{"id":1166,"date":"2018-07-19T03:01:44","date_gmt":"2018-07-19T03:01:44","guid":{"rendered":"http:\/\/163.180.4.222\/lab\/?p=1166"},"modified":"2019-10-14T14:37:38","modified_gmt":"2019-10-14T05:37:38","slug":"listen-ai-robot-mixes-chemicals-to-discover-reactions","status":"publish","type":"post","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=1166","title":{"rendered":"Listen: AI robot mixes chemicals to discover reactions"},"content":{"rendered":"<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>(<a href=\"https:\/\/www.nature.com\/articles\/d41586-018-05776-9?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+nature%2Frss%2Fcurrent+%28Nature+-+Issue%29\">\uc6d0\ubb38<\/a>)<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h6>Automated machine conducts, assesses and learns from experiments with random reagents.<\/h6>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<header class=\"article-item__header clear cleared pull--both\">\n<div class=\"article-item__teaser-text serif\"><\/div>\n<\/header>\n<div class=\"align-left\">\n<div class=\"article__body serif cleared\">\n<div class=\"embed intensity--high\">\n<div class=\"ratio--16-9\"><iframe src=\"https:\/\/www.youtube.com\/embed\/qndZ5_VFLdc\" frameborder=\"0\" allowfullscreen=\"allowfullscreen\" data-mce-fragment=\"1\"><\/iframe><\/div>\n<\/div>\n<p>Reporter Adam Levy talks to chemist Lee Cronin about his team\u2019s search<sup><a href=\"https:\/\/www.nature.com\/articles\/d41586-018-05776-9?utm_source=feedburner&amp;utm_medium=feed&amp;utm_campaign=Feed%3A+nature%2Frss%2Fcurrent+%28Nature+-+Issue%29#ref-CR1\">1<\/a><\/sup>\u00a0for new chemical reactions.\u00a0<a href=\"https:\/\/doi.org\/10.1038\/s41586-018-0307-8\" data-track=\"click\" data-label=\"https:\/\/doi.org\/10.1038\/s41586-018-0307-8\" data-track-category=\"body text link\">Read the research.<\/a><\/p>\n<p><a href=\"https:\/\/itunes.apple.com\/gb\/podcast\/nature-podcast\/id81934659\" data-track=\"click\" data-label=\"https:\/\/itunes.apple.com\/gb\/podcast\/nature-podcast\/id81934659\" data-track-category=\"body text link\"><b>Subscribe to the Nature Podcast on iTunes<\/b><\/a>\u00a0or your favourite podcast app.<\/p>\n<p><a href=\"http:\/\/rss.acast.com\/nature\" data-track=\"click\" data-label=\"http:\/\/rss.acast.com\/nature\" data-track-category=\"body text link\"><b>Head here for the Nature Podcast RSS feed.<\/b><\/a><\/p>\n<div class=\"embed box\">\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h3 class=\"box__title sans-serif\">TRANSCRIPT<\/h3>\n<div class=\"box__content cleared\">\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>For chemist Lee Cronin chemistry is all about discovery. And despite methods and techniques that have developed leaps and bounds over the centuries, for Lee the process of discovery is still all about the journey.<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>It\u2019s very difficult when you ask a chemist in the lab to go discover something. It\u2019s a bit like asking someone to go in a boat now and find a new continent. Something invariably goes wrong and more interesting happens, and then we follow that up, and I think that is the point where conventionally a lot of discoveries are made today.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>But despite his love of the voyage, Lee thinks it\u2019s time to change up the process. Not the aspect that relies on some magical combination of luck and intuition, but exactly how the search is carried out. Lee wants to automate the quest for new reactions. Machines already exist to automate certain tasks in chemistry, but they tend to follow specific programming and recipes rather than searching for new discoveries. There have also been attempts to aid discovery with machine learning, where a computer is trained with data and learns how reactions might operate. Lee wanted to make a machine that could learn and carry out tasks. I called him up to find out more.<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>So, what we\u2019ve tried to do is use machine learning to classify where the outcome of a reaction &#8211; that\u2019s when you mix two chemicals together &#8211; whether something has happened or not, and then you can use that as a basis to then, you know, navigate round if you like your new chemical space or sail your yacht around your unknown islands and map them.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>And your machine isn\u2019t just learning, it\u2019s doing, it\u2019s doing experiments.<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>Yeah, we do three crucially important things. Number one, we start with an empty database, except just it knows the ingredients that we have at our disposal. Number two, it just randomly selects the ingredients, the chemicals to add together so it has no bias. And number three, it does this in real time so it actually decides what to do and then mixes the chemicals together and watches what happens.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>When we say \u2018it\u2019 in these sentences, we\u2019re actually talking about a robot. Can you describe what this robot is, because it\u2019s not like some kind of humanoid thing sitting at a chemistry lab table, right?<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>No, but actually it does things very similar to what a humanoid would do or a human being would do at the chemistry lab table. A chemist would typically mix chemicals together in a round-bottom flask, put them on the stirrer and heat it up, and that is what this robot does. You plug the chemicals into the robot, and it moves those chemicals as liquids in a solvent to the reactor, and then the reaction happens and the robot automatically takes a sample and moves it to a detector. And it&#8217;s basically like a human being using its eyes or your ears so it happens really quickly and seamlessly.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>So, is this really a closed system? Is this doing everything or is there still need for human input at some stage?<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>Oh yeah, the human\u2019s crucial. This is not about replacing a human. So, what this robot does, it\u2019s just a labour-saving tool. The robot is only as good as the chemist that\u2019s trained it. Well, the robot would do the experiment and the chemist would tell the robot whether the outcome of the experiment was reactive or unreactive, so whether something happened or not. And so, the robot will then start to guess after a while and then the human will go yeah, you\u2019re right, you\u2019re right. And then there gets to a crucial point where it has done about 10% of the possible combinations, it is able to predict what will happen next and it just speeds up our ability to discover new reactions and new molecules. Human time is limited and so one of the things that the robot can do is basically do reactions the human doesn\u2019t have time to do and would normally discard. It can do about 36 reactions a day, and a chemist would only typically do maybe 3 or 4 such reactions a day.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>We\u2019ve described how the process works, but have you actually managed to find anything novel with this robot?<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>I\u2019m pretty happy to say that I think I could convince maybe 9 out of 10 chemists that the robot had done some reactions where the outcome couldn\u2019t be predicted beforehand, and that\u2019s for me really exciting.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>Robots and automated machines are already used in chemistry, in industry. Just how different is the system that you\u2019re using here from the kind of robots that might exist in other contexts in chemistry?<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>What\u2019s different about our system is its integration and the fact it searches for reactivity. What we\u2019re doing is actually quite unusual in that it basically is able to search without any target in mind, and then what we needed to make sure we were doing, not just having new sensors and not having targets, but actually having machine learning to actually correctly search those reagent or ingredient combinations.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>What actual applications will these differences be useful for?<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>Well, we\u2019re really excited because we think in terms of discovery science, anything we need new molecules, so new drugs, new dyes, drug delivery systems, new materials. Now, there\u2019s a problem when you\u2019re discovering when you don\u2019t know what you\u2019re looking for. So, the next thing that we\u2019re going to do is add another little sensor, but the sensor on to this will then have a desire and say right, we want to find, I don\u2019t know, the bluest blue thing. So now, let\u2019s not just look for new stuff but it has to be new and blue.<\/p>\n<p><b>Interviewer: Adam Levy<\/b><\/p>\n<p>And personally, what are you most excited about the opportunities that having this integrated robot system could open up?<\/p>\n<p><b>Interviewee: Lee Cronin<\/b><\/p>\n<p>Well, I\u2019m hoping that what it will do is tell us more about the laws of chemistry, and allow us to discover molecules that we just wouldn\u2019t have access to using our existing knowledge. I kind of liken it a bit like to writing poetry. Shakespeare was really interesting in writing poetry and verse because he invented new words. What I\u2019m interested in this robot seeing it do, is able to invent new reactions. Then those reactions can be translated back to the normal chemistry language, and then the chemist is able to use those new reactions to make new molecules. For me that\u2019s super exciting.<\/p>\n<\/div>\n<div class=\"box__author sans-serif\"><\/div>\n<\/div>\n<\/div>\n<aside class=\"c-latest-content mt40 hide-print\" data-simple-tab=\"\" data-tab-group=\"\" data-component-id=\"latest-news\" data-track=\"in-view\" data-track-action=\"in-view\" data-track-category=\"latest content\" data-track-label=\"visible\">\n<div id=\"latest-content\" role=\"tablist\">\n<p class=\"serif strong\">\n<\/div>\n<\/aside>\n<\/div>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h5 class=\"tighten-line-height small-space-below\" data-test=\"article-title\">Controlling an organic synthesis robot with machine learning to search for new reactivity<\/h5>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p><i data-test=\"journal-title\">Nature\u00a0<\/i><b data-test=\"journal-volume\"><span class=\"visually-hidden\">volume<\/span>\u00a0559<\/b>,\u00a0<span class=\"visually-hidden\">pages\u00a0<\/span>377\u2013381\u00a0(<span data-test=\"article-publication-year\">2018<\/span>)<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h6 id=\"Abs1\" class=\"js-section-title section-title strong position-relative tighten-line-height background-gray-light pt20 pb6 pl0 pr20 standard-space-below small-space-above mq640-pt10 mq640-pb10 mq640-pl20 mq640-mt0 extend-left\">Abstract<\/h6>\n<div id=\"Abs1-content\" class=\"pl20 mq875-pl0 js-collapsible-section\">\n<p>The discovery of chemical reactions is an inherently unpredictable and time-consuming process<sup><a id=\"ref-link-section-d19e380\" title=\"Collins, K. D., Gensch, T. &amp; Glorius, F. Contemporary screening approaches to reaction discovery and development. Nat. Chem. 6, 859\u2013871 (2014).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR1\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 1\">1<\/a><\/sup>. An attractive alternative is to predict reactivity, although relevant approaches, such as computer-aided reaction design, are still in their infancy<sup><a id=\"ref-link-section-d19e384\" title=\"Warr, W. A. A short review of chemical reaction database systems, computer-aided synthesis design, reaction prediction and synthetic feasibility. Mol. Inform. 33, 469\u2013476 (2014).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR2\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 2\">2<\/a><\/sup>. Reaction prediction based on high-level quantum chemical methods is complex<sup><a id=\"ref-link-section-d19e388\" title=\"Plata, R. E. &amp; Singleton, D. A. A case study of the mechanism of alcohol-mediated Morita Baylis-Hillman reactions. The importance of experimental observations. J. Am. Chem. Soc. 137, 3811\u20133826 (2015).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR3\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 3\">3<\/a><\/sup>, even for simple molecules. Although\u00a0machine learning is powerful for data analysis<sup><a id=\"ref-link-section-d19e392\" title=\"LeCun, Y., Bengio, Y. &amp; Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR4\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 4\">4<\/a>,<a id=\"ref-link-section-d19e395\" title=\"Jordan, M. I. &amp; Mitchell, T. M. Machine learning: trends, perspectives, and prospects. Science 349, 255\u2013260 (2015).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR5\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 5\">5<\/a><\/sup>, its applications in chemistry are still being developed<sup><a id=\"ref-link-section-d19e399\" title=\"Raccuglia, P. et al. Machine-learning-assisted materials discovery using failed experiments. Nature 533, 73\u201376 (2016).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR6\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 6\">6<\/a><\/sup>. Inspired by strategies based on chemists\u2019 intuition<sup><a id=\"ref-link-section-d19e404\" title=\"Graulich, N., Hopf, H. &amp; Schreiner, P. R. Heuristic thinking makes a chemist smart. Chem. Soc. Rev. 39, 1503\u20131512 (2010).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR7\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 7\">7<\/a><\/sup>, we propose that a reaction system controlled by a machine learning algorithm may be able to explore the space of chemical reactions quickly, especially if trained by an expert<sup><a id=\"ref-link-section-d19e408\" title=\"Gil, Y., Greaves, M., Hendler, J. &amp; Hirsh, H. Amplify scientific discovery with artificial intelligence. Science 346, 171\u2013172 (2014).\" href=\"https:\/\/www.nature.com\/articles\/s41586-018-0307-8#ref-CR8\" data-track=\"click\" data-track-action=\"reference anchor\" data-track-label=\"link\" data-test=\"citation-ref\" aria-label=\"Reference 8\">8<\/a><\/sup>. Here we present an organic synthesis robot that can perform chemical reactions and analysis faster than they can be performed manually, as well as predict the reactivity of possible reagent combinations after conducting a small number of experiments, thus effectively navigating chemical reaction space. By using machine learning for decision making, enabled by binary encoding of the chemical inputs, the reactions can be assessed in real time using nuclear magnetic resonance and infrared spectroscopy. The machine learning system was able to predict the reactivity of about 1,000 reaction combinations with accuracy greater than 80 per cent after considering the outcomes of slightly over 10 per cent of the dataset. This approach was also used to calculate the reactivity of published datasets. Further, by using real-time data from our robot, these predictions were followed up manually by a chemist, leading to the discovery of four reactions.<\/p>\n<\/div>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>http:\/\/www.etnews.com\/20180722000036<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<h6>AI\ub85c \uc2e0\ubb3c\uc9c8 \ubc1c\uacac \uc55e\ub2f9\uae30\ub294 &#8216;\ub85c\ubd07 \ud654\ud559\uc790&#8217;<\/h6>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p><span class=\"end_photo_org\"><img decoding=\"async\" src=\"https:\/\/imgnews.pstatic.net\/image\/030\/2018\/07\/22\/0002725742_001_20180722165111706.jpg?type=w647\" \/><em class=\"img_desc\">\uae00\ub798\uc2a4\uace0\ub300\uc5d0\uc11c \uac1c\ubc1c\ud55c \ub85c\ubd07 \ud654\ud559\uc790<\/em><\/span><\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>\uc758\ub8cc, \uc2e0\uc18c\uc7ac \ub4f1 \uc601\uc5ed\uc5d0\uc11c \ud601\uc2e0\uc744 \uac00\uc838\uc62c \uc0c8\ub85c\uc6b4 \ubb3c\uc9c8\uc744 \uac1c\ubc1c\ud558\ub294 \uacfc\uc815\uc740 \uae38\uace0 \uc5b4\ub835\ub2e4. \uc6b0\uc5f0\ud55c \ud589\uc6b4\uc774 \uc5c6\ub2e4\uba74 \uc218\ub9ce\uc740 \uc2e4\ud5d8\uc744 \uac70\uccd0 \ucd5c\uc801 \ud2b9\uc131\uc744 \uac00\uc9c4 \ubb3c\uc9c8\uc744 \ucc3e\uae30\uae4c\uc9c0 \uc218\ub144\uc774 \uac78\ub9b0\ub2e4. \uc774 \uac19\uc740 \uc5b4\ub824\uc6c0\uc744 \ud574\uc18c\ud574 \uc904 &#8216;\ub85c\ubd07 \ud654\ud559\uc790&#8217;\uac00 \uac1c\ubc1c\ub410\ub2e4. \uc778\uacf5\uc9c0\ub2a5(<span class=\"word_dic en\">AI<\/span>)\uc73c\ub85c \ud654\ud559 \ubc18\uc751 \uacb0\uacfc\ub97c \uc608\uce21, \uae30\uac04\uc744 \ub2e8\ucd95\uc2dc\ud0a8\ub2e4.<\/p>\n<p>\uae00\ub798\uc2a4\uace0\ub300 \uc5f0\uad6c\uc9c4\uc740 \ucd5c\uadfc \ud654\ud559 \ubc18\uc751 \uc2e4\ud5d8\uacfc \ubd84\uc790 \ubc1c\uacac\uc744 \uac00\uc18d\ud654\ud558\ub294 \ub85c\ubd07 \uacfc\ud559\uc790\ub97c \uacf5\uac1c\ud588\ub2e4. \uc774 \ub85c\ubd07\uc740\u00a0<span class=\"word_dic en\">AI<\/span>\u00a0\ubc29\ubc95\ub860\uc778 \uae30\uacc4\ud559\uc2b5(\uba38\uc2e0\ub7ec\ub2dd)\uc744 \uc0ac\uc6a9\ud574 \ud654\ud559 \ubc18\uc751\uc744 \uc608\uce21\ud560 \uc218 \uc788\ub2e4. \uc774\ub97c \uc704\ud574 \uc9c1\uc811 \uc2e4\ud5d8\uc744 \ud1b5\ud574 \uc218\uc9d1\ub41c \ub370\uc774\ud130\ub97c \ud65c\uc6a9\ud588\ub2e4.<\/p>\n<p>\uc774 \ub85c\ubd07\uc740 18\uac00\uc9c0 \ud654\ud559\ubb3c\uc9c8\uc744 \uc774\uc6a9\ud574 1000\uac00\uc9c0 \ubc18\uc751\uc774 \ub098\uc624\ub294 \uc2e4\ud5d8\uc5d0\uc11c 80% \uc815\ud655\ub3c4\ub85c \uc5f0\uad6c\uc5d0 \uc801\ud569\ud55c \ubc18\uc751\ub9cc \ucd94\ub824\ub0b4\uae30 \uc704\ud574 100\ubc88\uc758 \uc2e4\ud5d8\ub9cc \ud544\uc694\ud588\ub2e4. \uc5f0\uad6c\uc9c4\uc740 \uc774 \uc2e4\ud5d8\uc73c\ub85c \ub124 \uac00\uc9c0 \uc801\ud569\ud55c \ubc18\uc751\uc744 \ubc1c\uacac\ud588\uc73c\uba70 \uc774 \uac00\uc6b4\ub370 \ud55c \uac74\uc740 \uc0c1\uc704 1%\uc5d0 \ub4dc\ub294 \ub3c5\ud2b9\ud55c \ubc18\uc751\uc774\uc5c8\ub2e4\uace0 \uc124\uba85\ud588\ub2e4.<\/p>\n<p>\uc774\ubc88 \uc2e4\ud5d8 \uacb0\uacfc\uac00 \uc5c4\uccad\ub09c \uc131\uacf5\ucc98\ub7fc \ubcf4\uc774\uc9c0 \uc54a\uc744 \uc218\ub3c4 \uc788\ub2e4. \uadf8\ub7ec\ub098 \uc774 \uae30\uc220\uc740 \ud654\ud559\uc790\uac00 \uc2e0\ubb3c\uc9c8\uc744 \ubc1c\uacac\ud558\ub294 \uc18d\ub3c4\ub97c \ud68d\uae30\uc801\uc73c\ub85c \uac1c\uc120\ud560 \uc218 \uc788\ub2e4. \ud654\ud559\uc790\ub294\u00a0<span class=\"word_dic en\">AI<\/span>\uac00 \uc608\uce21\ud55c \uc131\uacf5 \uac00\ub2a5\uc131\uc774 \ub192\uc740 \uc18c\uc218 \ubc18\uc751\uc5d0 \ucd08\uc810\uc744 \ub9de\ucdb0 \uc5f0\uad6c, \ud0d0\uc0c9 \uacfc\uc815\uc744 \ub2e8\ucd95\ud560 \uc218 \uc788\ub2e4. \uc54c\uace0\ub9ac\uc998\ub3c4 \uc9c0\uc18d\uc801\uc778 \ub370\uc774\ud130 \ucd95\uc801\uacfc \ud559\uc2b5\uc744 \ud1b5\ud574 \uc815\uad50\ud574\uc9c8 \uac83\uc73c\ub85c \uc804\ub9dd\ub41c\ub2e4.<\/p>\n<p>\ubbf8\uad6d \uc815\ubcf4\uae30\uc220(<span class=\"word_dic en\">IT<\/span>) \ub9e4\uccb4 \uc5d4\uac00\uc82f\uc740 \u201c\uacfc\ud559\uc790\ub294 \ub85c\ubd07 \ud654\ud559\uc790\ub97c \uc774\uc6a9\ud574 \uc77c\uc0c1 \uc2e4\ud5d8\uc774 \uc544\ub2c8\ub77c \uae4c\ub2e4\ub85c\uc6b4 \ubd80\ubd84\uc5d0\ub9cc \uc9d1\uc911\ud558\uba74 \ub41c\ub2e4\u201d\uba74\uc11c \u201c\uc0c8 \uce58\ub8cc\ubc95, \uc0c8 \ubc30\ud130\ub9ac \uc18c\uc7ac, \ub354\uc6b1 \uac15\ub3c4 \ub192\uc740 \ubb3c\uc9c8 \ubc1c\uacac \ub4f1 \ub2e4\uc591\ud55c \uc601\uc5ed\uc5d0\uc11c \uc5f0\uad6c \uae30\uac04\uc744 \ud06c\uac8c \uc904\uc77c \uc218 \uc788\uc744 \uac83\u201d\uc774\ub77c\uace0 \ub9d0\ud588\ub2e4.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>&nbsp; &nbsp; (\uc6d0\ubb38) &nbsp; &nbsp; Automated machine conducts, assesses and learns from experiments with random reagents. &nbsp; &nbsp; Reporter Adam Levy talks to chemist Lee<a href=\"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=1166\" 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_post_was_ever_published":false,"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_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}},"categories":[34,35,29,30],"tags":[8,9,3,4],"class_list":["post-1166","post","type-post","status-publish","format-standard","hentry","category-lets-do-chemistry","category-lets-do-computer-science","category-lets-do-science","category-recent-science-news","tag-lets-do-chemistry","tag-lets-do-computer-science","tag-lets-do-science","tag-recent-science-news"],"aioseo_notices":[],"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack-related-posts":[{"id":2954,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=2954","url_meta":{"origin":1166,"position":0},"title":"Hidden flaws in common piece of lab kit could botch experiments","author":"biochemistry","date":"March 27, 2019","format":false,"excerpt":"\u00a0 Well-used magnetic stirrers harbour metal atoms that could bias the results of chemical and biochemical reactions. \u00a0 Magnetic stirring bars are ubiquitous in research labs, but the bars accumulate damage over time that could muddy experimental results. Credit: Getty \u00a0 \u00a0 \u00a0 The rapidly whirling magnets used to stir\u2026","rel":"","context":"In &quot;Essays on Science&quot;","block_context":{"text":"Essays on Science","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=32"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":3411,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=3411","url_meta":{"origin":1166,"position":1},"title":"Automation: Chemistry shoots for the Moon","author":"biochemistry","date":"April 23, 2019","format":false,"excerpt":"\u00a0 \u00a0 A new class of chemical instrumentation seeks to alleviate the tedium and complexity of organic syntheses. \u00a0 A machine for synthesizing small molecules at the University of Illinois at Urbana\u2013Champaign relies on syringe pumps to push reagents into reaction stations.Credit: L. Brian Stauffer, Univ. Illinois \u00a0 \u00a0 In\u2026","rel":"","context":"In &quot;Let's Do Chemistry!&quot;","block_context":{"text":"Let's Do Chemistry!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=34"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":1183,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=1183","url_meta":{"origin":1166,"position":2},"title":"Rethinking chemical risks","author":"biochemistry","date":"July 20, 2018","format":false,"excerpt":"\u00a0 \u00a0 (\uc6d0\ubb38: \uc5ec\uae30\ub97c \ud074\ub9ad\ud558\uc138\uc694~) \u00a0 \u00a0 Science\u00a0\u00a020 Jul 2018: Vol. 361, Issue 6399, pp. 240-242 DOI: 10.1126\/science.361.6399.240-r \u00a0 \u00a0 Modern life relies on vast numbers of different chemicals, from pharmaceuticals and cleaning products to pesticides and plastics. Wastewater treatment is widely used to avoid their release into the environment.\u2026","rel":"","context":"In &quot;Essays on Science&quot;","block_context":{"text":"Essays on Science","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=32"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":2551,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=2551","url_meta":{"origin":1166,"position":3},"title":"Synthetic innovation in drug development","author":"biochemistry","date":"January 19, 2019","format":false,"excerpt":"\u00a0 \u00a0 Chemical synthesis plays a key role in pharmaceutical research and development. Campos\u00a0et al.\u00a0review some of the advantages that have come from recent innovations in synthetic methods. In particular, they highlight small-molecule catalysts stimulated by visible light, enzymes engineered for versatility beyond their intrinsic function, and bio-orthogonal reactions to\u2026","rel":"","context":"In &quot;Let's Do Chemistry!&quot;","block_context":{"text":"Let's Do Chemistry!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=34"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":4189,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=4189","url_meta":{"origin":1166,"position":4},"title":"Double-click enables synthesis of chemical libraries for drug discovery","author":"biochemistry","date":"October 6, 2019","format":false,"excerpt":"\u00a0 \u00a0 Operationally simple chemical reactions, termed click reactions, are widely used in many scientific fields. A streamlined synthesis of compounds called azides looks set to expand the role of click chemistry still further. \u00a0 \u00a0 Generating molecules and materials that have desirable functional properties is arguably the central goal\u2026","rel":"","context":"In &quot;Let's Do Chemistry!&quot;","block_context":{"text":"Let's Do Chemistry!","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=34"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":2940,"url":"https:\/\/biochemistry.khu.ac.kr\/lab\/?p=2940","url_meta":{"origin":1166,"position":5},"title":"Charting a course for chemistry","author":"biochemistry","date":"March 23, 2019","format":false,"excerpt":"\u00a0 \u00a0 To mark the occasion of\u00a0Nature Chemistry\u00a0turning 10 years old, we asked scientists working in different areas of chemistry to tell us what they thought the most exciting, interesting or challenging aspects related to the development of their main field of research will be \u2014 here is what they\u2026","rel":"","context":"In &quot;Essays on Science&quot;","block_context":{"text":"Essays on Science","link":"https:\/\/biochemistry.khu.ac.kr\/lab\/?cat=32"},"img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]}],"jetpack_sharing_enabled":false,"jetpack_shortlink":"https:\/\/wp.me\/p9Xo1j-iO","_links":{"self":[{"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts\/1166","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=1166"}],"version-history":[{"count":1,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts\/1166\/revisions"}],"predecessor-version":[{"id":4243,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=\/wp\/v2\/posts\/1166\/revisions\/4243"}],"wp:attachment":[{"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1166"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1166"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/biochemistry.khu.ac.kr\/lab\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1166"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}