{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:25:51Z","timestamp":1776374751906,"version":"3.51.2"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T00:00:00Z","timestamp":1730851200000},"content-version":"vor","delay-in-days":44,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32470995\uff0c62376254"],"award-info":[{"award-number":["32470995\uff0c62376254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32341018"],"award-info":[{"award-number":["32341018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of China & the Bill & Melinda Gates Foundation","award":["72361127503"],"award-info":[{"award-number":["72361127503"]}]},{"DOI":"10.13039\/501100007156","name":"Hong Kong Innovation and Technology Fund","doi-asserted-by":"crossref","award":["ITS\/241\/21"],"award-info":[{"award-number":["ITS\/241\/21"]}],"id":[{"id":"10.13039\/501100007156","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The clinical adoption of small interfering RNAs (siRNAs) has prompted the development of various computational strategies for siRNA design, from traditional data analysis to advanced machine learning techniques. However, previous studies have inadequately considered the full complexity of the siRNA silencing mechanism, neglecting critical elements such as siRNA positioning on mRNA, RNA base-pairing probabilities, and RNA\u2013AGO2 interactions, thereby limiting the insight and accuracy of existing models. Here, we introduce siRNADiscovery, a Graph Neural Network (GNN) framework that leverages both non-empirical and empirical rule-based features of siRNA and mRNA to effectively capture the complex dynamics of gene silencing. On multiple internal datasets, siRNADiscovery achieves state-of-the-art performance. Significantly, siRNADiscovery also outperforms existing methodologies in in vitro studies and on an externally validated dataset. Additionally, we develop a new data-splitting methodology that addresses the data leakage issue, a frequently overlooked problem in previous studies, ensuring the robustness and stability of our model under various experimental settings. Through rigorous testing, siRNADiscovery has demonstrated remarkable predictive accuracy and robustness, making significant contributions to the field of gene silencing. Furthermore, our approach to redefining data-splitting standards aims to set new benchmarks for future research in the domain of predictive biological modeling for siRNA.<\/jats:p>","DOI":"10.1093\/bib\/bbae563","type":"journal-article","created":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T07:19:32Z","timestamp":1729495172000},"source":"Crossref","is-referenced-by-count":14,"title":["siRNADiscovery: a graph neural network for siRNA efficacy prediction via deep RNA sequence analysis"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3755-5491","authenticated-orcid":false,"given":"Rongzhuo","family":"Long","sequence":"first","affiliation":[{"name":"School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University , 211198, Nanjing ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9606-9691","authenticated-orcid":false,"given":"Ziyu","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong , Central Ave, Hong Kong SAR ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0804-2964","authenticated-orcid":false,"given":"Da","family":"Han","sequence":"additional","affiliation":[{"name":"Institute of Molecular Medicine (IMM) and Department of Laboratory Medicine , Renji Hospital, School of Medicine, , 200240, Shanghai ,","place":["China"]},{"name":"Shanghai Jiao Tong University , Renji Hospital, School of Medicine, , 200240, Shanghai ,","place":["China"]},{"name":"Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences , 310022, Hangzhou, Zhejiang ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2595-4463","authenticated-orcid":false,"given":"Boxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Pharmacy , Faculty of Science, , Singapore, 117543 ,","place":["Singapore"]},{"name":"National University of Singapore , Faculty of Science, , Singapore, 117543 ,","place":["Singapore"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8683-4297","authenticated-orcid":false,"given":"Xudong","family":"Yuan","sequence":"additional","affiliation":[{"name":"ACON Pharmaceuticals , 2557 Route 130 S, Ste 3, Cranbury, NJ 08512 ,","place":["USA"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5892-8608","authenticated-orcid":false,"given":"Guangyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang Lab , Ke Chuang Avenue, 311121, Zhejiang ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3055-5034","authenticated-orcid":false,"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Chinese University of Hong Kong , Central Ave, Hong Kong SAR ,","place":["China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1146-7848","authenticated-orcid":false,"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences , 310022, Hangzhou, Zhejiang ,","place":["China"]}]}],"member":"286","published-online":{"date-parts":[[2024,11,6]]},"reference":[{"key":"2024110611482016100_ref1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.tcb.2005.03.006","article-title":"RNA silencing and genome regulation","volume":"15","author":"Almeida","year":"2005","journal-title":"Trends Cell Biol"},{"key":"2024110611482016100_ref2","doi-asserted-by":"publisher","first-page":"48","DOI":"10.59566\/IJBS.2017.13048","article-title":"Molecular mechanisms and biological functions of siRNA","volume":"13","author":"Dana","year":"2017","journal-title":"Int J Biomed Sci"},{"key":"2024110611482016100_ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/5043984","article-title":"Utilizing selected Di-and trinucleotides of siRNA to predict RNAi activity","volume":"2017","author":"Han","year":"2017","journal-title":"Comput Math Methods Med"},{"key":"2024110611482016100_ref4","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1093\/bioinformatics\/btl026","article-title":"siRecords: an extensive database of mammalian siRNAs with efficacy ratings","volume":"22","author":"Ren","year":"2006","journal-title":"Bioinformatics"},{"key":"2024110611482016100_ref5","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.bbrc.2004.06.116","article-title":"A comparison of siRNA efficacy predictors","volume":"321","author":"S\u00e6trom","year":"2004","journal-title":"Biochem Biophys Res Commun"},{"key":"2024110611482016100_ref6","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1038\/nbt1118","article-title":"Design of a genome-wide siRNA library using an artificial neural network","volume":"23","author":"Huesken","year":"2005","journal-title":"Nat Biotechnol"},{"key":"2024110611482016100_ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-7-520","article-title":"An accurate and interpretable model for siRNA efficacy prediction","volume":"7","author":"Vert","year":"2006","journal-title":"BMC Bioinform"},{"key":"2024110611482016100_ref8","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm699","article-title":"Thermodynamic instability of siRNA duplex is a prerequisite for dependable prediction of siRNA activities","volume":"35","author":"Ichihara","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2024110611482016100_ref9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-015-0495-2","article-title":"A semi-supervised tensor regression model for siRNA efficacy prediction","volume":"16","author":"Thang","year":"2015","journal-title":"BMC Bioinform"},{"key":"2024110611482016100_ref10","doi-asserted-by":"publisher","first-page":"1226336","DOI":"10.3389\/fgene.2023.1226336","article-title":"Machine learning for small interfering rnas: a concise review of recent developments","volume":"14","author":"Lee","year":"2023","journal-title":"Front Genet"},{"key":"2024110611482016100_ref11","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1186\/s12864-018-5028-8","article-title":"siRNA silencing efficacy prediction based on a deep architecture","volume":"19","author":"Han","year":"2018","journal-title":"BMC Genom"},{"key":"2024110611482016100_ref12","doi-asserted-by":"publisher","first-page":"14211","DOI":"10.3390\/ijms232214211","article-title":"A graph neural network approach for the analysis of siRNA-target biological networks","volume":"23","author":"La Rosa","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2024110611482016100_ref13","doi-asserted-by":"publisher","first-page":"102208","DOI":"10.1016\/j.omtn.2024.102208","article-title":"Deep learning facilitates efficient optimization of antisense oligonucleotide drugs","volume":"35","author":"Lin","year":"2024","journal-title":"Mol Ther Nucleic Acids"},{"key":"2024110611482016100_ref14","doi-asserted-by":"publisher","first-page":"690049","DOI":"10.3389\/fgene.2021.690049","article-title":"Graph neural networks and their current applications in bioinformatics","volume":"12","author":"Zhang","year":"2021","journal-title":"Front Genet"},{"key":"2024110611482016100_ref15","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.bbrc.2004.04.027","article-title":"The gene-silencing efficiency of siRNA is strongly dependent on the local structure of mRNA at the targeted region","volume":"318","author":"Luo","year":"2004","journal-title":"Biochem Biophys Res Commun"},{"key":"2024110611482016100_ref16","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1038\/256505a0","article-title":"5S RNA secondary structure","volume":"256","author":"Fox","year":"1975","journal-title":"Nature"},{"key":"2024110611482016100_ref17","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.cmpb.2003.09.002","article-title":"OptiRNAi, an RNAi design tool","volume":"75","author":"Cui","year":"2004","journal-title":"Comput Methods Programs Biomed"},{"key":"2024110611482016100_ref18","doi-asserted-by":"publisher","first-page":"603","DOI":"10.15171\/apb.2017.072","article-title":"Strategies for improving siRNA-induced gene silencing efficiency","volume":"7","author":"Safari","year":"2017","journal-title":"Adv Pharm Bull"},{"key":"2024110611482016100_ref19","doi-asserted-by":"publisher","first-page":"e27602","DOI":"10.1371\/journal.pone.0027602","article-title":"siPRED: predicting siRNA efficacy using various characteristic methods","volume":"6","author":"Pan","year":"2011","journal-title":"PloS One"},{"key":"2024110611482016100_ref20","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1089\/108729003321629638","article-title":"Sequence, chemical, and structural variation of small interfering RNAs and short hairpin RNAs and the effect on mammalian gene silencing","volume":"13","author":"Harborth","year":"2003","journal-title":"Antisense Nucleic Acid Drug Dev"},{"key":"2024110611482016100_ref21","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1093\/nar\/gkh247","article-title":"Guidelines for the selection of highly effective siRNA sequences for mammalian and chick RnA interference","volume":"32","author":"Ui-Tei","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2024110611482016100_ref22","doi-asserted-by":"publisher","first-page":"7108","DOI":"10.1074\/jbc.M210326200","article-title":"Efficient reduction of target RNAs by small interfering RNA and RNase H-dependent antisense agents: a comparative analysis","volume":"278","author":"Vickers","year":"2003","journal-title":"J Biol Chem"},{"key":"2024110611482016100_ref23","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/S0092-8674(03)00801-8","article-title":"Functional siRNAs and miRNAs exhibit strand bias","volume":"115","author":"Khvorova","year":"2003","journal-title":"Cell"},{"key":"2024110611482016100_ref24","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1093\/nar\/gks1191","article-title":"Improved nucleic acid descriptors for siRNA efficacy prediction","volume":"41","author":"Sciabola","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2024110611482016100_ref25","doi-asserted-by":"publisher","first-page":"e48057","DOI":"10.1371\/journal.pone.0048057","article-title":"DSIR: assessing the design of highly potent siRNA by testing a set of cancer-relevant target genes","volume":"7","author":"Filhol","year":"2012","journal-title":"PloS One"},{"key":"2024110611482016100_ref26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1748-7188-6-26","article-title":"ViennaRNA package 2.0","volume":"6","author":"Lorenz","year":"2011","journal-title":"Algorithms Mol Biol"},{"key":"2024110611482016100_ref27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-12-489","article-title":"Predicting RNA-protein interactions using only sequence information","volume":"12","author":"Muppirala","year":"2011","journal-title":"BMC Bioinform"},{"key":"2024110611482016100_ref28","doi-asserted-by":"publisher","first-page":"14719","DOI":"10.1021\/bi9809425","article-title":"Thermodynamic parameters for an expanded nearest-neighbor model for formation of RNA duplexes with Watson\u2013Crick base pairs","volume":"37","author":"Xia","year":"1998","journal-title":"Biochemistry"},{"key":"2024110611482016100_ref29","doi-asserted-by":"publisher","first-page":"44836","DOI":"10.1038\/srep44836","article-title":"Predicting siRNA efficacy based on multiple selective siRNA representations and their combination at score level","volume":"7","author":"He","year":"2017","journal-title":"Sci Rep"},{"key":"2024110611482016100_ref30","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1016\/j.jmb.2005.03.011","article-title":"Local RNA target structure influences siRNA efficacy: systematic analysis of intentionally designed binding regions","volume":"348","author":"Schubert","year":"2005","journal-title":"J Mol Biol"},{"key":"2024110611482016100_ref31","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.jbiotec.2017.07.007","article-title":"Recent advances in RNA folding","volume":"261","author":"Fallmann","year":"2017","journal-title":"J Biotechnol"},{"key":"2024110611482016100_ref32","doi-asserted-by":"publisher","first-page":"6598","DOI":"10.1093\/nar\/gkm663","article-title":"Reduced levels of Ago2 expression result in increased siRNA competition in mammalian cells","volume":"35","author":"Vickers","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2024110611482016100_ref33","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.ygeno.2013.07.009","article-title":"The effect of regions flanking target site on siRNA potency","volume":"102","author":"Liu","year":"2013","journal-title":"Genomics"},{"key":"2024110611482016100_ref34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1479-5876-11-305","article-title":"VIRsiRNApred: a web server for predicting inhibition efficacy of siRNAs targeting human viruses","volume":"11","author":"Qureshi","year":"2013","journal-title":"J Transl Med"},{"key":"2024110611482016100_ref35","doi-asserted-by":"publisher","first-page":"S2","DOI":"10.1186\/1471-2164-11-S3-S2","article-title":"Predicting siRNA potency with random forests and support vector machines","volume":"11","author":"Wang","year":"2010","journal-title":"BMC Genom"},{"key":"2024110611482016100_ref36","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024110611482016100_ref37","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019. August 4-8, 2019"},{"key":"2024110611482016100_ref38","doi-asserted-by":"publisher","first-page":"e49309","DOI":"10.1371\/journal.pone.0049309","article-title":"siRNA has greatly elevated mismatch tolerance at 3-UTR sites","volume":"7","author":"Wei","year":"2012","journal-title":"PloS One"},{"key":"2024110611482016100_ref39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2013\/637850","article-title":"Comparison between the repression potency of siRNA targeting the coding region and the 3-untranslated region of mRNA","volume":"2013","author":"Lai","year":"2013","journal-title":"Biomed Res Int"},{"key":"2024110611482016100_ref40","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1093\/bib\/bbaa257","article-title":"Biological network analysis with deep learning","volume":"22","author":"Muzio","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024110611482016100_ref41","doi-asserted-by":"publisher","first-page":"W5","DOI":"10.1093\/nar\/gkn201","article-title":"Ncbi blast: a better web interface","volume":"36","author":"Johnson","year":"2008","journal-title":"Nucleic Acids Res"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae563\/60441414\/bbae563.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/25\/6\/bbae563\/60441414\/bbae563.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T06:49:35Z","timestamp":1730875775000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbae563\/7877280"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,23]]},"references-count":41,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,9,23]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbae563","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.04.28.591509","asserted-by":"object"}]},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,9,23]]},"article-number":"bbae563"}}