><\/scr"+"ipt>"); else _d.write("<scr"+"ipt language=JavaScript src=/pirwww/menu/mmenudom.js><\/scr"+"ipt>"); </SCRIPT> <SCRIPT language=javascript src="/pirwww/menu/menu_data.js" type="text/javascript"></SCRIPT> <SCRIPT language=JavaScript src="/pirwww/menu/tooltips.js" type="text/javascript"></SCRIPT> <!-- Menu Related ends --> <script type="text/javascript"> var gaJsHost = (("https:" == document.location.protocol) ? "https://ssl." : "http://www."); document.write(unescape("%3Cscript src='" + gaJsHost + "google-analytics.com/ga.js' type='text/javascript'%3E%3C/script%3E")); </script> <script type="text/javascript"> var pageTracker = _gat._getTracker("UA-4232355-1"); pageTracker._initData(); pageTracker._trackPageview(); </script>