As drug discovery evolves, digital pathology platforms are playing a vital role in streamlining preclinical R&D processes and accelerating drug discovery. Proscia‘s Concentriq for Research reflects this trend.
Earlier this year, we profiled PathAI’s AISight, a digital pathology platform designed to support AI-driven research. To learn more about Proscia’s digital pathology technology, we caught up with Nathan Buchbinder, co-founder and chief product officer at Proscia, who discussed how the Concentriq for Research digital pathology platform streamlines the preclinical R&D process and accelerates studies. In the following Q&A, he highlights the benefits of Good Laboratory Practice (GLP) compliance, the role of AI in unlocking new insights and how the platform facilitates collaboration among researchers and stakeholders in drug development.
How does the Proscia Concentriq digital pathology platform streamline the preclinical R&D process?
Buchbinder: Preclinical R&D involves more pathology data than any other phase of drug discovery and development. This data has historically been contained on glass microscope slides, which has resulted in many inefficiencies. Glass slides are cumbersome to manage and incorporate into high throughput workflows. To share them outside of your immediate location, they must often be shipped.
Proscia is advancing the adoption of digital pathology, which shifts the standard from glass slides to high-resolution images called whole slide images. Our Concentriq for Research is an enterprise pathology platform that serves as an organization-wide system of record and sits at the center of routine operations; it empowers teams to work digitally.
In doing so, Concentriq for Research enables teams to realize efficiency and quality gains across the R&D value chain. It makes it easier to organize, manage, search for and share pathology data – whether for early discovery work or the drug safety studies conducted during preclinical R&D. Research teams can also leverage the platform to incorporate whole slide images into their workflows, helping them to make higher quality, more confident decisions that can further reduce study timelines. These benefits are especially noticeable for preclinical R&D given the vast amount of data involved.
We also recently announced new and enhanced functionality that aims to drive additional efficiency and quality gains for preclinical R&D teams. This includes a studies module for carrying out common workflows, including whole slide image scoring and peer review. It also includes expansions to the seamlessly embedded AI-powered automated quality control, which automatically identifies commonly occurring quality issues in whole slide images, as well as robust capabilities for GLP compliance.
Can you elaborate on the benefits of GLP compliance in digital pathology platforms?
Buchbinder: This is a great follow up question. The FDA requires that many preclinical studies are conducted in accordance with Good Laboratory Practice (GLP) principles to ensure the quality and integrity of results submitted as part of an Investigational New Drug (IND) application. So, by extension, preclinical R&D teams can only fully realize the benefits of digital pathology if they are conducting their studies in a GLP-compliant environment.
I’d argue that a GLP-compliant platform isn’t a nice-to-have for organizations looking to scale. It’s a must-have for any organization looking to conduct all of its preclinical research — GLP and non-regulated studies — digitally.
What challenges do researchers face when using point level solutions in digital pathology, and how does the Proscia Concentriq digital pathology technology address them?
Buchbinder: Point level solutions are common in digital pathology, and this isn’t surprising when you consider the siloed nature of R&D. Research teams have historically turned to specific data to answer particular questions during a given phase of discovery and development. Point level solutions have enabled them to continue doing just that.
The challenges become apparent when you consider that pathology data delivers tremendous impact across the R&D value chain. Point level solutions have failed to centralize this data and enable teams to incorporate it into their workflows throughout any phase of drug discovery and development. The immediate impact is inefficiency, but the bigger challenge is a missed opportunity to capitalize on the true promise of pathology data.
We built Concentriq for Research to help life sciences organizations unlock the full value of their data and accelerate the next wave of innovation. As an enterprise pathology platform, it unifies this data and enables teams to tap into it from discovery through development by incorporating it into diverse workflows, streamlining collaboration, and unlocking new insights with AI.
How does Proscia’s platform facilitate collaboration among researchers and stakeholders in drug development?
Buchbinder: Connecting distributed teams with their data is at the core of the value that Concentriq for Research delivers. And this is especially critical given the distributed nature of today’s research teams. Pharmaceutical companies often have scientists and pathologists situated across multiple sites. They are also increasingly relying on contract research organizations (CROs), which also have multi-site operations, to help accelerate studies.
Unlike glass slides, whole slide images and their associated metadata can be shared with stakeholders anywhere in the world with just a few clicks. A cloud-based solution, Concentriq for Research allows scientists and pathologists to collaborate on this data in real time with screen share and chat capabilities or asynchronously. They can then make more comprehensive decisions, and CROs can increasingly work as an extension of their sponsors’ teams.
What role does AI play in Proscia’s platform, and how does it contribute to unlocking new insights?
Buchbinder: AI is increasingly becoming a part of day-to-day research workflows. In sitting at the center of routine operations, Concentriq for Research is designed to enable scientists and pathologists to seamlessly incorporate a variety of AI applications. These include applications that Proscia has built, applications that other digital pathology companies have built, and applications that our customers have built – often on our platform using their own data.
Concentriq for Research is designed to be an open platform that integrates a wide variety of AI applications given the broad set of use cases that these applications currently address and the value that they will continue to deliver. At a high level, there are two categories of AI applications benefiting research teams today. One of these is made up of AI-powered process automation solutions that help to eliminate tedious, time-consuming tasks. For example, Proscia’s Automated Quality Control (QC) saves a technician from having to perform manual QC. It can take a well-trained technician roughly a day to QC 200 images, so this efficiency gain is pretty substantial.
As your question would suggest, the other category is comprised of AI solutions that can unlock new insights. These applications most often help scientists to work more quantitatively or recognize patterns in tissue that have previously gone unseen by the human eye. Image analysis applications are perhaps the most commonly used of these solutions, and specific use cases include identifying biomarkers like PD-L1, HER2 and Ki-67 as well as detecting tumors.
Remember that the Proscia Concentriq digital pathology platform also serves as an enterprise system of record. Life sciences organizations have valuable data assets, centralized in our platform. We recognize the tremendous potential of this data in advancing the use of AI and offer developer tools on Concentriq for Research to help research teams build their own applications and deploy them into their workflows.
While AI is already making an impact on R&D, I believe that it’s only scratched the surface in terms of delivering on its full promise. Concentriq for Research’s open approach to incorporating AI positions it to be a future-proof solution for life sciences organizations accelerating tomorrow’s breakthroughs.
Filed Under: Data science, Drug Discovery, Drug Discovery and Development, Immunology, Industry 4.0, machine learning and AI, Regulatory affairs, Women in Pharma and Biotech