{"id":12499,"date":"2022-05-13T12:11:18","date_gmt":"2022-05-13T09:11:18","guid":{"rendered":"http:\/\/journals.khnu.km.ua\/vestnik\/?p=12499"},"modified":"2022-06-07T01:24:37","modified_gmt":"2022-06-06T22:24:37","slug":"metod-meta-navchannya-dlya-vyznachennya-molekulyarnoyi-sporidnenosti","status":"publish","type":"post","link":"https:\/\/journals.khnu.km.ua\/vestnik\/?p=12499","title":{"rendered":"\u041c\u0435\u0442\u043e\u0434 \u043c\u0435\u0442\u0430-\u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0434\u043b\u044f \u0432\u0438\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f \u043c\u043e\u043b\u0435\u043a\u0443\u043b\u044f\u0440\u043d\u043e\u0457 \u0441\u043f\u043e\u0440\u0456\u0434\u043d\u0435\u043d\u043e\u0441\u0442\u0456"},"content":{"rendered":"

<\/p>\n

\u041c\u0415\u0422\u041e\u0414 \u041c\u0415\u0422\u0410-\u041d\u0410\u0412\u0427\u0410\u041d\u041d\u042f \u0414\u041b\u042f \u0412\u0418\u0417\u041d\u0410\u0427\u0415\u041d\u041d\u042f \u041c\u041e\u041b\u0415\u041a\u0423\u041b\u042f\u0420\u041d\u041e\u0407 \u0421\u041f\u041e\u0420\u0406\u0414\u041d\u0415\u041d\u041e\u0421\u0422\u0406<\/p>\n

METHOD SUPER LEARNING FOR DETERMINATION OF MOLECULAR RELATIONSHIP<\/p>\n

\u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438:\u00a01<\/strong>4<\/strong>-2<\/strong>4<\/strong>. \u041d\u043e\u043c\u0435\u0440: \u21162, 2022 (307)\u00a0 \"\"<\/a><\/strong>
\n\u00a0\u0410\u0432\u0442\u043e\u0440\u0438:<\/strong>
\n\u0413\u0443\u0440\u0431\u0438\u0447 \u041e.\u0412.
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u201c\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u201d
\nhttps:\/\/orcid.org\/0000-0002-6821-3390<\/a>
\ne-mail: oleksandr.v.hurbych@lpnu.ua<\/a>
\nGURBYCH A.V.
\nLviv Polytechnic National University
\n\u00a0DOI:<\/strong>\u00a0https:\/\/www.doi.org\/10.31891\/2307-5732-2022-307-2-14-24<\/a><\/p>\n

\u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443<\/strong><\/p>\n

\u0423 \u0446\u0456\u0439 \u0440\u043e\u0431\u043e\u0442\u0456 \u0437\u0430\u0441\u0442\u043e\u0441\u043e\u0432\u0430\u043d\u0438\u0439 \u043f\u0440\u0438\u043d\u0446\u0438\u043f \u043c\u0435\u0442\u0430-\u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0434\u043b\u044f \u043f\u0435\u0440\u0435\u0434\u0431\u0430\u0447\u0435\u043d\u043d\u044f \u043c\u043e\u043b\u0435\u043a\u0443\u043b\u044f\u0440\u043d\u043e\u0457 \u0441\u043f\u043e\u0440\u0456\u0434\u043d\u0435\u043d\u043e\u0441\u0442\u0456 \u043c\u0456\u0436 \u0440\u0435\u0446\u0435\u043f\u0442\u043e\u0440\u043e\u043c (\u0432\u0435\u043b\u0438\u043a\u0430 \u0431\u0456\u043e\u043c\u043e\u043b\u0435\u043a\u0443\u043b\u0430) \u0442\u0430 \u043b\u0456\u0433\u0430\u043d\u0434\u0430\u043c\u0438 (\u043c\u0430\u043b\u0456 \u043e\u0440\u0433\u0430\u043d\u0456\u0447\u043d\u0456 \u043c\u043e\u043b\u0435\u043a\u0443\u043b\u0438). \u041c\u0435\u0442\u0430-\u043c\u043e\u0434\u0435\u043b\u0456 \u0432\u0438\u0432\u0447\u0430\u044e\u0442\u044c \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u0443 \u043a\u043e\u043c\u0431\u0456\u043d\u0430\u0446\u0456\u044e \u043e\u043a\u0440\u0435\u043c\u0438\u0445 \u0431\u0430\u0437\u043e\u0432\u0438\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0443 \u0434\u0432\u043e\u0445 \u043f\u043e\u0441\u043b\u0456\u0434\u043e\u0432\u043d\u0438\u0445 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044f\u0445 – \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0439\u043d\u043e\u043c\u0443 \u0442\u0430 \u0440\u0435\u0433\u0440\u0435\u0441\u0456\u0439\u043d\u043e\u043c\u0443. \u041a\u043e\u0436\u0435\u043d \u0456\u0437 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u0456\u0432 \u043c\u0456\u0441\u0442\u0438\u0442\u044c \u043f\u043e \u0448\u0456\u0441\u0442\u044c \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u044f\u043a\u0456 \u043f\u043e\u0454\u0434\u043d\u0443\u044e\u0442\u044c\u0441\u044f \u043c\u0435\u0442\u043e\u0434\u043e\u043c \u0441\u0442\u0435\u043a\u0456\u043d\u0433\u0443. \u0411\u0430\u0437\u043e\u0432\u0456 \u043c\u043e\u0434\u0435\u043b\u0456 \u0432\u043a\u043b\u044e\u0447\u0430\u044e\u0442\u044c \u0432 \u0441\u0435\u0431\u0435 \u043c\u0435\u0442\u043e\u0434 \u043e\u043f\u043e\u0440\u043d\u0438\u0445 \u0432\u0435\u043a\u0442\u043e\u0440\u0456\u0432, \u0432\u0438\u043f\u0430\u0434\u043a\u043e\u0432\u0438\u0439 \u043b\u0456\u0441, \u0433\u0440\u0430\u0434\u0456\u0454\u043d\u0442\u043d\u0438\u0439 \u0431\u0443\u0441\u0442\u0438\u043d\u0433, \u0433\u0440\u0430\u0444\u043e\u0432\u0456 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0456 \u043c\u0435\u0440\u0435\u0436\u0456 \u0442\u0430 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0456 \u043c\u0435\u0440\u0435\u0436\u0456 \u043f\u0440\u044f\u043c\u043e\u0433\u043e \u043f\u043e\u0448\u0438\u0440\u0435\u043d\u043d\u044f, \u0430 \u0442\u0430\u043a\u043e\u0436 \u0442\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u0438. \u041f\u0435\u0440\u0448\u0438\u0439 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044c \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0454 \u0456\u043c\u043e\u0432\u0456\u0440\u043d\u0456\u0441\u0442\u044c \u0437\u0432\u2019\u044f\u0437\u0443\u0432\u0430\u043d\u043d\u044f \u0442\u0430 \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0443\u0454 \u0443\u0441\u0456 \u043c\u043e\u043b\u0435\u043a\u0443\u043b\u0438-\u043a\u0430\u043d\u0434\u0438\u0434\u0430\u0442\u0438 \u0434\u043e \u043e\u0431\u0440\u0430\u043d\u043e\u0433\u043e \u0440\u0435\u0446\u0435\u043f\u0442\u043e\u0440\u0443 \u043d\u0430 \u0430\u043a\u0442\u0438\u0432\u043d\u0456 \u0442\u0430 \u043d\u0435\u0430\u043a\u0442\u0438\u0432\u043d\u0456. \u041b\u0456\u0433\u0430\u043d\u0434\u0438, \u044f\u043a\u0456 \u043f\u0435\u0440\u0448\u0438\u0439 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044c \u0432\u0438\u0437\u043d\u0430\u0432 \u0430\u043a\u0442\u0438\u0432\u043d\u0438\u043c\u0438, \u043f\u043e\u0434\u0430\u044e\u0442\u044c\u0441\u044f \u0443 \u0434\u0440\u0443\u0433\u0438\u0439 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044c, \u044f\u043a\u0438\u0439 \u043f\u0435\u0440\u0435\u0434\u0431\u0430\u0447\u0430\u0454 \u0441\u0442\u0443\u043f\u0456\u043d\u044c \u0457\u0445\u043d\u044e \u0441\u043f\u043e\u0440\u0456\u0434\u043d\u0435\u043d\u043e\u0441\u0442\u0456 \u0434\u043e \u0440\u0435\u0446\u0435\u043f\u0442\u043e\u0440\u0443 \u0443 \u0432\u0438\u0433\u043b\u044f\u0434\u0456 \u043a\u043e\u0435\u0444\u0456\u0446\u0456\u0454\u043d\u0442\u0443 \u0435\u043d\u0433\u0456\u0431\u0456\u044e\u0432\u0430\u043d\u043d\u044f (Ki). \u041e\u0441\u043e\u0431\u043b\u0438\u0432\u0456\u0441\u0442\u044e \u043c\u0435\u0442\u043e\u0434\u0443 \u0454 \u0432\u0456\u0434\u043c\u043e\u0432\u0430 \u0432\u0456\u0434 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043d\u044f \u043a\u043e\u043e\u0440\u0434\u0438\u043d\u0430\u0442 \u0430\u0442\u043e\u043c\u0456\u0432 \u043e\u043a\u0440\u0435\u043c\u0438\u0445 \u043c\u043e\u043b\u0435\u043a\u0443\u043b \u0442\u0430 \u0457\u0445\u043d\u0456\u0445 \u043a\u043e\u043c\u043f\u043b\u0435\u043a\u0441\u0456\u0432 – \u0443 \u0442\u0430\u043a\u0438\u0439 \u0441\u043f\u043e\u0441\u0456\u0431 \u043d\u0456\u0432\u0435\u043b\u044e\u044e\u0442\u044c\u0441\u044f \u0435\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0430\u043b\u044c\u043d\u0456 \u043f\u043e\u0445\u0438\u0431\u043a\u0438 \u043f\u0456\u0434 \u0447\u0430\u0441 \u043f\u0456\u0434\u0433\u043e\u0442\u043e\u0432\u043a\u0438 \u0437\u0440\u0430\u0437\u043a\u0456\u0432 \u0442\u0430 \u0432\u0438\u043c\u0456\u0440\u044e\u0432\u0430\u043d\u043d\u044f \u043a\u043e\u043e\u0440\u0434\u0438\u043d\u0430\u0442 \u0430\u0442\u043e\u043c\u0456\u0432, \u0430 \u0442\u0430\u043a\u043e\u0436 \u0443\u043c\u043e\u0436\u043b\u0438\u0432\u043b\u044e\u0454\u0442\u044c\u0441\u044f \u0437\u0430\u0441\u0442\u043e\u0441\u0443\u0432\u0430\u043d\u043d\u044f \u043c\u0435\u0442\u043e\u0434\u0443 \u0434\u043b\u044f \u0432\u0438\u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f \u0441\u043f\u043e\u0440\u0456\u0434\u043d\u0435\u043d\u043e\u0441\u0442\u0456 \u0431\u0456\u043e\u043c\u043e\u043b\u0435\u043a\u0443\u043b \u0456\u0437 \u043d\u0435\u0432\u0456\u0434\u043e\u043c\u0438\u043c\u0438 \u043f\u0440\u043e\u0441\u0442\u043e\u0440\u043e\u0432\u0438\u043c\u0438 \u043a\u043e\u043d\u0444\u0456\u0433\u0443\u0440\u0430\u0446\u0456\u044f\u043c\u0438. \u041f\u043e\u043a\u0430\u0437\u0430\u043d\u043e, \u0449\u043e \u043c\u0435\u0442\u0430-\u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0437\u0431\u0456\u043b\u044c\u0448\u0443\u0454 \u0432\u0456\u0434\u0433\u0443\u043a (Recall) \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0439\u043d\u043e\u0433\u043e \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044e \u043d\u0430 34,9% \u0442\u0430 \u043a\u043e\u0435\u0444\u0456\u0446\u0456\u0454\u043d\u0442 \u0434\u0435\u0442\u0435\u0440\u043c\u0456\u043d\u0430\u0446\u0456\u0457 (R2<\/sup>) \u0440\u0435\u0433\u0440\u0435\u0441\u0456\u0439\u043d\u043e\u0433\u043e \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044e \u043d\u0430 21% \u0443 \u043f\u043e\u0440\u0456\u0432\u043d\u044f\u043d\u043d\u0456 \u0456\u0437 \u0441\u0435\u0440\u0435\u0434\u043d\u0456\u043c\u0438 \u0437\u043d\u0430\u0447\u0435\u043d\u043d\u044f\u043c\u0438. \u0423 \u0446\u0456\u0439 \u0440\u043e\u0431\u043e\u0442\u0456 \u043f\u043e\u043a\u0430\u0437\u0430\u043d\u043e, \u0449\u043e \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044c \u0437 \u043c\u0435\u0442\u0430-\u0441\u0442\u0435\u043a\u0456\u043d\u0433\u043e\u043c \u0454 \u0430\u0441\u0438\u043c\u043f\u0442\u043e\u0442\u0438\u0447\u043d\u043e \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u043e\u044e \u0441\u0438\u0441\u0442\u0435\u043c\u043e\u044e \u0434\u043b\u044f \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f. \u0420\u043e\u0437\u0433\u043b\u044f\u0434\u0430\u0454\u0442\u044c\u0441\u044f \u043e\u0441\u043e\u0431\u043b\u0438\u0432\u0456\u0441\u0442\u044c Super Learning\u2019\u0443 \u0434\u043b\u044f \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043d\u044f \u043f\u0435\u0440\u0435\u0445\u0440\u0435\u0441\u043d\u043e\u0457 \u043f\u0435\u0440\u0435\u0432\u0456\u0440\u043a\u0438 (k-fold cross-validation) \u0434\u043b\u044f \u0444\u043e\u0440\u043c\u0443\u0432\u0430\u043d\u043d\u044f \u043f\u0435\u0440\u0435\u0434\u0431\u0430\u0447\u0435\u043d\u044c \u00ab\u043f\u0435\u0440\u0448\u043e\u0433\u043e \u0440\u0456\u0432\u043d\u044f\u00bb, \u043d\u0430 \u044f\u043a\u0438\u0445 \u0432\u0438\u043a\u043e\u043d\u0443\u0454\u0442\u044c\u0441\u044f \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0434\u0440\u0443\u0433\u043e\u0433\u043e \u0440\u0456\u0432\u043d\u044f – \u0430\u0431\u043e \u043c\u0435\u0442\u0430-\u043c\u043e\u0434\u0435\u043b\u0435\u0439, – \u044f\u043a\u0456 \u043a\u043e\u043c\u0431\u0456\u043d\u0443\u044e\u0442\u044c \u043c\u043e\u0434\u0435\u043b\u0456 \u043f\u0435\u0440\u0448\u043e\u0433\u043e \u0440\u0456\u0432\u043d\u044f \u043e\u043f\u0442\u0438\u043c\u0430\u043b\u044c\u043d\u0438\u043c \u0447\u0438\u043d\u043e\u043c. \u0414\u043e\u0441\u043b\u0456\u0434\u0436\u0443\u0454\u0442\u044c\u0441\u044f \u0437\u0434\u0430\u0442\u043d\u0456\u0441\u0442\u044c \u043f\u0435\u0440\u0435\u0434\u0431\u0430\u0447\u0430\u0442\u0438 \u043c\u043e\u043b\u0435\u043a\u0443\u043b\u044f\u0440\u043d\u0443 \u0441\u043f\u043e\u0440\u0456\u0434\u043d\u0435\u043d\u0456\u0441\u0442\u044c \u0448\u0435\u0441\u0442\u0438 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u0430 \u0442\u0430\u043a\u043e\u0436 \u043f\u043e\u043a\u0440\u0430\u0449\u0435\u043d\u043d\u044f \u0435\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e\u0441\u0442\u0456 \u0443\u043d\u0430\u0441\u043b\u0456\u0434\u043e\u043a \u043f\u043e\u0454\u0434\u043d\u0430\u043d\u043d\u044f \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0443 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u0456 \u043c\u0435\u0442\u043e\u0434\u043e\u043c \u0441\u0442\u0435\u043a\u0456\u043d\u0433\u0443. \u041f\u043e\u043a\u0430\u0437\u0430\u043d\u0456 \u043c\u043e\u0434\u0435\u043b\u0456, \u044f\u043a\u0456 \u043f\u043e\u0454\u0434\u043d\u0430\u043d\u0456 \u0443 \u0434\u0432\u0430 \u043f\u043e\u0441\u043b\u0456\u0434\u043e\u0432\u043d\u0456 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u0456.
\n\u041a\u043b\u044e\u0447\u043e\u0432\u0456 \u0441\u043b\u043e\u0432\u0430:<\/strong> \u043c\u0435\u0442\u0430-\u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u043c\u0430\u0448\u0438\u043d\u043d\u0435 \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u043c\u0435\u0442\u043e\u0434\u0438 \u0430\u043d\u0441\u0430\u043c\u0431\u043b\u044e\u0432\u0430\u043d\u043d\u044f, \u043c\u043e\u043b\u0435\u043a\u0443\u043b\u044f\u0440\u043d\u0430 \u0441\u043f\u043e\u0440\u0456\u0434\u043d\u0435\u043d\u0456\u0441\u0442\u044c, \u0442\u0440\u0430\u043d\u0441\u0444\u043e\u0440\u043c\u0435\u0440\u0438, \u0431\u0443\u0441\u0442\u0438\u043d\u0433, \u0441\u0442\u0435\u043a\u0456\u043d\u0433, \u043a\u043e\u0435\u0444\u0456\u0446\u0456\u0454\u043d\u0442 \u0435\u043d\u0433\u0456\u0431\u0456\u044e\u0432\u0430\u043d\u043d\u044f.
\n\u00a0<\/strong><\/p>\n

\u00a0\u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0430\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u0430\u043d\u0433\u043b\u0456\u0439\u0441\u044c\u043a\u043e\u044e \u00a0\u043c\u043e\u0432\u043e\u044e<\/strong><\/p>\n

This paper uses the Super Learning principle to predict the molecular affinity between the receptor (large biomolecule) and ligands (small organic molecules). Meta-models study the optimal combination of individual basic models in two consecutive ensembles – classification and regression. Each costume contains six models of machine learning, which are combined by stacking. Base models include the reference vector method, random forest, gradient boosting, neural graph networks, direct propagation, and transformers. The first ensemble predicts binding probability and classifies all candidate molecules to the selected receptor into active and inactive. Ligands recognized as involved by the first ensemble are fed to the second ensemble, which assumes the degree of their affinity for the receptor in the form of an inhibition factor (Ki<\/sub>). A feature of the method is the rejection of the use of atomic coordinates of individual molecules and their complexes – thus eliminating experimental errors in sample preparation and measurement of nuclear coordinates and the method to determine the affinity of biomolecules with unknown spatial configurations. It is shown that meta-learning increases the response (Recall) of the classification ensemble by 34.9% and the coefficient of determination (R2<\/sup>) of the regression ensemble by 21% compared to the average values. This paper shows that an ensemble with meta-stacking is an asymptotically optimal system for learning. The feature of Super Learning is to use k-fold cross-validation to form first-level predictions that teach second-level models \u2014 or meta-models \u2014 that combine first-level models optimally. The ability to predict the molecular affinity of six machine learning models is studied, and the efficiency improvement is due to the combination of models in the ensemble by the stacking method. Models that are combined into two consecutive ensembles are shown.
\nKeywords:<\/strong> Super Learning, machine learning, ensemble methods, molecular affinity, transformers, boosting, stacking, inhibition coefficient.<\/p>\n

References<\/strong><\/p>\n

    \n
  1. Beck D., Haffari, G., Cohn, T. Graph-to-sequence learning using gated graph neural networks \/\/ Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Vol. 1. Association for Computational Linguistics, Melbourne, Australia. – 2018. – \u0420. 273\u2013283. https:\/\/doi.org\/10.18653\/v1\/P18- 1026.<\/li>\n
  2. Beck B., Shin B., Choi Y., Park S., Kang K. Predicting commercially available antiviral drugs that may act on the novel coronavirus (sars-cov-2) through a drug-target interaction deep learning model. Comput. Struct. Biotechnol. J. 2020. \u2013 784\u2013790. https:\/\/doi.org\/10.1016\/j.csbj.2020.03.025.<\/li>\n
  3. Breiman L. Random forests. Mach. Learn. 45 (1).- 2010. – P. 5\u201332. https:\/\/doi.org\/10.1023\/ A:1010933404324.<\/li>\n
  4. Chen Y.-C. Beware of docking! Trends Pharmacol. Sci. 36 (2). \u2013 2015. \u2013 P. 78\u201395. https:\/\/doi. org\/10.1016\/j.tips.2014.12.001.<\/li>\n
  5. Chen J.-Q., Chen H.-Y., Dai W.-j., Lv Q.-J., Chen C.-C. Artificial intelligence approach to find lead compounds for treating tumors. J. Phys. Chem. Lett. 10 (15). \u2013 2019. \u2013 P. 4382\u20134400. https:\/\/doi.org\/10.1021\/acs.jpclett.9b01426.<\/li>\n
  6. Chupakhin V., Marcou G., Baskin I., Varnek A., Rognan D. Predicting ligand binding modes from neural networks trained on protein-ligand interaction fingerprints. 53 (4). \u2013 2016. \u2013 P. 763\u2013772. https:\/\/doi.org\/10.1021\/ ci300200r.<\/li>\n
  7. Davis M., Hunt J., Herrgard S., Ciceri P., Wodicka L., Pallares G., Hocker M., Treiber D., Zarrinkar P. Comprehensive analysis of kinase inhibitor selectivity. Nat. Biotechnol. 29. \u2013 2010. \u2013 P. 1046\u20131051. https:\/\/doi.org\/10.1007\/978-1-4939-9752-7.<\/li>\n
  8. Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1. Association for Computational Linguistics, Minneapolis, Minnesota. \u2013 2019. – P. 4171\u20134186. https:\/\/doi.org\/10.18653\/v1\/N19-1423.<\/li>\n
  9. Ellingson S., Davis B., Allen J. Machine learning and ligand binding predictions: a review of data, methods, and obstacles. Biochim. Biophys. Acta (BBA) \u2013 General Subj. 1864 (6), \u2013 P. 129-545. https:\/\/doi.org\/10.1016\/j.bbagen.2020.129545.<\/li>\n
  10. Gao K., Nguyen D., Chen J., Wang R., Wei G.-W. Repositioning of 8565 existing drugs for COVID-19. 11 (13). \u2013 2020. \u2013 P. 5373\u20135382. https:\/\/doi.org\/ 10.1021\/acs.jpclett.0c01579.<\/li>\n
  11. Hartshorn M., Verdonk M., Chessari G., Brewerton S., Mooij W., Mortenson P., Murray C. Diverse, high-quality test set for the validation of protein-ligand docking performance. J. Med. Chem. 50 (4). \u2013 2007. \u2013 P. 726\u2013741. https:\/\/doi.org\/10.1021\/ jm061277y.<\/li>\n
  12. He T., Heidemeyer M., Ban F., Cherkasov A., Ester M. SimBoost: a read-across approach for predicting drug-target binding affinities using gradient boosting machines. 9. \u2013 2017. \u2013 P. https:\/\/doi.org\/10.1186\/s13321-017-0209-z.<\/li>\n
  13. Heck G., Pintro V., Pereira R., de Avila M., Levin N., de Azevedo Jr. W. Supervised machine learning methods applied to predict ligand-binding affinity. Curr. Med. Chem. 24 (23). \u2013 2017. \u2013 P. 2459\u20132470. https:\/\/doi.org\/10.2174\/ 0929867324666170623092503.<\/li>\n
  14. Kim S., Chen J., Cheng T., Gindulyte A., He J., He S., Li Q., Shoemaker B., Thiessen P., Yu B., Zaslavsky L., Zhang J., Bolton E. PubChem 2019 update: improved access to chemical data. Nucleic Acids Res. \u2013 2019. \u2013 P. 1102\u20131109.<\/li>\n
  15. Kowalewski J., Ray A. Predicting novel drugs for sars-cov-2 using machine learning from a >10 million chemical space. Helion 6, e04639. \u2013 2020.https:\/\/doi.org\/ 10.1016\/j.heliyon.2020.e04639.<\/li>\n
  16. Kundu I., Paul G., Banerjee R. A machine learning approach towards the prediction of protein-ligand binding affinity based on fundamental molecular properties. RSC Adv. 8. \u2013 2018. \u2013 P. 12127\u201312137. https:\/\/doi.org\/10.1039\/C8RA00003D.<\/li>\n
  17. Kwon Y., Shin W.-H., Ko J., Lee J. Ak-score: accurate protein-ligand binding affinity prediction using an ensemble of 3d-convolutional neural networks. Int. J. Mol. Sci. 21 (22). \u2013 2020. \u2013 P. https:\/\/doi.org\/10.3390\/ijms21228424.<\/li>\n<\/ol>\n

     <\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[65],"tags":[],"_links":{"self":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/12499"}],"collection":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=12499"}],"version-history":[{"count":3,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/12499\/revisions"}],"predecessor-version":[{"id":12577,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/12499\/revisions\/12577"}],"wp:attachment":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=12499"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=12499"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=12499"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}