{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T04:49:05Z","timestamp":1769316545753,"version":"3.49.0"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2021,9,9]],"date-time":"2021-09-09T00:00:00Z","timestamp":1631145600000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["109-2320-B-002-040-"],"award-info":[{"award-number":["109-2320-B-002-040-"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007225","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST 109-2823-8-002-010-CV"],"award-info":[{"award-number":["MOST 109-2823-8-002-010-CV"]}],"id":[{"id":"10.13039\/100007225","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008761","name":"TFD","doi-asserted-by":"publisher","award":["MOHW110-FDA-D-114-000611"],"award-info":[{"award-number":["MOHW110-FDA-D-114-000611"]}],"id":[{"id":"10.13039\/501100008761","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010016","name":"NTU","doi-asserted-by":"publisher","award":["NTU-110L8809"],"award-info":[{"award-number":["NTU-110L8809"]}],"id":[{"id":"10.13039\/100010016","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010016","name":"NTU","doi-asserted-by":"publisher","award":["NTU-CC-110L890803"],"award-info":[{"award-number":["NTU-CC-110L890803"]}],"id":[{"id":"10.13039\/100010016","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,17]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The key to generating the best deep learning model for predicting molecular property is to test and apply various optimization methods. While individual optimization methods from different past works outside the pharmaceutical domain each succeeded in improving the model performance, better improvement may be achieved when specific combinations of these methods and practices are applied. In this work, three high-performance optimization methods in the literature that have been shown to dramatically improve model performance from other fields are used and discussed, eventually resulting in a general procedure for generating optimized CNN models on different properties of molecules. The three techniques are the dynamic batch size strategy for different enumeration ratios of the SMILES representation of compounds, Bayesian optimization for selecting the hyperparameters of a model and feature learning using chemical features obtained by a feedforward neural network, which are concatenated with the learned molecular feature vector. A total of seven different molecular properties (water solubility, lipophilicity, hydration energy, electronic properties, blood\u2013brain barrier permeability and inhibition) are used. We demonstrate how each of the three techniques can affect the model and how the best model can generally benefit from using Bayesian optimization combined with dynamic batch size tuning.<\/jats:p>","DOI":"10.1093\/bib\/bbab367","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T11:20:51Z","timestamp":1631100051000},"source":"Crossref","is-referenced-by-count":20,"title":["A general optimization protocol for molecular property prediction using a deep learning network"],"prefix":"10.1093","volume":"23","author":[{"given":"Jen-Hao","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, and he is an engineer with Chunghwa Telecom Co., Ltd., Taipei, Taiwan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8461-6181","authenticated-orcid":false,"given":"Yufeng Jane","family":"Tseng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan"}]}],"member":"286","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"key":"2022011921015878400_ref1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky","year":"2012"},{"key":"2022011921015878400_ref2","first-page":"3156","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2017"},{"key":"2022011921015878400_ref3","article-title":"Youtube-8m: a large-scale video classification benchmark","author":"Abu-El-Haija","year":"2016"},{"key":"2022011921015878400_ref4","first-page":"6299","volume-title":"proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Carreira","year":"2017"},{"key":"2022011921015878400_ref5","doi-asserted-by":"crossref","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","author":"Cho","year":"2014"},{"key":"2022011921015878400_ref6","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"2022011921015878400_ref7","doi-asserted-by":"crossref","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","article-title":"The rise of deep learning in drug discovery","volume":"23","author":"Chen","year":"2018","journal-title":"Drug Discov Today"},{"key":"2022011921015878400_ref8","first-page":"1","volume-title":"International Workshop on Multiple Classifier Systems","author":"Dietterich","year":"2000"},{"key":"2022011921015878400_ref9","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1021\/acs.jcim.6b00601","article-title":"Convolutional embedding of attributed molecular graphs for physical property prediction","volume":"57","author":"Coley","year":"2017","journal-title":"J Chem Inf Model"},{"key":"2022011921015878400_ref10","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1021\/ci400187y","article-title":"Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules","volume":"53","author":"Lusci","year":"2013","journal-title":"J Chem Inf Model"},{"key":"2022011921015878400_ref11","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"Perez","year":"2017"},{"key":"2022011921015878400_ref12","article-title":"Synergy effect between convolutional neural networks and themultiplicity of SMILES for improvement of molecular prediction","author":"Kimber","year":"2018"},{"key":"2022011921015878400_ref13","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv.7297379.v1","article-title":"Molecular transformer for chemical reaction prediction and uncertainty estimation","author":"Schwaller","year":"2018"},{"key":"2022011921015878400_ref14","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2022011921015878400_ref15","doi-asserted-by":"crossref","first-page":"18601","DOI":"10.1109\/ACCESS.2020.2968535","article-title":"Molecular property prediction based on a multichannel substructure graph","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"2022011921015878400_ref16","first-page":"2224","volume-title":"Advances in Neural Information Processing Systems","author":"Duvenaud","year":"2015"},{"key":"2022011921015878400_ref17","first-page":"1717","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Oquab","year":"2014"},{"key":"2022011921015878400_ref18","article-title":"Strategies for pre-training graph neural networks","author":"Hu","year":"2019"},{"key":"2022011921015878400_ref19","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1145\/3219819.3219838","volume-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Goh","year":"2018"},{"key":"2022011921015878400_ref20","article-title":"Augment your batch: better training with larger batches","author":"Hoffer","year":"2019"},{"key":"2022011921015878400_ref21","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1109\/JPROC.2015.2494218","article-title":"Taking the human out of the loop: a review of Bayesian optimization","volume":"104","author":"Shahriari","year":"2015","journal-title":"Proc IEEE"},{"key":"2022011921015878400_ref22","article-title":"Smiles2vec: an interpretable general-purpose deep neural network for predicting chemical properties","author":"Goh","year":"2017"},{"key":"2022011921015878400_ref23","doi-asserted-by":"crossref","first-page":"6091","DOI":"10.1039\/C8SC02339E","article-title":"\u201cFound in translation\u201d: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models","volume":"9","author":"Schwaller","year":"2018","journal-title":"Chem Sci"},{"key":"2022011921015878400_ref24","article-title":"Chemixnet: mixed dnn architectures for predicting chemical properties using multiple molecular representations","author":"Paul","year":"2018"},{"key":"2022011921015878400_ref25","doi-asserted-by":"crossref","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular representations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2022011921015878400_ref26","article-title":"Different molecular enumeration influences in deep learning: an example using aqueous solubility","volume":"22","author":"Chen","year":"2021","journal-title":"Brief Bioinform"},{"key":"2022011921015878400_ref27","article-title":"Convolutional sequence to sequence learning","author":"Gehring","year":"2017"},{"key":"2022011921015878400_ref28","first-page":"115","volume-title":"International Conference on Machine Learning","author":"Bergstra","year":"2013"},{"key":"2022011921015878400_ref29","first-page":"2546","volume-title":"Advances in Neural Information Processing Systems","author":"Bergstra","year":"2011"},{"key":"2022011921015878400_ref30","first-page":"1139","volume-title":"International Conference on Machine Learning","author":"Sutskever","year":"2013"},{"key":"2022011921015878400_ref31","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: a benchmark for molecular machine learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem Sci"},{"key":"2022011921015878400_ref32","volume-title":"Deep Learning for the Life Sciences: Applying Deep Learning to Genomics, Microscopy, Drug Discovery, and More","author":"Ramsundar","year":"2019"},{"key":"2022011921015878400_ref33","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"2022011921015878400_ref34","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"2022011921015878400_ref35","doi-asserted-by":"crossref","first-page":"1900131","DOI":"10.1002\/minf.201900131","article-title":"The effect of resampling on data-imbalanced conditions for prediction towards nuclear receptor profiling using deep learning","volume":"39","author":"Lee","year":"2020","journal-title":"Mol Inform"},{"key":"2022011921015878400_ref36","volume-title":"Rdkit: Open-source cheminformatics","author":"Landrum","year":"2006"},{"key":"2022011921015878400_ref37","first-page":"1","article-title":"Randomized SMILES strings improve the quality of molecular generative models","volume":"11","author":"Ar\u00fas-Pous","year":"2019","journal-title":"J Chem"},{"key":"2022011921015878400_ref38","article-title":"SMILES enumeration as data augmentation for neural network modeling of molecules","author":"Bjerrum","year":"2017"},{"key":"2022011921015878400_ref39","first-page":"848","volume-title":"Proceedings of the 20th International Conference on Machine Learning (icml-03)","author":"Yan","year":"2003"},{"key":"2022011921015878400_ref40","doi-asserted-by":"crossref","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/1\/bbab367\/42229720\/bbab367.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/23\/1\/bbab367\/42229720\/bbab367.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T21:03:49Z","timestamp":1642626229000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbab367\/6366324"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,8]]},"references-count":40,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,1,17]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbab367","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,1]]},"published":{"date-parts":[[2021,9,8]]},"article-number":"bbab367"}}