BAGIM is an active community of Boston area scientists bringing together people from diverse fields of modeling and informatics to impact life and health sciences. BAGIM strives to create a forum for great scientific discussions covering a wide range of topics including data management, visualization, computational chemistry, drug discovery, protein structure, molecular modeling, structure-based drug design, data mining, software tools, and the sharing of goals and experiences. Our community is made up of participants from academia, government, and industry whose goal is to engage in the discussion of science involving a synthesis of theory and technology. Discussions sponsored by BAGIM are targeted to the needs and interests of informatics scientists, computational chemists, medicinal chemists, and statisticians. BAGIM also provides opportunities for networking within these disciplines as well as an arena for the dissemination of information of specific interest to the membership.

Wednesday, October 18, 2017

BAGIM Event: Dr Gabriel Musso at the Broad Institute in Cambridge Thursday November 16, starting at 6pm

Dr. Gabriel Musso, the CSO of BioSymetrics in Toronto, will present "Using Machine Learning to Screen Small Molecules" on November 16th. The presentation will start at 6pm at the Broad Institute. Please use the 415 Main Street entrance and arrive a few minutes early. Networking and refreshments will follow at around 7pm at Meadhall, 4 Cambridge Center, Cambridge. Please RSVP for this event.


Drug discovery in the post-genomic era has largely focused on modulation of disease-relevant drug targets in hypothesis-driven screens. However, despite tremendous achievements, there is substantial pressure within the industry to address the high attrition rate associated with drug development. Failures in the clinical development of lead compounds may arise from lack of efficacy, unexpected toxicity, or anomalies in absorption, distribution, metabolism, or excretion. One potential solution to this problem is to incorporate an initial phenotype-based screen able to assess multiple specificity and toxicity phenotypes simultaneously. In this talk I’ll begin by describing previous work in which we performed phenotype-based screening of a library of bioactive compounds, using the results to generate machine learning models that prioritized as-yet-untested compounds for specific phenotypic effects. These models were used to generate nearly 700 million predicted structure-activity relationships, and highlight a mechanism-agnostic means for combined in vivo and in silico screening of massive chemical libraries. Our current goal is to design an informatics suite that would produce more advanced small molecule activity predictions by incorporating experimental data from multiple sources. We feel this approach has the ability to disrupt traditional lead compound discovery frameworks.

BAGIM is sponsored by Dassault Systemes, DNASTAR, LabAnswer, OpenEye Scientific, Schrodinger, Silicon Therapeutics, Acellera, Acpharis, Cambridge Crystallographic Data Centre, Chemical Computing Group, Dotmatics, Cresset, Cyrus Biotechnology, Optibrium, Team Arrayo, and Scilligence