Patients, life science industry and regulatory authorities are united in their goal to reduce the disease burden of patients by closing remaining unmet needs. Patients have, however, not always been systematically and consistently involved in the drug development process. Recognizing this gap, regulatory bodies worldwide have initiated patient-focused drug development (PFDD) initiatives to foster a more systematic involvement of patients in the drug development process and to ensure that outcomes measured in clinical trials are truly relevant to patients and represent significant improvements to their quality of life.
Resource Tag: Delivering Data Driven Value
Data Quality for LLMs: Building a Reliable Data Foundation
Achieving value with Large Language Models (LLMs) hinges on a reliable data foundation. This is becoming increasingly relevant with the introduction of conversational AI agents that exploit RAG (retrieval augmented generation) techniques to extract information from biomedical data. What isn’t emphasized enough, is the crucial role that well-annotated data and its accessibility to the models plays.
In this webinar, we look at how data quality affects the performance of LLMs. For this, we assess how LLM-powered AI agents query across three versions of the same gene expression corpus, but with varying degrees of quality:
- Unstructured Data from GEO (Gene expression Omnibus)
- Structured Data from the CREEDS project
- ML-ready data, annotated using Elucidata’s Polly
Speaker
- Abhishek Jha, CEO & Co-Founder at Elucidata
Strategic Priorities Update February 2024
Join us for this inaugural update on the newly formed Strategic Priorities of the Pistoia Alliance, followed by a 30 minutes Q&A with our panelists
Agenda
Dr Becky Upton, President of the Pistoia Alliance
- Introduction
Dr Christian Baber, Chief Portfolio Officer, Pistoia Alliance
- Strategic Priorities Overview
- Harnessing AI to Expedite R&D
- Delivering Data-Driven Value
Thierry Escudier, Portfolio Lead, Pistoia Alliance
- Accelerating Use of Real-World Data
- Sustainability Driven R&D
Pharmaceutical CMC Process Ontology – February 2024
This project aims to build a pharmaceutical (CMC) process ontology based on the ISA88/95 framework to standardize laboratory and plant production process recipes to establish standardized definitions, facilitate digital technology transfers, and integration with execution systems in order to capture structured process data for material lot genealogy tracking, streamlined technology transfers, and advanced process analytics, thereby enhancing efficiency and transparency throughout the pharmaceutical production lifecycle.
This meeting will cover the background of the project, the scope of work and the MVP in progress.
Informed Consent Blockchain Project
Drug Discovery World : Publication on Pistoia Alliance’s Blockchain Based Informed Consent
This project seeks to demonstrate the value of blockchain technology as part of a decentralized digital identity solution for the Informed Consent process in clinical trials.
IDMP Community of Interest Meeting January 2024
Join us for our upcoming Community of Interest meeting to learn more about our IDMP-O initiative. Our newly launched IDMP-O version 1.0 covers all five ISO IDMP standards, enabling a broad range of use cases around substance identification, regulatory processes integration with manufacturing, supply-chain analytics, therapeutic indications, representation of jurisdiction-agnostic medicinal products and pharmacovigilance.
Our focus for 2024 is on supporting the production implementation of IDMP-O in the pharmaceutical sector. We’re introducing dedicated support and training programs to assist pharma and industry professionals in integrating IDMP-O into their workflows and systems. Parallel to our Phase 3 project activities, governance will be further secured by ISO Technical Specification (TS) 21405 – Methodology and Framework for the Development and representation of IDMP Ontology, co-led by Sheila Elz, Bayer Pharma, and Vada Perkins, Boehringer-Ingelheim. The TS has a timeline of two years, with the target date for final publication July 2025.
Agenda
- Intro & Highlights from 2023
- IDMP-O Release 1.0
- Pharma Implementations
- IDMP-O Plans 2024
- Discussion
Liquid Biopsies Enabling a Future of Precision Medicine
Liquid biopsies can be used to detect early cancer recurrence, explore therapeutic resistance, and personalize treatment. In this seminar, we will explore three different perspectives to delve into the potential of ctDNA and rare cells in the context of an ever-increasing drive to personalize medicine:
We will explore the value of rare cells, discuss advances in single-cell techniques, touch upon the value of multi-omic analysis, and examine its relevance to the emerging interest in spatial biology.
AGENDA
CLINICAL PERSPECTIVE – Liquid Biopsy: A new diagnostic concept in oncology
The clinical utility of rare cells, an introduction to the biology and with a focus on patient impact and treatment – Prof Klaus Pantel, Director of the Center of Experimental Medicine, Institute of Tumour Biology, Germany
R&D PERSPECTIVE – Rapid phenotyping of CTC metastatic potential and drug response with TetherChip microfluidics.
Technical innovations in using CTCs for novel assays for anti metastatic drug discovery – Dr Stuart Martin, Professor at University of Maryland School of Medicine – Greenebaum Comprehensive Cancer Center, USA
PHARMA PERSPECTIVE
A biopharma perspective, examining the relevance of these analytes to a therapy development agenda. Paola Marco-Casanova, Associate Director, AstraZeneca, UK
Interactive Q&A session
Unpacking Unstructured Data: Extracting Insights from Neuropathological Reports of Parkinson’s Disease
Linking pathology data with molecular and clinical data allows for a deeper understanding of disease, more accurate diagnosis, and ultimately better patient treatment. Pathology data needs to be structured in order to achieve this.
The aim of this study was to make unstructured neuropathological data, located in the NeuroBioBank (NBB), follow FAIR (Findability, Accessibility, Interoperability, and Reusability) principles, and investigate the potential of Large Language Models (LLMs) in wrangling unstructured neuropathological reports. By making the currently inconsistent and disparate data findable, our overarching goal was to enhance research output and speed.
Playing FAIR with AI: Supporting Scientific Discovery
Technological advancements exhibit varying degrees of longevity. Some are tried and trusted, enduring longer than others, more often when applied strategically to address tangible business challenges. Conversely, certain technologies succumb to fleeting hype without attaining substantive fruition.
A constant, in this dynamic landscape is the data. To harness the full potential of cutting-edge technologies, it is imperative to have your house, or more specifically, your data, in order. Here, we discuss the importance of foundational data management and the role of FAIR in enabling organisations, specifically within the life sciences, are agile enough to adapt to, and make use of, state-of-the-art technologies.
We will specifically discuss how the SciBite FAIR factory can be used to enable the application of large language models (LLMs) to democratise scientific data, and expedite the extraction of insight.
Speaker: Joe Mullen, Director of Professional Services, SciBite
The Methods Database Project
The Pistoia Alliance Methods Hub is envisioned to be a platform where semantically interoperable analytical methods and supportive tools are available to the Pharmaceutical Industry.
Advancing Data Interoperability: Exploring Ontology Mapping for FAIR Data Initiatives
Achieving data interoperability is fundamental for successful FAIR (Findable, Accessible, Interoperable, and Reusable) data initiatives, and the utilisation of ontology and terminology standards plays a crucial role in this endeavor.
Nevertheless, challenges arise when organisations adopt competing or overlapping standards, necessitating access to mapping solutions to align datasets effectively. This issue is especially prevalent in industries, where internal and private terminology codes must be mapped to public ontology identifiers for integrating public datasets seamlessly.
High-quality mapping between public ontologies exists and standards have emerged that facilitate the publication and sharing of these mappings. Numerous tools and best practices are also available to generate novel ontology mappings. Despite such progress, industries continue to invest significant resources into generating and curating mappings. Consequently, services are in demand to ensure mappings remain updated and accurate as data and ontologies grow and evolve.
In this webinar, we delve into the landscape of ontology mapping, exploring existing mapping sets and innovative approaches to generating and maintaining ontology mappings.
Speakers:
- Jane Lomax, Head of Ontologies, SciBite
- Simon Jupp, Head of Semantic Technologies, SciBite
Revolutionizing Laboratory Workflows
The Methods Database Enables Digitization for Faster and More Reproducible Results
During this webinar we will demonstrate how using a common, machine-readable data format will enable a digital transfer of analytical High Performance Liquid Chromatography (HPLC) instructions between chromatography data systems (CDS). We will share results from Merck & Co and GSK, where there has been an effective transfer of HPLC information between different systems and sites. With the Methods Db we can eliminate the manual keying of instructions to reduce risk, steps, and error while improving overall flexibility.