Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Timur Gimadiev"'
Publikováno v:
Journal of Cheminformatics, Vol 15, Iss 1, Pp 1-12 (2023)
Abstract In this work, we provide further development of the junction tree variational autoencoder (JT VAE) architecture in terms of implementation and application of the internal feature space of the model. Pretraining of JT VAE on a large dataset a
Externí odkaz:
https://doaj.org/article/4697268f5b9747b0b552a45c1608cda7
Autor:
William Bort, Igor I. Baskin, Timur Gimadiev, Artem Mukanov, Ramil Nugmanov, Pavel Sidorov, Gilles Marcou, Dragos Horvath, Olga Klimchuk, Timur Madzhidov, Alexandre Varnek
Publikováno v:
Scientific Reports, Vol 11, Iss 1, Pp 1-15 (2021)
Abstract The “creativity” of Artificial Intelligence (AI) in terms of generating de novo molecular structures opened a novel paradigm in compound design, weaknesses (stability & feasibility issues of such structures) notwithstanding. Here we show
Externí odkaz:
https://doaj.org/article/3d91d19a63b3499ebdae5082b570347c
In this work, we provide further development of the junction tree variational autoencoder (JT VAE) architecture in terms of implementation and application of the internal feature space of the model. Pretraining of JT VAE on a large dataset and furthe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::78e62590fbbaec886727a9a39b9860fc
https://doi.org/10.26434/chemrxiv-2022-z1l07
https://doi.org/10.26434/chemrxiv-2022-z1l07
Autor:
Nobuya Tsuji, Pavel Sidorov, Chendan Zhu, Yuuya Nagata, Timur Gimadiev, Alexandre Varnek, Benjamin List
Publikováno v:
Angewandte chemie-international edition. 62(11):e202218659
Catalyst optimization process is typically relying on an inductive and qualitative assumption of chemists based on screening data. While machine learning models using molecular properties or calculated 3D structures enable quantitative data evaluatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c2052f5bc2e3b7b6a4fba59477ab036
http://hdl.handle.net/2115/88658
http://hdl.handle.net/2115/88658
Autor:
William Bort, Igor I. Baskin, Pavel Sidorov, Gilles Marcou, Dragos Horvath, Timur Madzhidov, Alexandre Varnek, Timur Gimadiev, Ramil Nugmanov, Artem Mukanov
Here, we report an application of Artificial Intelligence techniques to generate novel chemical reactions of the given type. A sequence-to-sequence autoencoder was trained on the USPTO reaction database. Each reaction was converted into a single Cond
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22b1270df08122ea5013468a9b4a00ad
https://doi.org/10.26434/chemrxiv.11635929
https://doi.org/10.26434/chemrxiv.11635929
Publikováno v:
Transition Metal Chemistry; Oct2008, Vol. 33 Issue 7, p921-924, 4p