Date: 5th September 2025
Venue: QA280 Queen Ann Court, University of Greenwich, Old Royal Naval College, Park Row, London SW10 9LS
Artificial Intelligence (AI) is transforming the pharmaceutical landscape – from early-stage drug discovery to clinical trials and manufacturing. However, unlocking its full potential depends not only on advanced algorithms, but also on high-quality data and robust digital infrastructure.
This FREE one-day discussion meeting (funded by EPSRC) brings together speakers from both industry and academia to explore the critical triad underpinning innovation in pharmaceutical AI. Through expert talks, panel discussions and networking opportunities, we aim to foster dialogue and collaboration on the following themes:
Data Readiness and FAIR Principles: Ensuring that pharmaceutical data is Findable, Accessible, Interoperable, and Reusable to power machine learning and AI tools.
Digital Infrastructure: the platforms and computational resources needed to manage, process and scale data-driven solutions in pharma.
AI Algorithms: State-of-the-art AI algorithms and their potentials for pharmaceutical applications.
The meeting will feature cross-sector perspectives, highlighting how the convergence of data science, digital infrastructure, and AI methodologies can accelerate pharmaceutical R&D. Whether you’re a researcher, data scientist, engineering and IT lead or strategist, this event offers insights into best practices and emerging technologies for integrating AI into R&D pipelines.
Confirmed Speakers:
Christian Baber, Chief Portfolio Officer, Pistoia Alliance
Gian Marco Ghiandoni, Associate Principal AI engineer, AstraZeneca
Prakash Rathi, Director of engineering, data analytics and AI, AstraZeneca
Barbara Zdrazil, ChEMBL Team Coordinator, EMBL-EBI
Speaker Bio
J. Christian Baber
Christian is a computational chemist with a PhD in AI-driven synthetic accessibility and de novo compound design. He continued this work with a postdoctoral fellowship at Osaka University before transitioning to industry, where he has led informatics, predictive modelling, and automation teams across startups and large pharma. Christian previously led Scientific Computing & Informatics at Shire/Takeda and the global Scientific & Pharmaceutical Data, Informatics and Systems function in Janssen R&D. Currently as Chief Portfolio Officer of the Pistoia Alliance, he is responsible for all of the projects, communities and training run under the umbrella of the Alliance from the initial idea, through execution, to delivery of artifacts and sustainability of products.
Gian Marco Ghiandoni
Gian Marco is a cheminformatics and machine learning engineer at AstraZeneca whose role is to bridge science and technology to accelerate drug discovery programs. He is involved in leading the development of chemistry services and molecular property and retrosynthesis prediction capabilities. Beyond his core role, he is an active contributor across different areas of research, an industrial supervisor in graduate programmes, and a committee member of the Molecular Graphics and Modelling Society. Barbara is an accomplished expert in cheminformatics and computational drug discovery with nearly 20 years of experience
Barbara Zdrazil
Barbara is an accomplished expert in cheminformatics and computational drug discovery with nearly 20 years of experience. She earned her PhD in Pharmaceutical Chemistry at the University of Vienna in 2006 and completed her postdoctoral research at the University of Dusseldorf. As a group leader at the University of Vienna she achieved her Habilitation in Pharmacoinformatics in 2019. Since 2021, Barbara has been part of the European Bioinformatics Institute (EMBL-EBI), first as Safety Data Scientist and Consultant for Open Targets and, in 2022, became ChEMBL Team Coordinator within the Chemical Biology Services Team. From 2024-2025, she acted as the Interim Team Leader for Chemical Biology Resources at EMBL-EBI. She also serves as Editor-in-Chief of the Journal of Cheminformatics, contributing her expertise to advancing the field of Cheminformatics.
With support from
