AI and Omics Data in Drug Discovery: From Data Chaos to Confident Decisions
How can we use AI to move from complex omics data to confident decisions in drug discovery?
In this talk from NextGen Omics Conference 2025, our VP of Scientific Solutions – Jan Majta, walks through real-world use cases showing how Ardigen applies artificial intelligence across the drug development pipeline — from target identification and validation, through compound selection, to patient stratification before clinical trials.
Watch the full talk and get inspired by what’s possible when omics meets machine learning.
🔑 Key topics covered:
The role of synthetic lethality in making AI-based target identification more biologically grounded.
How multimodal data integration (e.g. cell painting, omics, ligand data) supports early molecule selection and toxicity assessment.
The importance of selecting relevant experimental models, based on genomic and cohort similarity to patient populations.
A case study on using AI to define a sensitivity biomarker ahead of a Phase I clinical trial.
The benefits of AI tools designed for scientists, enabling analysis without coding or technical support.
A five-step framework for building practical, sustainable AI strategies in life science R&D — from assessing data maturity to implementing feedback loops.
Further Reading from Ardigen’s Knowledge Hub
Explore more insights into AI, omics data, and drug discovery strategies:
- Data Lakehouses: A Strategic Imperative for the Future of Clinical Studies.
- Multimodal Data Integration for Machine Learning Projects
Interested in topics like this?
If you’d like to stay up to date with similar insights and case studies, sign up for our newsletter below — or get in touch with us directly. We’d be happy to hear from you.
Expert Contribution
Reviewed by: Jan Majta, PhD
Role: Director of AI Solutions, AI‑Driven Drug Discovery
Expertise: Biotechnology, bioinformatics, AI-driven drug discovery, team leadership, strategic solutions for pharma and biotech projects
