{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:05:25Z","timestamp":1785423925941,"version":"3.56.0"},"posted":{"date-parts":[[2026,1,23]]},"group-title":"Bioinformatics","reference-count":29,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T00:00:00Z","timestamp":1769126400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"NIH","award":["K25CA270079"],"award-info":[{"award-number":["K25CA270079"]}]},{"name":"NIH","award":["P20GM162339."],"award-info":[{"award-number":["P20GM162339."]}]},{"name":"NSF","award":["2443386"],"award-info":[{"award-number":["2443386"]}]},{"name":"NSF","award":["2341725"],"award-info":[{"award-number":["2341725"]}]},{"award":["BIC2.0"],"award-info":[{"award-number":["BIC2.0"]}],"id":[{"id":"https:\/\/ror.org\/02aqsxs83","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,7,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Colorectal tumorigenesis follows stepwise mutational progression patterns, but inferring dependencies from mutation data remains challenging. We propose a directed co-occurrence asymmetry graph to infer graph-derived mutational paths from 2,344 colon adenocarcinoma samples covering 23,858 mutated genes.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce a gene-conditioned shared Long Short-Term Memory (LSTM) model with attention to predict mutation status along inferred paths. The attention mechanism learns to weight informative predecessor mutations directly, while gene embeddings adapt the shared model to each target gene. We compare this model with standard per-gene LSTM and dilated Convolutional Neural Network (CNN) architectures. Graph-derived paths substantially improved precision and recall over the reproduced frequency-ordering baseline, with weighted paths performing best overall. The attention-based shared LSTM achieved competitive area under the ROC curve (AUC) and high recall, indicating that attention over predecessor mutations provides a useful representation for target-gene prediction.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Code and data<\/jats:title>\n                  <jats:p>\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/github.com\/moussa-lab\/MutationPrediction\">github.com\/moussa-lab\/MutationPrediction<\/jats:ext-link>\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.01.22.701121","type":"posted-content","created":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T00:20:15Z","timestamp":1769214015000},"source":"Crossref","is-referenced-by-count":0,"title":["Predicting Gene Mutations in Colon Cancer Using Long-Term Temporal Dependency Learning on a Directed Co-Occurrence Asymmetry Graph"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8402-6815","authenticated-orcid":false,"given":"Collin","family":"Sumrell","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Oklahoma, Norman, OK 73019, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8593-3839","authenticated-orcid":false,"given":"Aleksandr","family":"Shishkin","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Oklahoma, Norman, OK 73019, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ekene","family":"Okeke","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Georgia State University, Atlanta, GA 30303, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4424-4691","authenticated-orcid":false,"given":"Alexander","family":"Zelikovsky","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Georgia State University, Atlanta, GA 30303, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0574-6656","authenticated-orcid":false,"given":"Marmar R.","family":"Moussa","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Oklahoma, Norman, OK 73019, United States"},{"name":"Stephenson School of Biomedical Engineering, University of Oklahoma, Norman, OK 73019, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026070907101029000_2026.01.22.701121v2.1","unstructured":"M. B. Amin , S. B. Edge , F. L. Greene , et al. , editors. AJCC Cancer Staging Manual. Springer, New York, 8th edition, 2017."},{"key":"2026070907101029000_2026.01.22.701121v2.2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1901695116"},{"key":"2026070907101029000_2026.01.22.701121v2.3","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"2026070907101029000_2026.01.22.701121v2.4","doi-asserted-by":"publisher","DOI":"10.1038\/nature11252"},{"key":"2026070907101029000_2026.01.22.701121v2.5","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-12-0095"},{"key":"2026070907101029000_2026.01.22.701121v2.6","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.Can-23-0816"},{"key":"2026070907101029000_2026.01.22.701121v2.7","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(93)90079-O"},{"key":"2026070907101029000_2026.01.22.701121v2.8","doi-asserted-by":"publisher","DOI":"10.1016\/0092-8674(90)90186-I"},{"issue":"7","key":"2026070907101029000_2026.01.22.701121v2.9","doi-asserted-by":"crossref","first-page":"745","DOI":"10.15252\/emmm.201606184","article-title":"Tgf\u03b2 signaling directs serrated adenomas to the mesenchymal colorectal cancer subtype","volume":"8","year":"2016","journal-title":"EMBO molecular medicine"},{"key":"2026070907101029000_2026.01.22.701121v2.10","doi-asserted-by":"publisher","DOI":"10.1126\/scisignal.2004088"},{"key":"2026070907101029000_2026.01.22.701121v2.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2016.03.075"},{"key":"2026070907101029000_2026.01.22.701121v2.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-021-00791-5"},{"key":"2026070907101029000_2026.01.22.701121v2.13","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2026070907101029000_2026.01.22.701121v2.14","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"2026070907101029000_2026.01.22.701121v2.15","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2015-310784"},{"key":"2026070907101029000_2026.01.22.701121v2.16","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0712345105"},{"key":"2026070907101029000_2026.01.22.701121v2.17","unstructured":"D. P. Kingma and J. Ba . Adam: A method for stochastic opti-mization. 2017. URL https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"2026070907101029000_2026.01.22.701121v2.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.032"},{"key":"2026070907101029000_2026.01.22.701121v2.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2020.08.002"},{"key":"2026070907101029000_2026.01.22.701121v2.20","unstructured":"T. Lin , P. Goyal , R. B. Girshick , K. He , and P. Doll\u00e1r . Focal loss for dense object detection. CoRR, abs\/1708.02002, 2017. URL http:\/\/arxiv.org\/abs\/1708.02002."},{"key":"2026070907101029000_2026.01.22.701121v2.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02324-5"},{"key":"2026070907101029000_2026.01.22.701121v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/nature11282"},{"key":"2026070907101029000_2026.01.22.701121v2.23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1359"},{"key":"2026070907101029000_2026.01.22.701121v2.24","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1981.4308636"},{"key":"2026070907101029000_2026.01.22.701121v2.25","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41695-z"},{"key":"2026070907101029000_2026.01.22.701121v2.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.03.030"},{"key":"2026070907101029000_2026.01.22.701121v2.27","doi-asserted-by":"publisher","DOI":"10.1126\/science.1235122"},{"key":"2026070907101029000_2026.01.22.701121v2.28","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1963.10500845"},{"key":"2026070907101029000_2026.01.22.701121v2.29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.01.22.701121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T14:10:19Z","timestamp":1783606219000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.01.22.701121"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,23]]},"references-count":29,"URL":"https:\/\/doi.org\/10.64898\/2026.01.22.701121","relation":{},"subject":[],"published":{"date-parts":[[2026,1,23]]},"subtype":"preprint"}}