Disease-Drug Relationship Visualisation Solution

Galactic AI is a technology that automates the discovery of relationships between drugs, genes, and diseases. It replaces manual searches with an efficient system that quickly identifies and curates relevant cause-and-effect connections, streamlining research processes.

cause and effect paths
cause and effect paths
cause and effect paths

Role

Role

Lead Designer

Duration

Duration

July - Nov 2023

Platform

Platform

Web

Revenue

Revenue

$10.5 Million (2024)

Company size

Company size

100+

Challenge

The existing platform suffered from unintuitive navigation and complex workflows, frustrating users and hindering task completion. Our challenge was to streamline the experience through modern design principles while maintaining robust functionality.

Results

Following the redesign, our platform saw dramatic improvements across all key metrics. User engagement surged by 42%, while user retention increased by 35%. Most notably, time spent within the app grew by 54%, demonstrating the significant impact of our enhanced user experience.

42%

Increase in User Engagement

35%

Increase in User Retention

54%

Increase in Time Spent on App

  • User journey

    We mapped a biologist's research journey to understand her challenges in drug discovery, revealing key pain points that guided our tool's redesign.

  • User testing

    User testing revealed critical improvements for our Drug Discovery tool, highlighting navigation challenges and data interpretation issues while showcasing increased user engagement and satisfaction.

  • User flow

    Our original Drug Discovery interface was a maze for researchers, with confusing navigation, murky confidence levels, and scattered research links. This visual tells the story of why we needed a complete redesign.

  • User journey

    We mapped a biologist's research journey to understand her challenges in drug discovery, revealing key pain points that guided our tool's redesign.

  • User testing

    User testing revealed critical improvements for our Drug Discovery tool, highlighting navigation challenges and data interpretation issues while showcasing increased user engagement and satisfaction.

  • User flow

    Our original Drug Discovery interface was a maze for researchers, with confusing navigation, murky confidence levels, and scattered research links. This visual tells the story of why we needed a complete redesign.

  • User journey

    We mapped a biologist's research journey to understand her challenges in drug discovery, revealing key pain points that guided our tool's redesign.

  • User testing

    User testing revealed critical improvements for our Drug Discovery tool, highlighting navigation challenges and data interpretation issues while showcasing increased user engagement and satisfaction.

  • User flow

    Our original Drug Discovery interface was a maze for researchers, with confusing navigation, murky confidence levels, and scattered research links. This visual tells the story of why we needed a complete redesign.

Process

Research & Discovery: We conducted user interviews and analyzed existing feedback to understand pain points in exploring disease-drug connections. We identified key challenges in complexity, visual representation, and confidence scoring.


Information Architecture: Based on our findings, we designed an interactive knowledge graph and a structured table view, ensuring users could navigate and interrogate data effectively.


Wireframing & Prototyping: We developed low-fidelity wireframes for early feedback, refining them through multiple iterations. We then built a high-fidelity, interactive prototype to test usability.


Usability Testing: We conducted usability tests and discovered that users struggled to interpret the numerical confidence scale. We redesigned it using “High, Medium, and Low” labels for clarity.


Interaction Design & Navigation: We introduced tabbed navigation to allow seamless switching between the graph and table views. We also added customizable confidence filters for better data control.


Visual Design & Tooltips: We enhanced the UI with detailed tooltips, providing quick access to key data points. We ensured visual consistency while making information easily accessible.

Stack

Stack

Stack

causal mentions tables
causal mentions tables
causal mentions tables

“With our new visual branding and language in place, the new Shopify brand clearly captures the essence of our current and target customer base, our employees, and our values.”

Harris Kaufman

Head of R&D | Top Pharma Company

causal mentions
causal mentions
causal mentions

Conclusion

This project transformed how researchers work with complex biomedical data by creating clearer ways to visualize disease-drug connections. The new design made it much easier for them to spot important patterns and make informed decisions.

What really stood out was seeing how a more intuitive interface could make such a difference in scientific work. By adding features like interactive filtering and different ways to view the data, researchers could work more efficiently without sacrificing any of the detailed information they needed.

The success of this approach showed that there's real value in making scientific tools more user-friendly. I'm excited to see how these design principles can be applied to future updates, making data exploration even more straightforward for researchers.