Search

Drug target identification is one of the most important aspects of pre-clinical development yet it is also among the most complex, labor-intensive, and costly. This represents a major issue, as lack of proper target identification can be detrimental in determining the clinical application of a bioactive small molecule. To improve target identification, we developed BANDIT, a novel paradigm that integrates multiple data types within a Bayesian machine-learning framework to predict the targets and mechanisms for small molecules with unprecedented accuracy and versatility. Using only public data BANDIT achieved an accuracy of approximately 90% over 2000 different small molecules – substantially better than any other published target identification platform. We applied BANDIT to a library of small molecules with no known targets and generated ∼4,000 novel molecule-target predictions. From this set we identified and experimentally validated a set of novel microtubule inhibitors, including three with activity on cancer cells resistant to clinically used anti-microtubule therapies. We next applied BANDIT to ONC201 – an active anti- cancer small molecule in clinical development – whose target has remained elusive since its discovery in 2009. BANDIT identified dopamine receptor 2 as the unexpected target of ONC201, a prediction that we experimentally validated. Not only does this open the door for clinical trials focused on target-based selection of patient populations, but it also represents a novel way to target GPCRs in cancer. Additionally, BANDIT identified previously undocumented connections between approved drugs with disparate indications, shedding light onto previously unexplained clinical observations and suggesting new uses of marketed drugs. Overall, BANDIT represents an efficient and highly accurate platform that can be used as a resource to accelerate drug discovery and direct the clinical application of small molecule therapeutics with improved precision.

ObjectiveThis paper describes the Precision Medicine Knowledge Base (PMKB; https://pmkb.weill.cornell.edu), an interactive online application for collaborative editing, maintenance and sharing of structured clinical-grade cancer mutations interpretations.Materials and MethodsPMKB was built using the Ruby on Rails Web application framework. Leveraging existing standards such as Human Genome Variation Society (HGVS) variant description format, we implemented a data model that links variants to tumor-specific and tissue-specific interpretations. Key features of PMKB include support for all major variant types, standardized authentication, distinct user roles including high-level approvers, detailed activity history. A REpresentational State Transfer (REST) application-programming interface (API) was implemented to query the PMKB programmatically.ResultsAt the time of writing, PMKB contains 457 variant descriptions with 281 clinical-grade interpretations. The EGFR, BRAF, KRAS, and KIT genes are associated with the largest numbers of interpretable variants. The PMKB’s interpretations have been used in over 1,500 AmpliSeq tests and 750 whole exome sequencing tests. The interpretations are accessed either directly via the Web interface or programmatically via the existing API.DiscussionAn accurate and up-to-date knowledge base of genomic alterations of clinical significance is critical to the success of precision medicine programs. The open-access, programmatically accessible PMKB represents an important attempt at creating such a resource in the field of oncology.ConclusionThe PMKB was designed to help collect and maintain clinical-grade mutation interpretations and facilitates reporting for clinical cancer genomic testing. The PMKB was also designed to enable the creation of clinical cancer genomics automated reporting pipelines via an API.