Incyte Partners with Edison Scientific to Integrate AI Across Drug Discovery and Translational Research

Incyte and Edison Scientific announced a strategic collaboration aimed at embedding artificial intelligence (AI) across the biopharmaceutical discovery and development process, with an initial focus on target discovery, validation, and translational biology.¹

Under the agreement, Incyte will deploy Edison Scientific’s Kosmos AI platform throughout its research and development workflows. The companies said the platform is designed to continuously learn from translational, biomarker, and clinical datasets to support experimental design, evidence synthesis, and predictive modeling of therapeutic performance.¹

“Our vision is for our data to become a learning system that enhances every decision,” said Pablo J. Cagnoni, MD, president and global head of research and development at Incyte, in the company announcement.¹ “Our goal is not just faster development, but better outcomes across our programs.”

How is AI expanding its role in biopharma research and development?

The collaboration reflects a broader industry trend toward integrating generative and predictive AI technologies into pharmaceutical R&D operations. Large biopharma companies increasingly are exploring AI-driven systems to improve decision-making efficiency, accelerate target identification, and optimize clinical development strategies.²

According to the companies, the first phase of deployment will focus on embedding Kosmos into Incyte’s workflows for analyzing experimental and clinical datasets, including biomarker information. The partners also stated they intend to evaluate the impact of the platform on decision quality and long-term pipeline productivity as the system evolves.¹

Edison Scientific described Kosmos as a collaborative “AI scientist” platform designed to continuously improve as additional datasets are incorporated into the system. “What we are building treats data as something to learn from continuously,” said Sam Rodriques, PhD, chief executive officer of Edison Scientific, in the release.¹

Could continuous-learning AI systems improve drug development outcomes?

The announcement comes as AI adoption in pharmaceutical R&D continues to expand across areas such as protein design, clinical trial optimization, biomarker discovery, and translational medicine.^2,3 A growing number of companies are evaluating whether machine learning systems trained on proprietary experimental and clinical data can improve predictive accuracy and reduce attrition rates during drug development.

Recent analyses suggest AI-enabled approaches could support earlier identification of promising therapeutic targets and improve interpretation of complex biological datasets, although many platforms remain in early implementation stages.^2,4 Regulatory agencies and industry stakeholders also continue assessing how AI-generated insights may be incorporated into drug development workflows while maintaining transparency, reproducibility, and data integrity standards.⁴

Incyte stated that the collaboration initially will concentrate on high-impact research applications but could expand across broader R&D operations over time.¹ Financial terms of the agreement were not disclosed.

References

1. Incyte and Edison Scientific announce strategic collaboration to employ the Kosmos AI platform for research and development. (2026 May 19). Business Wire. https://www.businesswire.com/news/home/20260519000000/en/Incyte-and-Edison-Scientific-Announce-Strategic-Collaboration-to-Employ-the-Kosmos-AI-Platform-for-Research-and-Development
2. Paul D, Sanap G, Shenoy S, et al. (2021 Jan). Artificial intelligence in drug discovery and development. Drug Discovery Today. https://pubmed.ncbi.nlm.nih.gov/33099022/
3. National Institutes of Health. Use of artificial intelligence and machine learning in clinical research. ClinicalTrials.gov website. Accessed May 19, 2026. https://clinicaltrials.gov/search?term=artificial%20intelligence%20drug%20development
4. Considerations for the use of artificial intelligence to support regulatory decision-making for drug and biological products. (2025 Jan). FDA. Accessed May 19, 2026. https://www.fda.gov/regulatory-information/search-fda-guidance-documents/considerations-use-artificial-intelligence-support-regulatory-decision-making-drug-and-biological