Cargando…
End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins
Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undisc...
Autores principales: | , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9886305/ https://www.ncbi.nlm.nih.gov/pubmed/36652496 http://dx.doi.org/10.1371/journal.pcbi.1010851 |
_version_ | 1784880107192582144 |
---|---|
author | Cai, Tian Xie, Li Zhang, Shuo Chen, Muge He, Di Badkul, Amitesh Liu, Yang Namballa, Hari Krishna Dorogan, Michael Harding, Wayne W. Mura, Cameron Bourne, Philip E. Xie, Lei |
author_facet | Cai, Tian Xie, Li Zhang, Shuo Chen, Muge He, Di Badkul, Amitesh Liu, Yang Namballa, Hari Krishna Dorogan, Michael Harding, Wayne W. Mura, Cameron Bourne, Philip E. Xie, Lei |
author_sort | Cai, Tian |
collection | PubMed |
description | Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space. |
format | Online Article Text |
id | pubmed-9886305 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-98863052023-01-31 End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins Cai, Tian Xie, Li Zhang, Shuo Chen, Muge He, Di Badkul, Amitesh Liu, Yang Namballa, Hari Krishna Dorogan, Michael Harding, Wayne W. Mura, Cameron Bourne, Philip E. Xie, Lei PLoS Comput Biol Research Article Systematically discovering protein-ligand interactions across the entire human and pathogen genomes is critical in chemical genomics, protein function prediction, drug discovery, and many other areas. However, more than 90% of gene families remain “dark”—i.e., their small-molecule ligands are undiscovered due to experimental limitations or human/historical biases. Existing computational approaches typically fail when the dark protein differs from those with known ligands. To address this challenge, we have developed a deep learning framework, called PortalCG, which consists of four novel components: (i) a 3-dimensional ligand binding site enhanced sequence pre-training strategy to encode the evolutionary links between ligand-binding sites across gene families; (ii) an end-to-end pretraining-fine-tuning strategy to reduce the impact of inaccuracy of predicted structures on function predictions by recognizing the sequence-structure-function paradigm; (iii) a new out-of-cluster meta-learning algorithm that extracts and accumulates information learned from predicting ligands of distinct gene families (meta-data) and applies the meta-data to a dark gene family; and (iv) a stress model selection step, using different gene families in the test data from those in the training and development data sets to facilitate model deployment in a real-world scenario. In extensive and rigorous benchmark experiments, PortalCG considerably outperformed state-of-the-art techniques of machine learning and protein-ligand docking when applied to dark gene families, and demonstrated its generalization power for target identifications and compound screenings under out-of-distribution (OOD) scenarios. Furthermore, in an external validation for the multi-target compound screening, the performance of PortalCG surpassed the rational design from medicinal chemists. Our results also suggest that a differentiable sequence-structure-function deep learning framework, where protein structural information serves as an intermediate layer, could be superior to conventional methodology where predicted protein structures were used for the compound screening. We applied PortalCG to two case studies to exemplify its potential in drug discovery: designing selective dual-antagonists of dopamine receptors for the treatment of opioid use disorder (OUD), and illuminating the understudied human genome for target diseases that do not yet have effective and safe therapeutics. Our results suggested that PortalCG is a viable solution to the OOD problem in exploring understudied regions of protein functional space. Public Library of Science 2023-01-18 /pmc/articles/PMC9886305/ /pubmed/36652496 http://dx.doi.org/10.1371/journal.pcbi.1010851 Text en © 2023 Cai et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Cai, Tian Xie, Li Zhang, Shuo Chen, Muge He, Di Badkul, Amitesh Liu, Yang Namballa, Hari Krishna Dorogan, Michael Harding, Wayne W. Mura, Cameron Bourne, Philip E. Xie, Lei End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
title | End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
title_full | End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
title_fullStr | End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
title_full_unstemmed | End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
title_short | End-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
title_sort | end-to-end sequence-structure-function meta-learning predicts genome-wide chemical-protein interactions for dark proteins |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9886305/ https://www.ncbi.nlm.nih.gov/pubmed/36652496 http://dx.doi.org/10.1371/journal.pcbi.1010851 |
work_keys_str_mv | AT caitian endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT xieli endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT zhangshuo endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT chenmuge endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT hedi endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT badkulamitesh endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT liuyang endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT namballaharikrishna endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT doroganmichael endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT hardingwaynew endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT muracameron endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT bournephilipe endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins AT xielei endtoendsequencestructurefunctionmetalearningpredictsgenomewidechemicalproteininteractionsfordarkproteins |