Extension of multi-site analogue series with potent compounds using a bidirectional transformer-based chemical language model-Reference-Cited by-同舟云学术

Extension of multi-site analogue series with potent compounds using a bidirectional transformer-based chemical language model

Published:2024 Issue:7 Volume:15 Page:2527-2537
ISSN:2632-8682
Container-title:RSC Medicinal Chemistry
language:en
Short-container-title:RSC Med. Chem.

Author:

Chen Hengwei¹,Yoshimori Atsushi²,Bajorath Jürgen¹³^ORCID

Affiliation:

1. Department of Life Science Informatics and Data Science, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, University of Bonn, Friedrich-Hirzebruch-Allee 5/6, D-53115 Bonn, Germany

2. Institute for Theoretical Medicine, Inc., 26-1 Muraoka-Higashi 2-chome, Fujisawa, Kanagawa 251-0012, Japan

3. Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Friedrich-Hirzebruch-Allee 5/6, D-53115 Bonn, Germany

Abstract

Shown is the extension of an analogue series with a new potent compound using a chemical language model. Substitution sites and non-hydrogen R-groups are colored in red (the log-likelihood score for the new analogue is reported in parentheses).

Funder

China Scholarship Council

Publisher

Royal Society of Chemistry (RSC)

Link

http://pubs.rsc.org/en/content/articlepdf/2024/MD/D4MD00423J

Reference38 articles.

1. Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

2. Applications of Deep Learning in Molecule Generation and Molecular Property Prediction

3. Exploring chemical space using natural language processing methodologies for drug discovery

4. AI-based language models powering drug discovery and development

5. Generating Focused Molecule Libraries for Drug Discovery with Recurrent Neural Networks