Biopharmaceutical organizations of every size are undergoing digital transformation driven by requirements of new modalities such as multispecifics, cell and gene therapies, and RNA therapeutics, as well as the steady increase in laboratory automation. We will discuss how biopharma and biotech companies are implementing AI/ML approaches, connecting every part of data and analytics ecosystems to extract maximum value, reduce effort duplication, and empower scientists to make data-driven decisions faster.

Large-molecule R&D data has been captured in multiple systems by various groups. Therefore, it has been very challenging for scientists to find quality data to make informed decisions for selecting drug candidates and applying AI/ML technology. We will show you how to build a federated data ecosystem to provide quality data on-demand for AI/ML projects and biologics drug discovery without centralizing it in a single monolithic data repository.

Biosciences research is digital, and start-ups depend on software tools that are open-source and newly released from academia or research labs. Yet, start-ups rarely have the skills to set up and configure these solutions. Flagship has created the Digital Backbone for Research Science to address this challenge, leveraging AWS, to create a portfolio of tools that accelerate science across our companies while improving return on investment.

The AI/ML technologies such as generative AI and large language models have been developed and leveraged in the field of Biologics and novel modalities discovery in the past 5-10 years. These AI/ML tools have the potential to revolutionize drug discovery by assisting in various tasks such as de novo design, predicting immunogenicity and developability and enhance our understanding of clinical outcomes. The field is also facing challenges in biologics and novel modalities discovery such as the complexity of biological systems and the need for innovative approaches.  It is important to integrate the AI/ML models with experimental data to improve the accuracy and further develop internal AI/ML models.

Bioprocess development groups face challenges with complex modalities, faster development cycles, and more experimental data from HT and PAT technologies. Historically, lab experimental data are dispersed in many different instrument software and unstructured file formats requiring substantial manual data manipulation efforts for experimental insights, decision-making, process modeling, and tech transfer. Here, we will share our journey to build and deploy a fit-for-science digital ecosystem within our bioprocess development labs.

Gain insight into best practices and lessons learned during Gilead’s journey implementing new workflows and solutions to digitize biopharma R&D efforts.

As we continue on our digitalization journey in drug discovery, the data challenges associated with multi-modal biotherapeutics and the biologics discovery workflow have become an increased focus for IT. This presentation will describe how we centrally capture the information associated with these entities and how we can register them alongside traditional synthetic molecules to provide a central entity repository that supports downstream screening and analysis.

Multispecific mAbs and emerging new modality molecules could provide therapeutic advantages over conventional mono-specific antibody therapeutics. These complex molecules present unique challenges from in silico design to activity characterization along with molecule construction in a high throughput (HTP) manner. Since 2019, J&J scientists and IT have partnered with Genedata to handle these challenges through customization and expansion of the functionalities of the Genedata Biologics (GDB) platform, especially in the engineering module. This presentation will highlight the HTP digitalization strategy for these complex molecules from design to characterization.

mRNA Vaccine R&D is complex and dynamic. Traditional monolithic biopharma R&D informatics systems and applications are hard to meet the needs of mRNA Vaccine R&D digitalization. This session will explore how we are evolving and modernizing Pfizer R&D data platforms to streamline data capture, analysis, and analytics.