State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis

Autor: Igor V. Tetko, Pavel Karpov, Ruud Van Deursen, Guillaume Godin

Publikováno v: Nature Communications, Vol 11, Iss 1, Pp 1-11 (2020)

Development of algorithms to predict reactant and reagents given a target molecule is key to accelerate retrosynthesis approaches. Here the authors demonstrate that applying augmentation techniques to the SMILE representation of target data significa

Externí odkaz: https://doaj.org/article/f3db04ada827413392a0875994a0169d

Transformer-CNN: Swiss knife for QSAR modeling and interpretation

Autor: Pavel Karpov, Guillaume Godin, Igor V. Tetko

Publikováno v: Journal of Cheminformatics, Vol 12, Iss 1, Pp 1-12 (2020)

Abstract We present SMILES-embeddings derived from the internal encoder state of a Transformer [1] model trained to canonize SMILES as a Seq2Seq problem. Using a CharNN [2] architecture upon the embeddings results in higher quality interpretable QSAR

Externí odkaz: https://doaj.org/article/6e78005fd43c4101b96dedb2d0b32a86

State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis

Autor: Guillaume Godin, Pavel Karpov, Ruud van Deursen, Igor V. Tetko

Publikováno v: Nature Communications
Nature Communications, Vol 11, Iss 1, Pp 1-11 (2020)
Nat. Commun. 11:5575 (2020)

We investigated the effect of different training scenarios on predicting the (retro)synthesis of chemical compounds using text-like representation of chemical reactions (SMILES) and Natural Language Processing (NLP) neural network Transformer archite

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::531e7b92d59fe077993c06fe72b3e9b6
https://pubmed.ncbi.nlm.nih.gov/33149154

Deep Generative Model for Sparse Graphs using Text-Based Learning with Augmentation in Generative Examination Networks

Autor: Ruud van Deursen, Guillaume Godin

Graphs and networks are a key research tool for a variety of science fields, most notably chemistry, biology, engineering and social sciences. Modeling and generation of graphs with efficient sampling is a key challenge for graphs. In particular, the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a8fc4d9306a7e9caa3f011d9a79818e
https://doi.org/10.26434/chemrxiv.9901070.v2

Augmentation Is What You Need!

Autor: Guillaume Godin, Eric Bruno, Pavel Karpov, Talia B. Kimber, Igor V. Tetko

Publikováno v: Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions-28th International Conference on Artificial Neural Networks, Munich, Germany, September 17–19, 2019, Proceedings
Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions ISBN: 9783030304928
ICANN (Workshop)
Lect. Notes Comput. Sc. 11731 LNCS, 831-835 (2019)
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions

We investigate the effect of augmentation of SMILES to increase theperformance of convolutional neural network models by extending the results ofour previous study [1] to new methods and augmentation scenarios. Wedemonstrate that augmentation signifi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::913b20dfd2964135c3292c148c971369
https://zenodo.org/record/3515037