The rapid pace of growth and scientific innovation in research and preclinical development at Regeneron has presented many interesting opportunities for digital transformation. This presentation will focus on our journey from capturing and connecting data in the labs to driving decisions and insights from the data for research leadership; including the current challenges, opportunities, successes, and strategies for continuing our journey going forward.

To take the next steps in digitalization and automation of lab workflows and to significantly boost drug discovery effectiveness while also catalyzing innovation, we at Roche Pharma Research and Early Development (pRED) have developed an application suite that allows all researchers to have all relevant information at their fingertips at any time. The challenges and success stories of rolling out such an application suite, fundamentally changing the ways of working for all pRED, will be shared in this talk to highlight the importance of collaboration and mindset when aiming for the next level of digital transformation.

As a leader of a data team in a biotech organization, it isn't enough to build systems that will support your organization. You need to build an organization that can use those systems to become more than the sum of its parts. This talk will present twelve principles designed to guide leaders of Biotech Data teams to adopt more broadly scoped objectives, collaborate more effectively with wet lab teams, and align their development practices more closely with the organization’s needs. We’ll discuss how to define objectives and priorities to drive scientific discovery, how to structure communications to ensure effective information flow, and how to align and integrate technical development with experimental timelines.

In this talk, we highlight the trends that are driving technology convergence and digital transformation in a drug discovery or development lab, including: the use of new therapeutic modalities; the adoption of lab-scale automation; the opportunities of high content assay approaches; and the deployment of ML & AI to a scientist's workflow. Before drilling down and exploring some of our current experiences in the ML & AI theme.

Modern harmonization technologies enable the integration of the multi-modal RNA-binding small molecule data that Arrakis and others have accumulated over the years for driving insights into drug candidates for currently undruggable genomic targets. We employ these data to empower state-of-the-art, emerging machine learning approaches to predicting RNA ligandable pockets for small molecule binding. Here we present the overall Arrakis platform alongside a data-engine case study focused on RNA-binding chemotypes (related to poster P04).

It is no easy feat to coordinate agile workflows across departments and systems, but it can be done with a combination of data services. This talk will discuss a global rollout of self-service analytical processes to a large global organization. We'll discuss data integration, document management, and infrastructure.

Globally over a million drug profiles are in development, and analyzing the research and development landscape across all therapeutic areas from discovery to launch can be challenging. Focusing on making data FAIR can accelerate drug development and support your strategic decision-making processes. This talk will highlight strategies and best practices.

The Journal of Medicinal Chemistry in PubMed was curated for the detection of new compound codes and lead molecules constituting the cutting edge of drug R&D. From 2000 abstracts, 260 codes were found which could be manually mapped to structures although code forms varied widely. While many had name-to-structure (n2s) matches in PubChem others were novel.  However, most leads remain difficult to map into databases because of trivial compound naming (e.g. compound 22b). Causes and amelioration of these FAIRness issues will be outlined.