{"id":3170,"date":"2020-05-31T18:37:44","date_gmt":"2020-05-31T18:37:44","guid":{"rendered":"https:\/\/daslab-tmp.su.domains\/?p=3170"},"modified":"2024-08-01T18:45:07","modified_gmt":"2024-08-01T18:45:07","slug":"which-rna-secondary-structure-package-best-predicts-experimental-data-hannah-wayment-steele-used-high-throughput-structural-data-from-eterna-to-answer-this-question-and-found-a-suprising-r","status":"publish","type":"post","link":"https:\/\/daslab-tmp.su.domains\/?p=3170","title":{"rendered":"Which RNA secondary structure package best predicts experimental data?\u00a0Hannah Wayment-Steele\u00a0used high-throughput structural data from Eterna to answer this question, and found a suprising result: lesser-known packages developed by statistical learning performed notably better than more widely-used packages."},"content":{"rendered":"<p>Which RNA secondary structure package best predicts experimental data?\u00a0<b>Hannah Wayment-Steele<\/b>\u00a0used high-throughput structural data from Eterna to answer this question, and found a suprising result: lesser-known packages developed by statistical learning performed notably better than more widely-used packages. Motivated by these results, she developed a\u00a0<b>multi-task learning algorithm<\/b>\u00a0trained on Eterna data, named\u00a0<b>EternaFold<\/b>, which showed the best predictions on Eterna data as well as completely independent datasets of viral RNAs and synthetic mRNAs important for vaccine design. We hope that the EternaFold algorithm will be useful for improving RNA design, and that the\u00a0<b>EternaBench<\/b>\u00a0database will provide an independent platform to benchmark more improvements in secondary structure prediction.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Which RNA secondary structure package best predicts experimental data?\u00a0Hannah Wayment-Steele\u00a0used high-throughput structural data from Eterna to answer this question, and found a suprising result: lesser-known packages developed by statistical learning performed notably better than more widely-used packages. Motivated by these results, she developed a\u00a0multi-task learning algorithm\u00a0trained on Eterna data, named\u00a0EternaFold, which showed the best predictions [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":3206,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[],"class_list":["post-3170","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=\/wp\/v2\/posts\/3170","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3170"}],"version-history":[{"count":0,"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=\/wp\/v2\/posts\/3170\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=\/wp\/v2\/media\/3206"}],"wp:attachment":[{"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3170"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3170"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/daslab-tmp.su.domains\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3170"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}