Accelerating high-concentration monoclonal antibody development with large-scale viscosity data and ensemble deep learning.

Journal: mAbs
PMID: 40170162

Abstract

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.

Authors

  • Lateefat A Kalejaye
    Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken, NJ, USA.
  • Jia-Min Chu
    Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken, NJ, USA.
  • I-En Wu
    Department of Chemical Engineering and Materials Science, Stevens Institute of Technology, Hoboken 07030 New Jersey.
  • Bismark Amofah
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Amber Lee
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Mark Hutchinson
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Chacko Chakiath
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Andrew Dippel
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Gilad Kaplan
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Melissa Damschroder
    Biologics Engineering, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Valentin Stanev
    Data Science and Modeling, BioPharmaceuticals R&D, AstraZeneca, Gaithersburg, Maryland 20878, United States.
  • Maryam Pouryahya
    PathAI, Boston, MA, USA.
  • Mehdi Boroumand
    Data Science and Modeling, BioPharmaceuticals Development, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Jenna Caldwell
    Dosage Form Design and Development, BioPharmaceuticals R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Alison Hinton
    Dosage Form Design and Development, BioPharmaceuticals R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Madison Kreitz
    Dosage Form Design and Development, BioPharmaceuticals R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Mitali Shah
    Dosage Form Design and Development, BioPharmaceuticals Development, R&D, AstraZeneca, Gaithersburg, MD, USA.
  • Austin Gallegos
    Dosage Form Design and Development, AstraZeneca, Gaithersburg, Maryland, USA.
  • Neil Mody
    Dosage Form Design and Development, AstraZeneca, Gaithersburg, Maryland, USA.
  • Pin-Kuang Lai
    Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.

Keywords

External Resources

Popular Topics
Recent Journals