mAbsPub Date : 2025-12-01Epub Date: 2025-01-08DOI: 10.1080/19420862.2024.2442750
Aubin Ramon, Mingyang Ni, Olga Predeina, Rebecca Gaffey, Patrick Kunz, Shimobi Onuoha, Pietro Sormanni
{"title":"Prediction of protein biophysical traits from limited data: a case study on nanobody thermostability through NanoMelt.","authors":"Aubin Ramon, Mingyang Ni, Olga Predeina, Rebecca Gaffey, Patrick Kunz, Shimobi Onuoha, Pietro Sormanni","doi":"10.1080/19420862.2024.2442750","DOIUrl":"10.1080/19420862.2024.2442750","url":null,"abstract":"<p><p>In-silico prediction of protein biophysical traits is often hindered by the limited availability of experimental data and their heterogeneity. Training on limited data can lead to overfitting and poor generalizability to sequences distant from those in the training set. Additionally, inadequate use of scarce and disparate data can introduce biases during evaluation, leading to unreliable model performances being reported. Here, we present a comprehensive study exploring various approaches for protein fitness prediction from limited data, leveraging pre-trained embeddings, repeated stratified nested cross-validation, and ensemble learning to ensure an unbiased assessment of the performances. We applied our framework to introduce NanoMelt, a predictor of nanobody thermostability trained with a dataset of 640 measurements of apparent melting temperature, obtained by integrating data from the literature with 129 new measurements from this study. We find that an ensemble model stacking multiple regression using diverse sequence embeddings achieves state-of-the-art accuracy in predicting nanobody thermostability. We further demonstrate NanoMelt's potential to streamline nanobody development by guiding the selection of highly stable nanobodies. We make the curated dataset of nanobody thermostability freely available and NanoMelt accessible as a downloadable software and webserver.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2442750"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11730357/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142950964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-02-27DOI: 10.1080/19420862.2025.2468845
Puneet Rawat, Silvia Crescioli, R Prabakaran, Divya Sharma, Victor Greiff, Janice M Reichert
{"title":"YAbS: The Antibody Society's antibody therapeutics database.","authors":"Puneet Rawat, Silvia Crescioli, R Prabakaran, Divya Sharma, Victor Greiff, Janice M Reichert","doi":"10.1080/19420862.2025.2468845","DOIUrl":"10.1080/19420862.2025.2468845","url":null,"abstract":"<p><p>Therapeutic antibodies have gained prominence in recent years due to their precision in targeting specific diseases. As these molecules become increasingly essential in modern medicine, comprehensive data tracking and analysis are critical for advancing research and ensuring successful clinical outcomes. YAbS, The Antibody Society's Antibody Therapeutics Database, serves as a vital resource for monitoring the development and clinical progress of therapeutic antibodies. The database catalogs detailed information on over 2,900 commercially sponsored investigational antibody candidates that have entered clinical study since 2000, as well as all approved antibody therapeutics. Data for the late-stage clinical pipeline and antibody therapeutics in regulatory review or approved (over 450 molecules) are openly accessible (https://db.antibodysociety.org). Antibody-related information includes molecular format, targeted antigen, current development status, indications studied, and the clinical development timeline of the antibodies, as well as the geographical region of company sponsors. Furthermore, the database supports in-depth industry trends analysis, facilitating the identification of innovative developments and the assessment of success rates within the field. This resource is continually updated and refined, providing invaluable insights to researchers, clinicians, and industry professionals engaged in antibody therapeutics development.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2468845"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11869773/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143515965","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-01-30DOI: 10.1080/19420862.2025.2457471
Jeremy Loyau, Thierry Monney, Marco Montefiori, Fedir Bokhovchuk, Jeremy Streuli, Matthew Blackburn, Arnaud Goepfert, Lydia N Caro, Samitabh Chakraborti, Stefania De Angelis, Camille Grandclément, Stanislas Blein, M Lamine Mbow, Ankita Srivastava, Mario Perro, Stefano Sammicheli, Eugene A Zhukovsky, Michael Dyson, Cyrille Dreyfus
{"title":"Biparatopic binding of ISB 1442 to CD38 in trans enables increased cell antibody density and increased avidity.","authors":"Jeremy Loyau, Thierry Monney, Marco Montefiori, Fedir Bokhovchuk, Jeremy Streuli, Matthew Blackburn, Arnaud Goepfert, Lydia N Caro, Samitabh Chakraborti, Stefania De Angelis, Camille Grandclément, Stanislas Blein, M Lamine Mbow, Ankita Srivastava, Mario Perro, Stefano Sammicheli, Eugene A Zhukovsky, Michael Dyson, Cyrille Dreyfus","doi":"10.1080/19420862.2025.2457471","DOIUrl":"10.1080/19420862.2025.2457471","url":null,"abstract":"<p><p>ISB 1442 is a bispecific biparatopic antibody in clinical development to treat hematological malignancies. It consists of two adjacent anti-CD38 arms targeting non-overlapping epitopes that preferentially drive binding to tumor cells and a low-affinity anti-CD47 arm to enable avidity-induced blocking of proximal CD47 receptors. We previously reported the pharmacology of ISB 1442, designed to reestablish synthetic immunity in CD38+ hematological malignancies. Here, we describe the discovery, optimization and characterization of the ISB 1442 antigen binding fragment (Fab) arms, their assembly to 2 + 1 format, and present the high-resolution co-crystal structures of the two anti-CD38 Fabs, in complex with CD38. This, with biophysical and functional assays, elucidated the underlying mechanism of action of ISB 1442. In solution phase, ISB 1442 forms a 2:2 complex with CD38 as determined by size-exclusion chromatography with multi-angle light scattering and electron microscopy. The predicted antibody-antigen stoichiometries at different CD38 surface densities were experimentally validated by surface plasmon resonance and cell binding assays. The specific design and structural features of ISB 1442 enable: 1) enhanced trans binding to adjacent CD38 molecules to increase Fc density at the cancer cell surface; 2) prevention of avid cis binding to monomeric CD38 to minimize blockade by soluble shed CD38; and 3) greater binding avidity, with a slower off-rate at high CD38 density, for increased specificity. The superior CD38 targeting of ISB 1442, at both high and low receptor densities, by its biparatopic design, will enhance proximal CD47 blockade and thus counteract a major tumor escape mechanism in multiple myeloma patients.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2457471"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11784651/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143066701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-04-11DOI: 10.1080/19420862.2025.2490789
Megan H Cleveland, Ioannis L Karageorgos, John P Marino, Michael J Tarlov, Katharina S Yandrofski, Rebecca A Zangmeister, Zvi Kelman
{"title":"Recommended nomenclature convention for the NISTCHO cell line and its product monoclonal antibody, cNISTmAb.","authors":"Megan H Cleveland, Ioannis L Karageorgos, John P Marino, Michael J Tarlov, Katharina S Yandrofski, Rebecca A Zangmeister, Zvi Kelman","doi":"10.1080/19420862.2025.2490789","DOIUrl":"https://doi.org/10.1080/19420862.2025.2490789","url":null,"abstract":"<p><p>NISTCHO is a Chinese hamster ovary (CHO) cell line expressing the same amino acid sequences as the heavy and light chains of the National Institute of Standards and Technology (NIST) monoclonal antibody [Reference Material (RM) 8671 NISTmAb]. NISTCHO was generated by MilliporeSigma to be developed by NIST as a RM to support biomanufacturing research and innovation, method development and qualification, and pre-competitive research collaboration. The RM cell line, denoted as RM 8675 NISTCHO, Clonal CHO-K1 Cell Line Producing cNISTmAb, is of interest to the biopharmaceutical and biomanufacturing industries, regulatory and government agencies, and academic institutions. In contrast to other NIST RMs, however, which are typically discrete and finite, the NISTCHO is a living RM that can be propagated, expanded, and used repeatedly to express the non-originator NISTmAb product, cNISTmAb. Therefore, a uniform naming convention should be adopted by the user community to best track the origins of materials (the cell line and products) used in studies derived from the RM 8675 NISTCHO. Here, we provide a naming convention for the derivatives of the RM 8675 NISTCHO and the cNISTmAb produced by these NISTCHO derivatives and recommend these naming conventions for adoption by the scientific community.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2490789"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12005425/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143989548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-04-18DOI: 10.1080/19420862.2025.2492238
Raffaella Briante, Qianting Zhai, Suchismita Mohanty, Pingping Zhang, Alissa O'Connor, Hiwot Misker, Willie Wang, Cindy Tan, Mastewal Abuhay, Jessica Morgan, Richard Theolis, Paul Ponath, Robert Arathoon
{"title":"Successful targeting of multidrug-resistant tumors with bispecific antibodies.","authors":"Raffaella Briante, Qianting Zhai, Suchismita Mohanty, Pingping Zhang, Alissa O'Connor, Hiwot Misker, Willie Wang, Cindy Tan, Mastewal Abuhay, Jessica Morgan, Richard Theolis, Paul Ponath, Robert Arathoon","doi":"10.1080/19420862.2025.2492238","DOIUrl":"https://doi.org/10.1080/19420862.2025.2492238","url":null,"abstract":"<p><p>Multidrug resistance (MDR) hinders efficacious cancer chemotherapy. Overexpression of the P-glycoprotein (P-gp) efflux pump (EP) on cancer cells is a primary cause of MDR since it expels numerous anticancer drugs. Small molecule intracellular P-gp antagonists have been investigated clinically to redress MDR but have failed primarily due to adverse effects on P-gp in normal tissue. We used a new approach to counteract P-gp with bispecific antibodies (BsAbs) that simultaneously bound P-gp and CD47 <i>in cis</i> on MDR cells but not normal tissue. Affinities of the individual arms of the BsAbs were low enough to minimize normal tissue binding, but, when the two targets were co-located on MDR cancer cells, both arms of the BsAb engaged with effective avidity. Proof-of-concept was shown in three different MDR xenograft tumor models with a non-humanized chimeric BsAb (targeting P-gp and CD47) that potently restored tumor sensitivity to paclitaxel. Fully humanized variants were successfully developed and characterized. Significant anti-tumor efficacy was observed with the BsAbs both when combined with paclitaxel and as single agents in the absence of paclitaxel. Treatment of MDR cancers with BsAbs using this novel approach has several distinct advantages over prior efforts with small molecule antagonists, including 1) invoking a direct immune attack on the tumors, 2) multimodal mechanisms of action, 3) tumor-specific targeting (with reduced toxicity to normal tissue), and 4) broad applicability as single agents and compatibility with other therapeutics.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2492238"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12013451/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143989551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-04-03DOI: 10.1080/19420862.2025.2480666
Tiexin Wang, Alec A Desai, Greg M Thurber, Peter M Tessier
{"title":"Maximizing activity and selectivity of antibody-mediated effector functions using antibody mixtures.","authors":"Tiexin Wang, Alec A Desai, Greg M Thurber, Peter M Tessier","doi":"10.1080/19420862.2025.2480666","DOIUrl":"10.1080/19420862.2025.2480666","url":null,"abstract":"<p><p>Fc-mediated effector functions are key for conferring potent antibody-mediated killing of cancer cells. However, it is difficult to achieve highly selective targeting of cancer cells while minimizing toxicity on healthy tissue because of the expression of most receptors, albeit at lower levels, on non-cancer cells. Previous attempts to increase the selectivity of antibody-mediated effector functions have sought to reduce binding affinity and/or increase avidity, which typically results in modest improvements in selectivity. To overcome this limitation, we report the use of mixtures of antibody variants that achieve high selectivity based on receptor level while maintaining high activity for cells with high receptor levels. We have studied mixtures of two variants of an anti-HER2 antibody (trastuzumab), one that is affinity-reduced and effector-competent and a second high-affinity variant that is effectorless. Notably, we observe that the high-affinity, effectorless antibody reduces effector function for cells with low receptor levels, including reduced antibody-dependent cellular cytotoxicity (ADCC) and phagocytosis (ADCP), while the high-avidity, effector-competent antibody mediates significant effector function for cells with high receptor levels. Moreover, replacing the effector-competent Fc region of the affinity-reduced antibody with high-affinity Fc domains that enhance effector function drives high activity while maintaining high selectivity for the antibody mixtures. These findings outline a general strategy for maximizing the therapeutic window by selectively targeting cancer cells based on receptor levels that could be applied to a wide range of applications involving antibody-mediated synapse formation, including antibody-drug conjugates and bispecific antibodies, such as T cell engagers.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2480666"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11980503/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143780424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Structural and biochemical differences between non-catalytic and catalytic antibodies.","authors":"Taizo Uda, Ryuichi Kato, Yasuteru Shigeta, Shun Hirota, Jun Kobayashi, Hisashi Yoshida, Masato Tsuyuguchi, Kowit Hengphasatporn, Moe Tsujita, Hiroaki Taguchi, Emi Hifumi","doi":"10.1080/19420862.2025.2503978","DOIUrl":"10.1080/19420862.2025.2503978","url":null,"abstract":"<p><p>A conventional antibody can be converted into its catalytic counterparts by deleting Pro95 in the CDR-3 of human and mice antibody light chains, as previously reported. T99wt is a naturally occurring human antibody light chain that we transformed into its catalytic antibody using Pro95 deletion. In peptidase activity tests, T99wt exhibited a low catalytic activity against a synthetic peptide Arg-pNA and hardly cleaved amyloid-β peptide. In contrast, the engineered variant (T99-Pro95(-)) demonstrated significant catalytic activity, effectively cleaving both Arg-pNA substrate and amyloid-β peptides. In this study, the structural basis for the acquisition of enzymatic function through Pro95 deletion in the CDR-3 region of the light chain was elucidated using X-ray crystallography and molecular dynamics (MD) simulations. X-ray crystallography revealed that Pro95 deletion substantially reduces the distance between Asp1 and His93-key residues for catalytic activity - from 9.56 Å in T99wt to 3.84 Å in T99-Pro95(-). The observed decrease in distance indicates a strong interaction between Asp1(Oδ1) and His93(Nε2), contributing to the formation of an active site in T99-Pro95(-). MD simulations revealed that the entire structure exhibits slight fluctuations and adopts various configurations upon the removal of Pro95. In particular, when His residues in the catalytic region are fully deprotonated, Asp1, His93, and Ser27a transiently come into close proximity, enabling the formation of a functional catalytic triad. Catalytic antibodies can be made starting from just the amino acid sequence of a desired mAb, which may be available in databases such as OAS or IMGT. Therefore, our finding represents a significant technological advancement.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2503978"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12077472/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144011412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-05-16DOI: 10.1080/19420862.2025.2502673
Melanie Grandits, Lais C G F Palhares, Olivia Macleod, John Devlin, Oliver E Amin, James Birtley, Leanne Partington, Tim Wilson, Elizabeth Hardaker, Sophia N Karagiannis, Heather J Bax, Kevin FitzGerald
{"title":"Hybrid IgE-IgG1 antibodies (IgEG): a new antibody class that combines IgE and IgG functionality.","authors":"Melanie Grandits, Lais C G F Palhares, Olivia Macleod, John Devlin, Oliver E Amin, James Birtley, Leanne Partington, Tim Wilson, Elizabeth Hardaker, Sophia N Karagiannis, Heather J Bax, Kevin FitzGerald","doi":"10.1080/19420862.2025.2502673","DOIUrl":"10.1080/19420862.2025.2502673","url":null,"abstract":"<p><p>IgG-based anti-cancer therapies have achieved promising clinical outcomes, but, especially for patients with solid tumors, response rates vary. IgE antibodies promote distinct immune responses compared to IgG and have shown anti-tumoral pre-clinical activity and preliminary efficacy and safety profile in clinical testing. To improve potency further, we engineered a hybrid IgE-IgG1 antibody (IgEG), to combine the functions of both isotypes. Two IgEGs were generated with variable regions taken from trastuzumab (Tras IgEG) and from a novel anti-HER2 IgE (26 IgEG). Both IgEGs expressed well in mammalian cells and demonstrated IgE-like stability. IgEGs demonstrated both IgE and IgG1 functionality <i>in vitro</i>. A lack of type I hypersensitivity associated with IgEG incubation with human blood is suggestive of acceptable safety. <i>In vivo</i>, IgEGs exhibited distinct pharmacokinetic profiles and produced anti-tumoral efficacy comparable to IgE. These findings highlight the potential of IgEG as a new therapeutic modality in oncology.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2502673"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12087487/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144078890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
mAbsPub Date : 2025-12-01Epub Date: 2025-04-01DOI: 10.1080/19420862.2025.2483944
Lateefat A Kalejaye, Jia-Min Chu, I-En Wu, Bismark Amofah, Amber Lee, Mark Hutchinson, Chacko Chakiath, Andrew Dippel, Gilad Kaplan, Melissa Damschroder, Valentin Stanev, Maryam Pouryahya, Mehdi Boroumand, Jenna Caldwell, Alison Hinton, Madison Kreitz, Mitali Shah, Austin Gallegos, Neil Mody, Pin-Kuang Lai
{"title":"Accelerating high-concentration monoclonal antibody development with large-scale viscosity data and ensemble deep learning.","authors":"Lateefat A Kalejaye, Jia-Min Chu, I-En Wu, Bismark Amofah, Amber Lee, Mark Hutchinson, Chacko Chakiath, Andrew Dippel, Gilad Kaplan, Melissa Damschroder, Valentin Stanev, Maryam Pouryahya, Mehdi Boroumand, Jenna Caldwell, Alison Hinton, Madison Kreitz, Mitali Shah, Austin Gallegos, Neil Mody, Pin-Kuang Lai","doi":"10.1080/19420862.2025.2483944","DOIUrl":"10.1080/19420862.2025.2483944","url":null,"abstract":"<p><p>Highly concentrated antibody solutions are necessary for developing subcutaneous injections but often exhibit high viscosities, posing challenges in antibody-drug development, manufacturing, and administration. Previous computational models were only limited to a few dozen data points for training, a bottleneck for generalizability. In this study, we measured the viscosity of a panel of 229 monoclonal antibodies (mAbs) to develop predictive models for high concentration mAb screening. We developed DeepViscosity, consisting of 102 ensemble artificial neural network models to classify low-viscosity (≤20 cP) and high-viscosity (>20 cP) mAbs at 150 mg/mL, using 30 features from a sequence-based DeepSP model. Two independent test sets, comprising 16 and 38 mAbs with known experimental viscosity, were used to assess DeepViscosity's generalizability. The model exhibited an accuracy of 87.5% and 89.5% on both test sets, respectively, surpassing other predictive methods. DeepViscosity will facilitate early-stage antibody development to select low-viscosity antibodies for improved manufacturability and formulation properties, critical for subcutaneous drug delivery. The webserver-based application can be freely accessed via https://devpred.onrender.com/DeepViscosity.</p>","PeriodicalId":18206,"journal":{"name":"mAbs","volume":"17 1","pages":"2483944"},"PeriodicalIF":5.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143764268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}