Our Scientific Heritage
Built on a bedrock of peer-reviewed science and industry expertise
Our team previously developed machine learning models for predicting pharmacologically relevant kinase conformational states
Our team previously created a web resource called KinaMetrix to investigate kinase conformational and small molecule inhibitor space
Our team previously managed and led a multi-national DREAM challenge to solve kinase-kinase inhibitor binding prediction
Our team previously explored the chemical landscape of the druggable kinome to identify novel kinase therapeutics
Our team previously developed approaches to predict kinase anti-targets and chemical structures associated with toxicity
Our team previously developed and experimentally validated state-of-the-art machine learning approaches to predict kinase inhibitor binding profiles
Our team previously created web resources to analyze large scale drug screening experiments
Our team previously analyzed the optimal ways to rationally design multi-target inhibitors to overcome resistance and improve efficacy
Our team previously developed novel structure and machine learning-based approaches to analyze multi-omics data
Our team previously developed a machine learning method for drug bioactivity prediction integrating multiple biomedical data sources