Cargando…
Improving Compound Activity Classification via Deep Transfer and Representation Learning
[Image: see text] Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure–activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neura...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2022
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8945064/ https://www.ncbi.nlm.nih.gov/pubmed/35350358 http://dx.doi.org/10.1021/acsomega.1c06805 |
_version_ | 1784673863245758464 |
---|---|
author | Dey, Vishal Machiraju, Raghu Ning, Xia |
author_facet | Dey, Vishal Machiraju, Raghu Ning, Xia |
author_sort | Dey, Vishal |
collection | PubMed |
description | [Image: see text] Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure–activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks. |
format | Online Article Text |
id | pubmed-8945064 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | American Chemical Society |
record_format | MEDLINE/PubMed |
spelling | pubmed-89450642022-03-28 Improving Compound Activity Classification via Deep Transfer and Representation Learning Dey, Vishal Machiraju, Raghu Ning, Xia ACS Omega [Image: see text] Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure–activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks. American Chemical Society 2022-03-11 /pmc/articles/PMC8945064/ /pubmed/35350358 http://dx.doi.org/10.1021/acsomega.1c06805 Text en © 2022 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Dey, Vishal Machiraju, Raghu Ning, Xia Improving Compound Activity Classification via Deep Transfer and Representation Learning |
title | Improving Compound Activity Classification via Deep
Transfer and Representation Learning |
title_full | Improving Compound Activity Classification via Deep
Transfer and Representation Learning |
title_fullStr | Improving Compound Activity Classification via Deep
Transfer and Representation Learning |
title_full_unstemmed | Improving Compound Activity Classification via Deep
Transfer and Representation Learning |
title_short | Improving Compound Activity Classification via Deep
Transfer and Representation Learning |
title_sort | improving compound activity classification via deep
transfer and representation learning |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8945064/ https://www.ncbi.nlm.nih.gov/pubmed/35350358 http://dx.doi.org/10.1021/acsomega.1c06805 |
work_keys_str_mv | AT deyvishal improvingcompoundactivityclassificationviadeeptransferandrepresentationlearning AT machirajuraghu improvingcompoundactivityclassificationviadeeptransferandrepresentationlearning AT ningxia improvingcompoundactivityclassificationviadeeptransferandrepresentationlearning |