{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T22:31:58Z","timestamp":1784845918018,"version":"3.55.0"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T00:00:00Z","timestamp":1671321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Jiangsu Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Anhui Science Foundation for Distinguished Young Scholars"},{"name":"Project of Stable Support for Youth Team in Basic Research Field, CAS"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The rapid progress of machine learning (ML) in predicting molecular properties enables high-precision predictions being routinely achieved. However, many ML models, such as conventional molecular graph, cannot differentiate stereoisomers of certain types, particularly conformational and chiral ones that share the same bonding connectivity but differ in spatial arrangement. Here, we designed a hybrid molecular graph network, Chemical Feature Fusion Network (CFFN), to address the issue by integrating planar and stereo information of molecules in an interweaved fashion. The three-dimensional (3D, i.e., stereo) modality guarantees precision and completeness by providing unabridged information, while the two-dimensional (2D, i.e., planar) modality brings in chemical intuitions as prior knowledge for guidance. The zipper-like arrangement of 2D and 3D information processing promotes cooperativity between them, and their synergy is the key to our model\u2019s success. Experiments on various molecules or conformational datasets including a special newly created chiral molecule dataset comprised of various configurations and conformations demonstrate the superior performance of CFFN. The advantage of CFFN is even more significant in datasets made of small samples. Ablation experiments confirm that fusing 2D and 3D molecular graphs as unambiguous molecular descriptors can not only effectively distinguish molecules and their conformations, but also achieve more accurate and robust prediction of quantum chemical properties.<\/jats:p>","DOI":"10.1093\/bib\/bbac560","type":"journal-article","created":{"date-parts":[[2022,12,18]],"date-time":"2022-12-18T12:57:51Z","timestamp":1671368271000},"source":"Crossref","is-referenced-by-count":25,"title":["Fusing 2D and 3D molecular graphs as unambiguous molecular descriptors for conformational and chiral stereoisomers"],"prefix":"10.1093","volume":"24","author":[{"given":"Wenjie","family":"Du","sequence":"first","affiliation":[{"name":"University of Science and Technology of China School of Software Engineering, , Hefei 230026, China"},{"name":"University of Science and Technology of China Suzhou Institute for Advanced Research, , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoting","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China Suzhou Institute for Advanced Research, , Suzhou, Jiangsu 215123, China"},{"name":"University of Science and Technology of China School of Computer Science and Technology, , Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China School of Software Engineering, , Hefei 230026, China"},{"name":"University of Science and Technology of China Suzhou Institute for Advanced Research, , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"FenFen","family":"Ma","sequence":"additional","affiliation":[{"name":"Suzhou Laboratory , Suzhou 215123, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China School of Chemistry and Materials Science, , Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaochao","family":"Bao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China Suzhou Institute for Advanced Research, , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoyuan","family":"Huo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China Suzhou Institute for Advanced Research, , Suzhou, Jiangsu 215123, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China School of Chemistry and Materials Science, , Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Suzhou Laboratory , Suzhou 215123, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6079-7053","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China School of Software Engineering, , Hefei 230026, China"},{"name":"University of Science and Technology of China Suzhou Institute for Advanced Research, , Suzhou, Jiangsu 215123, China"},{"name":"University of Science and Technology of China School of Computer Science and Technology, , Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,12,18]]},"reference":[{"issue":"7715","key":"2023011917081920400_ref1","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"issue":"6","key":"2023011917081920400_ref2","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1038\/s41570-021-00278-1","article-title":"Molecular excited states through a machine learning lens","volume":"5","author":"Dral","year":"2021","journal-title":"Nat Rev Chem"},{"issue":"1","key":"2023011917081920400_ref3","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1038\/s41467-021-23720-w","article-title":"Algebraic graph-assisted bidirectional transformers for molecular property prediction","volume":"12","author":"Chen","year":"2021","journal-title":"Nat Commun"},{"issue":"9","key":"2023011917081920400_ref4","doi-asserted-by":"crossref","first-page":"1801367","DOI":"10.1002\/advs.201801367","article-title":"Deep learning spectroscopy: neural networks for molecular excitation spectra","volume":"6","author":"Ghosh","year":"2019","journal-title":"Adv Sci (Weinh)"},{"issue":"22","key":"2023011917081920400_ref5","doi-asserted-by":"crossref","first-page":"224104","DOI":"10.1063\/5.0073689","article-title":"Forecasting nonadiabatic dynamics using hybrid convolutional neural network\/long short-term memory network","volume":"155","author":"Wu","year":"2021","journal-title":"J Chem Phys"},{"issue":"3","key":"2023011917081920400_ref6","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1021\/acs.jcim.9b00943","article-title":"Bidirectional molecule generation with recurrent neural networks","volume":"60","author":"Grisoni","year":"2020","journal-title":"J Chem Inf Model"},{"issue":"5","key":"2023011917081920400_ref7","doi-asserted-by":"crossref","first-page":"2175","DOI":"10.1021\/acs.jcim.0c01366","article-title":"Dielectric polymer property prediction using recurrent neural networks with optimizations","volume":"61","author":"Nazarova","year":"2021","journal-title":"J Chem Inf Model"},{"issue":"3","key":"2023011917081920400_ref8","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1093\/bib\/bbz042","article-title":"Graph convolutional networks for computational drug development and discovery","volume":"21","author":"Sun","year":"2020","journal-title":"Brief Bioinform"},{"issue":"18","key":"2023011917081920400_ref9","doi-asserted-by":"crossref","first-page":"e2202713119","DOI":"10.1073\/pnas.2202713119","article-title":"Machine learning recognition of protein secondary structures based on two-dimensional spectroscopic descriptors","volume":"119","author":"Ren","year":"2022","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"11","key":"2023011917081920400_ref10","doi-asserted-by":"crossref","first-page":"1444","DOI":"10.1038\/s41587-021-00946-z","article-title":"Prediction of drug efficacy from transcriptional profiles with deep learning","volume":"39","author":"Zhu","year":"2021","journal-title":"Nat Biotechnol"},{"issue":"12","key":"2023011917081920400_ref11","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1021\/acscentsci.7b00355","article-title":"Computer-assisted retrosynthesis based on molecular similarity","volume":"3","author":"Coley","year":"2017","journal-title":"ACS Cent Sci"},{"issue":"7698","key":"2023011917081920400_ref12","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1038\/nature25978","article-title":"Planning chemical syntheses with deep neural networks and symbolic AI","volume":"555","author":"Segler","year":"2018","journal-title":"Nature"},{"issue":"1","key":"2023011917081920400_ref13","doi-asserted-by":"crossref","first-page":"5575","DOI":"10.1038\/s41467-020-19266-y","article-title":"State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis","volume":"11","author":"Tetko","year":"2020","journal-title":"Nat Commun"},{"issue":"15","key":"2023011917081920400_ref14","first-page":"1","article-title":"Extraction of organic chemistry grammar from unsupervised learning of chemical reactions","volume":"7","author":"Philippe Schwaller","year":"2021","journal-title":"Sci Adv"},{"issue":"12","key":"2023011917081920400_ref15","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1038\/s42256-021-00418-8","article-title":"Geometric deep learning on molecular representations","volume":"3","author":"Atz","year":"2021","journal-title":"Nat Mach Intell"},{"issue":"1","key":"2023011917081920400_ref16","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"Smiles, a chemical language and information-system .1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Comput Sci"},{"issue":"6","key":"2023011917081920400_ref17","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab152","article-title":"MG-BERT: leveraging unsupervised atomic representation learning for molecular property prediction","volume":"22","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2023011917081920400_ref18","first-page":"429\u201336","volume-title":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","author":"Wang","year":"2019"},{"issue":"16","key":"2023011917081920400_ref19","doi-asserted-by":"crossref","first-page":"8373","DOI":"10.1039\/D0CP00305K","article-title":"Are 2D fingerprints still valuable for drug discovery?","volume":"22","author":"Gao","year":"2020","journal-title":"Phys Chem Chem Phys"},{"issue":"2","key":"2023011917081920400_ref20","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1021\/acs.accounts.0c00699","article-title":"Applications of deep learning in molecule generation and molecular property prediction","volume":"54","author":"Walters","year":"2021","journal-title":"Acc Chem Res"},{"issue":"2","key":"2023011917081920400_ref21","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/s42256-021-00438-4","article-title":"Geometry-enhanced molecular representation learning for property prediction","volume":"4","author":"Fang","year":"2022","journal-title":"Nat Mach Intell"},{"issue":"5","key":"2023011917081920400_ref22","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab078","article-title":"A spatial-temporal gated attention module for molecular property prediction based on molecular geometry","volume":"22","author":"Li","year":"2021","journal-title":"Brief Bioinform"},{"issue":"10","key":"2023011917081920400_ref23","doi-asserted-by":"crossref","first-page":"5044","DOI":"10.1109\/JBHI.2021.3089162","article-title":"3DMol-net: learn 3D molecular representation using adaptive graph convolutional network based on rotation invariance","volume":"26","author":"Li","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"issue":"17","key":"2023011917081920400_ref24","doi-asserted-by":"crossref","first-page":"1604","DOI":"10.1002\/cmdc.201900458","article-title":"Enhanced deep-learning prediction of molecular properties via augmentation of bond topology","volume":"14","author":"Cho","year":"2019","journal-title":"ChemMedChem"},{"key":"2023011917081920400_ref25","article-title":"3D Infomax improves GNNs for molecular property prediction","volume":"162","author":"St\u00e4rk","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"2023011917081920400_ref26","first-page":"991","article-title":"SchNet: a continuous-filter convolutional neural network for modeling quantum interactions","volume-title":"31st Annual Conference on Neural Information Processing Systems (NIPS)","author":"Sch\u00fctt","year":"2017"},{"key":"2023011917081920400_ref27","article-title":"Directional message passing for molecular graphs","author":"Klicpera","year":"2020"},{"key":"2023011917081920400_ref28","article-title":"Spherical message passing for 3D graph networks","author":"Liu","year":"2022","journal-title":"International Conference on Learning Representations"},{"issue":"7843","key":"2023011917081920400_ref29","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1038\/d41586-020-03259-4","article-title":"Accurate machine learning in materials science facilitated by using diverse data sources","volume":"589","author":"Rohit","year":"2021","journal-title":"Nature"},{"issue":"1","key":"2023011917081920400_ref30","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1038\/s43588-020-00002-x","article-title":"Learning properties of ordered and disordered materials from multi-fidelity data","volume":"1","author":"Chen","year":"2021","journal-title":"Nat Comput Sci"},{"key":"2023011917081920400_ref31","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.commatsci.2016.12.004","article-title":"Multi-fidelity machine learning models for accurate bandgap predictions of solids","volume":"129","author":"Pilania","year":"2017","journal-title":"Comput Mater Sci"},{"key":"2023011917081920400_ref32","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/j.jcp.2016.12.039","article-title":"Error correction in multi-fidelity molecular dynamics simulations using functional uncertainty quantification","volume":"334","author":"Reeve","year":"2017","journal-title":"J Comput Phys"},{"issue":"31","key":"2023011917081920400_ref33","doi-asserted-by":"crossref","first-page":"16998","DOI":"10.1039\/D1CP02521J","article-title":"Robustness and accuracy improvement of data processing with 2D neural networks for transient absorption dynamics","volume":"23","author":"Zhao","year":"2021","journal-title":"Phys Chem Chem Phys"},{"issue":"6","key":"2023011917081920400_ref34","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","article-title":"Physics-informed machine learning","volume":"3","author":"Karniadakis","year":"2021","journal-title":"Nat Rev Phys"},{"key":"2023011917081920400_ref35","doi-asserted-by":"crossref","first-page":"140022","DOI":"10.1038\/sdata.2014.22","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci Data"},{"issue":"6","key":"2023011917081920400_ref36","doi-asserted-by":"crossref","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","article-title":"PhysNet: a neural network for predicting energies, forces, dipole moments, and partial charges","volume":"15","author":"Unke","year":"2019","journal-title":"J Chem Theory Comput"},{"issue":"1","key":"2023011917081920400_ref37","doi-asserted-by":"crossref","first-page":"5223","DOI":"10.1038\/s41467-020-19093-1","article-title":"Quantum chemical accuracy from density functional approximations via machine learning","volume":"11","author":"Bogojeski","year":"2020","journal-title":"Nat Commun"},{"issue":"13","key":"2023011917081920400_ref38","doi-asserted-by":"crossref","first-page":"1315","DOI":"10.1002\/cmdc.201700798","article-title":"Chiral cliffs: investigating the influence of chirality on binding affinity","volume":"13","author":"Schneider","year":"2018","journal-title":"ChemMedChem"},{"issue":"16","key":"2023011917081920400_ref39","doi-asserted-by":"crossref","first-page":"11169","DOI":"10.1103\/PhysRevB.54.11169","article-title":"Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set","volume":"54","author":"Kresse","year":"1996","journal-title":"Phys Rev B"},{"key":"2023011917081920400_ref40","first-page":"2547","article-title":"Pathfinder discovery networks for neural message passing","author":"Rozemberczki","year":"2021"},{"key":"2023011917081920400_ref41","first-page":"14","article-title":"Open Babel: an open chemical toolbox","volume":"3","author":"O'Boyle","year":"2011","journal-title":"J Chem"},{"issue":"3","key":"2023011917081920400_ref42","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1038\/s42256-020-0160-y","article-title":"Generative molecular design in low data regimes","volume":"2","author":"Moret","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2023011917081920400_ref43","first-page":"258","article-title":"RDKit: open-source cheminformatics from machine learning to chemical registration","author":"Landrum","year":"2019"},{"key":"2023011917081920400_ref44","year":"2018"},{"key":"2023011917081920400_ref45","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017"},{"key":"2023011917081920400_ref46","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"International Conference on Learning Representations","author":"Kipf","year":"2017"},{"key":"2023011917081920400_ref47","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"Maas","year":"2013"},{"issue":"11","key":"2023011917081920400_ref56","doi-asserted-by":"crossref","first-page":"5255","DOI":"10.1021\/acs.jctc.7b00577","article-title":"Prediction errors of molecular machine learning models lower than hybrid DFT error","volume":"13","author":"Faber","year":"2017","journal-title":"J Chem Theory Comput"},{"key":"2023011917081920400_ref48","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"2023011917081920400_ref49","volume-title":"Molecular Modelling: Principles and Applications","author":"Leach","year":"2001"},{"issue":"11","key":"2023011917081920400_ref50","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J Chem Inf Model"},{"key":"2023011917081920400_ref51","doi-asserted-by":"crossref","first-page":"13890","DOI":"10.1038\/ncomms13890","article-title":"Quantum-chemical insights from deep tensor neural networks","volume":"8","author":"Schutt","year":"2017","journal-title":"Nat Commun"},{"issue":"1","key":"2023011917081920400_ref52","doi-asserted-by":"crossref","first-page":"3887","DOI":"10.1038\/s41467-018-06169-2","article-title":"Towards exact molecular dynamics simulations with machine-learned force fields","volume":"9","author":"Chmiela","year":"2018","journal-title":"Nat Commun"},{"issue":"2","key":"2023011917081920400_ref53","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1515\/nanoph-2018-0167","article-title":"Metamaterials and chiral sensing: a review of fundamentals and applications","volume":"8","author":"Yoo","year":"2019","journal-title":"Nanophotonics"},{"key":"2023011917081920400_ref54","article-title":"Neural architecture search: a survey","volume":"20","author":"Elsken","year":"2019","journal-title":"J Mach Learn Res"},{"issue":"9","key":"2023011917081920400_ref55","doi-asserted-by":"crossref","first-page":"4571","DOI":"10.1073\/pnas.1906831117","article-title":"Expert-augmented machine learning","volume":"117","author":"Gennatas","year":"2020","journal-title":"Proc Natl Acad Sci U S A"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/1\/bbac560\/48781977\/bbac560.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/1\/bbac560\/48781977\/bbac560.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,19]],"date-time":"2023-01-19T17:15:03Z","timestamp":1674148503000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbac560\/6931719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,18]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,19]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbac560","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1]]},"published":{"date-parts":[[2022,12,18]]},"article-number":"bbac560"}}