Digital Health will affect pharma companies in many areas. Digital therapeutics are a great way to improve patients' treatment outcomes. Digital drug companions have clinically backed evidence in increasing adherence and persistence on therapy. This talk will demonstrate an exergaming approach for patients doing physiotherapy exercises during their treatments, leveraging the capabilities of the Microsoft Kinect device.

Between Discovery and Clinical Research, Translational Medicine exists to advance science from laboratories to patients. We generate and consume vast amounts of heterogeneous pan-omics preclinical and clinical data from a multitude of internal and external sources, systems and applications. To reach our goals we require wholistic data interoperability. We have adopted a data-centric approach that enables frictionless reuse of data across our systems, platforms and applications. Key steps in our journey and lessons learned will be described.

Intelligent Process Development (IPD) delivers predictive models of process performance and product quality to achieve right-first-time scale-up, and shorten development time. It harnesses multivariate information from across unit operations and time. Traditionally, process development has been limited because it's too hard to combine batch parameters, offline analytics, and online/at-line data for a complete picture. Learn how Riffyn integrates data on a process model in real-time to make IPD a reality.

The virtual world extends and improves our understanding of the real world.  With real world experimental data from the lab, we can model the mechanism of action of likely candidates against druggable targets.  Clinical evidence from real-world trials helps to better understand patient populations, and build models to improve our understanding of disease.  Using real-world bioprocess data, we can understand variability and create models to optimize biologics production of cell and gene therapies.  The real-world gives us the data, models give us understanding, the virtual world generates insights.  By combining data and processes from both worlds, we can accelerate drug discovery and development like never before.

Design Hub is a DMTA application from ChemAxon that focuses on compound design, tracking and data analysis. In this talk we will show how synthesis CROs can be efficiently and securely brought into the daily work of medicinal chemistry project teams, and what criteria were identified to prove safety of the system while maintaining convenience for end-users - a difficult requirement under any circumstances and in any industry.

You need billions of dollars, thousands of people, hundreds of compounds, and a dozen years to discover and develop the typical drug. Information sets the speed for this process. With insight apps (and the underlying search platform), you can find what you know faster and discover what you don’t. Hear how these apps accelerate information access, analysis, and discovery across the drug development cycle. 

BC Platforms has the world's largest federated data partner network with over 22 million patient lives in our catchment area and data partners across the EU, North America and Asia-Pacific. Find out how we were able to leverage this capability to help our pharma collaborator access real-world data (RWD) in Finland and Estonia in order to identify and characterize patient populations with atherosclerotic cardiovascular disease (ASCVD). 

Despite the success of SARS-CoV-2 vaccines, there is a crucial need for new antiviral drugs, especially since the virus is likely to become globally endemic, and the leading target for SARS-CoV-2 antivirals is the M-Protease. This talk will address the history of the SARS-CoV-2 M-Protease as an antiviral drug target and complex research policy issues, including Open Science vs. closed drug development, FAIR data, open access, repurposing, and reproducibility.

Lilly launched an innovative cloud-based platform, Biologica, that integrates next-generation sequencing, world-class laboratory automation, innovative computational algorithms and multi-parameter optimization, all while meeting FAIR data principles. This platform increased R&D productivity, cost savings, and cost avoidance, with the ultimate goal of discovering new medicines with greater speed and precision. Biologica accelerated discovery, development, and launch (under an EUA) of the first COVID-19 antibody treatment. This represents unprecedented record for speed, ~4-5x faster, without compromising quality.

Innovation is accelerating at an exponential rate, however, bottlenecks still remain. Inconvertible formats, obsolete and disparate instrumentation, on-prem legacy systems, and hundreds of file extensions are blocking access to insights from experimental data. To keep pace with data generation velocity and rapid scientific innovation, organizations must adopt data-centric strategies that not only ensure FAIR data but are future-proofed to keep pace with future technologies and solutions. 

Life science organizations face the challenge of managing ever-increasing volumes of text information. With 80% of data in unstructured formats, organizations can’t afford to ignore this source of competitive advantage. Deploying NLP is key to achieving a step change in insight generation, decision making and innovation by enabling novel insights and practical decision support. This talk provides an overview of pharma use cases, highlighting solutions where significant benefit has been found.

This presentation will discuss some of the recent advances we achieved in addressing complex scientific questions using multi-modal data with machine and deep learning methodologies. The presentation will illustrate key challenges and success factors for selected use cases and highlight general considerations for developing robust and scalable IT solutions for such scenarios.

A major challenge for diagnosing genetically driven diseases is that many genetic variants are poorly characterized "Variants of Uncertain Significance."  For specific genes, working with Genomenon, we have dramatically increased the actionable variants with literature support, ensured that Health Care Providers interact with that knowledge in the best possible way, and made that variant information freely available through the Mastermind platform.

As wearables for consumers have grown in popularity, wellness and consumer electronics companies have collected enormous data sets around health parameters that allow them to develop their own digital biomarkers. Coupled with paradigm shifts in healthcare towards preventative care, companies that focus on fitness, recovery, and nutrition, are poised to enter the healthcare market – and have potential as either competitors with existing healthcare stakeholders, or as new customers.

• Why connecting bench workers to the informatics system is a matter of interface
• Current status of voice technology: what about Siri or Alexa?  
• How voice-powered digital lab assistants increase data quality and lab efficiency
• Watching an example of voice-enabled data capture  

A biotech company’s organizational scale is often limited by data and metadata infrastructure, but scaling for operational complexity and growth across multiple therapeutic areas remains difficult. I will present a framework designed to (1) assess how different components of a biotech data platform impact its ability to scale, (2) identify ways to optimize them, (3) guide design decisions and technical solutions, then (4) help communicate these decisions to stakeholders.

The challenges of developing a robust architecture that can scale with multiple studies and newer datasets can become expensive. Here we showcase an efficient app-store type architecture approach where we can scale in all directions by adding newer genomics pipelines and data sources. This approach allows the platform to work with future software/data management tools and still maintains data governance. This overall system enables biologists to interact with the data themselves, reducing the bioinformatics knowledge barrier. This also allows our bioinformaticians to build AI models and computational algorithms on cutting-edge cell therapy datasets to be able to perform biomarker analytics.

In this presentation, we will present our approach to introduce a unified FAIR preclinical in vivo data landscape that should enable our scientists to easily find and access data in a modality and producer independent way. We will discuss the technical architecture of the platform, the parts it will consist of and how it is planned to be integrated into the currently fragmented landscape.