Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets
Abstract The assessment of protein–ligand interactions is critical at early stage of drug discovery. Computational approaches for efficiently predicting such interactions facilitate drug development. Recently, methods based on deep learning, including structure- and sequence-based models, have achie...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-04-01
|
Series: | Journal of Cheminformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13321-021-00510-6 |
id |
doaj-28244e0eeb884753ad2cf40e77c9ee87 |
---|---|
record_format |
Article |
spelling |
doaj-28244e0eeb884753ad2cf40e77c9ee872021-04-18T11:44:31ZengBMCJournal of Cheminformatics1758-29462021-04-0113111410.1186/s13321-021-00510-6Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasetsFan Hu0Jiaxin Jiang1Dongqi Wang2Muchun Zhu3Peng Yin4Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesGuangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesGuangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesGuangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesGuangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of SciencesAbstract The assessment of protein–ligand interactions is critical at early stage of drug discovery. Computational approaches for efficiently predicting such interactions facilitate drug development. Recently, methods based on deep learning, including structure- and sequence-based models, have achieved impressive performance on several different datasets. However, their application still suffers from a generalizability issue because of insufficient data, especially for structure based models, as well as a heterogeneity problem because of different label measurements and varying proteins across datasets. Here, we present an interpretable multi-task model to evaluate protein–ligand interaction (Multi-PLI). The model can run classification (binding or not) and regression (binding affinity) tasks concurrently by unifying different datasets. The model outperforms traditional docking and machine learning on both binary classification and regression tasks and achieves competitive results compared with some structure-based deep learning methods, even with the same training set size. Furthermore, combined with the proposed occlusion algorithm, the model can predict the important amino acids of proteins that are crucial for binding, thus providing a biological interpretation.https://doi.org/10.1186/s13321-021-00510-6InterpretableDeep learningMulti‐taskDrug discovery |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fan Hu Jiaxin Jiang Dongqi Wang Muchun Zhu Peng Yin |
spellingShingle |
Fan Hu Jiaxin Jiang Dongqi Wang Muchun Zhu Peng Yin Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets Journal of Cheminformatics Interpretable Deep learning Multi‐task Drug discovery |
author_facet |
Fan Hu Jiaxin Jiang Dongqi Wang Muchun Zhu Peng Yin |
author_sort |
Fan Hu |
title |
Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets |
title_short |
Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets |
title_full |
Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets |
title_fullStr |
Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets |
title_full_unstemmed |
Multi-PLI: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets |
title_sort |
multi-pli: interpretable multi‐task deep learning model for unifying protein–ligand interaction datasets |
publisher |
BMC |
series |
Journal of Cheminformatics |
issn |
1758-2946 |
publishDate |
2021-04-01 |
description |
Abstract The assessment of protein–ligand interactions is critical at early stage of drug discovery. Computational approaches for efficiently predicting such interactions facilitate drug development. Recently, methods based on deep learning, including structure- and sequence-based models, have achieved impressive performance on several different datasets. However, their application still suffers from a generalizability issue because of insufficient data, especially for structure based models, as well as a heterogeneity problem because of different label measurements and varying proteins across datasets. Here, we present an interpretable multi-task model to evaluate protein–ligand interaction (Multi-PLI). The model can run classification (binding or not) and regression (binding affinity) tasks concurrently by unifying different datasets. The model outperforms traditional docking and machine learning on both binary classification and regression tasks and achieves competitive results compared with some structure-based deep learning methods, even with the same training set size. Furthermore, combined with the proposed occlusion algorithm, the model can predict the important amino acids of proteins that are crucial for binding, thus providing a biological interpretation. |
topic |
Interpretable Deep learning Multi‐task Drug discovery |
url |
https://doi.org/10.1186/s13321-021-00510-6 |
work_keys_str_mv |
AT fanhu multipliinterpretablemultitaskdeeplearningmodelforunifyingproteinligandinteractiondatasets AT jiaxinjiang multipliinterpretablemultitaskdeeplearningmodelforunifyingproteinligandinteractiondatasets AT dongqiwang multipliinterpretablemultitaskdeeplearningmodelforunifyingproteinligandinteractiondatasets AT muchunzhu multipliinterpretablemultitaskdeeplearningmodelforunifyingproteinligandinteractiondatasets AT pengyin multipliinterpretablemultitaskdeeplearningmodelforunifyingproteinligandinteractiondatasets |
_version_ |
1721521908345733120 |