AUGMENTED INTELLIGENCE IN DRUG DISCOVERY XCHANGE
EUROPE 2022
Zurich, November 25
Welcome to hubXchange’s Europe Augmented Intelligence (AI) in Drug Discovery Xchange 2022, bringing together executives from pharma and biotech to address and find solutions to the key issues faced in AI-led drug discovery.
Discussion topics will cover Data Quality, Target Identification, Lead Generation, Lead Optimization and Drug Response Prediction.
Take advantage of this unique highly interactive meeting format designed for maximum engagement, collaboration and networking with your peers.
Please note this is an In-Person meeting.
VENUE DETAILS: Hilton Zurich Airport Hotel, Hohenbuehlstrasse 10 – 8152 Opfikon, Switzerland
Data Quality
Opening Address & Keynote Presentation
X–Chem’s ArtemisAI Platform: a flexible approach to AI for drug discovery
- Intro to X-Chem
- ArtemisAI: X-Chem’s AI platform for DEL and beyond
- Overview of ArtemisAI case studies
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
Garbage in, garbage out – curating data for activity / property prediction in drug discovery
- Internal databases not standardized (typos, negligence, delays, manual curation, historical artefacts, …)
- Extreme data imbalance
- Automated solutions hard to coordinate with multiple stakeholders involved
- Multidisciplinary expertise required
Senior Data Scientist ML/AI, Janssen Pharmaceuticals
Maciej Kanduła is a Senior Scientist at Janssen, designing, developing, and deploying AI-driven pipelines for finding potential drug candidates, and serving as an AI/ML lead in discovery programs. He focuses on enabling image-based compound activity prediction, supporting Janssen’s small molecule portfolio; and integrating information from heterogeneous data sources, at the input level—combining data modalities, and the desired output—fusing property data from databases.
Prior to joining Janssen, Maciej worked at the Institute for ML at the JKU Linz (Austria), consulted at the IARAI Institute in Vienna (Austria), and was a visiting scholar at the Boston University (US). Maciej holds a Ph.D. in Bioinformatics and contributed to multiple peer-reviewed publications.
Data quality and integrity: how do we achieved it?
- What approaches do you use to ensure and maintain data quality?
- Do you have a recurring process to confirm the relevancy if data through its lifetime?
- How can we get access to shared data?
- How does data quality affect your day-to-day efficiency?
- How do you improve data quality over time, balance that with the cost of generating data, and ensure that you are collecting informative rather than redundant data?
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
Networking Lunch
1-2-1 Meetings / Networking Break
1-2-1 Meetings / Networking Break
Afternoon Refreshments
How to ensure high data quality sourced externally, either as datasets or as cloud-based service?
- Is it beneficial to use a cloud data-provider service instead of integrating databases locally?
- How to address local integration of data obtained from diverse sources?
- How to deal with a large degree of uniqueness in OMICs “big-data”?
Director Bioinformatics, Hengrui European Biosciences
Victor Zharavin has 15 years of academia and biotech experience. Being a well-respected achiever in the computational and life-science fields, he worked at Biozentrum Basel, TUM, collaborated with major companies including Novartis, Medigene Therapeutics, Agilent and Bruker. He has also consulted with several organizations including Roswell Park Cancer Center in Buffalo, USA.
Victor has conducted in-depth research on integrating tools into in silico pipelines on HPC platforms such as Galaxy.EU infrastructure, automation of cancer genetic diagnostics and therapy recommendations for Freiburg uniclinic/DKFZ, development of anti-cancer vaccines and prediction of potential side effects of immunotherapies.
Target Identification
Opening Address & Keynote Presentation
X-Chem’s ArtemisAI Platform: a flexible approach to AI for drug discovery
- Intro to X-Chem
- ArtemisAI: X-Chem’s AI platform for DEL and beyond
- Overview of ArtemisAI case studies
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
- Design principles and challenges in creating highly reliable recommendation systems
- The best data structures to organize your data and how you can accelerate discovery
- Real World Data (RWD) and how to assess the trustability, quality and privacy of data
Global R&D Tech Head & Director of Innovation and Data Science, GlaxoSmithKline
Fausto has a double PhD (Information Technology and Computer Science), earning his second master’s and PhD at the University of California – Irvine. He has worked in multi-disciplinary teams and has over 20 years of experience in academia and industry. As a Physicist, Mathematician, Engineer, Computer Scientist, and HPC and Data Science expert, Fausto has worked on key projects at European and American government institutions and with key individuals, like Nobel Prize winner Michael J. Prather. After his time at NVIDIA corporation in Silicon Valley, Fausto worked at the IBM T J Watson Center in New York and now at GSK.
Credentialing
- Siloed nature of OMICs data
- Limited clinical data availability
- Approaches for credentialing targets
FSRB Assoc. Vice President – Bioinformatics, Excelra
Chandra Sekhar Pedamallu comes with extensive experience in Bioinformatics and Computational Biology
specializing in cancer genomics. Before joining Excelra, Chandra was associated with Sanofi Inc., identifying novel
drug targets in Oncology (Molecular and Immuno-oncology). Prior to Sanofi, he was at Dr. Meyerson Lab,
Dana-Farber Cancer Institute, and a visiting scientist at The Broad Institute of MIT and Harvard. During his 6-year
tenure at Harvard, he led microbial analysis, pathogen discovery projects in cancer and other diseases. He has
contributed substantially to over a dozen projects under the auspices of the Cancer Genome Atlas (TCGA).
Chandra holds a Ph.D. in Systems Engineering (area of research: Global Optimization) from School of Mechanical
and Aerospace Engineering, Nanyang Technological University, Singapore. He has co-authored over 80 manuscripts, published in highly reputed journals including Nature, Nature Genetics, Science, Cell, PNAS, etc., and has been inducted as a Fellow of the Royal Society of Biology (FRSB).
Poster Session
Scalable Generation of Predictive Binding Models Based on DEL Screening Data Using ArtemisAI
- ArtemisAI platform
- Case study
- Experimental approach to validate the ArtemisAI platform
- Application of this approach to >20 protein targets
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
14:00 – 14:30
16:20 – 17:20
Discovering novel drug targets using AI
- Identifying new drug targets
- What can we learn from patients at baseline as opposed to relapsed-refractory?
- Combine data mining to mechanistic understanding
Associate Director, Precision Oncology & Virology, Molecular Partners
Ana Maria Florescu is currently leading a computational disease biology group at Molecular Partners that covers hematological malignancies, solid tumors and virology ranging from discovery to early clinical development. Prior to that she was part of the Precision Oncology group at Sanofi. Her main scientific interest in using statistics, modelling, and machine learning to elucidate disease mechanisms, drug mode of actions and resistance and back translate those mechanisms into new targets.
Lead Generation
Opening Address & Keynote Presentation
X–Chem’s ArtemisAI Platform: a flexible approach to AI for drug discovery
- Intro to X-Chem
- ArtemisAI: X-Chem’s AI platform for DEL and beyond
- Overview of ArtemisAI case studies
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
innovator under 35 and in BBC 100 women.
How can artificial intelligence accelerate drug discovery and development?
- Lead optimisation or optimised leads; can AI improve pre-clinical success rates?
- Data is the new oil; how can we fuel the AI machine?
- The curse of innovation; what might prevent lead success?
- Born of mind and machine; what does an augmented drug discovery process look like?
Principal Machine Learning Engineer, Healx
Daniel O’Donovan has over 15 years experience applying machine learning to scientific problems. He studied for his PhD at the University of Cambridge; “Bayesian Analysis of NMR Data” back when machine learning was called statistics. After spending time as a post-doc at Harvard Medical School, he joined industry to disrupt empirical scientific processes with data and algorithms. He later joined Healx as an early employee and plays a critical role building the award winning start-up’s AI powered rare disease treatment platform.
Poster Session
AI driven Lead Generation – Key factors of success
Example of projects from Lead Generation pointing out the main key factors that were important during the project delivery
Focus on AI/ML methodology used during such projects
Focus on technological site – must have from the architecture point of view to make those project run smoothly:
- Data management & harmonization
- MLOps for large scale image analysis
Executive Vice President and Board Member, Ardigen
Kaja Milanowska-Zabel, PhD is a precision medicine enthusiast and a bioinformatics researcher. Her personal and professional ambitions led her to exploit the importance of different data analysis approaches in human health. In 2016, Kaja joined Ardigen and started research activities, primarily in the area of oncology. In 2018, after becoming one-third of Ardigen’s management board, she took over a new position and the responsibility of the R&D projects. Currently, Kaja is a Business Development Executive and Board Member. Kaja is also broadening her knowledge in business by realizing a curriculum in Executive MBA at Kozminski University in Warsaw.
Principal Software Developer and Executive Director of Technology, Ardigen
Mr. Piotr Radkowski, a scientist, an engineer and a teacher. Has almost two decades of experience working in both the IT industry and academia. Recently Principal Software Developer and Executive Director of Technology at Ardigen. His current endeavors focus on developing robust solutions for Life Science research and integrating cutting-edge computer technologies.
AI-guided protein structure prediction and biomolecular simulations
- The Alphafold 2 revolution and its implications
- Machine learning molecular force fields for biomolecules
- Automatic collective variable prediction for enhanced sampling simulations
- Machine learning accelerated binding pose prediction
Senior Director, External Innovation, Ipsen
Matthew Beard is Senior Director, External Innovation, with Ipsen, responsible for identifying and evaluating new partnership opportunities in Rare Disease and Neuroscience. He has over 15 years of experience in pre-clinical and clinical drug development in pain, endocrine, neurology, and neuromuscular disease areas. His scientific background is the molecular cell biology of cell signaling, the mammalian secretory pathway, and neurotransmitter release.
Using AI to make a complex drug discovery process smarter
- Which data capture and analysis challenges are the most impactful ones when going from target ID to lead optimization?
- What is the most enabling data to select the “best” lead molecules?
- Which elements hinder a bi-directional data flow between target identification and lead optimization (and probably beyond)?
- Where can quick wins be implemented through the application of specific predictive AI models?
- AI is a data-hungry process – how can we optimize the feeding in terms of quality and quantity of data?
Director, Data Science, Novartis
Florian Nigsch studied chemistry and biology in Vienna, Austria, and Paris, France, where he graduated with a Master’s degree in Physical and Theoretical Chemistry. He then obtained a PhD in chemistry from Cambridge University, UK. After a postdoc at NIBR at the interface of cheminformatics and bioinformatics, he joined NIBR in Basel, Switzerland in 2012. Florian is currently leading a group of bio- and cheminformatics scientists in the Chemical Biology & Therapeutics department focused on project progression in early drug discovery.
Lead Optimization
Opening Address & Keynote Presentation
X–Chem’s ArtemisAI Platform: a flexible approach to AI for drug discovery
- Intro to X-Chem
- ArtemisAI: X-Chem’s AI platform for DEL and beyond
- Overview of ArtemisAI case studies
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
12:20 – 13:20
Networking Lunch
14:00 – 14:30
15:00 – 15:10
15:15 – 16:15
- ‘Black Box’ vs ‘Explainable AI (XAI)’ trends in Lead Optimization. How to strategically choose between the two approaches in the different phases of Lead Optimization? What are the cost-benefits of XAI vs black box solutions?
- Lead optimization and AI in the RNA therapeutics era: are the current AI methodologies ready for the new class of RNA-based therapeutic approaches? Which novel AI solutions are making their way to industry? How is AI helping prediction and optimization of drug delivery?
- A war of acronyms: AI for DMPK and ADMET, beyond on-target affinity optimization. How do we build adequate training datasets and models to optimize Absorption, Distribution, Metabolism, Excretion and Toxicity aspects?
Director, HAYA Therapeutics
After receiving his doctoral degree in Information Engineering from the University of Padova, Marco held a postdoctoral position in Cancer Genomics at the University of Lausanne, focusing on functional dependencies between cancer mutations and their therapeutic actionability. He later transitioned to industrial research at SOPHiA Genetics, leading a team focusing on variant annotation and pathogenicity prediction for the interpretation of patient molecular data. Most recently Marco joined HAYA Therapeutics, a startup pioneering the development of RNA-based therapeutics for fibrotic diseases, as head of data Science and Computational Biology. His team focuses on multiple R&D aspects of the target discovery and lead optimization platforms.
Drug Response Prediction
Opening Address & Keynote Presentation
X–Chem’s ArtemisAI Platform: a flexible approach to AI for drug discovery
- Intro to X-Chem
- ArtemisAI: X-Chem’s AI platform for DEL and beyond
- Overview of ArtemisAI case studies
Senior Vice President & General Manager, X-Chem
Noor is a serial biotech entrepreneur with a track record of achievements in AI having held an Assistant Professorship from Aalborg University.
Noor has published numerous papers in the field of artificial intelligence and is an inventor on a handful of patents. She is passionate about data and AI and on a mission to cure disease with the power of human and machine learning.
She is a recognised healthcare leader, MIT innovator under 35 and in BBC 100 women.
Vice President, Scientific Computing and Data Science, X-Chem
Marie-Aude has dedicated her career to the application of informatics in the field of drug discovery. At X-Chem, she has led a collaborative approach to generating high-quality data management solutions and a world-leading integrated suite of software tools to support X-Chem’s DNA-encoded library (DEL) platform. Having been part of X-Chem’s groundbreaking forays into machine learning on DEL, she now plays a key role in the continual expansion of X-Chem’s AI platform.
Challenges in bringing molecular precision medicine to cancer drug response prediction
- How can machine learning approaches overcome the limitations of small n datasets for developing predictive models?
- What is the effect of heterogeneity in patient populations on the robustness of drug response prediction
- What role does the difference between molecular subtypes of cancers play in predicting the response to the same therapeutic?
- How important is an understanding of drug MoA on a molecular / cellular level for developing accurate models of drug response?
Director of Data Science, Scailyte AG
Sarah Carl is the Director of Data Science at Scailyte, where she leads a team of data scientists committed to developing Scailyte’s AI-driven single-cell analytics platform, ScaiVision, as well as driving data analysis for Scailyte’s biomarker discovery projects, with the goal of advancing precision medicine. Sarah holds a BA in Biology from the University of Chicago and a PhD in Genetics from the University of Cambridge. She previously worked as a bioinformatician at the Friedrich Miescher Institute in Basel, Switzerland, for four years before joining Scailyte in 2018.
15:15 – 16:15
Applications of AI to patient stratification and drug response prediction
- Integrating different data modalities for drug response prediction and patient stratification. What are the challenges, what are we missing?
- Current landscape of AI/ML approaches for drug response prediction and patient stratification. How do we ensure that the AI-model is fit-for-purpose?
- How to best leverage pre-clinical and clinical omics data for drug response prediction? Share experiences in combining pre-clinical and clinical data.
Associate Director & Senior Principal Scientist, Oncology Data Science, Novartis Institutes for BioMedical Research (NIBR)
Slavica Dimitrieva works as an Associate Director & Senior Principal Scientist at the Novartis Institutes for BioMedical Research Oncology in Basel. She has over 10 years of bioinformatics experience working closely with biologists, clinicians, and scientists in academia, hospitals, and pharma, helping with deriving insights from large-scale biomedical data. At Novartis she co-leads the data science efforts in target identification. She is passionate about applying AI on multi-omics data for oncology drug discovery and precision medicine.
Slavica has a background in Computer Science and a PhD in Bioinformatics from the EPFL in Lausanne, Switzerland. After a postdoc at the Imperial College London, she worked as a Bioinformatics Scientist and Lecturer at the Functional Genomics Centre at ETH Zurich and University of Zurich, before joining Novartis. At Novartis her focus is on data-driven drug discovery from single cell and spatial omics .
16:20 – 17:20
Enhancing drug response prediction – can AI be the new defining factor before First Time in Human studies?
- How can AI and ML use clinical data to enhance drug response prediction?
- Can the AI and ML shed light into possible mechanisms that are not fully understood that can influence drug responses?
- How to better integrate clinical pharmacology with AI to better inform a dose range before a phase I trial?
- Can AI predict drug responses, including differing toxicity levels across a spectrum of patients?
Associate Director, Clinical Research and Development Lead, GlaxoSmithKline
Marco completed his MD in his home country of Costa Rica in 2014, where he practiced primary care and pre-hospital emergency medicine before having the opportunity to transition into academia, where his research interests lied in cardiovascular and stroke medicine. After earning his PhD in stroke medicine at the University of Manchester, he transitioned into industry, where he currently works as an Associate Director, Clinical Research and Development Lead at GSK, working on various clinical development projects.