Digital transformation is still a driving principle in pharma R&D with the ultimate goal being to streamline processes and enable precision medicine. This talk will showcase examples of digital technologies driving transformation and tangible results in R&D.

Companies that have successfully transformed their business demonstrate the necessity of commensurate cultural change. Similarly, our ecosystem must embrace a data-centric design focus to deliver successful digital transformation and enduring value. Without implementing standards to deliver interoperable data with complete, consistent, standard contextual metadata, we will fail to transform the laboratory and data value chain. Continuing to generate data as a by-product of process and software underserves R&D objectives.

While the value of FAIR data has been established–as well as the costs of un-FAIR data–adoption lacks easy routes. The Pistoia Alliance FAIR data toolkit and Innovative Medicines Initiative (IMI) FAIRplus Cookbook offer frameworks to start. Key decisions on what to name things (e.g., identifiers) and their semantics (e.g., vocabularies) are critical at journey inception. Once established, FAIR knowledge graphs and FAIR analytic services become enterprise data-centric enablers.

We aim to transform drug development and translational sciences by establishing the data and informatics ecosystem. Where do you even start when data are not readily accessible and are constantly evolving? How do you mobilize the organization to change the mindset for data sharing? This talk will share with you the journey we are on to revamp the data management practice and to build the end-to-end engine for FAIRification of our key data assets. We will share the challenges we have overcome and the successes leading to scientific impacts.

The FAIRification of data is gaining impetus. However, for drug discovery, the envisaged increased flow of structures and bioactivity into major public databases, such as PubChem, has not happened. Reasons will be reviewed, but a key impediment is that even when supplementary data from journal papers is submitted to open repositories, such as figshare, there is neither push nor pull into PubChem. Ways to ameliorate this major bottleneck will be discussed, including bypassing the entombment of chemistry in PDFs.

We will introduce ChemAxon’s platform for integration of a variety of data sources and services to augment real-time design. We cover 2 use cases:

1. How MMP analysis supports design out of hERG liability.

2. How a search on >500M molecules, from combined public databases, can be analyzed in seconds.

High-quality data is a prerequisite for machine learning and high-throughput R&D. A first step is to ensure data is centralized and standardized. Learn how leading companies are using modern informatics to organize and structure R&D data - all the way from results-producing instruments to advanced analysis.

Faster therapeutic development demands a non-trivial array of software capabilities, including data automation, system flexibility, ease of use, global collaboration, and analytics-ready data. Nexus, the world’s first process data system, meets this need — supporting dynamic, modular biologics development and tech transfer activities with clean, connected data and real-time analytics

As pharma is embracing digital and agile, new challenges for the retention and sharing of information are emerging. While the information standards of a validated environment remain, ad hoc processes and distributed cloud solutions are creating new islands of knowledge. In this presentation, I will present a knowledge strategy based on automated discovery and integration for a development department of several thousand scientists at Roche.

Making true “molecule”-“mechanism”-“observation” relationship connections is a time-consuming, iterative and laborious process. In addition, it is very easy to miss critical information that affects key decisions or helps make plausible scientific connections. The current practice for deciphering such relationships frequently involves subject matter experts (SMEs) requesting resources from already constrained data science departments to refine and redo highly similar ad hoc searches. The result of this is impairment of both the pace and quality of scientific reviews. In this presentation, I show how semantic integration can be made to ultimately become part of an integrated learning framework for more informed scientific decision-making. I will take the audience through our pilot journey and highlight practical learnings that should inform subsequent endeavors.

We conducted in silico screens trying to repurpose >100 compounds for ~4000 rare disease indications. Various data types were utilized (protein-protein interaction network, pathways, disease-driven genes, competitive intelligence, etc.), and different computational methods were implemented and evaluated. Some biologically interesting drug/disease pairs were observed.

The drug development value chain starts with target selection – missteps at this stage result in costly failures downstream.  We’ll discuss work with industry leaders on an AI-assisted approach that brings together patient genomics and real-world data with information from clinical trials and drug approvals to prioritize and predict high-value targets.

The real world data hype caused high expectations, including RCTs might only play a minor role in future drug development. But  they are rather complementary to RCT data and cannot replace them. Artificial intelligence may change  drug development and time to market significantly, but will not replace past knowledge and experience. Real World Evidence generation can be enhanced by AI and is key for public health.

Rare disease patients suffer too often from long diagnostic delays and misidentified diseases. This creates a significant burden, not just for patients, but for healthcare systems. We present in this talk examples of instances where we have collaborated with researchers and hospital systems to develop novel approaches for rare disease patient identification using tools like genomics, machine learning, and NLP.

This presentation describes a novel data warehouse solution that captures and integrates 8 major public datasets of small molecule data.  With a pharmacology focus, the data are available for search, visualization of compound space, and machine learning.  

Pharma teams need insights across drug development/commercialization from multiple data sources. NLP transforms unstructured RWD sources, like patient forums, social media, medical records, into structured data. Insights Hub dashboards and search portals enable users to navigate the knowledge landscape. We will present use cases from disease understanding to medical affairs.

Transformational change in R&D productivity is required to reverse declining trends in R&D returns across the biopharma industry. Efficiently generating insights and evidence from research, clinical trials, and real world data has become mission critical and plays a central role in this transformation. We will discuss trends, technologies, and experiences.

How do you use data / digitization today to drive scientific discovery / product development?

What are you greatest scientific pain points / gaps that are not being met by digitization?

What kinds of outcomes do you believe digital tools could help you achieve?

Welcome to this discussion group on the growth of demand for HPC in scientific research. We are looking forward to a lively forum. We'll start by looking at three related topics:

- What events trigger demand in your organization? How has the current pandemic impacted resources?

- What could make scale and collaboration more accessible to more researchers?

- Share a recent experience of shifting workloads to manage HPC capacity.

In this session we’ll discuss how to provide researchers with performance and scale in genomics & research analytics, to drive results at a price point that’s economically viable on public & private cloud.

Storage solutions we’ve been using force bioinformaticists to make trade-offs between the capacity and low-cost of disk and the performance of flash. This results in complex tiering configurations that only deliver performance for a small slice of the data. In this session, we will review how advancements in technology enable VAST Data to revolutionize the cost of all-flash and allows bioinformatists faster analysis across larger datasets for deeper insights.