{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:57:06Z","timestamp":1790607426275,"version":"4.1.0"},"reference-count":19,"publisher":"American Chemical Society (ACS)","issue":"18","license":[{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T00:00:00Z","timestamp":1789344000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["B2404003"],"award-info":[{"award-number":["B2404003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFA0912400"],"award-info":[{"award-number":["2022YFA0912400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Shenzhen Basic Research Fund","doi-asserted-by":"publisher","award":["22333006"],"award-info":[{"award-number":["22333006"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Shenzhen Key Projects","doi-asserted-by":"publisher","award":["D2403003"],"award-info":[{"award-number":["D2403003"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Shenzhen Medical Research Fund","doi-asserted-by":"publisher","award":["JCYJ20190807170801656"],"award-info":[{"award-number":["JCYJ20190807170801656"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Shenzhen Medical Research Fund","doi-asserted-by":"publisher","award":["JCYJ20220818100804009"],"award-info":[{"award-number":["JCYJ20220818100804009"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Shenzhen AI-Driven Public Service Platform for Pharmaceutical R&D","doi-asserted-by":"publisher","award":["XMHT20251128002"],"award-info":[{"award-number":["XMHT20251128002"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]}],"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>Antibody developability is inherently multidimensional, involving thermal stability, aggregation and hydrophobicity, nonspecific interactions, and expression-related manufacturability. Instead of treating developability as a single composite label, we investigated assay-level modeling using GDPa1 as a benchmark data set. We developed a two-branch framework combining interpretable developability descriptors and data-driven calibration. One branch fits assay-specific descriptor models to derive end point-specific physicochemical weights, while the other integrates frozen pretrained VH\/VL sequence embeddings with computed descriptors in a multitask regression architecture. Internal validation across eight GDPa1 assays showed assay-dependent predictability, with hydrophobicity- and aggregation-related readouts generally showing stronger signals than expression-related and some thermal stability end points. Descriptor coefficient analysis revealed distinct physicochemical patterns across assays, supporting the view that antibody developability cannot be represented by a single universal descriptor weighting scheme. External held-out validation on GDPa3 revealed limited cross-data set transferability. Across seven directly matched assays, mean Spearman correlations were 0.126 for the full descriptor model, 0.139 for the sequence-only descriptor model, and 0.125 for the hybrid sequence\u2013descriptor model. HIC retention time was the most transferable end point, whereas SEC monomer percentage and several thermal stability end points showed weak external correlations. The hybrid model did not consistently outperform descriptor-only baselines, indicating that pretrained sequence embeddings provided limited and assay-dependent incremental value in this small-data setting. GDPa1 sequence-cluster analysis showed that internal validation estimates depended on clustering threshold and fold construction, whereas GDPa3 provided a more direct external assessment of cross-data set transferability. These results support a cautious assay-level framework for antibody developability modeling. Descriptor-based representations remain strong and interpretable baselines, while sequence embeddings require end point-specific and external validation. The proposed workflow can convert assay-level predictions into domain-level profiles for computational triage, but prospective candidate prioritization requires binding assessment and experimental validation.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c02385","type":"journal-article","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T17:02:01Z","timestamp":1789405321000},"page":"11882-11894","source":"Crossref","is-referenced-by-count":0,"title":["Assay-Level Modeling\nand External Validation of Antibody\nDevelopability Using Physicochemical Descriptors and Sequence Embeddings"],"prefix":"10.1021","volume":"66","author":[{"given":"Shasha","family":"Jiang","sequence":"first","affiliation":[{"name":"Shenzhen University of Advanced Technology , , ,","place":["Shenzhen, China, 518107"]},{"name":"Southern University of Science and Technology , , , ,","place":["Shenzhen, Guangdong, P.R. China, 518055"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark Akinola","family":"Ige","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , , 1068 Xueyuan Avenue, Nanshan District , ,","place":["Shenzhen, China, 518055"]},{"name":"University of Chinese Academy of Sciences , ,","place":["Beijing, China, 100049"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4566-5746","authenticated-orcid":true,"given":"Hei Wun","family":"Kan","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology , , ,","place":["Shenzhen, China, 518107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochun","family":"Wan","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , , 1068 Xueyuan Avenue, Nanshan District , ,","place":["Shenzhen, China, 518055"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junxin","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences , , 1068 Xueyuan Avenue, Nanshan District , ,","place":["Shenzhen, China, 518055"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John Z. H.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology , , ,","place":["Shenzhen, China, 518107"]},{"name":"University of Lagos , , , ,","place":["Akoka, Lagos, Nigeria, 101017"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology , , ,","place":["Shenzhen, China, 518107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2133-1768","authenticated-orcid":true,"given":"Haiping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology , , ,","place":["Shenzhen, China, 518107"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"issue":"2","key":"2026092810072900300_cit1","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1080\/19420862.2018.1553476","article-title":"Structure, Heterogeneity and Developability\nAssessment of Therapeutic Antibodies","volume":"11","author":"Xu","year":"2019","journal-title":"mAbs"},{"issue":"6","key":"2026092810072900300_cit2","doi-asserted-by":"publisher","first-page":"753","DOI":"10.4161\/mabs.22189","article-title":"A Strategy\nfor Risk Mitigation of Antibodies with Fast Clearance","volume":"4","author":"Ho\u0308tzel","year":"2012","journal-title":"mAbs"},{"issue":"1","key":"2026092810072900300_cit3","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2021.1895540","article-title":"Discovery-Stage Identification of\nDrug-like Antibodies Using Emerging Experimental and Computational\nMethods","volume":"13","author":"Makowski","year":"2021","journal-title":"mAbs"},{"issue":"1","key":"2026092810072900300_cit4","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2023.2200540","article-title":"Identifying\nDevelopability Risks\nfor Clinical Progression of Antibodies Using High-Throughput in Vitro\nand in Silico Approaches","volume":"15","author":"Jain","year":"2023","journal-title":"mAbs"},{"issue":"1","key":"2026092810072900300_cit5","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2020.1743053","article-title":"Predicting\nAntibody Developability\nProfiles Through Early Stage Discovery Screening","volume":"12","author":"Bailly","year":"2020","journal-title":"mAbs"},{"issue":"1","key":"2026092810072900300_cit6","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1093\/abt\/tbac029","article-title":"Developability Assessment at Early-Stage Discovery\nto Enable Development\nof Antibody-Derived Therapeutics","volume":"6","author":"Zhang","year":"2023","journal-title":"Antibody Ther."},{"issue":"1","key":"2026092810072900300_cit7","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2023.2171248","article-title":"Assessing Developability Early in the Discovery Process\nfor Novel Biologics","volume":"15","author":"Ferna\u0301ndez-Quintero","year":"2023","journal-title":"mAbs"},{"issue":"1","key":"2026092810072900300_cit8","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2021.1999195","article-title":"Polyreactivity\nand Polyspecificity in Therapeutic Antibody Development: Risk Factors\nfor Failure in Preclinical and Clinical Development Campaigns","volume":"13","author":"Cunningham","year":"2021","journal-title":"mAbs"},{"key":"2026092810072900300_cit9","doi-asserted-by":"crossref","unstructured":"Akbar, R.; Bashour, H.; Rawat, P.; Robert, P. A.; Smorodina, E.; Cotet, T.-S.; Flem-Karlsen, K.; Frank, R.; Mehta, B. B.; Vu, M. H.; Zengin, T.; Gutierrez-Marcos, J.; Lund-Johansen, F.; Andersen, J. T.; Greiff, V.\n          Progress and Challenges for\nthe Machine Learning-Based Design of Fit-for-Purpose Monoclonal Antibodies\n          MAbs\n          14(1), 200879010.1080\/19420862.2021.2008790.","DOI":"10.1080\/19420862.2021.2008790"},{"issue":"10","key":"2026092810072900300_cit10","doi-asserted-by":"publisher","first-page":"4025","DOI":"10.1073\/pnas.1810576116","article-title":"Five Computational\nDevelopability Guidelines for Therapeutic Antibody Profiling","volume":"116","author":"Raybould","year":"2019","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"issue":"8","key":"2026092810072900300_cit11","doi-asserted-by":"publisher","first-page":"2502","DOI":"10.4049\/jimmunol.1800708","article-title":"Observed Antibody Space:\nA Resource for Data Mining\nNext-Generation Sequencing of Antibody Repertoires","volume":"201","author":"Kovaltsuk","year":"2018","journal-title":"J. Immunol."},{"issue":"1","key":"2026092810072900300_cit12","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2026.2634216","article-title":"2025 Ginkgo Datapoints Antibody Developability Competition\nOutcomes: Limited Model Performance and a Call for Data Standardization","volume":"18","author":"Van Niekerk","year":"2026","journal-title":"mAbs"},{"issue":"1","key":"2026092810072900300_cit13","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-023-05744-8","article-title":"Contextualising\nthe Developability Risk of Antibodies with Lambda Light Chains Using\nEnhanced Therapeutic Antibody Profiling","volume":"7","author":"Raybould","year":"2024","journal-title":"Commun.\nBiol."},{"issue":"D1","key":"2026092810072900300_cit14","doi-asserted-by":"publisher","first-page":"D545","DOI":"10.1093\/nar\/gkad1056","article-title":"The Patent\nand Literature Antibody Database (PLAbDab): An Evolving Reference\nSet of Functionally Diverse, Literature-Annotated Antibody Sequences\nand Structures","volume":"52","author":"Abanades","year":"2024","journal-title":"Nucleic Acids Res."},{"issue":"1","key":"2026092810072900300_cit15","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1002\/pro.4205","article-title":"Observed Antibody Space: A Diverse\nDatabase of Cleaned, Annotated, and Translated Unpaired and Paired\nAntibody Sequences","volume":"31","author":"Olsen","year":"2022","journal-title":"Protein Sci."},{"issue":"1","key":"2026092810072900300_cit16","doi-asserted-by":"publisher","DOI":"10.1080\/19420862.2025.2593055","article-title":"A High-Throughput\nPlatform for Biophysical Antibody Developability Assessment to Enable\nAI\/ML Model Training","volume":"17","author":"Arsiwala","year":"2025","journal-title":"mAbs"},{"issue":"6637","key":"2026092810072900300_cit17","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-Scale\nPrediction of Atomic-Level Protein Structure with\na Language Model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"issue":"D1","key":"2026092810072900300_cit18","doi-asserted-by":"publisher","first-page":"D545","DOI":"10.1093\/nar\/gkad1056","article-title":"The Patent\nand Literature Antibody Database (PLAbDab): An Evolving Reference\nSet of Functionally Diverse, Literature-Annotated Antibody Sequences\nand Structures","volume":"52","author":"Abanades","year":"2024","journal-title":"Nucleic Acids Res."},{"issue":"5","key":"2026092810072900300_cit19","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1073\/pnas.1616408114","article-title":"Biophysical Properties of the Clinical-Stage Antibody\nLandscape","volume":"114","author":"Jain","year":"2017","journal-title":"Proc. Natl. Acad. Sci. U.S.A."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c02385","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11882\/68503781\/acs.jcim.6c02385.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/18\/11882\/68503781\/acs.jcim.6c02385.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T14:11:42Z","timestamp":1790604702000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/18\/11882\/5429617\/Assay-Level-Modeling-and-External-Validation-of"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":19,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9,14]]},"published-print":{"date-parts":[[2026,9,28]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c02385","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]}}}