AI Case Study
GlaxoSmithKline (GSK) plans to reduce drug discovery to trial time from six years to 12 months using machine learning models to predict molecular behaviour
GSK in partnership with UC San Francisco attempts to discover new applications for previously developed compounds - both successful and unsuccessful, by analysing chemical and in-vitro biological data combined with publicly available data. This data is used to predict molecular behaviour and speed up clinical trials by targeting.
Industry
Healthcare
Pharmaceuticals And Biotech
Project Overview
"The goal of the consortium – Accelerating Therapeutics for Opportunities in Medicine (ATOM) – is to create a new paradigm of drug discovery that would reduce the time from an identified drug target to clinical candidate from the current approximately six years to just 12 months. ATOM aims to transform cancer drug discovery from a time-consuming, sequential, and high-risk process into an approach that is rapid, integrated, and with better patient outcomes -- using supercomputers to pretest many molecules simultaneously for safety and efficacy.
ATOM will develop, test, and validate a multidisciplinary approach to drug discovery in which modern science, technology and engineering, supercomputing simulations, data science, and artificial intelligence are highly integrated into a single drug-discovery platform that can untimately be shared with the drug development community at large.
GSK is working to set a precedent with pharmaceutical companies by sharing data on failed compounds.GSK will initially contribute chemical and in vitro biological data for more than 2 million compounds from its historic and current screening collection, as well as preclinical and clinical information on 500 molecules that have failed in development but could help accelerate development of new compounds by providing knowledge about the underlying biology of candidate compounds and that of the human body. Combined with data on successful drugs, GSK’s offering represents a broad base of information for ATOM researchers. In addition, GSK will provide expertise in drug discovery and development, computational chemistry, and biology."
Reported Results
Research; Results not yet available
Technology
"The variety of deep learning ATOM might be most interested in is unstructured or unsupervised feature learning, where the focus is on early-stage identification of data sets that go together and significant patterns without predetermined parameters or expectations. The work is comparable to what Google has accomplished with face recognition, he says, but the data sets are much larger and far more complex."
Function
R And D
Product Development
Background
"Lawrence Livermore National Laboratory, Frederick National Laboratory for Cancer Research, GSK, and University of California San Francisco will combine vast data stores, supercomputing, and scientific expertise to reinvent discovery process for cancer medicines"
Benefits
Data
"GSK will contribute chemical and in vitro biological data for more than 2 million compounds from its historic and current screening collection, as well as preclinical and clinical information on 500 molecules that have failed in development
Large amounts of experimental data—genomic data, transcriptome data, assay data—on how biological systems respond to chemicals and their structures."