{"id":4961,"date":"2020-02-24T19:15:20","date_gmt":"2020-02-24T10:15:20","guid":{"rendered":"http:\/\/163.180.4.222\/lab\/?p=4961"},"modified":"2020-02-24T19:15:20","modified_gmt":"2020-02-24T10:15:20","slug":"powerful-antibiotics-discovered-using-ai","status":"publish","type":"post","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=4961","title":{"rendered":"Powerful antibiotics discovered using AI"},"content":{"rendered":"<p>&nbsp;<\/p>\n<h5><\/h5>\n<h5>Machine learning spots molecules that work even against \u2018untreatable\u2019 strains of bacteria.<\/h5>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<div class=\"article__body serif cleared\">\n<figure class=\"figure\">\n<div class=\"embed intensity--high\">\n<div class=\"embed intensity--high\"><img decoding=\"async\" class=\"figure__image\" src=\"https:\/\/media.nature.com\/lw800\/magazine-assets\/d41586-020-00018-3\/d41586-020-00018-3_17728252.jpg\" alt=\"Coloured scanning electron micrograph (SEM) of Escherichia coli bacteria (green) taken from the small intestine of a child.\" data-src=\"\/\/media.nature.com\/lw800\/magazine-assets\/d41586-020-00018-3\/d41586-020-00018-3_17728252.jpg\" \/><\/div>\n<\/div><figcaption>\n<p class=\"figure__caption sans-serif\"><span class=\"mr10\"><i>Escherichia coli<\/i>\u00a0bacteria, coloured green, in a scanning electron micrograph.<\/span>Credit: Stephanie Schuller\/SPL<\/p>\n<\/figcaption><\/figure>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>A pioneering machine-learning approach has identified powerful new types of antibiotic from a pool of more than 100 million molecules \u2014 including one that works against a wide range of bacteria, including tuberculosis and strains considered untreatable.<\/p>\n<p>&nbsp;<\/p>\n<aside class=\"recommended pull pull--left sans-serif\" data-label=\"Related\"><a href=\"https:\/\/www.nature.com\/news\/antibiotic-resistance-has-a-language-problem-1.21915\" data-track=\"click\" data-track-label=\"recommended article\"><img decoding=\"async\" class=\"recommended__image\" src=\"https:\/\/media.nature.com\/w400\/magazine-assets\/d41586-020-00018-3\/d41586-020-00018-3_15296878.jpg\" \/><\/a><\/p>\n<p class=\"recommended__title serif\">Antibiotic resistance has a language problem<\/p>\n<\/aside>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>The researchers say the antibiotic, called halicin, is the first discovered with artificial intelligence (AI). Although AI has been used to aid parts of the antibiotic-discovery process before, they say that this is the first time it has identified completely new kinds of antibiotic from scratch, without using any previous human assumptions. The work, led by synthetic biologist Jim Collins at the Massachusetts Institute of Technology in Cambridge, is published in\u00a0<i>Cell<\/i><sup><a href=\"https:\/\/www.nature.com\/articles\/d41586-020-00018-3?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+nature%2Frss%2Fcurrent+%28Nature+-+Issue%29#ref-CR1\" data-track=\"click\" data-action=\"anchor-link\" data-track-label=\"go to reference\" data-track-category=\"references\">1<\/a><\/sup>.<\/p>\n<p>The study is remarkable, says Jacob Durrant, a computational biologist at the University of Pittsburgh, Pennsylvania. The team didn\u2019t just identify candidates, but also validated promising molecules in animal tests, he says. What\u2019s more, the approach could also be applied to other types of drug, such as those used to treat cancer or neurodegenerative diseases, says Durrant.<\/p>\n<p>Bacterial resistance to antibiotics is rising dramatically worldwide, and researchers predict that unless new drugs are developed urgently,\u00a0<a href=\"https:\/\/www.nature.com\/articles\/d41586-019-01409-x\" data-track=\"click\" data-label=\"https:\/\/www.nature.com\/articles\/d41586-019-01409-x\" data-track-category=\"body text link\">resistant infections could kill ten million people per year by 2050<\/a>. But over the past few decades, the discovery and regulatory approval of new antibiotics has slowed. \u201cPeople keep finding the same molecules over and over,\u201d says Collins. \u201cWe need novel chemistries with novel mechanisms of action.\u201d<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h2>Forget your assumptions<\/h2>\n<p>&nbsp;<\/p>\n<p>Collins and his team developed a neural network \u2014 an AI algorithm inspired by the brain\u2019s architecture \u2014 that learns the properties of molecules atom by atom.<\/p>\n<p>The researchers trained its neural network to spot molecules that inhibit the growth of the bacterium\u00a0<i>Escherichia coli<\/i>, using a collection of 2,335 molecules for which the antibacterial activity was known. This includes a library of about 300 approved antibiotics, as well as 800 natural products from plant, animal and microbial sources.<\/p>\n<p>The algorithm learns to predict molecular function without any assumptions about how drugs work and without chemical groups being labelled, says Regina Barzilay, an AI researcher at MIT and a co-author of the study. \u201cAs a result, the model can learn new patterns unknown to human experts.\u201d<\/p>\n<p>Once the model was trained, the researchers used it to screen a library called the Drug Repurposing Hub, which contains around 6,000 molecules under investigation for human diseases. They asked it to predict which would be effective against\u00a0<i>E. coli<\/i>, and to show them only molecules that look different from conventional antibiotics.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<aside class=\"recommended pull pull--left sans-serif\" data-label=\"Related\"><a href=\"https:\/\/www.nature.com\/news\/resistance-to-last-ditch-antibiotic-has-spread-farther-than-anticipated-1.22140\" data-track=\"click\" data-track-label=\"recommended article\"><img decoding=\"async\" class=\"recommended__image\" src=\"https:\/\/media.nature.com\/w400\/magazine-assets\/d41586-020-00018-3\/d41586-020-00018-3_15296882.jpg\" \/><\/a><\/p>\n<p class=\"recommended__title serif\">Resistance to last-ditch antibiotic has spread farther than anticipated<\/p>\n<\/aside>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>From the resulting hits, the researchers selected about 100 candidates for physical testing. One of these \u2014 a molecule being investigated as a diabetes treatment \u2014 turned out to be a potent antibiotic, which they called halicin after HAL, the intelligent computer in the film\u00a0<i>2001: A Space Odyssey<\/i>. In tests in mice, this molecule was active against a wide spectrum of pathogens, including a strain of\u00a0<i>Clostridioides difficile<\/i>\u00a0and one of\u00a0<i>Acinetobacter baumannii\u00a0<\/i>that is \u2018pan-resistant\u2019 and against which new antibiotics are urgently required.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h2>Proton block<\/h2>\n<p>&nbsp;<\/p>\n<p>Antibiotics work through a range of mechanisms, such as blocking the enzymes involved in cell-wall biosynthesis, DNA repair or protein synthesis. But halicin\u2019s mechanism is unconventional: it disrupts the flow of protons across a cell membrane. In initial animal tests, it also seemed to have low toxicity and be robust against resistance. In experiments, resistance to other antibiotic compounds typically arises within a day or two, says Collins. \u201cBut even after 30 days of such testing we didn\u2019t see any resistance against halicin.\u201d<\/p>\n<p>The team then screened more than 107 million molecular structures in a database called ZINC15. From a shortlist of 23, physical tests identified 8 with antibacterial activity. Two of these had potent activity against a broad range of pathogens, and could overcome even antibiotic-resistant strains of\u00a0<i>E. coli<\/i>.<\/p>\n<p>The study is \u201ca great example of the growing body of work using computational methods to discover and predict properties of potential drugs\u201d, says Bob Murphy, a computational biologist at Carnegie Mellon University in Pittsburgh. He notes that AI methods have previously been developed to mine huge databases of genes and metabolites to identify molecule types that could include new antibiotics<sup><a href=\"https:\/\/www.nature.com\/articles\/d41586-020-00018-3?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+nature%2Frss%2Fcurrent+%28Nature+-+Issue%29#ref-CR2\" data-track=\"click\" data-action=\"anchor-link\" data-track-label=\"go to reference\" data-track-category=\"references\">2<\/a><\/sup><sup>,<\/sup><sup><a href=\"https:\/\/www.nature.com\/articles\/d41586-020-00018-3?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+nature%2Frss%2Fcurrent+%28Nature+-+Issue%29#ref-CR3\" data-track=\"click\" data-action=\"anchor-link\" data-track-label=\"go to reference\" data-track-category=\"references\">3<\/a><\/sup>.<\/p>\n<p>But Collins and his team say that their approach is different \u2014 rather than search for specific structures or molecular classes, they\u2019re training their network to look for molecules with a particular activity. The team is now hoping to partner with an outside group or company to get halicin into clinical trials. It also wants to broaden the approach to find more new antibiotics, and design molecules from scratch. Barzilay says their latest work is a proof of concept. \u201cThis study puts it all together and demonstrates what it can do.\u201d<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<\/div>\n<div class=\"emphasis\">doi: 10.1038\/d41586-020-00018-3<\/div>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>(\uc6d0\ubb38: <a href=\"https:\/\/www.nature.com\/articles\/d41586-020-00018-3?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+nature%2Frss%2Fcurrent+%28Nature+-+Issue%29\">\uc5ec\uae30<\/a>\ub97c \ud074\ub9ad\ud558\uc138\uc694~)<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&nbsp; Machine learning spots molecules that work even against \u2018untreatable\u2019 strains of bacteria. &nbsp; &nbsp; Escherichia coli\u00a0bacteria, coloured green, in a scanning electron micrograph.Credit: Stephanie<a href=\"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=4961\" class=\"more-link\">(more&#8230;)<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2},"jetpack_post_was_ever_published":false},"categories":[33,35,29],"tags":[],"class_list":["post-4961","post","type-post","status-publish","format-standard","hentry","category-do-biology","category-lets-do-computer-science","category-lets-do-science"],"aioseo_notices":[],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":4197,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=4197","url_meta":{"origin":4961,"position":0},"title":"DNA pushes back the microbiome frontier","author":"biochemistry","date":"October 6, 2019","format":false,"excerpt":"\u00a0 \u00a0 Over the past 15 years, researchers have come to appreciate how profoundly the diverse zoo of microbes in the human gut, skin, and mouth affects our health. But their identities and exactly how they exert their effects have remained mysterious. Now, two research groups have made this microbial\u2026","rel":"","context":"In &quot;Let's Do Biology!&quot;","block_context":{"text":"Let's Do Biology!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=33"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":3815,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=3815","url_meta":{"origin":4961,"position":1},"title":"Microbes make metabolic mischief by targeting drugs","author":"biochemistry","date":"June 19, 2019","format":false,"excerpt":"\u00a0 \u00a0 Tests of whether a range of gut bacteria can metabolize a diverse group of drugs has revealed that all the microbes metabolized some drugs and that more than half of the drugs were metabolized. \u00a0 \u00a0 All humans are different and, unsurprisingly, also differ in their response to\u2026","rel":"","context":"In &quot;Let's Do Biology!&quot;","block_context":{"text":"Let's Do Biology!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=33"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":3874,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=3874","url_meta":{"origin":4961,"position":2},"title":"Machine-learning-assisted selection of antibiotic prescription","author":"biochemistry","date":"July 12, 2019","format":false,"excerpt":"\u00a0 \u00a0 Machine learning can use patients\u2019 demographic information and previous clinical history to help physicians select the antibiotics most likely to successfully treat urinary tract infections, despite growing levels of resistance. \u00a0 \u00a0 Recent years have seen a worrying increase in the levels of antibiotic resistance of many bacterial\u2026","rel":"","context":"In &quot;Let's Do Biology!&quot;","block_context":{"text":"Let's Do Biology!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=33"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":3813,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=3813","url_meta":{"origin":4961,"position":3},"title":"Selective killing of antibiotic-resistant bacteria from within","author":"biochemistry","date":"June 19, 2019","format":false,"excerpt":"\u00a0 \u00a0 Some bacteria naturally transfer pieces of their DNA within and between species. Such a piece of DNA has been engineered to act as a molecular \u2018Trojan horse\u2019 that unleashes a toxin to selectively kill antibiotic-resistant\u00a0Vibrio cholerae\u00a0bacteria. \u00a0 \u00a0 Antibiotic resistance among infectious bacteria is an increasing problem worldwide,\u2026","rel":"","context":"In &quot;Let's Do Biology!&quot;","block_context":{"text":"Let's Do Biology!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=33"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":3407,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=3407","url_meta":{"origin":4961,"position":4},"title":"Deciphering bacterial signalling","author":"biochemistry","date":"April 23, 2019","format":false,"excerpt":"\u00a0 \u00a0 Bacterial communication is a potential strategy to control bacterial behaviours and thus, attenuate pathogen infectivity; however, identifying the signalling molecules that regulate communication pathways is challenging. Now, a robust strategy to rapidly identify previously unknown signalling peptides has been developed. This approach provides a means to map out\u2026","rel":"","context":"In &quot;Let's Do Biology!&quot;","block_context":{"text":"Let's Do Biology!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=33"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":472,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=472","url_meta":{"origin":4961,"position":5},"title":"How gut microbes are joining the fight against cancer","author":"biochemistry","date":"May 30, 2018","format":false,"excerpt":"\u00a0 \u00a0 (\uc6d0\ubb38) \u00a0 \u00a0 The intestinal microbiome seems to influence how well some cancer drugs work. But is the science ripe for clinical trials? \u00a0 \u00a0 \u00a0 Illustration by Ola Niepsuj Bertrand Routy earned a lamentable reputation with Parisian oncologists in 2015. A doctoral student at the nearby Gustave\u2026","rel":"","context":"In &quot;Let's Do Biology!&quot;","block_context":{"text":"Let's Do Biology!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=33"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"jetpack_sharing_enabled":false,"jetpack_shortlink":"https:\/\/wp.me\/p9Xo1j-1i1","_links":{"self":[{"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts\/4961","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4961"}],"version-history":[{"count":1,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts\/4961\/revisions"}],"predecessor-version":[{"id":4962,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts\/4961\/revisions\/4962"}],"wp:attachment":[{"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4961"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4961"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4961"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}