Cargando…
Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model
In drug design, the prediction of new active compounds from protein sequence data has only been attempted in a few studies thus far. This prediction task is principally challenging because global protein sequence similarity has strong evolutional and structural implications, but is often only vaguel...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10216779/ https://www.ncbi.nlm.nih.gov/pubmed/37238703 http://dx.doi.org/10.3390/biom13050833 |
_version_ | 1785048379797012480 |
---|---|
author | Yoshimori, Atsushi Bajorath, Jürgen |
author_facet | Yoshimori, Atsushi Bajorath, Jürgen |
author_sort | Yoshimori, Atsushi |
collection | PubMed |
description | In drug design, the prediction of new active compounds from protein sequence data has only been attempted in a few studies thus far. This prediction task is principally challenging because global protein sequence similarity has strong evolutional and structural implications, but is often only vaguely related to ligand binding. Deep language models adapted from natural language processing offer new opportunities to attempt such predictions via machine translation by directly relating amino acid sequences and chemical structures to each based on textual molecular representations. Herein, we introduce a biochemical language model with transformer architecture for the prediction of new active compounds from sequence motifs of ligand binding sites. In a proof-of-concept application on inhibitors of more than 200 human kinases, the Motif2Mol model revealed promising learning characteristics and an unprecedented ability to consistently reproduce known inhibitors of different kinases. |
format | Online Article Text |
id | pubmed-10216779 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-102167792023-05-27 Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model Yoshimori, Atsushi Bajorath, Jürgen Biomolecules Article In drug design, the prediction of new active compounds from protein sequence data has only been attempted in a few studies thus far. This prediction task is principally challenging because global protein sequence similarity has strong evolutional and structural implications, but is often only vaguely related to ligand binding. Deep language models adapted from natural language processing offer new opportunities to attempt such predictions via machine translation by directly relating amino acid sequences and chemical structures to each based on textual molecular representations. Herein, we introduce a biochemical language model with transformer architecture for the prediction of new active compounds from sequence motifs of ligand binding sites. In a proof-of-concept application on inhibitors of more than 200 human kinases, the Motif2Mol model revealed promising learning characteristics and an unprecedented ability to consistently reproduce known inhibitors of different kinases. MDPI 2023-05-13 /pmc/articles/PMC10216779/ /pubmed/37238703 http://dx.doi.org/10.3390/biom13050833 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yoshimori, Atsushi Bajorath, Jürgen Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model |
title | Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model |
title_full | Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model |
title_fullStr | Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model |
title_full_unstemmed | Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model |
title_short | Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model |
title_sort | motif2mol: prediction of new active compounds based on sequence motifs of ligand binding sites in proteins using a biochemical language model |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10216779/ https://www.ncbi.nlm.nih.gov/pubmed/37238703 http://dx.doi.org/10.3390/biom13050833 |
work_keys_str_mv | AT yoshimoriatsushi motif2molpredictionofnewactivecompoundsbasedonsequencemotifsofligandbindingsitesinproteinsusingabiochemicallanguagemodel AT bajorathjurgen motif2molpredictionofnewactivecompoundsbasedonsequencemotifsofligandbindingsitesinproteinsusingabiochemicallanguagemodel |