{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T13:05:49Z","timestamp":1772543149278,"version":"3.50.1"},"reference-count":53,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T00:00:00Z","timestamp":1660867200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T00:00:00Z","timestamp":1660867200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Complex scientific inquiries rely increasingly upon large and autonomous multiscale simulation campaigns, which fundamentally require <jats:italic>similarity metrics<\/jats:italic> to quantify \u2018sufficient\u2019 changes among data and\/or configurations. However, subject matter experts are often unable to articulate similarity precisely or in terms of well-formulated definitions, especially when new hypotheses are to be explored, making it challenging to design a meaningful metric. Furthermore, the key to practical usefulness of such metrics to enable autonomous simulations lies in <jats:italic>in situ<\/jats:italic> inference, which requires generalization to possibly substantial distributional shifts in unseen, future data. Here, we address these challenges in a cancer biology application and develop a meaningful similarity metric for <jats:italic>\u2018patches\u2019<\/jats:italic>\u2014regions of simulated human cell membrane that express interactions between certain proteins of interest and relevant lipids. In the absence of well-defined conditions for similarity, we leverage several biology-informed notions about data and the underlying simulations to impose inductive biases on our metric learning framework, resulting in a suitable similarity metric that also generalizes well to significant distributional shifts encountered during the deployment. We combine these intuitions to organize the learned embedding space in a multiscale manner, which makes the metric robust to incomplete and even contradictory intuitions. Our approach delivers a metric that not only performs well on the conditions used for its development and other relevant criteria, but also learns key spatiotemporal relationships without ever being exposed to any such information during training.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac8523","type":"journal-article","created":{"date-parts":[[2022,7,28]],"date-time":"2022-07-28T22:43:58Z","timestamp":1659048238000},"page":"035010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A biology-informed similarity metric for simulated patches of human cell membrane"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8712-7773","authenticated-orcid":true,"given":"Harsh","family":"Bhatia","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jayaraman J","family":"Thiagarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4186-3502","authenticated-orcid":false,"given":"Rushil","family":"Anirudh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T S","family":"Jayram","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6366-7190","authenticated-orcid":false,"given":"Tomas","family":"Oppelstrup","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7613-9143","authenticated-orcid":false,"given":"Helgi I","family":"Ing\u00f3lfsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felice C","family":"Lightstone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4107-3831","authenticated-orcid":false,"given":"Peer-Timo","family":"Bremer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2022,8,19]]},"reference":[{"key":"mlstac8523bib1","first-page":"pp 265","article-title":"TensorFlow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"mlstac8523bib2","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.semcdb.2009.11.011","article-title":"Multiscale simulation of protein mediated membrane remodeling","volume":"21","author":"Ayton","year":"2010","journal-title":"Semin. Cell Dev. Biol."},{"key":"mlstac8523bib3","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2020.2990275","article-title":"Speaker verification by partial AUC optimization with mahalanobis distance metric learning","volume":"28","author":"Bai","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"mlstac8523bib4","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1038\/s42256-021-00327-w","article-title":"Machine learning based dynamic-importance sampling for adaptive multiscale simulations","volume":"3","author":"Bhatia","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstac8523bib5","doi-asserted-by":"crossref","DOI":"10.1145\/3458817.3476210","article-title":"Generalizable coordination of large multiscale workflows: challenges and learnings at scale","author":"Bhatia","year":"2021"},{"key":"mlstac8523bib6","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1186\/s12859-018-2507-5","article-title":"Deep clustering of protein folding simulations","volume":"19","author":"Bhowmik","year":"2018","journal-title":"BMC Bioinform."},{"key":"mlstac8523bib7","first-page":"pp 1320","article-title":"Beyond triplet loss: a deep quadruplet network for person re-identification","author":"Chen","year":"2017"},{"key":"mlstac8523bib8","article-title":"Keras","author":"Chollet","year":"2015"},{"key":"mlstac8523bib9","first-page":"pp 539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume":"vol 1","author":"Chopra","year":"2005"},{"key":"mlstac8523bib10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/110842545","article-title":"Importance sampling for multiscale diffusions","volume":"10","author":"Dupuis","year":"2012","journal-title":"Multiscale Model. Simul."},{"key":"mlstac8523bib11","doi-asserted-by":"publisher","first-page":"5607","DOI":"10.1021\/acs.chemrev.8b00538","article-title":"Multiscale simulations of biological membranes: the challenge to understand biological phenomena in a living substance","volume":"119","author":"Enkavi","year":"2019","journal-title":"Chem. Rev."},{"key":"mlstac8523bib12","first-page":"pp 272","article-title":"Deep metric learning with hierarchical triplet loss","author":"Ge","year":"2018"},{"key":"mlstac8523bib13","first-page":"pp 1735","article-title":"Dimensionality reduction by learning an invariant mapping","volume":"vol 2","author":"Hadsell","year":"2006"},{"key":"mlstac8523bib14","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2013.0377","article-title":"Multiscale modelling and simulation: a position paper","volume":"372","author":"Hoekstra","year":"2014","journal-title":"Phil. Trans. R. Soc. A"},{"key":"mlstac8523bib15","first-page":"pp 84","article-title":"Deep metric learning using triplet network","author":"Hoffer","year":"2015"},{"key":"mlstac8523bib16","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1109\/TIP.2018.2860898","article-title":"Semi-supervised metric learning-based anchor graph hashing for large-scale image retrieval","volume":"28","author":"Hu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"mlstac8523bib17","doi-asserted-by":"publisher","first-page":"7819","DOI":"10.1021\/acs.jpcb.0c03368","article-title":"Capturing biologically complex tissue-specific membranes at different levels of compositional complexity","volume":"124","author":"Ing\u00f3lfsson","year":"2020","journal-title":"J. Phys. Chem. B"},{"key":"mlstac8523bib18","doi-asserted-by":"publisher","first-page":"2271","DOI":"10.1016\/j.bpj.2017.10.017","article-title":"Computational lipidomics of the neuronal plasma membrane","volume":"113","author":"Ing\u00f3lfsson","year":"2017","journal-title":"Biophys. J."},{"key":"mlstac8523bib19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2113297119","article-title":"Machine learning-driven multiscale modeling reveals lipid-dependent dynamics of RAS signaling proteins","volume":"119","author":"Ing\u00f3lfsson","year":"2022","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstac8523bib20","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1177\/10943420211010930","article-title":"Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models","volume":"35","author":"Jacobs","year":"2021","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"mlstac8523bib21","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.3390\/sym11091066","article-title":"Deep metric learning: a survey","volume":"11","author":"Kaya","year":"2019","journal-title":"Symmetry"},{"key":"mlstac8523bib22","doi-asserted-by":"publisher","first-page":"15823","DOI":"10.1073\/pnas.1904529116","article-title":"Drugging an undruggable pocket on KRAS","volume":"116","author":"Kessler","year":"2019","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstac8523bib23","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2017"},{"key":"mlstac8523bib24","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1002\/nme.2339","article-title":"Adaptive sampling in hierarchical simulation","volume":"76","author":"Knap","year":"2008","journal-title":"Int. J. Numer. Methods Eng."},{"key":"mlstac8523bib25","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1016\/j.procs.2015.05.268","article-title":"Multiscale modelling and simulation workshop: 12 years of inspiration","volume":"51","author":"Krzhizhanovskaya","year":"2015","journal-title":"Proc. Comput. Sci."},{"key":"mlstac8523bib26","first-page":"pp 340","article-title":"Automatic speaker recognition with limited data","author":"Li","year":"2020"},{"key":"mlstac8523bib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101494","article-title":"Improving malicious urls detection via feature engineering: linear and nonlinear space transformation methods","volume":"91","author":"Li","year":"2020","journal-title":"Inf. Syst."},{"key":"mlstac8523bib28","first-page":"pp 55","article-title":"A social recommendation based on metric learning and network embedding","author":"Li","year":"2020"},{"key":"mlstac8523bib29","first-page":"pp 310","article-title":"Multi-modal media retrieval via distance metric learning for potential customer discovery","author":"Liu","year":"2018"},{"key":"mlstac8523bib30","doi-asserted-by":"publisher","first-page":"19342","DOI":"10.1109\/ACCESS.2017.2756102","article-title":"Metric learning combining with boosting for user distance measure in multiple social networks","volume":"5","author":"Liu","year":"2017","journal-title":"IEEE Access"},{"key":"mlstac8523bib31","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1016\/j.neucom.2018.08.086","article-title":"Visual content-based web page categorization with deep transfer learning and metric learning","volume":"338","author":"L\u00f3pez-S\u00e1nchez","year":"2019","journal-title":"Neurocomputing"},{"key":"mlstac8523bib32","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/MSP.2017.2732900","article-title":"Deep metric learning for visual understanding: an overview of recent advances","volume":"34","author":"Lu","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstac8523bib33","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/JIOT.2019.2946500","article-title":"Transforming device fingerprinting for wireless security via online multitask metric learning","volume":"7","author":"Luo","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"mlstac8523bib34","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aaf5da","article-title":"Nasopharyngeal carcinoma segmentation based on enhanced convolutional neural networks using multi-modal metric learning","volume":"64","author":"Ma","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"mlstac8523bib35","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1137\/17M1162366","article-title":"Optimized sampling for multiscale dynamics","volume":"17","author":"Manohar","year":"2019","journal-title":"Multiscale Model. Simul."},{"key":"mlstac8523bib36","doi-asserted-by":"publisher","first-page":"8032","DOI":"10.1063\/1.478705","article-title":"Dynamic density functional theory of fluids","volume":"110","author":"Marconi","year":"1999","journal-title":"J. Chem. Phys."},{"key":"mlstac8523bib37","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/TIP.2018.2870941","article-title":"Kernel distance metric learning using pairwise constraints for person re-identification","volume":"28","author":"Nguyen","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"mlstac8523bib38","doi-asserted-by":"publisher","first-page":"2969","DOI":"10.1158\/0008-5472.CAN-19-3682","article-title":"The frequency of RAS mutations in cancer","volume":"80","author":"Prior","year":"2020","journal-title":"Cancer Res."},{"key":"mlstac8523bib39","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/nature08144","article-title":"The structure and function of G-protein-coupled receptors","volume":"459","author":"Rosenbaum","year":"2009","journal-title":"Nature"},{"key":"mlstac8523bib40","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1016\/j.cpc.2014.03.011","article-title":"Spatial adaptive sampling in multiscale simulation","volume":"185","author":"Rouet-Leduc","year":"2014","journal-title":"Comput. Phys. Commun."},{"key":"mlstac8523bib41","first-page":"pp 815","article-title":"FaceNet: a unified embedding for face recognition and clustering","author":"Schroff","year":"2015"},{"key":"mlstac8523bib42","first-page":"pp 41","article-title":"Learning a distance metric from relative comparisons","volume":"vol 16","author":"Schultz","year":"2004"},{"key":"mlstac8523bib43","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.cell.2017.06.009","article-title":"RAS proteins and their regulators in human disease","volume":"170","author":"Simanshu","year":"2017","journal-title":"Cell"},{"key":"mlstac8523bib44","article-title":"A tutorial on distance metric learning: mathematical foundations, algorithms, experimental analysis, prospects and challenges (with appendices on mathematical background and detailed algorithms explanation)","author":"Su\u00e1rez-D\u00edaz","year":"2020"},{"key":"mlstac8523bib45","doi-asserted-by":"publisher","first-page":"8461","DOI":"10.1038\/s41598-018-26832-4","article-title":"Molecular recognition of RAS\/RAF complex at the membrane: role of RAF cysteine-rich domain","volume":"8","author":"Travers","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstac8523bib46","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstac8523bib47","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1021\/acs.accounts.6b00572","article-title":"A multiscale description of biomolecular active matter: the chemistry underlying many life processes","volume":"50","author":"Voth","year":"2017","journal-title":"Acc. Chem. Res."},{"key":"mlstac8523bib48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.inffus.2020.05.005","article-title":"Deep feature fusion through adaptive discriminative metric learning for scene recognition","volume":"63","author":"Wang","year":"2020","journal-title":"Inf. Fusion"},{"key":"mlstac8523bib49","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a031435","article-title":"KRAS: the critical driver and therapeutic target for pancreatic cancer","volume":"8","author":"Waters","year":"2018","journal-title":"Cold Spring Harb. Perspect. Med."},{"key":"mlstac8523bib50","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000018724","article-title":"A multi-feature image retrieval scheme for pulmonary nodule diagnosis","volume":"99","author":"Wei","year":"2020","journal-title":"Medicine"},{"key":"mlstac8523bib51","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.neunet.2020.01.021","article-title":"Effective metric learning with co-occurrence embedding for collaborative recommendations","volume":"124","author":"Wu","year":"2020","journal-title":"Neural Netw."},{"key":"mlstac8523bib52","first-page":"pp 521","article-title":"Distance metric learning with application to clustering with side-information","volume":"vol 15","author":"Xing","year":"2003"},{"key":"mlstac8523bib53","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107014","article-title":"Similarity learning with joint transfer constraints for person re-identification","volume":"97","author":"Zhao","year":"2020","journal-title":"Pattern Recognit."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,19]],"date-time":"2022-08-19T09:12:10Z","timestamp":1660900330000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac8523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,19]]},"references-count":53,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2022,8,19]]},"published-print":{"date-parts":[[2022,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac8523","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,19]]},"assertion":[{"value":"A biology-informed similarity metric for simulated patches of human cell membrane","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-01-23","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-07-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-08-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}