The pace of innovation in drug discovery is accelerating, driven by advances in genomics, automation, and data science. As research becomes more complex, so do the requirements for the software tools that support it. From managing vast volumes of experimental data to enabling collaboration across global teams, today’s research and development environments require more than just digital recordkeeping—they need intelligent, integrated platforms that can streamline workflows, enhance reproducibility, and accelerate time to insight.

Drug discovery software has evolved to meet these demands, moving from isolated, on-premises systems to flexible, cloud-based solutions that bring together data capture, analysis, and decision-making in one place. By unifying the scientific process across disciplines and stages of development, these platforms are helping researchers respond to the growing complexity of modern therapeutics.

One such solution is Signals One, developed by Revvity Signals. Designed to support the full Design-Make-Test-Decide cycle, Signals One is a workflow-centric platform built to enhance drug discovery efficiency through intuitive data analytics and visualization, seamless collaboration, and scalable cloud architecture.

To explore the impact of this new platform and the thinking behind its development, Drug Discovery News  spoke with Chris Stumpf, Director of Drug Discovery Informatics Solutions at Revvity Signals.

How does Signals One simplify the drug discovery process, and what makes it different from other software solutions in the market?

Signals One simplifies drug discovery by providing an integrated data capture, processing, and decision making solution that unifies data, workflows, and analytics in one environment. The key difference is its comprehensive end-to-end approach that connects previously siloed processes across the drug discovery pipeline. 

Unlike competitors that focus on narrow applications in drug discovery, Signals One offers a holistic solution that delivers research depth for traditional and new drug modalities while fostering a unified breadth of collaboration for multidisciplinary workflows. By focusing on both depth and breadth, Signals One provides seamless data flow between discovery stages, real time collaboration capabilities, and advanced analytics that accelerate decision making throughout the design-make-test-decide R&D lifecycle while maintaining data integrity and compliance.

How does the platform handle complex data visualization tasks, such as in vitro curve fitting and in vivo data visualization?

Signals One handles complex data visualization through sophisticated yet intuitive tools that transform raw experimental data into actionable insights. There are two levels of data analytics and visualization in Signals One. For routine data processing, Signals One provides guided workflows for common tasks such as in vitro curve fitting, in vivo data analysis, and group comparisons. The goal is to keep simple analytics simple by empowering day-to-day analytics needs with intuitive, streamlined tools.

In more sophisticated cases such as assay development, custom in vivo, and in vitro studies, Signals One empowers researchers with integrated Spotfire. By leveraging Spotfire in Signals One, researchers can weave together apps into guided workflows without coding. Whether using native analytics or Spotfire, Signals One empowers researchers with one solution to handle hundreds of assay modalities to make more informed decisions.

What role does integrated generative AI and large language models (LLMs) play in improving the user experience and ensuring IP protection within Signals One?

With AI and machine learning (ML), our strategy has three parts. First, Signals One incorporates generative AI and LLMs to enhance user experience and streamline workflows, while ensuring that the data and intellectual property remain secure. Examples of this would be semantic search and experimental summarization assistants.  The second part is integrating third-party science based AI models into our software. Some examples of this would be digital lab assistants, antibody developability dashboards, and chemical reaction recommendations. 

Finally, and fundamentally, leveraging AI isn’t really possible without AI-ready data. We’ve always had an eye towards making sure data is unified and modelled for advanced analytics and visualization which serves us well now with AI.   Additionally, we’re doing further development to optimize data preparation for AI integration. An example of this is ensuring that our Assay Repository, where experimental test results are kept, is well-defined and ontologically aware so that researchers can discover unknown relationships and accelerate insights.

Could you describe how the platform supports F.A.I.R. data principles and how this improves research outcomes?

As a unified solution, Signals One facilitates the capture, processing, modeling, and analysis of scientific data all within one system. Because researchers are working and collaborating in one solution, they are incentivized to record their observations into structured, contextualized, and analyzable data using standardized input forms so that details are captured with precision and clarity within each workflow. This attention to detail by Signals One ensures that data can be leveraged to its fullest potential during analytics investigations or by AI/ML algorithms.

How does Signals One facilitate real-time experimental planning and collaboration in wet-lab environments?

Signals One facilitates real-time experimental planning and collaboration in wet-lab environments through its integrated digital lab notebook capabilities and collaborative workflow tools. Scientists can design experiments with standardized templates, access protocols at the bench, and utilize natively integrated ChemDraw to design both small molecules and biopolymers using hierarchical editing language for macromolecules (HELM) notation. 

This solution enables seamless communication between team members through annotation features, task assignments to request assay testing, and notification systems. Integration with lab instruments through Scitara Digital Laboratory Exchange (DLX) automates data capture, reducing manual entry errors and saving time. This connected environment ensures that insights and decisions can be made collaboratively as experiments unfold rather than after completion.

Can Signals One integrate with existing systems and workflows in pharmaceutical research?

Signals One offers extensive application programming interface (API) connectivity for electronic data capture and management built with a microservice cloud architecture, designed to be resilient, scalable, and frequently updated as a SaaS application with minimal risk and interruption to end-users. With the Signals One API environment, developers and power users can create custom workflows, integrate with analysis tools, automate reporting, and seamlessly connect with existing laboratory information management systems (LIMS), chromatography data systems (CDS), instrument data systems, and enterprise software. The core components of the Signals One API environment include REST APIs, External Actions, External Notifications, and External Lists and Data Sources. The Revvity Signals Developer guide is conveniently published on the Revvity Signals webpage so that developers and power users can extend the power of Signals One.

What is the most significant bottleneck or challenge your customers face when integrating software like Signals One into their drug discovery workflows?

The most significant challenge customers face is managing organizational change and data harmonization across diverse research teams. Many pharmaceutical organizations have accumulated years of legacy data in various formats and systems, making standardization and migration complex. Scientists often have established workflows and may resist adopting new tools that disrupt their processes. Additionally, ensuring consistent data quality and ontology across different research domains requires significant effort. To address these challenges, Revvity Signals provides comprehensive change management support, phased implementation approaches, and data harmonization services to ensure smooth transitions while preserving valuable historical research assets.

Are there any key innovations or advancements that have made Signals One possible, and how do they enhance its capabilities in drug discovery?

Several key innovations have brought about the Signals One solution. First, advances in cloud computing architecture allow for scalable processing of massive scientific datasets while maintaining security. Second, the development of flexible data models that can adapt to evolving scientific methods ensures the solution remains relevant as research approaches change. Third, breakthroughs in scientific knowledge graphs and ontologies enable more intelligent connections between seemingly disparate data points. Fourth, advancements in UX design, specifically for scientific applications, have created interfaces that match how scientists actually work. Fifth, since Revvity Signals employs agile development processes to deliver ten releases a year of our SaaS solution, we can rapidly incorporate new science into Signals One so that researchers are always working with the latest methodologies. These innovations collectively enhance drug discovery by enabling more predictive analytics, supporting novel experimental approaches, accelerating the identification of promising compounds, and facilitating more effective collaboration across specialized research teams.

What untapped opportunities in drug discovery do you believe Signals One could help researchers explore, and how does the platform enable these new avenues of research?

Signals One opens several untapped opportunities in drug discovery to help researchers unleash their big, beautiful science. First, it enables more effective multimodal data integration, allowing researchers to correlate chemical and biological data in ways previously difficult to achieve. This supports phenotypic drug discovery approaches that identify compounds based on their effects rather than predetermined targets. Second, the platform's advanced analytics capabilities facilitate AI-driven drug repurposing, helping identify new applications for existing compounds. Third, Signals One supports scientific workflow depth in support of complex new drug modalities so that researchers have the tools they need within a single, unified solution. The solution enables these opportunities through its flexible SaaS data architecture, advanced analytics and visualization capabilities, and collaborative environment that breaks down silos between different scientific disciplines and research phases.