Deepak Bandyopadhyay

About Deepak Bandyopadhyay

I am a data scientist, data science team leader and innovator with experience in all stages of pharmaceutical R&D - drug discovery, process development and clinical trials. At J&J I lead a team of Data Scientists within Quality Analytics to build data products and derive business value from Clinical Trial Quality & Compliance, Operations and related data. We have created, deployed and continue to innovate on a suite of text analytics and machine learning apps for Quality data. At my most recent role at GSK as a data scientist in drug product development (CMC), I led a project to bring GSK\'s large molecule process and analytical data onto our big data platform and develop new analysis and modeling capabilities. Previously as a computational chemist (i.e. a data scientist in drug discovery), I built tools for and supported the work of scientists from many domains, including chemists, biologists, and other informaticians. Deriving insight by custom data integration is one of my specialties; for example I designed and implemented a platform for integrating data sets from multiple experiments that was used by GSK screening scientists to find and combine hits.I enjoy digging into all the computational aspects of life science research, and solving data challenges by exploiting adjacencies and connections - between diverse fields of knowledge, and the equally diverse scientists trained in them. A trained computer scientist and cheminformatician, I\'ve been an active member of the algorithms, data science and internal innovation communities at GSK and J&J, leading many of these efforts. My Ph.D. work introduced new computational geometry techniques for structural bioinformatics and protein function prediction. In graduate school I also made contributions to virtual and augmented reality that have been recognized for their long-term impact.

Experience

1. Director, Data Science, R & d Quality

   Johnson & Johnson

   Oct 2023 — Present · Horsham, PA, US

   I lead a high-performing team of data scientists who are tackling the most challenging problems in R&D Quality and beyond. We leverage our base of NLP, ML and Data Engineering technical excellence and bring in strong Product Management expertise to maximize the business value of what we build and deploy. The proof is in the pudding (and the products), as we are repeatedly called in to high-priority projects and deliverables, and deliver what the customer needs (not necessarily what they asked for). We hope to partner with internal J&J groups to solve your business problems, and make the external world a better place via thought leadership, publications and open source code releases. We will be looking to build up our group via FTE hiring (as positions become available), postdocs and interns/co-ops. If you think you have what it takes, please get in touch!

Education

• The University of North Carolina at Chapel Hill

  Ph.D., Computer Science

  1999 — 2005

• The University of North Carolina at Chapel Hill

  MS, Computer Science

• Indian Institute of Technology, Delhi

  B.Tech., Computer Science and Engineering

  1995 — 1999

Skills

• Protein Structure
• Software Development
• Drug Discovery
• Pattern Recognition
• Algorithms
• Life Sciences
• Data Mining
• Computational Biology
• Computational Chemistry
• Augmented Reality
• High Throughput Screening
• High Content Screening
• Cheminformatics
• Exploratory Data Analysis
• Workflow Software
• Bioinformatics
• Transcriptomics
• Biotechnology
• Molecular Modeling
• Data Analysis
• Scientific Visualization
• Projection Mapping
• Drug Design
• 3d Visualization
• Data Visualization
• Computer Science
• Data Science
• Computational Geometry
• Structural Bioinformatics