КФУ. Карточка публикации. Deep conditional variational autoencoder for reaction conditions prediction

КАЗАНСКИЙ
ФЕДЕРАЛЬНЫЙ УНИВЕРСИТЕТ

RUS

- EN
- 中文
- ES

DEEP CONDITIONAL VARIATIONAL AUTOENCODER FOR REACTION CONDITIONS PREDICTION

Форма представления

Тезисы и материалы конференций в зарубежных журналах и сборниках

Год публикации

2020

Язык

русский

Авторы, сотрудники КФУ

Афонина Валентина Александровна, автор

Варнек Александр , автор

Лин Аркадий Игоревич, автор

Маджидов Тимур Исмаилович, автор

Мазитов Данияр Амирович, автор

Нугманов Рамиль Ирекович, автор

Скибина Юлия Дмитриевна, автор

Авторы, студенты КФУ

Ахметшин Тагир Наилевич, автор

Библиографическое описание на языке оригинала

Madzhidov T.I. Deep conditional variational autoencoder for reaction conditions prediction / T.I.Madzhidov, D.A. Mazitov, V.A. Afonina, T.N. Akhmetshin, J.D. Skibina, A.I. Lin, R.I. Nugmanov, A. Varnek // 3rd RSC-BMCS/RSC-CICAG Artificial Intelligence in Chemistry. - London, 2020. - P. 55.

Аннотация

3rd RSC-BMCS/RSC-CICAG Artificial Intelligence in Chemistry

Ключевые слова

хемоинформатика, искусственный интеллект, предсказание условий, информатика реакций

Название журнала

3rd RSC-BMCS/RSC-CICAG Artificial Intelligence in Chemistry

Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на эту карточку

https://repository.kpfu.ru/?p_id=258451

Файлы ресурса

Название файла	Размер (Мб)	Формат
thesis.pdf	0,17	pdf	посмотреть / скачать

Полная запись метаданных

Поле DC	Значение	Язык
dc.contributor.author	Афонина Валентина Александровна	ru_RU
dc.contributor.author	Варнек Александр	ru_RU
dc.contributor.author	Лин Аркадий Игоревич	ru_RU
dc.contributor.author	Маджидов Тимур Исмаилович	ru_RU
dc.contributor.author	Мазитов Данияр Амирович	ru_RU
dc.contributor.author	Нугманов Рамиль Ирекович	ru_RU
dc.contributor.author	Скибина Юлия Дмитриевна	ru_RU
dc.contributor.author	Ахметшин Тагир Наилевич	ru_RU
dc.date.accessioned	2020-01-01T00:00:00Z	ru_RU
dc.date.available	2020-01-01T00:00:00Z	ru_RU
dc.date.issued	2020	ru_RU
dc.identifier.citation	Madzhidov T.I. Deep conditional variational autoencoder for reaction conditions prediction / T.I.Madzhidov, D.A. Mazitov, V.A. Afonina, T.N. Akhmetshin, J.D. Skibina, A.I. Lin, R.I. Nugmanov, A. Varnek // 3rd RSC-BMCS/RSC-CICAG Artificial Intelligence in Chemistry. - London, 2020. - P. 55.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/?p_id=258451	ru_RU
dc.description.abstract	3rd RSC-BMCS/RSC-CICAG Artificial Intelligence in Chemistry	ru_RU
dc.description.abstract	Synthesis planning domain has a second birthday after seminal paper of Segler et al.1 who proposed AI-powered technology for retrosynthetic route prediction. However, selection of optimal conditions for every reaction in synthetic route is almost as challenging and as important as prediction of the route itself. The main complication in prediction of optimal conditions are absence of negative examples, very large condition space, voids in reaction-condition matrix (all possible conditions for given reaction are unavailable). For some reactions, conditions are well-studied and documented, but for the other selection of conditions could be tricky and requires good knowledge and experience of chemists. Here, we propose an approach based on deep neural networks that predicts combination of catalyst-reagent-temperature-pressure best suited for a particular reaction. Unlike existing approaches2,3, here we do not rank possible conditions based on some technique but directly sample them using conditional variational autoencoder. Training and test sets comprised of hydrogenation reactions from Reaxys database, two datasets are collected: “small” consisting from 38K with limited set of conditions and “big” one including 196K reactions with vast variety of conditions. Three different latent distributions were compared, namely Gaussian (g-CVAE), Riemannian Normalizing Flow (mf-CVAE) and Hyperspherical Uniform (h-CVAE) distributions. Proposed approaches were shown superior performance to null model, which predicts conditions based on their popularity in training data, as well as over nearest-neighbor approach (KNN). The latter ranks possible conditions based on the similarity of corresponding reactions to a given one. For hydrogenation reactions, previously proposed approach of Gao et al.2 have shown mediocre performance	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	хемоинформатика	ru_RU
dc.subject	искусственный интеллект	ru_RU
dc.subject	предсказание условий	ru_RU
dc.subject	информатика реакций	ru_RU
dc.title	Deep conditional variational autoencoder for reaction conditions prediction	ru_RU
dc.type	Тезисы и материалы конференций в зарубежных журналах и сборниках	ru_RU