ABSTRACT
The development of novel therapeutic proteins is a lengthy and costly process, with an average attrition rate of 91% (Thomas et al. Clinical Development Success Rates and Contributing Factors 2011-2020, 2021). To increase the probability of success and ensure robust drug supply beyond approval, it is essential to assess the developability profile of new potential drug candidates as early and broadly as possible in development (Jain et al. MAbs, 2023. https://doi.org/10.1016/j.copbio.2011.06.002 ). Predicting these properties in silico is expected to be the next leap in innovation as it would enable significantly reduced development timelines combined with broader screens at lower costs. However, developing predictive algorithms typically requires substantial datasets generated under very defined conditions, a limiting factor especially for new classes of therapeutic proteins that hold immense clinical promise. Here we describe a strategy for assessing the developability of a novel class of small therapeutic Anticalin® proteins using machine learning in conjunction with a knowledge-driven approach. The knowledge-driven approach considers developability attributes such as aggregation propensity, charge variants, immunogenicity, specificity, thermal stability, hydrophobicity, and potential post-translational modifications, to calculate a holistic developability score. Based on sequence-derived descriptors as input parameters we established novel statistical models designed to predict the developability scores for Anticalin proteins. The best models yielded low root mean square errors across the entire dataset and were further validated by removing input data from individual screening campaigns and predicting developability scores for those drug candidates. The adoption of the described workflow will enable significantly streamlined preclinical development of Anticalin drug candidates and could potentially be applied to other therapeutic protein scaffolds.
Subject(s)
Computer Simulation , Machine Learning , Proteins , Humans , Proteins/chemistry , Algorithms , Drug Discovery/methods , Drug DesignABSTRACT
The FGFR4/FGF19 signaling axis is overactivated in 20% of liver tumors and currently represents a promising targetable signaling mechanism in this cancer type. However, blocking FGFR4 or FGF19 has proven challenging due to its physiological role in suppressing bile acid synthesis which leads to increased toxic bile acid plasma levels upon FGFR4 inhibition. An FGFR4-targeting antibody, U3-1784, was generated in order to investigate its suitability as a cancer treatment without major side effects.U3-1784 is a high-affinity fully human antibody that was obtained by phage display technology and specifically binds to FGFR4. The antibody inhibits cell signaling by competing with various FGFs for their FGFR4 binding site thereby inhibiting receptor activation and downstream signaling via FRS2 and Erk. The inhibitory effect on tumor growth was investigated in 10 different liver cancer models in vivo The antibody specifically slowed tumor growth of models overexpressing FGF19 by up to 90% whereas tumor growth of models not expressing FGF19 was unaffected. In cynomolgus monkeys, intravenous injection of U3-1784 caused elevated serum bile acid and liver enzyme levels indicating potential liver damage. These effects could be completely prevented by the concomitant oral treatment with the bile acid sequestrant colestyramine, which binds and eliminates bile acids in the gut. These results offer a new biomarker-driven treatment modality in liver cancer without toxicity and they suggest a general strategy for avoiding adverse events with FGFR4 inhibitors.