Speaker

Title

Causal Machine Learning in Drug Development

Abstract

While Drug Development traditionally relies on controlled experiments to establish causality, for example in Pre-clinical animal PK/PD studies or RCTs in Clinical Development, there have been rapid advances in Causal Inference methodologies which have enabled the generation of causal evidence from Observational and Real World Data (RWD) sources at a population level.

Causal Machine Learning enables valid inferences on individualized treatment effects which could be potentially predictive in unseen patient cohorts, thus paving the way towards personalized treatment regiments and enrichment strategies in Clinical Development.

In this talk, I give an example of a use-case which is relevant to both Clinical and Commercial development of drugs - synthetic and external control arms which are being used either as comparator arms in Clinical Development or as head-to-head effectiveness comparisons with other medications in Commercial Development.

About Dr. Ashar Ahmad

Ashar Ahmad has a multidisciplinary background with a Chemical Engineering bachelor’s degree from IIT Bombay followed by Master’s degree in Computer Science specializing in Modelling and Simulation. Between 2014 and 2018 he worked at b-it in Prof. Dr. Holger Fröhlich’s lab on Statistical Machine Learning methodologies and contributing to translational projects at the University Medical Centre in Bonn.

After receiving his PhD, he joined UCB Pharma as a Post Doctoral Scientist working in the Translational Medicine department. Since 2021, he has been working as an Associate Director at Grünenthal GmbH in Aachen leading a team of Data Scientists and driving several high impact use-cases across Global R&D and Global Commercial business units.

Title

Foundation Models for the Smart Hospital of the Future

Abstract

Large language models like ChatGPT are changing the world right now. Healthcare can and must benefit from these developments. A shortage of skilled workers, demographic developments and rapidly increasing data volumes make process automation unavoidable. This is especially true for complex systems like hospitals. In this talk I will present current challenges and approaches to optimize clinical and non-clinical processes in the hospital domain with AI.

About Dario Antweiler

Dario Antweiler is a Data Scientist at Fraunhofer IAIS in Sankt Augustin in the Healthcare Analytics business unit and is responsible for projects in the areas of AI in pharmacology and digitization in hospitals. His research field is machine learning on graphs and networks. Background in Mathematics and Computer Science from the University of Cologne.

Title

Enabling Biomedical Research Through ML: From Exploration to Production

Abstract

AI-based tools and applications are increasingly supporting Genomics England’s health care and research mission. This talk will overview examples of such efforts: from exploration to production. Progress, challenges and opportunities across the AI life cycle will be discussed.

About Dr. Francisco Azuaje

Francisco Azuaje is Director of Bioinformatics at Genomics England, leading AI/ML and data science. He brings leadership and research experience from academia and private sector, including the pharmaceutical industry, and is an Honorary Fellow of The University of Edinburgh. He has led research teams responsible for the predictive, integrated modelling of preclinical and clinically oriented datasets, including multi-omics, imaging data, natural language and other data types.

Title

Transforming the Chemical Industry: Exploring BASF's Innovative Use of AI

Abstract

Artificial Intelligence has become the crucial tool for modern businesses and chemical industry is no exception. In this talk, we will explore innovative ways in which BASF, a leading chemical company, has integrated AI its core to streamline the processes, improve customer experience and drive innovation. We start by looking into BASF's use of AI in our segment "Digitalisation of Businesses" from customer facing solutions, sales and marketing to e-commerce. Finally we explore company's digital transformation strategy, Key Digital Capability (KDC). KDC serves as a central hub for digital innovation and provides foundation to leverage the advancements in technology to drive growth and efficiency. This includes everything from building digital platform to developing our own AI models. These solutions have enabled BASF to optimise its processes, improve customer experience and create new business opportunities.

About Dr. Shweta Bagewadi Kawalia

As a seasoned professional with a diverse background, Shweta Bagewadi Kawalia brings a wealth of experience to the table. Her tenure at BASF as an R&D Knowledge Architect involved supporting the R&D division and driving advancements in Graphs+NLP as a Key Digital Capability Community Manager. Currently, at Digitalization of Businesses, she leads a team responsible for developing cognitive search and chatbot solutions for the operating divisions. In this role, she successfully spun-in a BASF's start-up venture.

Her academic background includes working in wet-lab during her bachelor's studies and applying this knowledge to computational life sciences during her Masters and PhD. During her PhD work, her main research focused on the prioritization of novel biomarkers using graph mining-based analysis for Neurodegenerative Diseases.

Title

Role of AI in Personalized Medicine

About Dr. Anna Bauer-Mehren

Anna Bauer-Mehren is a Bioinformatician by training and leads the Analytics Chapter in pREDs Data&Analytics organization. Her team is analyzing various types of data such as imaging data, genomic information, and data from electronic health records to better understand diseases and develop personalized therapies.

She holds a PhD in Bioinformatics and Biomedical Informatics from the University of Pompeu Fabra in Barcelona and a Master in Bioinformatics from the Ludwig-Maximilians-Universität and the Technische Universität München. She completed her postdoc education at the Faculty of Biomedical Informatics at Stanford University in the USA.

Title

Machine Learning for Genomics Driven Drug Discovery

About Dr. Johann de Jong

Johann de Jong obtained his PhD in Computational Cancer Biology from Delft University of Technology (the Netherlands), developing machine learning models for studying gene regulation and cancer gene discovery. After a number of years in academia and industry, including at the Netherlands Cancer Institute, BASF and UCB Pharma, he joined Boehringer Ingelheim in September 2021. Here, within Global Computational Biology and Digital Sciences, he combines hands-on work with building and leading a Statistical Modeling team centered on developing machine learning models for genomics driven drug discovery by integrating prior knowledge with multimodal and/or longitudinal data sources including human biobanks. Focus areas are target identification, patient stratification and biomarker identification across a wide range of indications including immune-, respiratory- and cardiometabolic diseases.

Title

Data Save Lives – Deep Learning from Health Data

About Prof. Dr. Roland Eils

Prof. Dr. Roland Eils is founding director of the BIH Digital Health Center at Charité  ̶ Universitätsmedizin Berlin and director of the Health Data Science unit at the Medical Faculty of Heidelberg University. Before, he was founding and managing director of Heidelberg University’s Systems Biology center BioQuant and Head of Division "Theoretical Bioinformatics" at the DKFZ in Heidelberg. His group has delivered significant contributions to the field of cancer genomics  systems biology and digital health. Since 2017 Roland Eils has been member of the Organizing Committee of the Human Cell Atlas initiative and Coordinator of the HiGHmed Consortium. Since 2021, he has coordinated the HEALTH-X dataLOFT („Legitimierter, Offener und Föderierter Gesundheitsdatenraum in GAIA-X“) consortium. He has published over 700 publications cited over 65000 times resulting in an h-index of 112 (source: google scholar, last visited 2023-05-15).

Title

From Data to Predictions: Computational Optimization of Multi-specific Protein Therapeutics

Abstract

Sanofi’s automated high-throughput engineering platform enables the fast generation of large panels of multi-specific antibody variants giving rise to big data sets. By mining our data sets we were able to extract engineering patters and to develop AI-based virtual screening workflows to guide the exploration of huge design spaces within biologics drug discovery.

About Dr. Norbert Furtmann

Upon finishing his studies in Pharmaceutical Sciences, Norbert Furtmann pursued his interdisciplinary PhD thesis in Computational Life Sciences and Pharmaceutical Chemistry at the University of Bonn focusing on computer-aided design, synthesis, and biological evaluation of protease inhibitors. After starting his professional career at Merck KGaA as Principal Scientist, Norbert Furtmann joined Sanofi in 2016 as bioinformatician within the Large Molecule Research department where he built a team for Data Science & Computational Design in the past years. Currently Norbert Furtmann is heading the Computational & High-throughput Protein Engineering group to support the discovery of next generation protein therapeutics. In addition, Norbert Furtmann is acting as Head of AI Innovation for Sanofi’s Nanobody platform to develop novel workflows for computational Nanobody design and optimization.

Title

Automatic Relation Extraction from Scientific Literature for Large Scale Knowledge Graph Creation

Abstract

Knowledge graphs are a powerful method to organize domain-specific knowledge and make it available for automatic analysis. Yet, often extensive manual efforts are needed to create and maintain them. We report on a join project with Fraunhofer SCAI where a large knowledge graph has been created automatically with cause-effect relations derived from scientific publications.

About Stefan Geißler

• M.A. in Linguistics / Computer Science from the Univ Erlangen-Nürnberg
• Seven years at the Scientific Center of IBM in Heidelberg
• Co-founded NLP/AI startup TEMIS in 2000, Managing director of its German branch until 2016 when TEMIS was acquired
• Co-founded NLP/AI startup Kairntech in 2018

Title

Machine Learning Models for Predicting Human in Vivo PK Parameters Using Chemical Structure and Dose

Abstract

Comprehensive pharmacokinetic characterization of potential drug candidates is critical to understanding the exposure at the site of action, including anticipated elimination processes, prior to their clinical development. For this, different in vitro and animal in vivo studies are routinely employed to estimate pharmacokinetic profiles in humans, which can often be costly and time-consuming. Therefore, in silico prediction of human pharmacokinetics at the point of design is expected to accelerate the development of novel candidate therapeutics. For this, we have established a comprehensive data curation protocol for the machine learning evaluation of 12 human in vivo pharmacokinetic parameters across 1001 unique compounds, using only chemical structure information and available doses as inputs. These models were thoroughly validated using an independent test set, diagnostic calculations, and AstraZeneca clinical data. For a subset of internal clinical candidates associated with preclinical DMPK predictions, we have compared our in silico approach with state-of-the-art pharmacokinetic models. As the result, three fit-for-purpose models were established: AUC PO, Cmax PO, and〖VdSS IV. Based on our findings, these machine learning models demonstrate considerable potential for assisting decision-making processes in drug discovery, including candidate prioritization towards the clinic.

About Dr. Filip Miljković

Filip Miljković obtained a Master's degree in pharmacy from the Medical Faculty, University of Niš, Serbia, in 2014. In 2016 he joined doctoral studies in Computational Life Sciences in the Department of Life Science Informatics, b-it, at the University of Bonn, Germany under the supervision of Prof. Dr. Jürgen Bajorath. In 2019, he obtained his Ph.D. degree and since then joined AstraZeneca, Sweden as a Senior Scientist, where he currently works in the Department of Early Cardiovascular, Renal and Metabolism (CVRM). He remains affiliated with his former academic group at the University of Bonn, Germany. His research interests include chemoinformatics and computational methodologies for medicinal chemistry and chemical biology, including machine learning and structure-based approaches.

Title

One Health – Vision and Reality

Abstract

Journey from the current state of fragmented data, information, insights, knowledge and decisions to collaborative intelligence for the global health security enabled by semantic AI.

About Dušan Milovanović

During his 28 years of professional career, acting in systems engineering, solutions architecture, and product management roles, Dušan Milovanović was engaged in the research and development of disruptive information and communication technologies. His curriculum includes a technology leadership career at Ericsson, then engagements within life science, healthcare, and public health domains. At the World Health Organization, he acts as a technology expert and a health intelligence architect within the core team of the Epidemic Intelligence from Open Sources initiative and the Hub for Pandemic and Epidemic Intelligence. Dušan Milovanović inspired and secured the acceptance for creation of three Hub's prime-mover's initiatives – Health Intelligence Knowledge Representation and Reasoning, Laboratory for Collaborative Intelligence, and the Open-Source Program Office. Dušan Milovanović has BSc in Electrical Engineering, including Computer Science and Telecommunications.

Title

From Cell Counting to Spatial Multiomics: The Role of ML and other Methods

Abstract

Miltenyi as a company started its journey with cell separation. Today we cover a much wider range of technologies including cell separation, flow cytometry, imaging and many more. We are also expanding our portfolio into therapeutics. The talk aims to bring forward how we are using various algorithms/methods in Machine Learning, Data Science across technologies to meet our global aim of making cancer history.

About Dr. Paurush Praveen

Paurush is leading the Bioinformatics group at Miltenyi Biotee responsible for handling lmaging, Flow Cytometry and Clinical data using various techniques of MUDS, Cloud Computing etc. He completed his doctoral studies from University of Bonn under the supervision of Prof. Dr. Holger Fröhlich.

Title

The Impact of Data Science and AI in Healthcare

Abstract

Data Science and AI are transforming the pharmaceutical, diagnostics and digital health arenas. Applications are broad and diverse, including disease understanding, molecular design, clinical measurement, and the use of multi-modal data in decision making. New data types and longitudinal data collection at scale continue to increase the challenges and value opportunities, with Large Language Models and Generative AI empowering the next wave of innovation.

About Dr. Bryn Roberts

Bryn Roberts gained his BSc and PhD in pharmacology from the University of Bristol, UK. Following post-doctoral work in neuropharmacology, he joined Organon as Senior Scientist in 1996. A number of roles followed with Zeneca and AstraZeneca before he joined Roche in Basel in 2006 to head up research informatics and data science. In his current role as Global Head of Data & Analytics within Roche Diagnostics, Bryn Roberts’ accountabilities include data strategy and engineering, data science, data governance, information and digital solutions.

Beyond Roche, Bryn Roberts is a Visiting Professor at the University of Bristol and a Visiting Fellow at the University of Oxford, with interests in digital health, computational systems biology, machine learning / AI, medical informatics, scientific software development, quantum computing. He is an Associated Faculty member with the University of Frankfurt Big Data Lab and lectures in medical informatics at the University of Applied Sciences, NW Switzerland.

He is a member of several advisory boards including the Pistoia Alliance, University of Oxford Dept of Statistics and SABS Centre for Doctoral Training, the Microsoft Research/University of Trento Center for Computational and Systems Biology, University of Edinburgh School of Informatics, RoX Health and Z-Inspection. Bryn Roberts is a non-executive director on the board of Deepmatter.

Title

Can Machine Learning Replace ADME Experiments in Drug Discovery?

Abstract

This talk will focus on how to use machine learning to leverage historical ADME/PK data and make predictions for new compounds. Machine learning models developed for PK property predictions will be presented, as well as some of their applications at NIBR.

About Dr. Raquel Rodríguez-Pérez

Raquel Rodríguez-Pérez is Principal Scientist at Novartis Institutes for Biomedical Research (NIBR). She works at the Modeling & Simulation Data Science team since 2020. Raquel Rodríguez-Pérez obtained her B.Sc. and M. Sc. degrees in Biomedical Engineering from the University of Barcelona, and her PhD in Computational Life Sciences from the University of Bonn. She was a Marie Sklodowska-Curie fellow and worked at the Computational Chemistry Data Science team at Boehringer Ingelheim in Germany. Her research has focused on predictive modeling and pattern recognition for different applications in chemistry and life sciences. Her interests include data analysis, machine learning, drug discovery, and bio-cheminformatics.

Title

Innovation and Freedom – Political Pragmatism in Innovation Policies

About Dr. h.c. Thomas Sattelberger

Dr. h.c. Thomas Sattelberger was a member of the German Bundestag from October 2017 to August 2022 and Parliamentary State Secretary to the Federal Minister of Education and Research from December 2021 to June 2022. Prior to that, he was a member of the executive boards of German DAX companies for many years, including as Chief Human Resources Officer at Deutsche Telekom and Continental AG. Among other things, he founded the national initiative "MINT Zukunft schaffen" (Creating a STEM Future) and was its chairman for many years.

Title

Towards a Prescriptive Field Testing Pipeline: How Data Science and Digital Technologies drive the Development of Future Crop Protection Products

Abstract

Advanced field trial designs, modern sensor technologies and cutting-edge data analytics are a powerful combination that is having a significant and growing impact on Bayer's crop protection field testing pipeline. This presentation provides a use-case rich introduction to how these three areas are being used, how they interact and how they contribute to the future vision of a prescriptive R&D pipeline.

About Dr. Philipp Senger

Philipp Senger brings a strong background in data science and has been successfully applying approaches such as machine learning, visual analytics, robotics, and semantic technologies to solve challenges in various life sciences for more than 15 years. He received his Ph.D. in Bioinformatics from the University of Tübingen in 2011 and worked for several years at the exciting interface between science and industrial application of technology in various projects and organizations. He joined Bayer CropScience in early 2016 and currently leads the Analytics and Pipeline Design team within Field Solution Technologies, which is globally responsible for all types of digital technologies and analyses related to field data in crop protection development.

Title

A Journey Through 5 Groundbreaking ML Innovations

About Prof. Dr. Mihaela van der Schaar

Mihaela van der Schaar is the John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge and a Fellow at The Alan Turing Institute in London. In addition to leading the van der Schaar Lab, Mihaela is founder and director of the Cambridge Centre for AI in Medicine (CCAIM).

Mihaela was elected IEEE Fellow in 2009. She has received numerous awards, including the Oon Prize on Preventative Medicine from the University of Cambridge (2018), a National Science Foundation CAREER Award (2004), 3 IBM Faculty Awards, the IBM Exploratory Stream Analytics Innovation Award, the Philips Make a Difference Award and several best paper awards, including the IEEE Darlington Award.

Mihaela is personally credited as inventor on 35 USA patents, many of which are still frequently cited and adopted in standards. She has made over 45 contributions to international standards for which she received 3 ISO Awards. In 2019, a Nesta report determined that Mihaela was the most-cited female AI researcher in the U.K.