Drug discovery using Open-source tools

Modern drug discovery is increasingly powered by open‑source software, machine learning, large datasets, and computational modeling. In this special PyData Singapore session, we explore how open tools are accelerating innovation in biology, chemistry, and pharmaceutical research. PyData Singapore is a community for users and developers of open‑source data tools — Python, R, Julia, and beyond — who gather to share ideas and learn from each other.

What this meetup is about
We’ll dive into how open‑source technologies are used in real drug discovery workflows, including:

AI/ML for target identification, compound screening, and lead optimization
Molecular simulations, docking, and generative chemistry
Open datasets for genomics, proteomics, and structural biology
Statistical and mathematical models for ADMET and toxicity prediction
Reproducible pipelines, cloud computing, and workflow automation
Collaboration between industry, academia, and open‑source communities

Speakers
We’re bringing together 3–4 experts from biotech companies (Hummingbird Bioscience), AI startups (LynxKite), research institutes, and open‑source projects. Each will share practical insights, tools, and case studies from their work in computational drug discovery.

Who should attend

Data scientists & ML engineers
Computational chemists & biologists
Bioinformatics researchers
Pharma & biotech professionals
Students and anyone curious about open‑source science

Why this matters
Drug discovery is becoming more open, more computational, and more collaborative. Whether you’re working in life sciences or simply interested in applied machine learning, this session will show how open‑source tools are reshaping the future of therapeutics.