Delivering Data Driven Value

Large Chemical Spaces or Smart Enumeration – From Millions to Trillions and Back

Virtual combinatorial chemical spaces have become valuable in drug discovery. This study examines the composition of the recently published “eXplore” space, which includes around 3.9 trillion virtual product molecules. Several methods, such as FTrees, SpaceLight, and Space-MACS, were used to evaluate the utility of eXplore in retrieving novel chemistry around approved drugs and common Bemis-Murcko scaffolds. A subset of 55 million virtual compounds, representing a commercially attractive and diverse selection of eXplore, was fully enumerated. AI-assisted tools, including ligand-, target-, and fingerprint-based searches, were applied to this subset, revealing new insights into chemical diversity around clinical and lead compounds. Further chemical space analysis, including 2D fingerprints, 3D shape, and electrostatic analyses, demonstrated that eXplore offers a highly diverse chemical space compared to other vendor sets.

Speaker

Peter Maas, Director of Scientific Consulting, eMolecules

Peter E.M. Maas graduated from the Rotterdam University of Applied Sciences in Organic Chemistry. He joined eMolecules (formerly Specs) after completing his internship at Shell Research and Technology Centre, Amsterdam, on the synthesis of ligands for homogeneous catalysis. At eMolecules he specialized in cheminformatics, medicinal chemistry, and early drug discovery. He coordinated numerous research collaborations with universities, pharmaceutical and biotech companies involving chemical and spectral data, solubility, stability for software development, and drug discovery on diverse targets and diseases topics. As Manager Lead Development, he was responsible for all services and expertise within eMolecules to develop lead candidates for drug discovery: library design, medicinal chemistry, formulation studies and patents. This led to the filing of several patents and the establishing of two spin-off companies. In September 2024, he assumed the position of Director of Scientific Consulting.

IDMP Ontology Github Repository

The ISO standards for Identification of Medicinal Products (IDMP) provide an internationally accepted framework to uniquely identify and describe medicinal products. Driven by regulatory requirements, the role of IDMP is to align the pharmaceutical industry on data standards for product and substance information. Realization of the full potential of IDMP depends on self-describing data to counteract diverse, non-standard IDMP implementations.

For this purpose, we will augment the existing IDMP standardization efforts with an IDMP Ontology that enables deep, semantic interoperability based on FAIR principles. This will ultimately enable entirely new ways of collaboration and enable early adopters to gain a competitive advantage in innovation, drug safety and overall operational efficiency. The IDMP Ontology (IDMP-O) effort extends the ISO standards as a digital standard to create interoperability by design. The intent is to submit the resulting ontology, once complete, either to the ISO directly or via the ISO PAS process through the Object Management Group.

Pistoia Alliance IDMP Ontology Wiki

Identification of Medicinal Products (IDMP) is a set of global standards developed by the International Organization for Standardization (ISO) for the identification and exchange of information about medicinal products to improve patient safety and facilitate the exchange of information between regulatory authorities, healthcare professionals, and pharmaceutical companies.

The IDMP Ontology provides a universal implementation of the IDMP product data model as a common language to effectively bridge the gap between people, processes, and systems.

In this wiki you can find all relevant information to help you implement the IDMP Ontology in your organization.

Quantum Computing: Where Are We Going?

Join the Pistoia Alliance for a 3-Part Webinar Series on Quantum Computing in the Pharmaceutical Industry

The Pistoia Alliance Quantum Computing Community of Interest is dedicated to exploring the rapidly evolving field of Quantum Computing and its transformative potential for the pharmaceutical industry. While Quantum Computing is still in its developmental stages, the promise it holds for revolutionizing pharma is immense. As stability in Quantum Computing technology is achieved, the opportunities for significant advancements in pharmaceutical research and development will soar.

In the current landscape, AI, ML, and generative AI dominate the spotlight, often overshadowing the advancements in Quantum Computing. This raises several pertinent questions: Does the rise of LLMs diminish the potential benefits of Quantum Computing for pharma? Can some tasks previously envisioned for Quantum Computing be handled by LLMs? How can the pharmaceutical industry integrate Quantum Computing into its problem-solving approaches? Moreover, does the industry possess the necessary skills to embrace this quantum revolution?

To address these crucial questions and more, the Pistoia Alliance is hosting a series of three webinars under the theme “Quantum Computing in Life Science R&D: Where Are We, Where Are We Going, When Will We Get There?”

Webinar #2: “Where Are We Going?”

Agenda

16:00 Welcome

16:05 #1 Pharma – Demand-Side Perspective

Thomas Ehmer, Business Technologies R&D Science and Technology – Innovation Incubator, Merck Group

16:15 #2 Academic Perspective

Brian Marsden, Associate Professor of Data Management and Research Informatics, Director of the NDM Biomedical Platform, Centre for Medicines Discovery & Associate Head of the Medical Sciences Division (Digital & Information)

16:25 #3 Non-Commercial R&D Perspective

Sonali Mohapatra , Quantum Innovation Sector Lead STFC UKRI, NQCC

16:35 Discussion

Chaired by Brian Martin, Head of AI in R&D Information Research, Research Fellow, AbbVie

FAIR Maturity Matrix Introduction

FAIR refers to findability, accessibility, interoperability, and reusability. These principles are foundational to enable data-centric organizations and value creation. Implementing the FAIR data principles in a life sciences organization involves transformational journeys that tend to be complex. At any given time, organizations may be experiencing different stages of their respective FAIR implementation journey, which makes it challenging to perform benchmarks and assess progress. So while there are multiple FAIR data maturity models, there was no maturity assessment model at the organizational level.

To address this gap in 2023 we collaboratively designed such an organizational model with the Pistoia Alliance Community of Experts.

Revolutionizing Scientific Literature Search

Join Mark Sheehan, VP for Data Science Life Sciences at Elsevier, to explore the power of advanced search techniques in our webinar, “Revolutionizing Scientific Literature Search: Marrying Traditional Taxo and Emerging Vector Techniques”.

In this webinar, Mark will review the world of scientific literature search, covering the full range of technologies from traditional taxo and keyword-based search methods vs the latest innovative vector and RAG-based approaches. Mark will also give an overview of Elsevier’s ongoing research into a dynamic hybrid search approach, which aims to seamlessly merge the strengths of traditional and vector searches.

Biography – Mark Sheehan

Mark Sheehan, a seasoned professional with over two decades of experience, serves as the Vice President of Data Science for Elsevier’s Life Sciences team. His extensive contributions have been instrumental in Elsevier’s digital evolution, transforming the company from a traditional publisher to a leader in information analytics and AI-driven research tools.

Mark’s current role is to leverage the latest data science and AI to support chemists and biologists in their daily research work. By attending this webinar, you will gain insights that can help you accelerate the development of new synthetic pathways and advance drug R&D. Mark’s belief in innovation as both a technological and a collaborative endeavour underscores the practical benefits of this webinar.

FAIR Research Maturity Frameworks

FAIR data is expected to add value to organisations among others by reducing time needed to find valuable information, facilitating interoperability, reusability and enabling AI initiatives. When starting to implement that FAIR data principles, many organisations realise they embark in a transformation journey which often goes beyond data itself.

How can we evaluate how “FAIR” data sets actually are? How do we evaluate, measure and support the maturation of organisations as they become increasingly adept at FAIR data?

This webinar will address the theme of FAIR data and organisational maturity frameworks including the FAIRplus Dataset Maturity (DSM) Model, FAIRassist.org and the Pistoia Alliance’s FAIR Maturity Matrix (fairmm.pistoiaalliance.org).

Speakers

Susanna Sansone, Mark Wilkinson and the authors of the FAIR Maturity Matrix

Prof. Susanna-Assunta Sansone (https://tinyurl.com/324t928x) is the Academic Lead of the Oxford University’s Research Practice Programme to define good practices for how research findings are published, disseminated, and evaluated. She is also Professor of Data Readiness in the Department of Engineering Science, the Director of the Oxford e-Research Centre. An author of the FAIR Principles, Susanna is part of international collaborative actives and funded projects to implement FAIR; in the European context she is a member of the EOSC FAIR Metrics and Digital Objects Task Force, and co-lead of the ELIXIR Interoperability Platform.

Mark Wilkinson has a B.Sc.(Hons) in Genetics from the University of Alberta, and a Ph.D. in Botany from the University of British Columbia. He spent four years at the Max Planck Institut für Züchtungsforschung in Köln, Germany, pursuing studies in a mix of plant molecular and developmental biology and bioinformatics. He then did a research associateship at the Plant Biotechnology Institute of the National Research Council Canada, focusing on the problem of biological data representation and integration for the purposes of automated data mining. In the subsequent 25 years, his laboratory has focused on designing biomedical data/tool representation, discovery, and automated reuse infrastructures – what are now called “FAIR Data” infrastructures. He is the lead author of the primary FAIR Data Principles paper, and lead author on the first paper describing a complete implementation of those principles over legacy data – what is now called the ‘FAIR Data Point’. He is a founding member of the FAIR Metrics working group, tasked with defining the precise, measurable behaviors that FAIR resources should exhibit, and the author of the first software application capable of a fully-automated and objective evaluation of “FAIRness”. He was co-Chair of the EOSC Task Force on FAIR Metrics and Data Quality until it closed in 2024, continues to work with EOSC in the Opportunity Area 3 (FAIR Assessment and Alignment) and is founder of a spin-off company, FAIR Data Systems S.L., that provides consulting, training, and customized software solutions that help clients become FAIR.

Unveiling the Power of Ontologies

While research and development in the life sciences have always been data-driven, the current era is witnessing an unprecedented explosion of data. The industry must harness the full potential of this data and in this webinar the Pistoia Alliance will illustrate the ability of ontologies significantly to improve R&D efficiency and effectiveness. The webinar will explore how the Pistoia Alliance, through its commitment to “Deliver Data-Driven Value,” is developing ontologies including: