Machine Learning Feature Selection for Predicting High Concentration Therapeutic Antibody Aggregation

Pin Kuang Lai, Amendra Fernando, Theresa K. Cloutier, Jonathan S. Kingsbury, Yatin Gokarn, Kevin T. Halloran, Cesar Calero-Rubio, Bernhardt L. Trout

Research output: Contribution to journalArticlepeer-review

26 Scopus citations

Abstract

Protein aggregation can hinder the development, safety and efficacy of therapeutic antibody-based drugs. Developing a predictive model that evaluates aggregation behaviors during early stage development is therefore desirable. Machine learning is a widely used tool to train models that predict data with different attributes. However, most machine learning techniques require more data than is typically available in antibody development. In this work, we describe a rational feature selection framework to develop accurate models with a small number of features. We applied this framework to predict aggregation behaviors of 21 approved monospecific monoclonal antibodies at high concentration (150 mg/mL), yielding a correlation coefficient of 0.71 on validation tests with only two features using a linear model. The nearest neighbors and support vector regression models further improved the performance, which have correlation coefficients of 0.86 and 0.80, respectively. This framework can be extended to train other models that predict different physical properties.

Original languageEnglish
Pages (from-to)1583-1591
Number of pages9
JournalJournal of Pharmaceutical Sciences
Volume110
Issue number4
DOIs
StatePublished - Apr 2021

Keywords

  • Antibody aggregations
  • Feature selections
  • Machine learning
  • Molecular dynamics simulations

Fingerprint

Dive into the research topics of 'Machine Learning Feature Selection for Predicting High Concentration Therapeutic Antibody Aggregation'. Together they form a unique fingerprint.

Cite this