{"id":5464,"date":"2022-03-02T20:00:00","date_gmt":"2022-03-02T20:00:00","guid":{"rendered":"https:\/\/www.aiproblog.com\/index.php\/2022\/03\/02\/machine-learning-can-help-read-the-language-of-life\/"},"modified":"2022-03-02T20:00:00","modified_gmt":"2022-03-02T20:00:00","slug":"machine-learning-can-help-read-the-language-of-life","status":"publish","type":"post","link":"https:\/\/www.aiproblog.com\/index.php\/2022\/03\/02\/machine-learning-can-help-read-the-language-of-life\/","title":{"rendered":"Machine learning can help read the language of life"},"content":{"rendered":"<p>Author: <\/p>\n<div>\n<div class=\"block-paragraph\">\n<div class=\"rich-text\">\n<p>DNA is the language of life: our DNA forms a living record of things that went well for our ancestors, and things that didn\u2019t. DNA tells our body (and every other organism) which proteins to produce; these proteins are tiny machines that carry out enormous tasks, from fighting off infection to helping you ace an upcoming exam in school.<\/p>\n<\/div>\n<\/div>\n<div class=\"block-paragraph\">\n<div class=\"rich-text\">\n<p>But for about a third of all proteins that all organisms produce, we just don\u2019t know what they do. It\u2019s kind of like we\u2019re in a factory where everything\u2019s buzzing, and we\u2019re surrounded by all these impressive tools, but we have only a vague idea of what\u2019s going on. Understanding how these tools operate, and how we can use them, is where we think machine learning can make a big difference.<\/p>\n<\/div>\n<\/div>\n<div class=\"block-image_full_width\">\n<div class=\"h-c-page\">\n<div class=\" article-image__is-caption h-c-grid__col-l--6 h-c-grid__col--8 h-c-grid__col-l--offset-3 h-c-grid__col--offset-2 \"><video alt=\"A previously solved protein structure\" autoplay=\"\" class=\"article-image__media\" loop=\"\" muted=\"\" playsinline=\"\" src=\"https:\/\/storage.googleapis.com\/gweb-uniblog-publish-prod\/original_videos\/trimmed_rotating_trpcf_480_2.mp4\" tabindex=\"0\" title=\"a depiction of a revolving model of a previously-solved protein structure\" type=\"video\/mp4\">Video format not supported<\/video><\/div><figcaption class=\"article-image__caption article-image__is-caption-image h-c-grid__col--8 h-c-grid__col--offset-2 h-c-grid__col-l--6 h-c-grid__col-l--offset-3\">\n<div class=\"rich-text\">\n<p>An example of a previously-solved protein structure (E. coli TrpCF) and the area where our AI makes predictions of its function. This protein produces tryptophan, which is a chemical that&#8217;s required in your diet to keep your body and brain running.<\/p>\n<\/div>\n<\/figcaption><\/div>\n<\/div>\n<div class=\"block-paragraph\">\n<div class=\"rich-text\">\n<p>Recently, DeepMind showed that AlphaFold can <a href=\"https:\/\/deepmind.com\/blog\/article\/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology\">predict the shape of protein machinery<\/a> with unprecedented accuracy. The shape of a protein provides very strong clues as to how the protein machinery can be used, but doesn\u2019t completely solve this question. So we asked ourselves: can we predict what function a protein performs?<\/p>\n<\/div>\n<\/div>\n<div class=\"block-paragraph\">\n<div class=\"rich-text\">\n<p>In our <a href=\"http:\/\/rdcu.be\/cHsqz\">Nature Biotechnology<\/a> article, we describe how neural networks can reliably reveal the function of this \u201cdark matter\u201d of the protein universe, outperforming state-of-the-art methods. We worked closely with internationally recognized experts at the <a href=\"https:\/\/www.ebi.ac.uk\/\">European Bioinformatics Institute<\/a> to annotate 6.8 million more protein regions in the Pfam v34.0 database release, a global repository for protein families and their function. These annotations exceed the expansion of the database over the last decade, and will enable the 2.5 million life-science researchers around the world to discover new antibodies, enzymes, foods, and therapeutics.<\/p>\n<\/div>\n<\/div>\n<div class=\"block-image_full_width\">\n<div class=\"h-c-page\">\n<div class=\" article-image__is-caption h-c-grid__col-l--6 h-c-grid__col--8 h-c-grid__col-l--offset-3 h-c-grid__col--offset-2 \"><img decoding=\"async\" alt=\"a chart showing the growth of the Pfam database\" class=\"article-image--large\" src=\"https:\/\/storage.googleapis.com\/gweb-uniblog-publish-prod\/original_images\/ezgif-3-2fbce907a7.gif\" tabindex=\"0\"><\/div><figcaption class=\"article-image__caption article-image__is-caption-image h-c-grid__col--8 h-c-grid__col--offset-2 h-c-grid__col-l--6 h-c-grid__col-l--offset-3\">\n<div class=\"rich-text\">\n<p>The Pfam database is a large collection of protein families and their sequences. Our ML models helped annotate 6.8 million more protein regions in the database.<\/p>\n<\/div>\n<\/figcaption><\/div>\n<\/div>\n<div class=\"block-paragraph\">\n<div class=\"rich-text\">\n<p>We also understand there\u2019s a reproducibility crisis in science, and we want to be part of the solution \u2014 not the problem. To make our research more accessible and useful, we\u2019re excited to <a href=\"https:\/\/google-research.github.io\/proteinfer\/\">launch an interactive scientific article<\/a> where you can play with our ML models \u2014 getting results in real time, all in your web browser, with no setup required.<\/p>\n<\/div>\n<\/div>\n<div class=\"block-paragraph\">\n<div class=\"rich-text\">\n<p>Google has always set out to help organize the world\u2019s information, and to make it useful to everyone. Equity in access to the appropriate technology and useful instruction for all scientists is an important part of this mission. This is why we\u2019re committed to making these models useful and accessible. Because, who knows, one of these proteins could unlock the solution to antibiotic resistance, and it\u2019s sitting right under our noses.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><a href=\"https:\/\/blog.google\/technology\/ai\/machine-learning-can-help-read-language-life\/\">Go to Source<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Author: DNA is the language of life: our DNA forms a living record of things that went well for our ancestors, and things that didn\u2019t. [&hellip;] <span class=\"read-more-link\"><a class=\"read-more\" href=\"https:\/\/www.aiproblog.com\/index.php\/2022\/03\/02\/machine-learning-can-help-read-the-language-of-life\/\">Read More<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":5465,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_bbp_topic_count":0,"_bbp_reply_count":0,"_bbp_total_topic_count":0,"_bbp_total_reply_count":0,"_bbp_voice_count":0,"_bbp_anonymous_reply_count":0,"_bbp_topic_count_hidden":0,"_bbp_reply_count_hidden":0,"_bbp_forum_subforum_count":0,"footnotes":""},"categories":[24],"tags":[],"_links":{"self":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/5464"}],"collection":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/comments?post=5464"}],"version-history":[{"count":0,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/posts\/5464\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media\/5465"}],"wp:attachment":[{"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/media?parent=5464"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/categories?post=5464"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.aiproblog.com\/index.php\/wp-json\/wp\/v2\/tags?post=5464"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}