{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T15:00:59Z","timestamp":1790607659620,"version":"4.1.0"},"reference-count":27,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Siriraj research development fund","award":["R016737002"],"award-info":[{"award-number":["R016737002"]}]},{"name":"the Program Management Unit for Human Resources & Institutional Development, Research, and Innovation","award":["B05F650015"],"award-info":[{"award-number":["B05F650015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Collision cross section (CCS) measurements from ion mobility\u2013mass spectrometry improve confidence in molecular identification in metabolomics and lipidomics and reduce false-positive annotations in untargeted analyses. However, experimental CCS coverage remains incomplete, and accurate computational prediction remains needed. Here, we present Deep3DCCS, a geometry-driven deep learning framework that predicts CCS from stacked multi-angle molecular projection tensors using a three-dimensional convolutional neural network operating across the projection-view and two spatial image dimensions. Three-dimensional molecular structures generated from SMILES strings were rotated around the x, y, and z-axes, converted into binary two-dimensional projections, and assembled into standardized multi-view tensors for CCS regression. Deep3DCCS was developed and evaluated using curated AllCCS and METLIN lipid CCS datasets containing 3948 molecule\u2013adduct entries across [M \u2013 H]\u2212, [M + H]+, and [M + Na]+ ions, and input optimization identified 32 \u00d7 32 pixel projections with five rotations per axis as a practical balance between prediction accuracy, model stability, and computational feasibility. In independent true-validation experiments, AllCCS-trained models achieved MRPE values of 3.27\u20133.79% on AllCCS validation data and 2.93\u20133.72% on METLIN validation data, whereas METLIN-trained models transferred less effectively to the broader AllCCS chemical space. Overall, these results support multi-view molecular projection tensors as a viable geometry-driven representation for CCS prediction and demonstrate that substantial CCS-relevant information can be learned directly from three-dimensional molecular morphology using a 3DCNN architecture, with low single-digit prediction errors across independent and cross-dataset validation experiments.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c00371","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T22:01:39Z","timestamp":1788818499000},"page":"11619-11630","source":"Crossref","is-referenced-by-count":0,"title":["Deep3DCCS: Geometry-Driven Collision Cross Section\nPrediction from Multi-View Molecular Projection Tensors"],"prefix":"10.1021","volume":"66","author":[{"given":"Pattipong","family":"Wisanpitayakorn","sequence":"first","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivek Bhakta","family":"Mathema","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0245-0833","authenticated-orcid":true,"given":"Kwanjeera","family":"Wanichthanarak","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thanyanatthamon","family":"Keawhawong","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7702-1323","authenticated-orcid":true,"given":"Narumol","family":"Jariyasopit","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pairash","family":"Saiviroonporn","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Trongtum","family":"Tongdee","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongyut","family":"Sirivatanauksorn","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9461-8597","authenticated-orcid":true,"given":"Sakda","family":"Khoomrung","sequence":"additional","affiliation":[{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Thailand Metabolomics Society , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Mahidol University , , ,","place":["Bangkok, Thailand, 10700"]},{"name":"Center of Excellence for Innovation in Chemistry (PERCH-CIC), Faculty of Science Mahidol University , ,","place":["Bangkok, Thailand, 10400"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"2026092810063930200_cit1","doi-asserted-by":"crossref","DOI":"10.1038\/nprot.2017.013","article-title":"Metabolomics and\nlipidomics using traveling-wave ion mobility mass spectrometry","volume-title":"Nature Protocols","author":"Paglia","year":"2017"},{"key":"2026092810063930200_cit2","doi-asserted-by":"publisher","DOI":"10.3791\/1985","article-title":"T-wave\nion mobility-mass spectrometry: basic experimental procedures for\nprotein complex analysis","volume":"41","author":"Michaelevski","year":"2010","journal-title":"J. Vis. Exp."},{"issue":"17","key":"2026092810063930200_cit3","doi-asserted-by":"publisher","first-page":"9048","DOI":"10.1021\/acs.analchem.7b01729","article-title":"An\ninterlaboratory evaluation\nof drift tube ion mobility\u2013mass spectrometry collision cross\nsection measurements","volume":"89","author":"Stow","year":"2017","journal-title":"Anal. Chem."},{"issue":"5","key":"2026092810063930200_cit4","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1021\/acs.jcim.3c01491","article-title":"Accurate Prediction\nof Ion Mobility Collision Cross-Section Using Ion\u2019s Polarizability\nand Molecular Mass with Limited Data","volume":"64","author":"Wisanpitayakorn","year":"2024","journal-title":"J. Chem.\nInf. Model."},{"issue":"5","key":"2026092810063930200_cit5","doi-asserted-by":"publisher","first-page":"100921","DOI":"10.1016\/j.jpha.2023.12.011","article-title":"Measurement of very low-molecular weight metabolites by traveling\nwave ion mobility and its use in human urine samples","volume":"14","author":"Kurilung","year":"2024","journal-title":"J. Pharm. Anal."},{"key":"2026092810063930200_cit6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18171-8","article-title":"Ion mobility collision cross-section atlas for known and unknown\nmetabolite annotation in untargeted metabolomics","volume":"11","author":"Zhou","year":"2020","journal-title":"Nat. Commun."},{"key":"2026092810063930200_cit7","doi-asserted-by":"publisher","first-page":"4548","DOI":"10.1021\/acs.analchem.9b05772","article-title":"Breaking down structural\ndiversity\nfor comprehensive prediction of ion-neutral collision cross sections","author":"Ross","year":"2020","journal-title":"Anal. Chem."},{"key":"2026092810063930200_cit8","doi-asserted-by":"crossref","DOI":"10.1039\/C8SC04396E","article-title":"Collision cross\nsection compendium to annotate and predict multi-omic compound identities","volume-title":"Chemical Science","author":"Picache","year":"2019"},{"issue":"D1","key":"2026092810063930200_cit9","doi-asserted-by":"publisher","first-page":"D622","DOI":"10.1093\/nar\/gkab1062","article-title":"HMDB 5.0: the human metabolome database for 2022","volume":"50","author":"Wishart","year":"2022","journal-title":"Nucleic Acids Res."},{"issue":"10","key":"2026092810063930200_cit10","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1021\/acs.jproteome.2c00413","article-title":"Traveling Wave Ion Mobility-Derived\nCollision Cross Section Database for Plant Specialized Metabolites:\nAn Application to Ventilago harmandiana Pierre","volume":"21","author":"Jariyasopit","year":"2022","journal-title":"J. Proteome Res."},{"key":"2026092810063930200_cit11","doi-asserted-by":"publisher","first-page":"16082","DOI":"10.1021\/jp961623v","article-title":"Structural\ninformation from ion mobility measurements: effects of the long-range\npotential","volume":"100","author":"Mesleh","year":"1996","journal-title":"J. Phys. Chem."},{"key":"2026092810063930200_cit12","doi-asserted-by":"publisher","first-page":"1540","DOI":"10.1007\/s13361-017-1661-8","article-title":"Benchmark\ncomparison for a multi-processing ion mobility calculator in the free\nmolecular regime","volume":"28","author":"Shrivastav","year":"2017","journal-title":"J. Am. Soc. Mass Spectrom."},{"key":"2026092810063930200_cit13","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1039\/c8an02150c","article-title":"A parallelized molecular\ncollision cross section package with optimized accuracy and efficiency","volume":"144","author":"Ieritano","year":"2019","journal-title":"Analyst"},{"issue":"37","key":"2026092810063930200_cit14","doi-asserted-by":"publisher","first-page":"13913","DOI":"10.1021\/acs.analchem.3c02267","article-title":"AllCCS2:\nCuration of ion mobility collision cross-section atlas for small molecules\nusing comprehensive molecular representations","volume":"95","author":"Zhang","year":"2023","journal-title":"Anal. Chem."},{"issue":"50","key":"2026092810063930200_cit15","doi-asserted-by":"publisher","first-page":"17456","DOI":"10.1021\/acs.analchem.2c03491","article-title":"CCS Predictor 2.0: An open-source jupyter notebook\ntool for filtering out false positives in metabolomics","volume":"94","author":"Rainey","year":"2022","journal-title":"Anal. Chem."},{"key":"2026092810063930200_cit16","doi-asserted-by":"publisher","first-page":"5191","DOI":"10.1021\/acs.analchem.8b05821","article-title":"Predicting\nion mobility collision cross-sections using a deep neural network:\nDeepCCS","volume":"91","author":"Plante","year":"2019","journal-title":"Anal. Chem."},{"issue":"1","key":"2026092810063930200_cit17","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1038\/s42004-023-00939-w","article-title":"Highly accurate\nand large-scale collision cross sections prediction with graph neural\nnetworks","volume":"6","author":"Guo","year":"2023","journal-title":"Commun. Chem."},{"key":"2026092810063930200_cit18","doi-asserted-by":"publisher","first-page":"125970","DOI":"10.1016\/j.talanta.2024.125970","article-title":"Predicting ion mobility\ncollision\ncross sections and assessing prediction variation by combining conventional\nand data driven modeling","volume":"274","author":"Bouwmeester","year":"2024","journal-title":"Talanta"},{"issue":"7","key":"2026092810063930200_cit19","doi-asserted-by":"publisher","DOI":"10.1002\/cem.70040","article-title":"Accurate and Rational Collision Cross\nSection Prediction Using Voxel-Projected Area and Deep Learning","volume":"39","author":"Wang","year":"2025","journal-title":"J. Chemom."},{"key":"2026092810063930200_cit20","doi-asserted-by":"publisher","first-page":"105588","DOI":"10.1016\/j.chemolab.2025.105588","article-title":"SigmaCCS2: Collision Cross Section\nPrediction Using Molecular Topological and Geometric Information With\nGraph Neural Network","volume":"268","author":"Liao","year":"2026","journal-title":"Chemom. Intell. Lab. Syst."},{"issue":"6","key":"2026092810063930200_cit21","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1038\/s42255-024-01058-z","article-title":"METLIN-CCS\nLipid Database: An authentic standards resource for lipid classification\nand identification","volume":"6","author":"Baker","year":"2024","journal-title":"Nat. Metab."},{"key":"2026092810063930200_cit22","unstructured":"Landrum, G.\n          \n          RDKit: Open-Source\nCheminformatics, 2026.03.5; 2006."},{"issue":"11","key":"2026092810063930200_cit23","doi-asserted-by":"publisher","first-page":"114110","DOI":"10.1063\/5.0197592","article-title":"CREST A program for\nthe exploration of low-energy molecular chemical space","volume":"160","author":"Pracht","year":"2024","journal-title":"J. Chem. Phys."},{"issue":"3","key":"2026092810063930200_cit24","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1021\/acs.jctc.8b01176","article-title":"GFN2-xTB An accurate and broadly\nparametrized self-consistent tight-binding quantum chemical method\nwith multipole electrostatics and density-dependent dispersion contributions","volume":"15","author":"Bannwarth","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"2026092810063930200_cit25","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4842-4240-7_1","article-title":"An introduction\nto deep learning and keras","volume-title":"Learn Keras\nfor Deep Neural Networks","author":"Moolayil","year":"2019"},{"key":"2026092810063930200_cit26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4842-4470-8_18","article-title":"Introduction to\nScikit-learn","volume-title":"Building Machine Learning\nand Deep Learning Models on Google Cloud Platform: A Comprehensive\nGuide for Beginners","author":"Bisong","year":"2019"},{"key":"2026092810063930200_cit27","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv.15004280\/v1","article-title":"CCSBase2:\nA Unified Benchmark Dataset and Machine Learning Framework for Robust\nCCS Prediction","author":"Bantwal","year":"2026","journal-title":"ChemRxiv"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c00371","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11619\/68435897\/acs.jcim.6c00371.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11619\/68435897\/acs.jcim.6c00371.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:49:35Z","timestamp":1790606975000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/18\/11619\/5425701\/Deep3DCCS-Geometry-Driven-Collision-Cross-Section"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":27,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,7]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c00371","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]}}}