Pub Date : 2021-12-01DOI: 10.1016/j.ailsci.2021.100022
Javed Iqbal, Martin Vogt, Jürgen Bajorath
Advances in image analysis through deep learning have catalyzed the recent use of molecular images in chemoinformatics and drug design for predictive modeling of compound properties and other applications. For image analysis and representation learning from molecular graphs, convolutional neural networks (CNNs) represent a preferred computational architecture. In this work, we have investigated the questions whether functional groups (FGs) and their distinguishing chemical features can be learned from compound images using CNNs of different complexity and whether such knowledge might be transferable to other prediction tasks. We have shown that frequently occurring FGs were comprehensively learned, leading to highly accurate multi-label FG predictions. Furthermore, we have determined that the FG knowledge acquired by CNNs was sufficient for accurate prediction of compound activity cliffs (ACs) via transfer learning. Re-training of FG prediction models on AC data optimized convolutional layer weights and further improved prediction accuracy. Through feature weight analysis and visualization, a rationale was provided for the ability of CNNs to learn FG chemistry and transfer this knowledge for effective AC prediction.
{"title":"Learning functional group chemistry from molecular images leads to accurate prediction of activity cliffs","authors":"Javed Iqbal, Martin Vogt, Jürgen Bajorath","doi":"10.1016/j.ailsci.2021.100022","DOIUrl":"10.1016/j.ailsci.2021.100022","url":null,"abstract":"<div><p>Advances in image analysis through deep learning have catalyzed the recent use of molecular images in chemoinformatics and drug design for predictive modeling of compound properties and other applications. For image analysis and representation learning from molecular graphs, convolutional neural networks (CNNs) represent a preferred computational architecture. In this work, we have investigated the questions whether functional groups (FGs) and their distinguishing chemical features can be learned from compound images using CNNs of different complexity and whether such knowledge might be transferable to other prediction tasks. We have shown that frequently occurring FGs were comprehensively learned, leading to highly accurate multi-label FG predictions. Furthermore, we have determined that the FG knowledge acquired by CNNs was sufficient for accurate prediction of compound activity cliffs (ACs) via transfer learning. Re-training of FG prediction models on AC data optimized convolutional layer weights and further improved prediction accuracy. Through feature weight analysis and visualization, a rationale was provided for the ability of CNNs to learn FG chemistry and transfer this knowledge for effective AC prediction.</p></div>","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667318521000222/pdfft?md5=cb926dd5579da39d2f820073674a8d1d&pid=1-s2.0-S2667318521000222-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47627435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-01DOI: 10.1016/j.ailsci.2021.100017
Denghui Liu , Chi Xu , Wenjun He , Zhimeng Xu , Wenqi Fu , Lei Zhang , Jie Yang , Zhihao Wang , Bing Liu , Guangdun Peng , Dali Han , Xiaolong Bai , Nan Qiao
Deep learning has achieved great successes in traditional fields like computer vision (CV), natural language processing (NLP), speech processing, and more. These advancements have greatly inspired researchers in genomics and made deep learning in genomics an exciting and popular topic. The convolutional neural network (CNN) and recurrent neural network (RNN) are frequently used to solve genomic sequencing and prediction problems, and multiple layer perception (MLP) and auto-encoders (AE) are frequently used for genomic profiling data like RNA expression data and gene mutation data. Here, we introduce a new neural network architecture-the residual fully-connected neural network (RFCN)-and describe its advantage in modeling genomic profiling data. We also incorporate AutoML algorithms and implement AutoGenome, an end-to-end, automated deep learning framework for genomic studies. By utilizing the proposed RFCN architecture, automatic hyper-parameter search, and neural architecture search algorithms, AutoGenome can automatically train high-performance deep learning models for various kinds of genomic profiling data. To help researchers better understand the trained models, AutoGenome can assess the importance of different features and export the most critical features for supervised learning tasks and the representative latent vectors for unsupervised learning tasks. We expect AutoGenome will become a popular tool in genomic studies.
{"title":"AutoGenome: An AutoML tool for genomic research","authors":"Denghui Liu , Chi Xu , Wenjun He , Zhimeng Xu , Wenqi Fu , Lei Zhang , Jie Yang , Zhihao Wang , Bing Liu , Guangdun Peng , Dali Han , Xiaolong Bai , Nan Qiao","doi":"10.1016/j.ailsci.2021.100017","DOIUrl":"https://doi.org/10.1016/j.ailsci.2021.100017","url":null,"abstract":"<div><p>Deep learning has achieved great successes in traditional fields like computer vision (CV), natural language processing (NLP), speech processing, and more. These advancements have greatly inspired researchers in genomics and made deep learning in genomics an exciting and popular topic. The convolutional neural network (CNN) and recurrent neural network (RNN) are frequently used to solve genomic sequencing and prediction problems, and multiple layer perception (MLP) and auto-encoders (AE) are frequently used for genomic profiling data like RNA expression data and gene mutation data. Here, we introduce a new neural network architecture-the residual fully-connected neural network (RFCN)-and describe its advantage in modeling genomic profiling data. We also incorporate AutoML algorithms and implement AutoGenome, an end-to-end, automated deep learning framework for genomic studies. By utilizing the proposed RFCN architecture, automatic hyper-parameter search, and neural architecture search algorithms, AutoGenome can automatically train high-performance deep learning models for various kinds of genomic profiling data. To help researchers better understand the trained models, AutoGenome can assess the importance of different features and export the most critical features for supervised learning tasks and the representative latent vectors for unsupervised learning tasks. We expect AutoGenome will become a popular tool in genomic studies.</p></div>","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667318521000179/pdfft?md5=cf6b23a0b87a53ab56b10caf93790902&pid=1-s2.0-S2667318521000179-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136694939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-11-01DOI: 10.1016/j.ailsci.2021.100024
Suwen Zhao
{"title":"GPCR Dock 2021: a blind docking competition in the post AlphaFold2 era","authors":"Suwen Zhao","doi":"10.1016/j.ailsci.2021.100024","DOIUrl":"https://doi.org/10.1016/j.ailsci.2021.100024","url":null,"abstract":"","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47624485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1016/j.ailsci.2023.100076
{"title":"Erratum regarding missing Conflict of Interest Statement & Ethical Statement in previously published articles","authors":"","doi":"10.1016/j.ailsci.2023.100076","DOIUrl":"https://doi.org/10.1016/j.ailsci.2023.100076","url":null,"abstract":"","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54191568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1016/j.ailsci.2023.100074
James Thompson, W. Walters, Jianwen A. Feng, Nicolas A. Pabon, Hongcheng Xu, Brian B. Goldman, D. Moustakas, M. Schmidt, Forrest York
{"title":"Corrigendum to “Optimizing active learning for free energy Calculations” [Artificial Intelligence in the Life Sciences, 2 (2022) 100050]","authors":"James Thompson, W. Walters, Jianwen A. Feng, Nicolas A. Pabon, Hongcheng Xu, Brian B. Goldman, D. Moustakas, M. Schmidt, Forrest York","doi":"10.1016/j.ailsci.2023.100074","DOIUrl":"https://doi.org/10.1016/j.ailsci.2023.100074","url":null,"abstract":"","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54191531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1016/j.ailsci.2023.100079
Astrid Stroobants, Lewis H. Mervin, O. Engkvist, G. Robb
{"title":"An industrial evaluation of proteochemometric modelling: Predicting drug-target affinities for kinases","authors":"Astrid Stroobants, Lewis H. Mervin, O. Engkvist, G. Robb","doi":"10.1016/j.ailsci.2023.100079","DOIUrl":"https://doi.org/10.1016/j.ailsci.2023.100079","url":null,"abstract":"","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54191637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.1016/j.ailsci.2023.100078
Negin Sadat Babaiha, H. Elsayed, Bide Zhang, Abish Kaladharan, Priya Sethumadhavan, Bruce Schultz, Jürgen Klein, Bruno Freudensprung, V. Lage-Rupprecht, A. Kodamullil, M. Jacobs, Stefan Geißler, S. Madan, M. Hofmann-Apitius
{"title":"A natural language processing system for the efficient updating of highly curated pathophysiology mechanism knowledge graphs","authors":"Negin Sadat Babaiha, H. Elsayed, Bide Zhang, Abish Kaladharan, Priya Sethumadhavan, Bruce Schultz, Jürgen Klein, Bruno Freudensprung, V. Lage-Rupprecht, A. Kodamullil, M. Jacobs, Stefan Geißler, S. Madan, M. Hofmann-Apitius","doi":"10.1016/j.ailsci.2023.100078","DOIUrl":"https://doi.org/10.1016/j.ailsci.2023.100078","url":null,"abstract":"","PeriodicalId":72304,"journal":{"name":"Artificial intelligence in the life sciences","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"54191598","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}