AUGMENTED INTELLIGENCE IN DRUG DISCOVERY XCHANGE
EUROPE 2023
Zurich, November 23
Welcome to hubXchange’s Europe Augmented Intelligence (AI) in Drug Discovery Xchange 2023, 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 & 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
SNAPSHOTS OF DISCUSSION TOPICS
- Improving data robustness and utility to drive biological hypothesis
- Integrating multiple data sources for target identification in augmented intelligence for drug discovery
- Building augmented intelligence for therapeutic target identification: foundations, best practices, challenges
- Exploring key issues in drug target identification
- Advances in augmented drug design: AI-driven insights and challenges for small and ‘new modalities’ molecules
- Transformation and technical challenges in augmenting lead optimisation with generative models
- Machine learning-based approaches for predicting drug response in patients
- Augmented intelligence-driven strategies for personalized medicine in drug response prediction
Data Quality
Opening Address & Keynote Presentation
Taming the beast: A one year vision on Generative AI in knowledge discovery on scientific literature and more
The keynote will emphasize the rapid evolution of Generative AI, commencing with GPT-2 in 2019 and progressing swiftly through GPT-3 to the recent introduction of ChatGPT and GPT-4. This transformation significantly impacted data science and innovation departments worldwide, particularly those in research-driven sectors like life sciences and pharmaceuticals. Our talk will give Digital Science’s perspective on this dynamic technological landscape, projecting past experiences into the future to formulate a vision for the coming year. We will highlight the rise of open-source community efforts in developing efficient transformer models, enabling comprehensive analysis of scientific literature.
Additionally, underscoring the integration of symbolic AI and structured data, emphasizing the challenge of effectively harnessing AI’s potential while ensuring trust, reliability, cost-efficiency, and sustainability in the field of data science and innovation.
Peter Dörr PhD is a business strategist with hands-on experience in sales, product marketing and product development. His experience expands over several industries including IT, consumer electronics to Knowledge and AI solutions for the pharma and other research intensive industries.
Peter is a regular speaker at events such as biotechX, Bio IT World, Reuters Pharma Europe. Digital innovation is his topic, and today that means above all how we can make existing knowledge more usable with the help of artificial intelligence. In his role at Digital Science he is an interface between customers, product development and professional services.
Improving data robustness and utility to drive biological hypothesis
- How do we differentiate between AI and ML and does it matter?
- ML models are open ended, when do you know the solution is optimised?
- Orthogonal checks in wet systems are axiomatic. How do you stop them being self-fulfilling?
- Given the complexity of data inputs, data outputs are complex. Are visualisation techniques comprehensive enough for explanation and interpretation?
Trevor is a Janssen Fellow and Head of Translational Genomics for Johnson & Johnson Innovation. He is responsible for identifying and validating drug targets or pathways from human genetic signatures though internal and external collaborations and has industrial experience in computational chemistry, medicinal chemistry, bioinformatics, genomics and structural biology. He serves on several UK Research Council scientific advisory bodies and boards and was the J&J scientific co-lead for UK Biobank WGS project. He also led J&J into Our Future Health aiming to collect a cohort of 5 million individuals
Challenges and opportunities of imaging-based AI for drug discovery
- Data access & quality: The what, why and how
- Curation pipelines
- AI computational workflows
Dr. Amina Chebira serves as the Director of Relationship Management and Field Application Scientist at Flywheel, overseeing EMEA customer solutions. Previously, she managed ELCA’s data science team in western Switzerland and led AI projects at CSEM. Amina holds degrees from University Paris 7, Swiss Federal Institute of Technology in Lausanne, and a Ph.D. in Biomedical Engineering from Carnegie Mellon University. With over 15 years of leadership experience, her expertise spans data science, imaging, and biomedical image processing. She has been an active member of IEEE’s bioimaging committee, co-chairing sessions at prominent conferences and contributing as a reviewer for several journals. Additionally, she holds multiple patents
Networking Lunch
Spotlight Presentation
Â
Knowledge Extraction with Smart Data Management
IPA is pioneering antibody discovery and characterization by integrating cutting-edge neuro-symbolic techniques. We elucidate how Retrieval Augmented Generation (RAG) models in combination with knowledge graphs play a pivotal role in mitigating life sciences data-specific challenges while significantly enhancing
model performance. Furthermore, our exploration extends to the LENSai platform, a dynamic tool that streamlines access to a unified knowledge repository, efficiently manages data, and optimizes processes. This seamless integration serves as the linchpin for unleashing the full potential of amalgamating insights from experimental and computational domains, thereby expediting the clinical development of biotherapeutics.
Arnout Van Hyfte’s journey with BioStrand, now a subsidiary of IPA
(ImmunoPrecise Antibodies), began in 2019 as a key member of the founding team. He has played a pivotal role in shaping the company’s commercial strategies, setting the stage for its remarkable growth, and building a robust infrastructure that forms the very foundation of BioStrand’s operations. Arnout oversees the development team, ensuring their seamless coordination and fostering a culture of innovation. His leadership extends to crafting effective sales and marketing strategies, as well as engaging with the market to cultivate meaningful relationships
1-2-1 Meetings / Networking Break
1-2-1 Meetings / Networking Break
Poster Session
Lead Generation & Optimization topic: Synergistic Strategies for Enhanced Lead Optimization
The pursuit of efficacious compounds demands a comprehensive approach to lead optimization. This presentation explores our latest advancements, incorporating strategies that seamlessly integrate AI-driven molecular design and physics-based simulations. Key aspects covered include:
- Overcoming AI over-creativity with a streamlined process, ensuring optimal activity without sacrificing feasibility.
- Approaching reality by integration of generative AI with an understanding of structural relationships.
- Balancing efficiency by adjusting methods to data, highlighting why large models may not always be the optimal fit for molecular tasks.
- Implementing a new paradigm for molecule discovery with the emergence of phenotypic-powered lead optimization.
Â
Ardigen, a pioneering AI CRO, stands at the forefront of enabling AI transformation for biotech and pharmaceutical sectors. Our mission is to increase the probability of success in the drug development process. Positioned at the intersection of biology and computational science, we utilize our advanced platforms and deep expertise to turn vast amounts of data into pivotal, ready-to-use scientific insights. This proficiency aids in areas such as finding the right therapeutic targets, optimizing small molecules, and advancing biologics.
Leveraging our expertise, we also enhance the infrastructure that allows our clients to integrate and utilize these capabilities seamlessly within their organizations. Our specialized solutions and services focused on data engineering such as digital transformation, data processing, and data management, to fully support the needs of our partners.
By empowering companies with both essential knowledge and advanced tech solutions, Ardigen is committed to shaping the future of an AI-driven biopharma landscape.
Integrating multiple data sources for target identification in augmented intelligence for drug discovery
- How do we best leverage different data modalities for target identification and biomarker discovery?
- What data modalities are the most informative, what are we missing?
- Share experiences in data acquisition and quality control.
- What are the challenges in integrating data coming from different sources and how to overcome them.
Frank Dondelinger is the group lead for the Basel team in Oncology Data Science at Novartis Biomedical Research, and the strategy lead for AI in Oncology. His team focus on pre-clinical and early stage clinical research in the Novartis oncology drug portfolio, and employ AI and computational biology for data integration, data augmentation and predictive modelling. He hold a PhD in Machine Learning for Systems Biology and has previously led an academic research group on machine learning for computational biology at Lancaster University, as well as working as data analysis lead for digital biomarkers at Roche.
Target Identification
Opening Address & Keynote Presentation
Taming the beast: A one year vision on Generative AI in knowledge discovery on scientific literature and more
The keynote will emphasize the rapid evolution of Generative AI, commencing with GPT-2 in 2019 and progressing swiftly through GPT-3 to the recent introduction of ChatGPT and GPT-4. This transformation significantly impacted data science and innovation departments worldwide, particularly those in research-driven sectors like life sciences and pharmaceuticals. Our talk will give Digital Science’s perspective on this dynamic technological landscape, projecting past experiences into the future to formulate a vision for the coming year. We will highlight the rise of open-source community efforts in developing efficient transformer models, enabling comprehensive analysis of scientific literature.
Additionally, underscoring the integration of symbolic AI and structured data, emphasizing the challenge of effectively harnessing AI’s potential while ensuring trust, reliability, cost-efficiency, and sustainability in the field of data science and innovation.
Peter Dörr PhD is a business strategist with hands-on experience in sales, product marketing and product development. His experience expands over several industries including IT, consumer electronics to Knowledge and AI solutions for the pharma and other research intensive industries.
Peter is a regular speaker at events such as biotechX, Bio IT World, Reuters Pharma Europe. Digital innovation is his topic, and today that means above all how we can make existing knowledge more usable with the help of artificial intelligence. In his role at Digital Science he is an interface between customers, product development and professional services.
Building augmented intelligence for therapeutic target identification: foundations, best practices, challenges
- What are the data requirements for target identification, are some more important than others, in what context?
- How to keep up with a rapidly changing data landscape?
- Where do knowledge graphs come in, how are they used, by whom?
- Which ML/AI methods are useful for data integration & target prioritization?
- What are collective thoughts about pre-competitive partnerships?
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 data scientists in the Discovery Sciences department focused on target identification and project progression in early drug discovery.
Augmented intelligence, data dynamics, and collaborative strategies for target identification in drug discovery
- What are your data requirements for target identification, and what would be your most important sources to obtain these?
- In a rapidly evolving data landscape, what strategies and technologies can help us effectively navigate and extract insights for improved target identification?
- How can we leverage augmented intelligence and optimize data integration to enhance the precision of therapeutic target identification?
- How might pre-competitive partnerships and advanced ML/AI methods aid us in prioritizing targets and fostering collaboration within the drug discovery process?
Hans-Peter Meulekamp, Sales Manager Pharma. Hans-Peter brings nearly two decades of extensive sales experience within the scientific industry, with a dedicated focus on the Life Science sector over the past 8 years. His expertise lies in fostering successful collaborations between technology and product teams, and customers, leading to the seamless introduction of innovative solutions into the hands of researchers. With a keen eye on maximizing business value, Hans-Peter is adept at driving change management processes essential for widespread adoption. He excels in cultivating long-term, mutually beneficial relationships among diverse stakeholders, ensuring sustained value creation from the adoption of new technologies.
Spotlight PresentationÂ
Knowledge Extraction with Smart Data Management
IPA is pioneering antibody discovery and characterization by integrating cutting-edge neuro-symbolic techniques. We elucidate how Retrieval Augmented Generation (RAG) models in combinationvwith knowledge graphs play a pivotal role in mitigating life sciences data-specific challenges while significantly enhancing
model performance. Furthermore, our exploration extends to the LENSai platform, a dynamic tool that streamlines access to a unified knowledge repository, efficiently manages data, and optimizes processes. This seamless integration serves as the linchpin for unleashing the full potential of amalgamating insights from experimental and computational domains, thereby expediting the clinical development of biotherapeutics.
Arnout Van Hyfte’s journey with BioStrand, now a subsidiary of IPA
(ImmunoPrecise Antibodies), began in 2019 as a key member of the founding team. He has played a pivotal role in shaping the company’s commercial strategies, setting the stage for its remarkable growth, and building a robust infrastructure that forms the very foundation of BioStrand’s operations. Arnout oversees the development team, ensuring their seamless coordination and fostering a culture of innovation. His leadership extends to crafting effective sales and marketing strategies, as well as engaging with the market to cultivate meaningful relationships
13:55 – 14:25
15:00 – 15:30
Poster Session
Lead Generation & Optimization topic: Leveraging the powerful, synergistic combination of in silico and wet lab technologies for accelerated lead selection
Traditionally, antibody discovery and optimization have been dominated by a standard linear triage funnel approach. However, IPA has transformed the lead selection process with revolutionary advancements in scalable computational biology and high-throughput antibody characterization. We use a highly integrated workflow that includes in silico antibody de-risking assessment – including immunogenicity and developability screening – and lead optimization, combined with wet lab evaluation of lead candidate properties. This robust approach, merging experimental and computational insights, significantly accelerates the development of molecules most suited for clinical applications.
Dr. Ilse Roodink serves as Chief Scientific Officer (CSO) of ImmunoPrecise Antibodies, supporting the Company’s global research and development teams. Prior to her appointment as CSO, she held different scientific positions at the Company’s Dutch facility in Oss. In her last role as Scientific Director of ImmunoPrecise Europe, she was overseeing contract research project execution and management and was actively involved in the integration of innovative technologies supporting antibody characterization and engineering. Ilse graduated from Radboud University of Nijmegen, the Netherlands with a Master’s degree in Biomedical Health Sciences and a Ph.D. in Medical Sciences
15:35 – 16:35
Exploring key issues in drug target identification
- How to convince functional and long-term experts of new methods like de novo target ID using machine learning ?
- How can we build a systematic learning of results from clinical trials into translational and mechanistic efforts ?
- How can we integrate real-world data to support target identification ?
Managing a team to support drug discovery and drug development using AI and ML and driving FAIR data platforms to support the above objectives.
Lead Generation & Optimization
Opening Address & Keynote Presentation
Taming the beast: A one year vision on Generative AI in knowledge discovery on scientific literature and more
The keynote will emphasize the rapid evolution of Generative AI, commencing with GPT-2 in 2019 and progressing swiftly through GPT-3 to the recent introduction of ChatGPT and GPT-4. This transformation significantly impacted data science and innovation departments worldwide, particularly those in research-driven sectors like life sciences and pharmaceuticals. Our talk will give Digital Science’s perspective on this dynamic technological landscape, projecting past experiences into the future to formulate a vision for the coming year. We will highlight the rise of open-source community efforts in developing efficient transformer models, enabling comprehensive analysis of scientific literature.
Additionally, underscoring the integration of symbolic AI and structured data, emphasizing the challenge of effectively harnessing AI’s potential while ensuring trust, reliability, cost-efficiency, and sustainability in the field of data science and innovation.
Peter Dörr PhD is a business strategist with hands-on experience in sales, product marketing and product development. His experience expands over several industries including IT, consumer electronics to Knowledge and AI solutions for the pharma and other research intensive industries.
Peter is a regular speaker at events such as biotechX, Bio IT World, Reuters Pharma Europe. Digital innovation is his topic, and today that means above all how we can make existing knowledge more usable with the help of artificial intelligence. In his role at Digital Science he is an interface between customers, product development and professional services.
Advances in augmented drug design: AI-driven insights and challenges for small and ‘new modalities’ molecules
- What’s the current status of chemical representation for small and ‘new modalities’ molecules in augmented drug design?
- How is AI aiding in unraveling biological complexity to predict in-vivo readouts with more data (biological, ADME, and PK/PD)?
- Does limited data hinder augmented drug design, especially for novel and complex targets?
- Which key areas of AI/ML in lead generation are expected to have a significant impact in the coming years?
Alfonso Pozzan is computational chemist and drug hunter with over 25 years of experience supporting drug discovery across various research organizations. His expertise spans drug design, molecular modeling, cheminformatics, and data analysis. Alfonso’s multidisciplinary background allows him to approach challenges with analytical prowess and an open mind. Possessing a problem-solving attitude and strong leadership skills, he currently leads the Molecular Architect department at Evotec Verona, where he collaborates with computational chemists and medicinal chemists to drive innovation in projects focused on discovering lead molecules.
Harnessing SAR databases for enriching knowledge graphs and ontologies in ML-driven lead generation and optimization
- Ontologies for Enhanced SAR Data Integration
- Knowledge Graphs for Uncovering Relationships
- Synergizing AI/ML with SAR Databases for Optimal Lead Generation
Norman, a seasoned product leader with degrees in Neuroscience and Biology from Wesleyan University and Harvard University, respectively, leads Excelra’s scientific products team. He focuses on Excelra’s flagship platforms like GOSTAR and GOBIOM, aligning innovation with a user-centric approach. With diverse experience, including key roles at Elsevier and ADP, he has become a vital asset at Excelra. His expertise in data management plays a central role in drug discovery lead generation and optimization, ensuring that scientists across various fields consistently benefit from Excelra’s adaptive product offerings.
Spotlight Presentation
Â
Knowledge Extraction with Smart Data Management
IPA is pioneering antibody discovery and characterization by integrating cutting-edge neuro-symbolic techniques. We elucidate how Retrieval Augmented Generation (RAG) models in combination with knowledge graphs play a pivotal role in mitigating life sciences data-specific challenges while significantly enhancing model performance. Furthermore, our exploration extends to the LENSai platform, a dynamic tool that streamlines access to a unified knowledge repository, efficiently manages data, and optimizes processes. This seamless integration serves as the linchpin for unleashing the full potential of amalgamating insights from experimental and computational domains, thereby expediting the clinical development of biotherapeutics.
Arnout Van Hyfte’s journey with BioStrand, now a subsidiary of IPA
(ImmunoPrecise Antibodies), began in 2019 as a key member of the founding team. He has played a pivotal role in shaping the company’s commercial strategies, setting the stage for its remarkable growth, and building a robust infrastructure that forms the very foundation of BioStrand’s operations. Arnout oversees the development team, ensuring their seamless coordination and fostering a culture of innovation. His leadership extends to crafting effective sales and marketing strategies, as well as engaging with the market to cultivate meaningful relationships
Poster Session
Informed lead generation from the screening of ultra large databases
Leveraging cutting-edge technologies, our validated fast-screening platform performs high-throughput virtual screening of billions of molecules in hours, affordably, on the AWS cloud. Using a representative database subset, we dock against targets, then validate with the PELE Monte Carlo algorithm. This data trains a surrogate model, predicting binding scores for the entire database. Our active learning approach, optimized for retraining, accurately explores vast molecular spaces. An explainability module highlights pivotal docking substructures, enhancing lead generation. Additionally, two generative models provide molecular diversity and refine top molecules, presenting fresh solutions for IP-dense areas. This platform offers a powerful tool for efficient screening of large databases and holds promise for accelerating drug discovery.
Alexis Molina, Director of AI. With a research background in protein folding and drug-drug interaction prediction, he joined Barcelona Supercomputing Center in 2019 to work with Prof. Victor Guallar on developing generative AI algorithms for molecules and proteins. As the current Director of AI at Nostrum Biodiscovery, his focus is on generative AI and screening methodologies for drug discovery.
Transformation and technical challenges in augmenting lead optimisation with generative models
- How to control innovativeness and accuracy of generative models?
- How to efficiently establish collaboration between chemists and generative models?
- How much scientists’ time and wet lab budget should be spent on improving models instead of doing work for drug discovery projects?
Marcin Kowiel is an accomplished professional with a diverse background in computer science, mathematics, and machine learning. He earned his PhD in small molecule crystallography from Poznan University of Medical Sciences in 2015 and continued research in protein crystallography at the Institute of Bioorganic Chemistry, Polish Academy of Sciences. Proficient in Python development and data science, since 2018 he has led teams in a cyber security company (F-Secure) and a genomics-focused startup (MNM Diagnostics). Currently as a Data Science Team Leader at Ryvu Therapeutics, Marcin leverages AI for drug discovery, with a primary focus on hit identification and lead optimization stages
Drug Response Prediction
Opening Address & Keynote Presentation
Taming the beast: A one year vision on Generative AI in knowledge discovery on scientific literature and more
The keynote will emphasize the rapid evolution of Generative AI, commencing with GPT-2 in 2019 and progressing swiftly through GPT-3 to the recent introduction of ChatGPT and GPT-4. This transformation significantly impacted data science and innovation departments worldwide, particularly those in research-driven sectors like life sciences and pharmaceuticals. Our talk will give Digital Science’s perspective on this dynamic technological landscape, projecting past experiences into the future to formulate a vision for the coming year. We will highlight the rise of open-source community efforts in developing efficient transformer models, enabling comprehensive analysis of scientific literature.
Additionally, underscoring the integration of symbolic AI and structured data, emphasizing the challenge of effectively harnessing AI’s potential while ensuring trust, reliability, cost-efficiency, and sustainability in the field of data science and innovation.
Peter Dörr PhD is a business strategist with hands-on experience in sales, product marketing and product development. His experience expands over several industries including IT, consumer electronics to Knowledge and AI solutions for the pharma and other research intensive industries.
Peter is a regular speaker at events such as biotechX, Bio IT World, Reuters Pharma Europe. Digital innovation is his topic, and today that means above all how we can make existing knowledge more usable with the help of artificial intelligence. In his role at Digital Science he is an interface between customers, product development and professional services.
Machine learning-based approaches for predicting drug response in patients
- Are we already seeing a leading type of machine learning-based approach among those being explored in personalized medicine?
- What is driving the success of certain models?
- How are the key challenges in leveraging these approaches evolving and who is leading the change?
- What aspects of the drug manufacturing process, from discovery to real world treatment, are the most likely to be influenced by personalized, precision, and predictive medicine in the next 2-3 years?
Marine Baxendell is a life sciences strategist with over 15 years of experience supporting innovation across various biotech and pharma organizations. Her expertise spans evidence generation, market access, and commercialization within neuroscience, oncology, and rare diseases. Marine’s multi-disciplinary background allows her to approach cross-functional challenges with analytical rigor and an open mind. She is currently leading both the digital health strategy for neuromuscular and Alzheimer’s diseases and the deployment of digital health solutions in Europe at Biogen, where she collaborates with translational medicine, biostatisticians and data scientists focused on applying machine learning-based approaches for predicting drug response in patients.
Drug response prediction – Way towards personalized treatment
- Associating patterns in large-scale multi-omics data, can help in decoding response to a given medication.
- Benefit can be identifying the right population fit for the treatment, and setting up proper clinical trials.
- AI/ML is helping the community to identify predictive molecular biomarkers, the unit behind effective personalized treatment.
Puneet Saxena comes with extensive experience in multiple disciplines in the Biomedical field. At Excelra, he has led & delivered multiple projects associated with different stages of drug discovery (majorly in inflammatory & neuro-degenerative disorders). Hit ID, Target ID and prioritization, NGS data analysis, AI/ML for Patient Stratification & Drug response prediction, DEL data analysis are some of his key areas of work. Moreover, he has also worked in the area of Semantics & Knowledge Graphs.
Puneet holds PhD in Computational Chemistry from School of Multiscale Modeling and Simulations, University Of Modena & Reggio Emilia, Italy. He has co-authored 15 publications & contributed to 1 book chapter in the area of Neglected Diseases. Extensively worked in the area of Tuberculosis & Ovarian Cancer. Co-authored & published more than 10 crystal Protein-complex structures in RCSB. He was also an active member of MM4TB & AIRC consortiums.
Spotlight Presentation
Â
Knowledge Extraction with Smart Data Management
IPA is pioneering antibody discovery and characterization by integrating cutting-edge neuro-symbolic techniques. We elucidate how Retrieval Augmented Generation (RAG) models in combination with knowledge graphs play a pivotal role in mitigating life sciences data-specific challenges while significantly enhancing
model performance. Furthermore, our exploration extends to the LENSai platform, a dynamic tool that streamlines access to a unified knowledge repository, efficiently manages data, and optimizes processes. This seamless integration serves as the linchpin for unleashing the full potential of amalgamating insights from experimental and computational domains, thereby expediting the clinical development of biotherapeutics.
Arnout Van Hyfte’s journey with BioStrand, now a subsidiary of IPA
(ImmunoPrecise Antibodies), began in 2019 as a key member of the founding team. He has played a pivotal role in shaping the company’s commercial strategies, setting the stage for its remarkable growth, and building a robust infrastructure that forms the very foundation of BioStrand’s operations. Arnout oversees the development team, ensuring
their seamless coordination and fostering a culture of innovation. His leadership extends to crafting effective sales and marketing strategies, as well as engaging with the market to cultivate meaningful relationships
15:35 – 16:35
Augmented intelligence-driven strategies for personalized medicine in drug response prediction
- There is a large number of datasets available for many disease indications and clinical treatments, how can these be repurposed to serve new drug discoveries and response predictions for new therapies and/or indications?
- How can we better incorporate domain knowledge into our models and discover new insights into the biological mechanisms behind drug mode of action?
- Our models are increasing in complexity as we add more modalities and neural net types, how can we put interpretability and explainability in front of the process so that we don’t lose sight of the biology behind the questions being asked.
Julian is a senior data scientist at Scailyte with a background in immunoinformatics and has extensive experience with a broad range of data types and analyes from flow-cytometry to single cell sequencing and T cell receptors. After finishing a PhD in bacterial stress responses in New Zealand he moved to Switzerland for a 6 year post-doc in the Experimental Immunology lab of Gennaro de Libero at the University of Basel.