14-15 November 2023
FHNW University of Applied Sciences and Arts Northwestern Switzerland
Basel, Switzerland
14-15 November 2023
FHNW University of Applied Sciences and Arts Northwestern Switzerland
Basel, Switzerland
This session explores how data flows from instruments capturing raw data to data mining applications where data is translated into meaningful results. Can instrument data be used to predict failures? How is quality controlled along the way? How do we integrate all this into an automated pipeline? Where does the scientist fit in? And how will AI have an effect on our pipelines?
Steven van Helden, Ph.D. (Wega Informatik)
Mohit Goel, M.S. (Moderna)
Analysis of Trends and Patterns in Automated Screening Data Within the High Throughput Screening (HTS) Department in AstraZeneca
Bethan Howells (AstraZeneca)
AstraZeneca's high-throughput screening department uses advanced automation platforms to conduct compound screening for drug discovery projects. These automation platforms are supplied by HighRes Biosolutions and are controlled using Cellario scheduling software. Cellario allows scientists to build complex ‘orders’ that are carried out by the automation platforms. A plethora of information is automatically recorded from these orders into a database, including move operations completed by each device, number of plates processed, and errors encountered on the platform. This data has been largely unmined and not used to its full potential. Here we describe our initial analysis of trends and patterns in the data and how we plan to continue the analysis to benefit the department and optimise platform usage in the future.
Transforming Drug Discovery and Development with AI-Powered Data Pipelines
Andrey Chursov, Ph.D. (Zephyr AI)
Drug discovery and development processes are laborious and time-consuming and require innovative, transformative approaches to accelerate R&D work, reduce the attrition rate in bringing new therapies to market, and improve clinical outcomes. The recent massive growth of multi-modal data catalyzed the integration of artificial intelligence (AI) solutions into research and clinical workflows to extract biologically meaningful insights that would help to address the industry's principal pain point: clinical failure rates. Here, we will discuss the data-intensive nature of modern drug discovery and development and underscore the critical importance of data pipelines as the backbone of AI-driven initiatives. We'll demonstrate how AI can streamline and enhance drug discovery and development processes and explore the pivotal role of AI platforms in reshaping traditional paradigms. Finally, we will also discuss opportunities and challenges for AI-powered acceleration in the development of life-changing therapeutics.
Implementing FAIR Principles in R&D: The Real Life
Daniel Domine, Ph.D. (wega Informatik AG)
After a quick recap of the FAIR data guiding principles and especially their extension to organizational setups, the presentation uses the extensive experience acquired over the years by wega staff in many different contexts from small startups to the largest pharma’s to illustrate through real-life cases what it takes to implement FAIR data principles. Examples deal with connecting instruments and getting the produced data seamlessly passed through processing and reporting to a global research data warehouse. The presentation also shares some lessons learned and hints on how to address the FAIRification of data based on the context (large pharma, CRO, startup, digital maturity, AS-IS IT landscape, organizational structure).