Explore how knowledge graphs integrate multi-source biological data, such as genetic, proteomic, and clinical information, into unified models that accelerate target discovery and disease understanding, with AI enhancing the extraction of actionable insights.
Learn how data normalization and the latest curation strategies ensure that biological datasets are clean, standardized, and AI-ready, enabling accurate analysis and improved model performance for drug development.
Mark Kiel, MD, PhD, and Molecular Genetic Pathology Fellow at University of Michigan, is the founder and CSO of Genomenon, where he oversees the company’s scientific direction and product development. Mark's passion is to power the practice of precision medicine by organizing the world’s genomic knowledge. To that end, he created Genomenon and the Mastermind suite of genomic tools.
Genomenon unlocks valuable real-world evidence buried in clinical literature to inform genetic disease and cancer research. Our data and insights empower precision therapeutic companies to optimize clinical trial design, support label expansion, enhance diagnostic patient yield, and streamline regulatory submissions.
Genomenon uses its AI knowledge graph to mine over 10 million full-text scientific articles to characterize patient data reviewed by its team of scientific experts. This comprehensive approach transforms previously inaccessible data into actionable insights, enabling refined disease-prevalence estimates, genotype- phenotype correlation discovery, and clarifying patient demographics and treatment outcomes.
Genomenon's RWE approach unlocks the vast repository of published research, capturing billions of dollars' worth of insights into rare disease and cancer patient presentations, clinical journeys, treatments, and outcomes.
Hear cross-functional perspectives on successfully implementing AI across process development teams, from aligning with quality, IT, and manufacturing to overcoming cultural and technical barriers, with a focus on driving operational efficiency and long-term value.
Harnesses collaborative innovation networks to integrate external expertise and accelerate breakthrough AI development.
Dive deep into how large language models are automating complex planning tasks, from trial feasibility assessments and synthetic protocol generation to cross-functional alignment and regulatory-ready documentation, with real-world examples of scalable implementation and measurable impact.
Explore how AI-driven digital twins and functional models integrate patient-specific biology to identify and validate high-confidence drug targets by simulating system-level responses to genetic or pharmacological perturbations.
Learn how perturbation modelling with multiomic and functional genomics data predicts the effects of interventions on disease pathways, while LLMs synthesize data to uncover and prioritize novel therapeutic targets.
Equip teams with AI tools that capture process knowledge and simulate scale-up scenarios, reducing tech transfer timelines and improving first-batch success rates - critical for aligning R&D, MSAT, and manufacturing expectations early.
Gain actionable strategies for embedding generative AI and large language models into early-phase trial design and execution, from protocol drafting and site selection to patient engagement, accelerating timelines while ensuring data quality and compliance
Reinforces trust and compliance by embedding robust data governance frameworks and ethical AI practices, to responsibly harness data and mitigate future regulatory risks.
