Deep Learning Based Protein Therapeutics Design to Treat HER2+ Cancers

The Ordaos Design Engine, a deep learning-based end-to-end protein therapeutics design platform, was developed and used to create de novo mini-proteins to target HER2. Candidate proteins are evaluated in silico for binding affinity and specificity, secondary and tertiary structure, isoelectric point, solubility, and other drug-like properties, and iteratively improved to achieve multi-objective optimization. These in silico designed binders can be produced with high yield and purity using mammalian protein expression systems, and have been shown to bind to human HER2 with EC50 in the nanomolar range by ELISA.