Juan-Carlos Mobarec
Head of Computational Structural Biology AstraZeneca
Juan Carlos Mobarec, Ph.D. is head of computational structural biology at AstraZeneca in Cambridge, England. He leads a team of highly skilled computational scientists driving the in silico design of investigative molecules for targets across multiple therapeutic areas. His industry experience covers the assembly of highly-efficient teams, establishment of external collaborations, molecular drug design with AI, large-scale computer simulations, large-scale virtual screening, protein/antibody design and molecular modelling with physics and data-driven approaches (ML/AI), having a proven track record of working with innovative and emerging technologies. He has held senior research positions at BenevolentAI, Heptares and the University of Essex. Juan Carlos earned his Ph.D. in Computational Biology in a NSF-sponsored interdisciplinary doctoral program between the Icahn School of Medicine at Mount Sinai and the Courant Institute of New York University in the USA. He has published numerous computational cross-collaborative articles in high-impact peer-reviewed journals.
Seminars
- Explore cutting-edge strategies to predict GPCR-GPCR and GPCR-peptide complexes using AI-enhanced structural modelling
- Demonstrate how dynamic modelling and conformational flexibility inform rational drug design for GPCR targets
- Share computational insights of GPCR dynamics integrating experimental data and machine learning
- Uncovering elusive allosteric binding sites by applying machine learning and predictive modelling, while addressing the experimental challenges of validating these computationally identified targets
- Translating computational workflows into tangible outcomes by moving beyond theoretical models to real-world applications, including the successful development of viable drug candidates and clinical strategies
- Integrating traditional structural biology with modern AI-driven methods by combining techniques like cryo-EM and crystallography with simulations and generative models, to create more dynamic and effective pharmaceutical pipelines
