{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T02:42:49Z","timestamp":1786934569264,"version":"build-2736575974"},"reference-count":53,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:00:00Z","timestamp":1771372800000},"content-version":"am","delay-in-days":382,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"NIH NIGMS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["jpharmsci.org","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Pharmaceutical Sciences"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1016\/j.xphs.2024.12.031","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T00:01:43Z","timestamp":1736985703000},"page":"1254-1263","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"title":["Representative training data sets are critical for accurate machine-learning classification of microscopy images of particles formed by lipase-catalyzed polysorbate hydrolysis"],"prefix":"10.1016","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4653-0413","authenticated-orcid":false,"given":"David N.","family":"Greenblott","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher P.","family":"Calderon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4292-4047","authenticated-orcid":false,"given":"Theodore W.","family":"Randolph","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.xphs.2024.12.031_bib0001","doi-asserted-by":"crossref","first-page":"2986","DOI":"10.1016\/j.xphs.2020.06.030","article-title":"Evaluation of super refinedTM polysorbate 20 with respect to polysorbate degradation, particle formation and protein stability","volume":"109","author":"Doshi","year":"2020","journal-title":"J Pharm Sci"},{"key":"10.1016\/j.xphs.2024.12.031_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejps.2023.106597","article-title":"How enzymatic hydrolysis of polysorbate 20 influences colloidal protein stability","volume":"191","author":"Gl\u00fccklich","year":"2023","journal-title":"Eur J Pharm Sci"},{"issue":"3","key":"10.1016\/j.xphs.2024.12.031_bib0003","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1016\/j.xphs.2021.10.008","article-title":"Fatty acids can induce the formation of proteinaceous particles in monoclonal antibody formulations","volume":"111","author":"Zhang","year":"2022","journal-title":"J Pharm Sci"},{"issue":"3","key":"10.1016\/j.xphs.2024.12.031_bib0004","doi-asserted-by":"crossref","first-page":"1093","DOI":"10.1016\/j.xphs.2020.11.027","article-title":"Extended characterization and impact of visible fatty acid particles - a case study with a mAb product","volume":"110","author":"Saggu","year":"2021","journal-title":"J Pharm Sci"},{"issue":"8","key":"10.1016\/j.xphs.2024.12.031_bib0005","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1002\/jps.21190","article-title":"Polysorbates 20 and 80 used in the formulation of protein biotherapeutics: structure and degradation pathways","volume":"97","author":"Kerwin","year":"2008","journal-title":"J Pharm Sci"},{"issue":"1","key":"10.1016\/j.xphs.2024.12.031_bib0006","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1208\/s12248-022-00773-3","article-title":"End-to-end approach to surfactant selection, risk mitigation, and control strategies for protein-based therapeutics","volume":"25","author":"Morales","year":"2022","journal-title":"AAPS J"},{"issue":"6","key":"10.1016\/j.xphs.2024.12.031_bib0007","doi-asserted-by":"crossref","first-page":"1577","DOI":"10.1016\/j.xphs.2022.02.013","article-title":"Catching speedy gonzales: driving forces for protein film formation on silicone rubber tubing during pumping","volume":"111","author":"Deiringer","year":"2022","journal-title":"J Pharm Sci"},{"issue":"6","key":"10.1016\/j.xphs.2024.12.031_bib0008","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1002\/jps.23973","article-title":"Protein aggregation and particle formation in prefilled glass syringes","volume":"103","author":"Gerhardt","year":"2014","journal-title":"J Pharm Sci"},{"key":"10.1016\/j.xphs.2024.12.031_bib0009","doi-asserted-by":"crossref","unstructured":"Yuk I.H., Koulis T., Doshi N., et al. Formulation mitigations for particle formation induced by enzymatic hydrolysis of polysorbate 20 in protein-based drug products: insights from a full-factorial longitudinal study. Published online 2022. 10.1186\/s41120-022-00064-3","DOI":"10.1186\/s41120-022-00064-3"},{"issue":"5","key":"10.1016\/j.xphs.2024.12.031_bib0010","doi-asserted-by":"crossref","first-page":"1633","DOI":"10.1016\/j.xphs.2016.02.022","article-title":"Polysorbates 20 and 80 degradation by group XV lysosomal phospholipase A2 isomer X1 in monoclonal antibody formulations","volume":"105","author":"Hall","year":"2016","journal-title":"J Pharm Sci"},{"issue":"11","key":"10.1016\/j.xphs.2024.12.031_bib0011","doi-asserted-by":"crossref","first-page":"3792","DOI":"10.1021\/acs.molpharmaceut.5b00310","article-title":"Understanding particle formation: solubility of free fatty acids as polysorbate 20 degradation byproducts in therapeutic monoclonal antibody formulations","volume":"12","author":"Doshi","year":"2015","journal-title":"Mol Pharm"},{"issue":"9","key":"10.1016\/j.xphs.2024.12.031_bib0012","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1007\/s11095-021-03087-9","article-title":"Evaluating a modified high purity polysorbate 20 designed to reduce the risk of free fatty acid particle formation","volume":"38","author":"Doshi","year":"2021","journal-title":"Pharm Res"},{"key":"10.1016\/j.xphs.2024.12.031_bib0013","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.ejpb.2023.07.018","article-title":"Screening techniques for monitoring the sub-visible particle formation of free fatty acids in biopharmaceuticals","volume":"190","author":"Chen","year":"2023","journal-title":"Eur J Pharm Biopharm"},{"issue":"8","key":"10.1016\/j.xphs.2024.12.031_bib0014","doi-asserted-by":"crossref","first-page":"2405","DOI":"10.1016\/j.xphs.2020.05.002","article-title":"Quantitative differentiation of protein aggregates from other subvisible particles in viscous mixtures through holographic characterization","volume":"109","author":"Winters","year":"2020","journal-title":"J Pharm Sci"},{"issue":"2","key":"10.1016\/j.xphs.2024.12.031_bib0015","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/jps.24126","article-title":"Free fatty acid particles in protein formulations, Part 1: microspectroscopic identification","volume":"104","author":"Cao","year":"2015","journal-title":"J Pharm Sci"},{"issue":"5","key":"10.1016\/j.xphs.2024.12.031_bib0016","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1007\/s11095-011-0385-x","article-title":"The degradation of polysorbates 20 and 80 and its potential impact on the stability of biotherapeutics","volume":"28","author":"Kishore","year":"2011","journal-title":"Pharm Res"},{"issue":"9","key":"10.1016\/j.xphs.2024.12.031_bib0017","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.1016\/j.xphs.2024.07.010","article-title":"A comparison of polysorbates and alternative surfactants for interfacial stress protection and mitigation of fatty acid particle formation in the presence of an esterase","volume":"113","author":"Roy","year":"2024","journal-title":"J Pharm Sci"},{"issue":"4","key":"10.1016\/j.xphs.2024.12.031_bib0018","doi-asserted-by":"crossref","first-page":"1200","DOI":"10.1208\/s12248-013-9522-2","article-title":"Flow imaging microscopy for protein particle analysis - A comparative evaluation of four different analytical instruments","volume":"15","author":"Z\u00f6lls","year":"2013","journal-title":"AAPS Journal"},{"key":"10.1016\/j.xphs.2024.12.031_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.xphs.2022.08.006","article-title":"Utility of three flow imaging microscopy instruments for image analysis in evaluating four types of subvisible particle in biopharmaceuticals","author":"Nishiumi","year":"2022","journal-title":"J Pharm Sci."},{"issue":"11","key":"10.1016\/j.xphs.2024.12.031_bib0020","doi-asserted-by":"crossref","first-page":"3322","DOI":"10.1002\/bit.27501","article-title":"Machine learning and statistical analyses for extracting and characterizing \u201cfingerprints\u201d of antibody aggregation at container interfaces from flow microscopy images","volume":"117","author":"Daniels","year":"2020","journal-title":"Biotechnol Bioeng"},{"issue":"4","key":"10.1016\/j.xphs.2024.12.031_bib0021","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1016\/j.xphs.2017.12.008","article-title":"Deep convolutional neural network analysis of flow imaging microscopy data to classify subvisible particles in protein formulations","volume":"107","author":"Calderon","year":"2018","journal-title":"J Pharm Sci"},{"issue":"12","key":"10.1016\/j.xphs.2024.12.031_bib0022","doi-asserted-by":"crossref","first-page":"3596","DOI":"10.1002\/bit.28239","article-title":"Machine learning approaches to root cause analysis, characterization, and monitoring of subvisible particles in monoclonal antibody formulations","volume":"119","author":"Greenblott","year":"2022","journal-title":"Biotechnol Bioeng"},{"key":"10.1016\/j.xphs.2024.12.031_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.xphs.2022.06.017","article-title":"Machine learning analysis provides insight into mechanisms of protein particle formation inside containers during mechanical agitation","author":"Thite","year":"2022","journal-title":"J Pharm Sci"},{"issue":"2","key":"10.1016\/j.xphs.2024.12.031_bib0024","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1007\/s11095-021-03130-9","article-title":"Testing precision limits of neural network-based quality control metrics in high-throughput digital microscopy","volume":"39","author":"Calderon","year":"2022","journal-title":"Pharm Res"},{"issue":"7","key":"10.1016\/j.xphs.2024.12.031_bib0025","doi-asserted-by":"crossref","first-page":"2743","DOI":"10.1016\/j.xphs.2021.02.029","article-title":"Machine learning and accelerated stress approaches to differentiate potential causes of aggregation in polyclonal antibody formulations during shipping","volume":"110","author":"Witeof","year":"2021","journal-title":"J Pharm Sci"},{"issue":"1","key":"10.1016\/j.xphs.2024.12.031_bib0026","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1016\/j.xphs.2019.10.034","article-title":"Automatic identification of the stress sources of protein aggregates using flow imaging microscopy images","volume":"109","author":"Gambe-Gilbuena","year":"2020","journal-title":"J Pharm Sci"},{"issue":"10","key":"10.1016\/j.xphs.2024.12.031_bib0027","doi-asserted-by":"crossref","first-page":"2745","DOI":"10.1016\/j.xphs.2022.07.006","article-title":"A collaborative study on the classification of silicone oil droplets and protein particles using flow imaging method","volume":"111","author":"Shibata","year":"2022","journal-title":"J Pharm Sci"},{"key":"10.1016\/j.xphs.2024.12.031_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.xphs.2023.07.010","article-title":"Interfacial adsorption controls particle formation in antibody formulations subjected to extensional flows and hydrodynamic shear","author":"Thite","year":"2023","journal-title":"J Pharm Sci"},{"key":"10.1016\/j.xphs.2024.12.031_bib0029","doi-asserted-by":"crossref","DOI":"10.1002\/bit.28488","article-title":"Deep learning image analysis models pretrained on daily objects are useful for the preliminary characterization of particulate pharmaceutical samples","author":"Salami","year":"2023","journal-title":"Biotechnol Bioeng"},{"key":"10.1016\/j.xphs.2024.12.031_bib0030","article-title":"Evaluation of a self-supervised machine learning method for screening of particulate samples: a case study in liquid formulations","author":"Salami","year":"2022","journal-title":"J Pharm Sci"},{"issue":"5","key":"10.1016\/j.xphs.2024.12.031_bib0031","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1016\/j.xphs.2024.03.003","article-title":"Features in backgrounds of microscopy images introduce biases in machine learning analyses","volume":"113","author":"Greenblott","year":"2024","journal-title":"J Pharm Sci"},{"issue":"5","key":"10.1016\/j.xphs.2024.12.031_bib0032","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1002\/bit.28671","article-title":"Supervised and unsupervised machine learning approaches for monitoring subvisible particles within an aluminum-salt adjuvanted vaccine formulation","volume":"121","author":"Greenblott","year":"2024","journal-title":"Biotechnol Bioeng"},{"key":"10.1016\/j.xphs.2024.12.031_bib0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.xphs.2022.05.022","article-title":"Combining machine learning and backgrounded membrane imaging: a case study in comparing and classifying different types of biopharmaceutically relevant particles","author":"Calderon","year":"2022","journal-title":"J Pharm Sci"},{"key":"10.1016\/j.xphs.2024.12.031_bib0034","doi-asserted-by":"crossref","DOI":"10.1016\/j.xphs.2023.07.003","article-title":"Image classification of degraded polysorbate, protein and silicone oil sub-visible particles detected by flow-imaging microscopy in biopharmaceuticals using a convolutional neural network model","author":"Fedorowicz","year":"2023","journal-title":"J Pharm Sci"},{"issue":"10","key":"10.1016\/j.xphs.2024.12.031_bib0035","doi-asserted-by":"crossref","first-page":"2108","DOI":"10.1016\/j.jid.2018.06.175","article-title":"Automated classification of skin lesions: from pixels to practice","volume":"138","author":"Narla","year":"2018","journal-title":"J Investig Dermatol"},{"key":"10.1016\/j.xphs.2024.12.031_bib0036","doi-asserted-by":"crossref","DOI":"10.1038\/s41551-023-01160-9","article-title":"Auditing the inference processes of medical-image classifiers by leveraging generative AI and the expertise of physicians","author":"DeGrave","year":"2023","journal-title":"Nat Biomed Eng."},{"key":"10.1016\/j.xphs.2024.12.031_bib0037","series-title":"Proceedings of the ACM International Conference Proceeding Series","article-title":"A framework for understanding sources of harm throughout the machine learning life cycle","author":"Suresh","year":"2021"},{"key":"10.1016\/j.xphs.2024.12.031_bib0038","unstructured":"National Center for Biotechnology Information. PubChem compound summary for CID 11005, myristic acid. 2024. Accessed June 26, 2024. https:\/\/pubchem.ncbi.nlm.nih.gov\/compound\/Myristic-Acid"},{"key":"10.1016\/j.xphs.2024.12.031_bib0039","unstructured":"National Center for Biotechnology Information. PubChem compound summary for CID 985, palmitic acid. 2024. Accessed June 26, 2024. https:\/\/pubchem.ncbi.nlm.nih.gov\/compound\/Palmitic-Acid"},{"issue":"5","key":"10.1016\/j.xphs.2024.12.031_bib0040","doi-asserted-by":"crossref","first-page":"418","DOI":"10.5731\/pdajpst.2018.008953","article-title":"Development of protein-like reference material for semiquantitatively monitoring visible proteinaceous particles in biopharmaceuticals","volume":"73","author":"Telikepalli","year":"2019","journal-title":"PDA J Pharm Sci Technol"},{"issue":"1","key":"10.1016\/j.xphs.2024.12.031_bib0041","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1016\/j.xphs.2019.03.024","article-title":"Backgrounded membrane imaging (BMI) for high-throughput characterization of subvisible particles during biopharmaceutical drug product development","volume":"109","author":"Helbig","year":"2020","journal-title":"J Pharm Sci"},{"key":"10.1016\/j.xphs.2024.12.031_bib0042","unstructured":"Sigma-Aldrich. Safety data sheet myristic acid 70079."},{"key":"10.1016\/j.xphs.2024.12.031_bib0043","unstructured":"Sigma-Aldrich. Safety data sheet palmitic acid 76119."},{"key":"10.1016\/j.xphs.2024.12.031_bib0044","unstructured":"Paszke A., Gross S., Massa F., et al. PyTorch: an imperative style, high-performance deep learning library.; 2019. Accessed February 25, 2024. https:\/\/arxiv.org\/abs\/1912.01703"},{"key":"10.1016\/j.xphs.2024.12.031_bib0045","unstructured":"Kingma D.P., Ba J.. Adam: A method for stochastic optimization. Published online December 22, 2014. http:\/\/arxiv.org\/abs\/1412.6980"},{"issue":"7","key":"10.1016\/j.xphs.2024.12.031_bib0046","doi-asserted-by":"crossref","first-page":"1455","DOI":"10.1007\/s11095-024-03723-0","article-title":"High-throughput fluorometric assay for quantifying polysorbate in biopharmaceutical products using micelle activated fluorescence probe N-phenyl-1-naphthylamine","volume":"41","author":"Dow","year":"2024","journal-title":"Pharm Res"},{"key":"10.1016\/j.xphs.2024.12.031_bib0047","series-title":"Bioscience Separations and Engineering","author":"Harrison","year":"2015"},{"key":"10.1016\/j.xphs.2024.12.031_bib0048","series-title":"Measurement of Crystal Growth and Nucleation Rates","author":"Garside","year":"2002"},{"key":"10.1016\/j.xphs.2024.12.031_bib0049","doi-asserted-by":"crossref","DOI":"10.1016\/j.ijpharm.2020.119934","article-title":"An in-depth examination of fatty acid solubility limits in biotherapeutic protein formulations containing polysorbate 20 and polysorbate 80","volume":"591","author":"Gl\u00fccklich","year":"2020","journal-title":"Int J Pharm"},{"issue":"2","key":"10.1016\/j.xphs.2024.12.031_bib0050","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1016\/j.xphs.2020.09.050","article-title":"Glass leachables as a nucleation factor for free fatty acid particle formation in biopharmaceutical formulations","volume":"110","author":"Allmendinger","year":"2021","journal-title":"J Pharm Sci"},{"issue":"4","key":"10.1016\/j.xphs.2024.12.031_bib0051","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1039\/C9SM01916B","article-title":"The role of the medium in the effective-sphere interpretation of holographic particle characterization data","volume":"16","author":"Odete","year":"2020","journal-title":"Soft Matter"},{"issue":"12","key":"10.1016\/j.xphs.2024.12.031_bib0052","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1016\/j.xphs.2023.08.020","article-title":"Evaluation of the in-use stability of monoclonal antibody IV admixtures prepared from drug products containing polysorbate 20 degraded by host-cell lipases","volume":"112","author":"Riccardi","year":"2023","journal-title":"J Pharm Sci"},{"issue":"8","key":"10.1016\/j.xphs.2024.12.031_bib0053","doi-asserted-by":"crossref","first-page":"2114","DOI":"10.1016\/j.xphs.2024.05.001","article-title":"Stain-free approach to determine and monitor cell heath using supervised and unsupervised image-based deep learning","volume":"113","author":"Thite","year":"2024","journal-title":"J Pharm Sci"}],"container-title":["Journal of Pharmaceutical Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022354925000085?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022354925000085?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T22:24:39Z","timestamp":1742682279000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0022354925000085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["S0022354925000085"],"URL":"https:\/\/doi.org\/10.1016\/j.xphs.2024.12.031","relation":{},"ISSN":["0022-3549"],"issn-type":[{"value":"0022-3549","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Representative training data sets are critical for accurate machine-learning classification of microscopy images of particles formed by lipase-catalyzed polysorbate hydrolysis","name":"articletitle","label":"Article Title"},{"value":"Journal of Pharmaceutical Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.xphs.2024.12.031","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 American Pharmacists Association. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}