---
library_name: multimolecule
license: agpl-3.0
pipeline: rna-secondary-structure
pipeline_tag: other
tags:
- Biology
- RNA
- rna-secondary-structure
- rna
widget:
- example_title: microRNA 21
  output:
    text: '......................'
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: UAGCUUAUCAGACUGAUGUUGA
- example_title: microRNA 146a
  output:
    text: '......................'
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: UGAGAACUGAAUUCCAUGGGUU
- example_title: microRNA 155
  output:
    text: '........................'
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: UUAAUGCUAAUCGUGAUAGGGGUU
- example_title: RNA component of mitochondrial RNA processing endoribonuclease
  output:
    text: '..............(((((.....)))))............(.[..[{)({[{{<A((BC[[[({[<D<E[{AB<{CBCCCDBD<FACDEEFFGGDFGHIHIEFJFGIJJJKKLGHIJJMKJNOKLMLNJ.JMMNNO.......)KPONO]}})>]>)a]}>]>abcb.d.cc..defeghif.jjgfjfjghkklimmnnologeoipmknjjfkkdnlj..mcno])b]]}}]>a}cb.c.d}de.h........jjigf...............'
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: GGUUCGUGCUGAAGGCCUGUAUCCUAGGCUACACACUGAGGACUCUGUUCCUCCCCUUUCCGCCUAGGGGAAAGUCCCCGGACCUCGGGCAGAGAGUGCCACGUGCAUACGCACGUAGACAUUCCCCGCUUCCCACUCCAAAGUCCGCCAAGAAGCGUAUCCCGCUGAGCGGCGUGGCGCGGGGGCGUCAUCCGUCAGCUCCCUCUAGUUACGCAGGCAGUGCGUGUCCGCGCACCAACCACACGGGGCUCAUUCUCAGCGCGGCUGUAAAAAAAAA
- example_title: 7SK small nuclear RNA
  output:
    text: '.........(((((((..[[[[[[.(....)..........))))))).......({<<ABCDC(ABBA{C{CA<EF.EGGG...H][.HI[GG[FJJ[[KLMNO.FGHGGFHH.KKFKJGHJKKILMFMKMGHNMIJLNOIMIKMOLNMMPQRMONOOPQPPRRSQ..SRSSRTSS)})>}}({U>aa{><aabcbbcc]cde]f]gh]f]gieiffijfhgkhghlghmfnggioghgijkpgmkqjlrlpsrmjompqsn)mm}>osmrt}kumsnkkmsokrspqrnoklmjnoh...............]]]]].............'
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: GGAUGUGAGGGCGAUCUGGCUGCGACAUCUGUCACCCCAUUGAUCGCCAGGGUUGAUUCGGCUGAUCUGGCUGGCUAGGCGGGUGUCCCCUUCCUCCCUCACCGCUCCAUGUGCGUCCCUCCCGAAGCUGCGCGCUCGGUCGAAGAGGACGACCAUCCCCGAUAGAGGAGGACCGGUCUUCGGUCAAGGGUAUACGAGUAGCUGCGCUCCCCUGCUAGAACCUCCAAACAAGCUCUCAAGGUCCAUUUGUAGGAGAACGUAGGGUAGUCAAGCUUCCAAGACUCCAGACACAUCCAAAUGAGGCGCUGCAUGUGGCAGUCUGCCUUUCUUUU
- example_title: telomerase RNA component
  output:
    text: .(......................[{<AB{<A<A................)..(([([{({([{(...([{<[[AACCDAC<B[BBC(AEDEFFEGHHIFDDEDDEFGGEGHDIFE(JF{AKABB[LLL[DMNBO{EJMADFGMC<DNFGM)GEFHCH]IGFPDE])})]]]}NO>P])})]}HI>aGaGHbbJca>))]}cadKaKKdLIJLKLaeeMbMMNOPMNMQQMRNQROORPb)b]a]}bcd}d)>a(([([(STfSTTSSeTUUTUVVWTTf}>>{{{g<WXgfhdgddaiahfiebjjkekkeldkeddlflgmnhmopmonmnompmqi)h)gqq])rcgfceffgedgfhfiggjejkh.h.i.lllmnAopAAA.mA....msn.s..mttnoptuv)}.>t}uwv]ustw.}.ctsxtr.a.raaa...a........
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: GGGUUGCGGAGGGUGGGCCUGGGAGGGGUGGUGGCCAUUUUUUGUCUAACCCUAACUGAGAAGGGCGUAGGCGCCGUGCUUUUGCUCCCCGCGCGCUGUUUUUCUCGCUGACUUUCAGCGGGCGGAAAAGCCUCGGCCUGCCGCCUUCCACCGUUCAUUCUAGAGCAAACAAAAAAUGUCAGCUGCUGGCCCGUUCGCCCCUCCCGGGGACCUGCGGCGGGUCGCCUGCCCAGCCCCCGAACCCCGCCUGGAGGCCGCGGUCGGCCCGGGGCUUCUCCGGAGGCACCCACUGCCACCGCGAAGAGUUGGGCUCUGUCAGCCGCGGGUCUCUCGGGGGCGAGGGCGAGGUUCAGGCCUUUCAGGCCGCAGGAAGAGGAACGGAGCGAGUCCCCGCGCGCGGCGCGAUUCCCUGAGCUGUGGGACGUGCACCCAGGACUCGGCUCACACAUGC
- example_title: vault RNA 2-1
  output:
    text: .(((((((..(.(((.(..((((....(((........((((.........))))..................)))..))))..).))).))))))))..........
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: CGGGUCGGAGUUAGCUCAAGCGGUUACCUCCUCAUGCCGGACUUUCUAUCUGUCCAUCUCUGUGCUGGGGUUCGAGACCCGCGGGUGCUUACUGACCCUUUUAUGCAA
- example_title: brain cytoplasmic RNA 1
  output:
    text: '....(.........([.{{([([[({([([[...((.....)).....(........<....)....................................................)]))])]]]}).])]}}....)............................................>..................'
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: GGCCGGGCGCGGUGGCUCACGCCUGUAAUCCCAGCUCUCAGGGAGGCUAAGAGGCGGGAGGAUAGCUUGAGCCCAGGAGUUCGAGACCUGCCUGGGCAAUAUAGCGAGACCCCGUUCUCCAGAAAAAGGAAAAAAAAAAACAAAAGACAAAAAAAAAAUAAGCGUAACUUCCCUCAAAGCAACAACCCCCCCCCCCCUUU
- example_title: HIV-1 TAR-WT
  output:
    text: (((.(((((((((((.(((((....(..........).)))))))))))))))))))
  pipeline_tag: rna-secondary-structure
  sequence_type: ncRNA
  task: rna-secondary-structure
  text: GGUCUCUCUGGUUAGACCAGAUCUGAGCCUGGGAGCUCUCUGGCUAACUAGGGAACC
- example_title: prion protein (Kanno blood group)
  output:
    text: '..........(.((...........(((((........)))))..........)).).........'
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AUGGCGAACCUUGGCUGCUGGAUGCUGGUUCUCUUUGUGGCCACAUGGAGUGACCUGGGCCUCUGC
- example_title: interleukin 10
  output:
    text: '......................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AUGCACAGCUCAGCACUGCUCUGUUGCCUGGUCCUCCUGACUGGGGUGAGGGCC
- example_title: Zaire ebolavirus
  output:
    text: '........((((((..........(.(...............((((..........))))[[{..<A<[B{{<B{{)B)(C((<<D(ABBCACBCD{{<DAACADBCBCDEBEEFFCDFGHEIFJHHH...II...........................................])}})}>a}>bb>c)}db}>]a]}caefdefaaebbcccbedddgc>c>af)bcbhfdhihibhij(([{(.[...(..[[..[.(..................))]]])])]}).......))))))..'
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AAUGUUCAAACACUUUGUGAAGCUCUGUUAGCUGAUGGUCUUGCUAAAGCAUUUCCUAGCAAUAUGAUGGUAGUCACAGAGCGUGAGCAAAAAGAAAGCUUAUUGCAUCAAGCAUCAUGGCACCACACAAGUGAUGAUUUUGGUGAGCAUGCCACAGUUAGAGGGAGUAGCUUUGUAACUGAUUUAGAGAAAUACAAUCUUGCAUUUAGAUAUGAGUUUACAGCACCUUUUAUAGAAUAUUGUAACCGUUGCUAUGGUGUUAAGAAUGUUUUUAAUUGGAUGCAUUAUACAAUCCCACAGUGUUAU
- example_title: SARS coronavirus
  output:
    text: '.......................................(....[[{..<<A..B.CDCDEEFFF....GC.D..HHIJIKKLJJKKLMJNNOKMPONPQQIQORPNQSRTSJRRTUSSUTVWWWWXUYUV..........(((......W.)))..V.......WXXYXYZX.ZX.YZ..Y)(].(((.U.VT}{][.[.......[{.[>.aAbcdcdce>defffghi{{i<iBjjjkjjh<Ak<lmm{{{<{{A<AABBCDDDCED.F.....nnnoopnqropGFHFHHIIHFGsJsHrHFIIGJHG)ttuv)uuv]}k}klkwvxxyyx>abxyzcdcdedbyda}}>}}a>}>w>a................f]g}]f..ga.ghfhffigijhhhijhhi]z.b)z}.qx...r)p.qq..s...rs......tu..u..vwtxyww(w((((.(.(((((....))))).).)))).)........'
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AUGUUUAUUUUCUUAUUAUUUCUUACUCUCACUAGUGGUAGUGACCUUGACCGGUGCACCACUUUUGAUGAUGUUCAAGCUCCUAAUUACACUCAACAUACUUCAUCUAUGAGGGGGGUUUACUAUCCUGAUGAAAUUUUUAGAUCAGACACUCUUUAUUUAACUCAGGAUUUAUUUCUUCCAUUUUAUUCUAAUGUUACAGGGUUUCAUACUAUUAAUCAUACGUUUGACAACCCUGUCAUACCUUUUAAGGAUGGUAUUUAUUUUGCUGCCACAGAGAAAUCAAAUGUUGUCCGUGGUUGGGUUUUUGGUUCUACCAUGAACAACAAGUCACAGUCGGUGAUUAUUAUUAACAAUUCUACUAAUGUUGUUAUACGAGCAUGUAACUUUGAAUUGUGUGACAACCCUUUCUUUGCUGUUUCUAAACCCAUGGGUACACAGACACAUACUAUGAUAUUCGAUAAUGCAUUUAAAUGCACUUUCGAGUACAUAUCU
- example_title: insulin
  output:
    text: '....................................................................(.......[.{[..[{<{[[{A)((<[B{ABBCABC<(D[A<E{DDCADCBFFGCGDDFDEEEFGEHGGHHI(I[G{HJ)K]H}IJLLMM..M.KNLLLLMNONNO))]]}}]}>a>)b]]a]>ab}}>ccadcbedbdee(f)g()ehgh(]a)ijh}ikgljkmnlllnigobhcnodllmcdddefnfmmfhgg....................................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AUGGCCCUGUGGAUGCGCCUCCUGCCCCUGCUGGCGCUGCUGGCCCUCUGGGGACCUGACCCAGCCGCAGCCUUUGUGAACCAACACCUGUGCGGCUCACACCUGGUGGAAGCUCUCUACCUAGUGUGCGGGGAACGAGGCUUCUUCUACACACCCAAGACCCGCCGGGAGGCAGAGGACCUGCAGGUGGGGCAGGUGGAGCUGGGCGGGGGCCCUGGUGCAGGCAGCCUGCAGCCCUUGGCCCUGGAGGGGUCCCUGCAGAAGCGUGGCAUUGUGGAACAAUGCUGUACCAGCAUCUGCUCCCUCUACCAGCUGGAGAACUACUGCAACUAG
- example_title: cyclin dependent kinase inhibitor 2A
  output:
    text: ..(...................((.....(((...)))......)).......[..[[.[[[([{(([{<AB[BBCC[<C(D<BAEC(C<D[[EE{FC(FFAB)ADGACA)C]]FBCEFBDGCEEDFDEDGHEFFDGEFGEFHHHIGJKGH))]})I]]}{KG)L]L(LJKMMJJLIMMLN(LKJKMKN)NKOLMNOIOPLMO>PPQQRaQRPSTUOUQTPVPURPTaQSUTPQQabaWcRRddSbTdTee}Tffd)ecTUUVVWWb..)([..{.)]}(>(>[[)>gec]]af]g}hdg]ga]ebii]j]e]cck(fcdlijlmkhmkbjcjnobciepq(pqfqprrstu)kvkwtjvdtbkwoplpml)pq)olqdrsnultrqstcecmqtnpufprotftnmohhefffgggelhkm......lu.mguu.v..w...............................
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AUGGAGCCGGCGGCGGGGAGCAGCAUGGAGCCUUCGGCUGACUGGCUGGCCACGGCCGCGGCCCGGGGUCGGGUAGAGGAGGUGCGGGCGCUGCUGGAGGCGGGGGCGCUGCCCAACGCACCGAAUAGUUACGGUCGGAGGCCGAUCCAGGUCAUGAUGAUGGGCAGCGCCCGAGUGGCGGAGCUGCUGCUGCUCCACGGCGCGGAGCCCAACUGCGCCGACCCCGCCACUCUCACCCGACCCGUGCACGACGCUGCCCGGGAGGGCUUCCUGGACACGCUGGUGGUGCUGCACCGGGCCGGGGCGCGGCUGGACGUGCGCGAUGCCUGGGGCCGUCUGCCCGUGGACCUGGCUGAGGAGCUGGGCCAUCGCGAUGUCGCACGGUACCUGCGCGCGGCUGCGGGGGGCACCAGAGGCAGUAACCAUGCCCGCAUAGAUGCCGCGGAAGGUCCCUCAGACAUCCCCGAUUGA
- example_title: human papillomavirus type 16 E6
  output:
    text: '...........................................(([..........................(({(<(..[{<{{{AAB(<(<BBC[DC({D<EE{FGG<HHIAFBFCAEFDGDDCEEEFEEFGDGDHHIEEIFH.G.HG...I..JKGKJHLIMMNMN)...)..)JKJKL]MMLJMLKNN)OPP((O}OPN}>PQ>QQQRSTaaAUVV]WWWXWXX}}..}b>>}>..{<{{{<YZc{YZZ<defedgggG...G.h..i.jkjkljll)mnmnopknqm)orqqstaqpuvvQRhQSTiabjbjakABBlkc)dmmnm)nede))fe])}}}>wwx}wc>g}xdxywezzgghhedh>figyze.i....cf.ef}.gfo>ppqfgqhihedrabbgstb................................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: mRNA
  task: rna-secondary-structure
  text: AUGCACCAAAAGAGAACUGCAAUGUUUCAGGACCCACAGGAGCGACCCAGAAAGUUACCACAGUUAUGCACAGAGCUGCAAACAACUAUACAUGAUAUAAUAUUAGAAUGUGUGUACUGCAAGCAACAGUUACUGCGACGUGAGGUAUAUGACUUUGCUUUUCGGGAUUUAUGCAUAGUAUAUAGAGAUGGGAAUCCAUAUGCUGUAUGUGAUAAAUGUUUAAAGUUUUAUUCUAAAAUUAGUGAGUAUAGACAUUAUUGUUAUAGUUUGUAUGGAACAACAUUAGAACAGCAAUACAACAAACCGUUGUGUGAUUUGUUAAUUAGGUGUAUUAACUGUCAAAAGCCACUGUGUCCUGAAGAAAAGCAAAGACAUCUGGACAAAAAGCAAAGAUUCCAUAAUAUAAGGGGUCGGUGGACCGGUCGAUGUAUGUCUUGUUGCAGAUCAUCAAGAACACGUAGAGAAACCCAGCUGUAA
- example_title: NRAS proto-oncogene
  output:
    text: ((((((((((.((((.......................)))).))))))..))))............................................................................
  pipeline_tag: rna-secondary-structure
  sequence_type: 5' UTR
  task: rna-secondary-structure
  text: GGGGCCGGAAGUGCCGCUCCUUGGUGGGGGCUGUUCAUGGCGGUUCCGGGGUCUCCAACAUUUUUCCCGGCUGUGGUCCUAAAUCUGUCCAAAGCAGAGGCAGUGGAGCUUGAGGUUCUUGCUGGUGUGAA
- example_title: amyloid beta precursor protein
  output:
    text: '......................(...................................(((.................................................................)))..)..................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 5' UTR
  task: rna-secondary-structure
  text: GUCAGUUUCCUCGGCAGCGGUAGGCGAGAGCACGCGGAGGAGCGUGCGCGGGGGCCCCGGGAGACGGCGGCGGUGGCGGCGCGGGCAGAGCAAGGACGCGGCGGAUCCCACUCGCACAGCAGCGCACUCGGUGCCCCGCGCAGGGUCGCG
- example_title: RUNX family transcription factor 1
  output:
    text: '.......................................(((.....)))................................................................................................................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 5' UTR
  task: rna-secondary-structure
  text: ACUUCUUUGGGCCUCAUAAACAACCACAGAACCACAAGUUGGGUAGCCUGGCAGUGUCAGAAGUCUGAACCCAGCAUAGUGGUCAGCAGGCAGGACGAAUCACACUGAAUGCAAACCACAGGGUUUCGCAGCGUGGUAAAAGAAAUCAUUGAGUCCCCCGCCUUCAGAAGAGGGUGCAUUUUCAGGAGGAAGCG
- example_title: fragile X messenger ribonucleoprotein 1
  output:
    text: '....(((..........([[((..((((........))))))..............................{{<<{ABC{D<A<BBABCCBDBCDDECEFGFGHIIJHBJ(KJKJ())(K[)](())LMNKLE)(FMNNNFG.(]][)]()(())}>(>)ababccb}dbe)ffg((ee}fccgf}>hb>ahijbkjkllmnnnmdnjkjdikgb........c.d))...................)))..........'
  pipeline_tag: rna-secondary-structure
  sequence_type: 5' UTR
  task: rna-secondary-structure
  text: CUCAGUCAGGCGCUCAGCUCCGUUUCGGUUUCACUUCCGGUGGAGGGCCGCCUCUGAGCGGGCGGCGGGCCGACGGCGAGCGCGGGCGGCGGCGGUGACGGAGGCGCCGCUGCCAGGGGGCGUGCGGCAGCGCGGCGGCGGCGGCGGCGGCGGCGGCGGCGGAGGCGGCGGCGGCGGCGGCGGCGGCGGCGGCUGGGCCUCGAGCGCCCGCAGCCCACCUCUCGGGGGCGGGCUCCCGGCGCUAGCAGGGCUGAAGAGAAG
- example_title: MYC proto-oncogene
  output:
    text: ..(.....[.[..{[[{<{{A[B[)..(C([.[B{{C{<AB.))]]}]}>ab]}]}]}}>a]}b]cbc((.[...........{{<<{A{B<A{ABBB<ACBB([DDCB[D{(...DEFGEH..EI.DD..C((...))...DE(FGCD[F(H[GICD[DEF{GHI<J{E<FEE<G<GAEEE<FAGBHIKCLLMCELMEMKHMHNMFNHNODLOPI))]}]>a>abJ}>]QO>>))Nc]]}))(c]((}>ab}}bbcc}d>dedefeefeghhdhheeeifegicfgdjaghijabklkcblbmn}e>>fmlal))gmfgnbcdhoimn)moddedddopeenfghqi...............
  pipeline_tag: rna-secondary-structure
  sequence_type: 5' UTR
  task: rna-secondary-structure
  text: AACUCGCUGUAGUAAUUCCAGCGAGAGGCAGAGGGAGCGAGCGGGCGGCCGGCUAGGGUGGAAGAGCCGGGCGAGCAGAGCUGCGCUGCGGGCGUCCUGGGAAGGGAGAUCCGGAGCGAAUAGGGGGCUUCGCCUCUGGCCCAGCCCUCCCGCUGAUCCCCCAGCCAGCGGUCCGCAACCCUUGCCGCAUCCACGAAACUUUGCCCAUAGCAGCGGGCGGGCACUUUGCACUGGAACUUACAACACCCGAGCAAGGACGCGACUCUCCCGACGCGGGGAGGCUAUUCUGCCCAUUUGGGGACACUUCCCCGCCGCUGCCAGGACCCGCUUCUCUGAAAGGCUCUCCUUGCAGCUGCUUAGACG
- example_title: activating transcription factor 4
  output:
    text: '......................................................([([[.{<<<<.<ABABCBBDDEFEEEG(([AGFHECBBACBCDGAACBED.()......................................[).)..]]..)]..}.>a)aabbccaddbeb]ca]bbcbcdeedeee>affgg>>>hb.......g......................................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 5' UTR
  task: rna-secondary-structure
  text: CAUUUCUACUUUGCCCGCCCACAGAUGUAGUUUUCUCUGCGCGUGUGCGUUUUCCCUCCUCCCCGCCCUCAGGGUCCACGGCCACCAUGGCGUAUUAGGGGCAGCAGUGCCUGCGGCAGCAUUGGCCUUUGCAGCGGCGGCAGCAGCACCAGGCUCUGCAGCGGCAACCCCCAGCGGCUUAAGCCAUGGCGCUUCUCACGGCAUUCAGCAGCAGCGUUGCUGUAACCGACAAAGACACCUUCGAAUUAAGCACAUUCCUCGAUUCCAGCAAAGCACCGCAAC
- example_title: Human GPI protein p137
  output:
    text: '........................................(((.(((((..........))))))))..............([{<A<ABCBDEFGG.(.EH)H.I.........JKJLMKM(NNOP.[...................................................................)...]...)]}>a>.abbcdeefgghhijjkklmmnonp..................................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 3' UTR
  task: rna-secondary-structure
  text: UUUUUAAAAGGAAAAGAUACCAAAUGCCUGCUGCUACCACCCUUUUCAAUUGCUAUGUUUUGAAAGGCACCAGUAUGUGUUUUAGAUUGAUUUAAAUGUUUCAUUUAAAUCACGGACAGUAGUUUCAGUUCUGAUGGUAUAAGCAAAACAAAUAAAACGUUUAUAAAAGUUGUAUCUUGAAACACUGGUGUUCAACAGCUAGCAGCUUAUGUGAUUCACCCCAUGCCACGUUAGUGUCACAAAUUUUAUGGUUUAUCUCCAGCAACAUUUCUCUAGUACUUGCACUUAUUAUCUGAAUUC
- example_title: nucleophosmin 1
  output:
    text: '......................................................(((((((.....))))))).....................((..[..........................(({([<[{[.{<A{<A{(<<[<B(C[AA{D{...........EDEFFFG.HIHFB(B<C[<JJ{GAKL<BHAKBF{AMCNBCMJAICDN)]}BLJD}GE>)]}aa>)]bb)a)c>]}}>dc>>})baa]]be}}>>)a])b}d>abccabcdefdfggehfijffghhijjkk..jll.mmnn...........................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 3' UTR
  task: rna-secondary-structure
  text: GAAAAUAGUUUAAACAAUUUGUUAAAAAAUUUUCCGUCUUAUUUCAUUUCUGUAACAGUUGAUAUCUGGCUGUCCUUUUUAUAAUGCAGAGUGAGAACUUUCCCUACCGUGUUUGAUAAAUGUUGUCCAGGUUCUAUUGCCAAGAAUGUGUUGUCCAAAAUGCCUGUUUAGUUUUUAAAGAUGGAACUCCACCCUUUGCUUGGUUUUAAGUAUGUAUGGAAUGUUAUGAUAGGACAUAGUAGUAGCGGUGGUCAGACAUGGAAAUGGUGGGGAGACAAAAAUAUACAUGUGAAAUAAAACUCAGUAUUUUAAUAAAGUAGCACGGUUUCUAUUGA
- example_title: superoxide dismutase 1
  output:
    text: '.................(..((((.........)))).)(([[{{[[<AA......................(...[{[([[({{<A((<AABBC(ADECDEFEFGFFHGGHHHIJ(..J)H.K............KKKLLMMNNNO....NO...............................................)))))]}})]]]>a}abcdeac>faeggfhbhhfdiejghfjhkklmklno.mnnno........))].]...]]}}>kaa........................................................................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 3' UTR
  task: rna-secondary-structure
  text: ACAUUCCCUUGGAUGUAGUCUGAGGCCCCUUAACUCAUCUGUUAUCCUGCUAGCUGUAGAAAUGUAUCCUGAUAAACAUUAAACACUGUAAUCUUAAAAGUGUAAUUGUGUGACUUUUUCAGAGUUGCUUUAAAGUACCUGUAGUGAGAAACUGAUUUAUGAUCACUUGGAAGAUUUGUAUAGUUUUAUAAAACUCAGUUAAAAUGUCUGUUUCAAUGACCUGUAUUUUGCCAGACUUAAAUCACAGAUGGGUAUUAAACUUGUCAGAAUUUCUUUGUCAUUCAAGCCUGUGAAUAAAAACCCUGUAUGGCACUUAUUAUGAGGCUAUUAAAAGAAUCCAAAUUCAAACUAAA
- example_title: hemoglobin subunit alpha 2
  output:
    text: ..(.....................................)....................................................................
  pipeline_tag: rna-secondary-structure
  sequence_type: 3' UTR
  task: rna-secondary-structure
  text: CUGGAGCCUCGGUAGCCGUUCCUCCUGCCCGCUGGGCCUCCCAACGGGCCCUCCUCCCCUCCUUGCACCGGCCCUUCCUGGUCUUUGAAUAAAGUCUGAGUGGGCAGCA
- example_title: BRAF proto-oncogene
  output:
    text: '......................................................([((({{<...)))[)(([({A[(.....B..([.({<A<B(A[C{{{AC<ADDBEFFDG)]}HH>IaJb}KKK)I)LMNODE)]}PP}>aa>abcc))])]]}((CCN(CQ(PRNNNOSTOLUCTO(RTU(VCUCLM(OBSMUBVUCCLTQTPWXPSNXNOSOWVYRPXdQQQUeWRWSTQRVZSS.d...dd.effghDDDDEFG][FGG[FE[[.}.}>i.h.ijk..a)bbcl)cbcc))cl)mnoclpm))knlmncqokoqqnporssqcnnopn]rsoo]pqpp]trqrrssststuvtuvuuvdwwuwttwxvuexxyzefdd]fgfdgg...........................'
  pipeline_tag: rna-secondary-structure
  sequence_type: 3' UTR
  task: rna-secondary-structure
  text: AACAAAUGAGUGAGAGAGUUCAGGAGAGUAGCAACAAAAGGAAAAUAAAUGAACAUAUGUUUGCUUAUAUGUUAAAUUGAAUAAAAUACUCUCUUUUUUUUUAAGGUGAACCAAAGAACACUUGUGUGGUUAAAGACUAGAUAUAAUUUUUCCCCAAACUAAAAUUUAUACUUAACAUUGGAUUUUUAACAUCCAAGGGUUAAAAUACAUAGACAUUGCUAAAAAUUGGCAGAGCCUCUUCUAGAGGCUUUACUUUCUGUUCCGGGUUUGUAUCAUUCACUUGGUUAUUUUAAGUAGUAAACUUCAGUUUCUCAUGCAACUUUUGUUGCCAGCUAUCACAUGUCCACUAGGGACUCCAGAAGAAGACCCUACCUAUGCCUGUGUUUGCAGGUGAGAAGUUGGCAGUCGGUUAGCCUGGG
- example_title: H3 clustered histone 1
  output:
    text: '.....(((((..((((((.............[[......))))))]])))))......'
  pipeline_tag: rna-secondary-structure
  sequence_type: 3' UTR
  task: rna-secondary-structure
  text: UUACUGUGGUCUCUCUGACGGUCCAAGCAAAGGCUCUUUUCAGAGCCACCACCUUUUC
---

# UFold

Pre-trained model for RNA secondary structure prediction using an image-like sequence representation and a U-Net.

## Disclaimer

This is an UNOFFICIAL implementation of [UFold: fast and accurate RNA secondary structure prediction with deep learning](https://doi.org/10.1093/nar/gkab1074) by Laiyi Fu, Yingxin Cao, et al.

The OFFICIAL repository of UFold is at [uci-cbcl/UFold](https://github.com/uci-cbcl/UFold).

> [!TIP]
> The MultiMolecule implementation is a direct PyTorch port of the original U-Net architecture and feature construction.

**The team releasing UFold did not write this model card for this model so this model card has been written by the MultiMolecule team.**

## Model Details

UFold predicts RNA base-pair contact maps from single RNA sequences. It represents a sequence as a 17-channel image: 16 channels are outer products of one-hot nucleotide indicators and one channel is a hand-crafted canonical/wobble pairing score. A U-Net predicts a symmetric contact score matrix, and the original constrained post-processing routine can be enabled to enforce base-pairing constraints.

### Model Specification

| Num Parameters (M) | FLOPs (G) | MACs (G) |
| ------------------ | --------- | -------- |
| 8.64               | 188.29    | 93.81    |

FLOPs and MACs are computed with `multimolecule.utils` for one 600 nt sequence.

### Links

- **Code**: [multimolecule.ufold](https://github.com/DLS5-Omics/multimolecule/tree/master/multimolecule/models/ufold)
- **Weights**: [multimolecule/ufold](https://huggingface.co/multimolecule/ufold)
- **Paper**: [UFold: fast and accurate RNA secondary structure prediction with deep learning](https://doi.org/10.1093/nar/gkab1074)
- **Developed by**: Laiyi Fu, Yingxin Cao, Jie Wu, Qinke Peng, Qing Nie, Xiaohui Xie
- **Original Repository**: [uci-cbcl/UFold](https://github.com/uci-cbcl/UFold)

## Usage

The model file depends on the [`multimolecule`](https://multimolecule.danling.org) library. You can install it using pip:

```bash
pip install multimolecule
```

### RNA Secondary Structure Pipeline

```python
import multimolecule
from transformers import pipeline

predictor = pipeline("rna-secondary-structure", model="multimolecule/ufold")
output = predictor("GGGCUAUUAGCUCAGUUGGUUAGAGCGCACCCCUGAUAAGGGUGAGGUCGCUGAUUCGAAUUCAGCAUAGCUCA")
```

### PyTorch Inference

```python
from multimolecule import RnaTokenizer, UfoldModel

tokenizer = RnaTokenizer.from_pretrained("multimolecule/ufold")
model = UfoldModel.from_pretrained("multimolecule/ufold")

sequence = "GGGCUAUUAGCUCAGUUGGUUAGAGCGCACCCCUGAUAAGGGUGAGGUCGCUGAUUCGAAUUCAGCAUAGCUCA"
inputs = tokenizer(sequence, return_tensors="pt")
output = model(**inputs)

contact_map = output.contact_map
```

To run the original constrained post-processing loop:

```python
output = model(**inputs, use_postprocessing=True)
contact_map = output.postprocessed_contact_map
```

## Training Details

UFold was trained for RNA secondary structure prediction from annotated contact maps and base-pairing rules.

### Training Data

- RNAStrAlign: 30,451 unique RNAs from eight RNA families; the paper reports a random split with 24,895 training RNAs and 2,854 test RNAs after redundancy filtering.
- bpRNA-1m: 102,318 RNAs from 2,588 families; CD-HIT was used to remove redundant sequences before splitting the data into TR0 and TS0.
- augmented data: synthetic training examples were generated from bpRNA-new sequences by random mutation and structure prediction.
- PDB training data: high-resolution RNA structures from bpRNA and the PDB were used for fine-tuning/evaluation experiments; test sets TS1, TS2, and TS3 were filtered at 80% sequence identity.
- evaluation data: ArchiveII, TS0, bpRNA-new, and PDB test data were used for benchmark evaluation.

### Training Procedure

- input representation: 16 outer-product channels following the MultiMolecule tokenizer order plus one hand-crafted pairing-score channel.
- objective: weighted binary cross entropy over base-pair contact maps.
- optimizer: Adam.
- training epochs: 100.
- batch size: 1.
- positive-class weight: 300.
- post-processing: constrained optimization with canonical/wobble pairing rules, sparsity shrinkage, and a 0.5 threshold.

## Citation

```bibtex
@article{fu2022ufold,
  author = {Fu, Laiyi and Cao, Yingxin and Wu, Jie and Peng, Qinke and Nie, Qing and Xie, Xiaohui},
  title = {UFold: fast and accurate RNA secondary structure prediction with deep learning},
  journal = {Nucleic Acids Research},
  volume = {50},
  number = {3},
  pages = {e14},
  year = {2022},
  doi = {10.1093/nar/gkab1074}
}
```

> [!NOTE]
> The artifacts distributed in this repository are part of the MultiMolecule project.
> If MultiMolecule supports your research, please cite the MultiMolecule project as follows:

```bibtex
@software{chen_2024_12638419,
  author    = {Chen, Zhiyuan and Zhu, Sophia Y.},
  title     = {MultiMolecule},
  doi       = {10.5281/zenodo.12638419},
  publisher = {Zenodo},
  url       = {https://doi.org/10.5281/zenodo.12638419},
  year      = 2024,
  month     = may,
  day       = 4
}
```

## Contact

Please use GitHub issues of [MultiMolecule](https://github.com/DLS5-Omics/multimolecule/issues) for any questions or comments on the model card.

Please contact the authors of the [UFold paper](https://doi.org/10.1093/nar/gkab1074) for questions or comments on the paper/model.

## License

This model implementation is licensed under the [GNU Affero General Public License](license.md).

For additional terms and clarifications, please refer to our [License FAQ](license-faq.md).

```spdx
SPDX-License-Identifier: AGPL-3.0-or-later
```