Application of interpretable artificial neural networks to early monoclonal antibodies development

Gentiluomo, Lorenzo; Roessner, Dierk; Augustijn, Dillen; Svilenov, Hristo ; Kulakova, Alina; Mahapatra, Sujata; Winter, Gerhard; Streicher, Werner; Rinnan, Asmund; Peters, Günther; Harris, Pernille und Friess, Wolfgang (August 2019): Application of interpretable artificial neural networks to early monoclonal antibodies development. In: European Journal of Pharmaceutics and Biopharmaceutics, Bd. 141: S. 81-89

Abstract

The development of a new protein drug typically starts with the design, expression and biophysical characterization of many different protein constructs. The initially high number of constructs is radically reduced to a few candidates that exhibit the desired biological and physicochemical properties. This process of protein expression and characterization to find the most promising molecules is both expensive and time-consuming. Consequently, many companies adopt and implement philosophies, e.g. platforms for protein expression and formulation, computational approaches, machine learning, to save resources and facilitate protein drug development. Inspired by this, we propose the use of interpretable artificial neuronal networks (ANNs) to predict biophysical properties of therapeutic monoclonal antibodies i.e. melting temperature Tm, aggregation onset temperature Tagg, interaction parameter kD as a function of pH and salt concentration from the amino acid composition. Our ANNs were trained with typical early-stage screening datasets achieving high prediction accuracy. By only using the amino acid composition, we could keep the ANNs simple which allows for high general applicability, robustness and interpretability. Finally, we propose a novel “knowledge transfer” approach, which can be readily applied due to the simple algorithm design, to understand how our ANNs come to their conclusions.

• Dokumententyp: Zeitschriftenartikel
• EU Funded Grant Agreement Number: 675074
• EU-Projekte: Horizon 2020 > Marie Skłodowska Curie Actions > Marie Skłodowska-Curie Innovative Training Networks > 675074: PIPPI - Protein-excipient Interactions and Protein-Protein Interactions in formulation
• Publikationsform: Postprint
• Keywords: Neural network(s); Machine learning; Protein aggregation; Protein formulation; Monoclonal antibody Stability
• Fakultät: Chemie und Pharmazie > Department für Pharmazie - Zentrum für Pharmaforschung
• Themengebiete: 500 Naturwissenschaften und Mathematik > 570 Biowissenschaften; Biologie
• ISSN: 0939-6411
• Sprache: Englisch