Developing a mechanistic model of IVT to include nucleation and growth of magnesium pyrophosphate crystals and subsequent agglomeration of crystals and DNA.
Nathan Stover
PhD Student, Chemical Engineering
Massachusetts Institute of Technology
Philip Tagari
Chief Scientific Officer
Insitro
Equip yourself with KPI dashboards and financial models to quantify time‑to‑value, optimize resource allocation, and build a compelling business case for AI investment.
Forges powerful ecosystems by aligning pharma, tech, and academia, enabling shared expertise and resources to accelerate breakthroughs and navigate complex R&D challenges.
Explore how machine learning techniques, such as supervised learning and deep learning, predict critical ADME properties like solubility, permeability, and DDI risk.
Discover how computational methods, including molecular docking and quantum chemistry simulations, optimize high-affinity drug-target interactions for enhanced efficacy.
Attila Csikász-Nagy
CEO
Cytocast
Attila is a visionary leader with a strong background in computational and systems biology. As a professor and researcher, he has made significant contributions to the field, with an impressive publication record and expertise in bioinformatics. With experience at renowned institutions like Microsoft Research and King's College London, Attila brings a unique blend of scientific knowledge and business management skills to his role as CEO. In addition to his professional pursuits, Attila enjoys playing basketball competitively with his old high school friends.
David Kombo
Principal Scientist
Sanofi
Jacob Berlin
CEO
Terray Therapeutics
Cytocast
Website: https://www.cytocast.com/
Cytocast, a TechBio startup based in Budapest, Hungary, accelerates drug discovery by combining bioinformatics, AI, and large‑scale digital‑twin simulations to predict side effects at the start of R&D. Pharma, biotech and CRO teams use the Cytocast technology to de‑risk portfolios earlier and focus resources on safer candidates.
The CYTOCAST DIGITAL TWIN Platform™ models cellular systems to deliver breadth‑first side‑effect profiling for early‑stage small‑molecule programs, including combinations. Proteome‑based simulations reveal how candidates perturb cellular processes and provide actionable evidence to refine chemistries and improve safety. The platform has been validated through pilots with small and mid‑size partners. Currently, the following products are available for the clients’ tailored needs:
- Cytocast Screener™: Rank thousands of compounds by likely side effects to guide early discovery.
- Cytocast Optimizer™: After in vitro/in vivo, refine leads with comparative safety insights for preclinical decisions.
- Cytocast Nominator™: In‑depth analyses to support final candidate selection for trials.
Cytocast has raised €2.5M pre‑seed to date. We are opening a new €5M seed to expand product capabilities and market reach with the goal of adoption at least 10 top‑100 pharma companies by 2027. Cytocast is a proud member of the Alliance for Artificial Intelligence in Healthcare (AAIH) and NVIDIA Inception.
Explore how AI-powered single-cell and spatial biology technologies reveal cellular heterogeneity, tissue organization, and microenvironmental interactions to uncover disease mechanisms and therapeutic targets.
Learn how AI models analyze high-dimensional cellular and spatial data to define pathogenic cell states, map dysregulated pathways, and prioritize targets for early-stage therapeutic discovery.
Discover practical strategies for scaling Process Analytical Technology (PAT) from R&D into regulated GMP environments , including method validation, data integrity, and cross-functional alignment to ensure continuity, compliance, and control at commercial scale.
Explore how generative AI is being used to analyze real-world data at scale, enabling earlier signal detection, automated safety reporting, and more dynamic risk-benefit monitoring, driving smarter, faster post-market decision-making across the product lifecycle.
Safeguards the innovation pipeline by proactively securing sensitive research data, enhancing risk resilience and ensuring stakeholder confidence in the integrity of AI-driven discoveries.
Explore how AI and large language models are revolutionizing reaction prediction, retrosynthesis planning, and synthetic accessibility scoring.
Learn how to evaluate and optimize AI-generated leads for real-world developability, including solubility, stability, and synthetic tractability.
Ethan Pickering
Head, Data Science & ML Research
Bayer