{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T00:02:08Z","timestamp":1772841728651,"version":"3.50.1"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T00:00:00Z","timestamp":1720137600000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302339"],"award-info":[{"award-number":["62302339"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372158"],"award-info":[{"award-number":["62372158"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Accurate prediction of acute dermal toxicity (ADT) is essential for the safe and effective development of contact drugs. Currently, graph neural networks, a form of deep learning technology, accurately model the structure of compound molecules, enhancing predictions of their ADT. However, many existing methods emphasize atom-level information transfer and overlook crucial data conveyed by molecular bonds and their interrelationships. Additionally, these methods often generate \u201cequal\u201d node representations across the entire graph, failing to accentuate \u201cimportant\u201d substructures like functional groups, pharmacophores, and toxicophores, thereby reducing interpretability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce a novel model, GraphADT, utilizing structure remapping and multi-view graph pooling (MVPool) technologies to accurately predict compound ADT. Initially, our model applies structure remapping to better delineate bonds, transforming \u201cbonds\u201d into new nodes and \u201cbond-atom-bond\u201d interactions into new edges, thereby reconstructing the compound molecular graph. Subsequently, we use MVPool to amalgamate data from various perspectives, minimizing biases inherent to single-view analyses. Following this, the model generates a robust node ranking collaboratively, emphasizing critical nodes or substructures to enhance model interpretability. Lastly, we apply a graph comparison learning strategy to train both the original and structure remapped molecular graphs, deriving the final molecular representation. Experimental results on public datasets indicate that the GraphADT model outperforms existing state-of-the-art models. The GraphADT model has been demonstrated to effectively predict compound ADT, offering potential guidance for the development of contact drugs and related treatments.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Our code and data are accessible at: https:\/\/github.com\/mxqmxqmxq\/GraphADT.git.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae438","type":"journal-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T10:03:54Z","timestamp":1720173834000},"source":"Crossref","is-referenced-by-count":13,"title":["GraphADT: empowering interpretable predictions of acute dermal toxicity with multi-view graph pooling and structure remapping"],"prefix":"10.1093","volume":"40","author":[{"given":"Xinqian","family":"Ma","sequence":"first","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Wenzhou University of Technology , Wenzhou 325027, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6840-2573","authenticated-orcid":false,"given":"Xiangzheng","family":"Fu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Changsha 410012, China"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Wenzhou University of Technology , Wenzhou 325027, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6586-0533","authenticated-orcid":false,"given":"Linlin","family":"Zhuo","sequence":"additional","affiliation":[{"name":"School of Data Science and Artificial Intelligence, Wenzhou University of Technology , Wenzhou 325027, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6406-1142","authenticated-orcid":false,"given":"Quan","family":"Zou","sequence":"additional","affiliation":[{"name":"Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China , Chengdu 611730, China"}]}],"member":"286","published-online":{"date-parts":[[2024,7,4]]},"reference":[{"key":"2024071222562444300_btae438-B1","author":"Bahdanau","year":"2015"},{"key":"2024071222562444300_btae438-B2","author":"BEE","year":"2017"},{"key":"2024071222562444300_btae438-B3","doi-asserted-by":"crossref","first-page":"27012","DOI":"10.1289\/EHP9341","article-title":"Stoptox: an in silico alternative to animal testing for acute systemic and topical toxicity","volume":"130","author":"Borba","year":"2022","journal-title":"Environ Health Perspect"},{"key":"2024071222562444300_btae438-B4","doi-asserted-by":"crossref","first-page":"2928","DOI":"10.1021\/acs.jcim.3c00045","article-title":"Fingerprint-enhanced graph attention network (fingat) model for antibiotic discovery","volume":"63","author":"Choo","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2024071222562444300_btae438-B5","first-page":"1561","article-title":"Equivariant graph neural networks for toxicity prediction","volume":"36","author":"Cremer","year":"2023","journal-title":"Chem Res Toxicol"},{"key":"2024071222562444300_btae438-B6","author":"Gasteiger","year":"2018"},{"key":"2024071222562444300_btae438-B7","first-page":"9176","article-title":"Equivariant graph hierarchy-based neural networks","volume":"35","author":"Han","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2024071222562444300_btae438-B8","first-page":"517","author":"Haveliwala","year":"2002"},{"key":"2024071222562444300_btae438-B9","doi-asserted-by":"crossref","first-page":"11966","DOI":"10.3390\/ijms241511966","article-title":"A benchmark study of graph models for molecular acute toxicity prediction","volume":"24","author":"Ketkar","year":"2023","journal-title":"Int J Mol Sci"},{"key":"2024071222562444300_btae438-B10","first-page":"3734","author":"Lee","year":"2019"},{"key":"2024071222562444300_btae438-B11","doi-asserted-by":"crossref","first-page":"1614","DOI":"10.1021\/acs.chemrestox.2c00207","article-title":"In silico prediction of human and rat liver microsomal stability via machine learning methods","volume":"35","author":"Li","year":"2022","journal-title":"Chem Res Toxicol"},{"key":"2024071222562444300_btae438-B12","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1021\/acs.chemrestox.4c00012","article-title":"In silico prediction of chemical acute dermal toxicity using explainable machine learning methods","volume":"37","author":"Lou","year":"2024","journal-title":"Chem Res Toxicol"},{"key":"2024071222562444300_btae438-B13","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1093\/toxsci\/kfy152","article-title":"Machine learning of toxicological data enables read-across structure activity relationships outperforming animal test reproducibility","volume":"165","author":"Luechtefeld","year":"2018","journal-title":"Toxicol Sci"},{"key":"2024071222562444300_btae438-B14","doi-asserted-by":"crossref","first-page":"108484","DOI":"10.1016\/j.compbiomed.2024.108484","article-title":"Advancing cancer driver gene detection via schur complement graph augmentation and independent subspace feature extraction","volume":"174","author":"Ma","year":"2024","journal-title":"Comput Biol Med"},{"key":"2024071222562444300_btae438-B15","doi-asserted-by":"crossref","first-page":"105043","DOI":"10.1016\/j.isci.2022.105043","article-title":"Edgeshaper: bond-centric shapely value-based explanation method for graph neural networks","volume":"25","author":"Mastropietro","year":"2022","journal-title":"Iscience"},{"key":"2024071222562444300_btae438-B16","author":"Page","year":"1999"},{"key":"2024071222562444300_btae438-B17","doi-asserted-by":"crossref","first-page":"168344","DOI":"10.1109\/ACCESS.2020.3022850","article-title":"Enhanced graph isomorphism network for molecular admet properties prediction","volume":"8","author":"Peng","year":"2020","journal-title":"Ieee Access"},{"key":"2024071222562444300_btae438-B18","doi-asserted-by":"crossref","first-page":"100621","DOI":"10.1016\/j.crmeth.2023.100621","article-title":"Molecular geometric deep learning","volume":"3","author":"Shen","year":"2023","journal-title":"Cell Rep Methods"},{"key":"2024071222562444300_btae438-B19","doi-asserted-by":"crossref","first-page":"1016","DOI":"10.1016\/j.csbj.2024.02.006","article-title":"Curvature-enhanced graph convolutional network for biomolecular interaction prediction","volume":"23","author":"Shen","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"key":"2024071222562444300_btae438-B20","author":"Torres","year":"2023"},{"key":"2024071222562444300_btae438-B21","doi-asserted-by":"crossref","first-page":"104865","DOI":"10.1016\/j.yrtph.2021.104865","article-title":"Increasing confidence in waiving dermal toxicity studies: a comparison of oral and dermal acute data with alternative approaches for agrochemicals and products","volume":"121","author":"Van Der Kamp","year":"2021","journal-title":"Regul Toxicol Pharmacol"},{"key":"2024071222562444300_btae438-B22","doi-asserted-by":"crossref","first-page":"bbae127","DOI":"10.1093\/bib\/bbae127","article-title":"Ms-bacl: enhancing metabolic stability prediction through bond graph augmentation and contrastive learning","volume":"25","author":"Wang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2024071222562444300_btae438-B23","doi-asserted-by":"crossref","first-page":"106783","DOI":"10.1016\/j.compbiomed.2023.106783","article-title":"Headtailtransfer: an efficient sampling method to improve the performance of graph neural network method in predicting sparse ncrna\u2013protein interactions","volume":"157","author":"Wei","year":"2023","journal-title":"Comput Biol Med"},{"key":"2024071222562444300_btae438-B24","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1016\/j.chemosphere.2017.09.047","article-title":"An interspecies correlation model to predict acute dermal toxicity of plant protection products to terrestrial life stages of amphibians using fish acute toxicity and bioconcentration data","volume":"189","author":"Weltje","year":"2017","journal-title":"Chemosphere"},{"key":"2024071222562444300_btae438-B25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ddtec.2020.11.009","article-title":"A compact review of molecular property prediction with graph neural networks","volume":"37","author":"Wieder","year":"2020","journal-title":"Drug Discov Today Technol"},{"key":"2024071222562444300_btae438-B26","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139088510","volume-title":"Social Media Mining: An Introduction","author":"Zafarani","year":"2014"},{"key":"2024071222562444300_btae438-B27","doi-asserted-by":"crossref","first-page":"bbad483","DOI":"10.1093\/bib\/bbad483","article-title":"Joint deep autoencoder and subgraph augmentation for inferring microbial responses to drugs","volume":"25","author":"Zhou","year":"2024","journal-title":"Brief Bioinform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae438\/58448662\/btae438.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/7\/btae438\/58531307\/btae438.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/7\/btae438\/58531307\/btae438.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,12]],"date-time":"2024-07-12T22:57:15Z","timestamp":1720825035000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae438\/7705980"}},"subtitle":[],"editor":[{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2024,7,1]]},"references-count":27,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae438","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,7,1]]},"article-number":"btae438"}}