Built using both predictive and generative artificial intelligence, dd4gh allows researchers to analyse large datasets, generate promising compound candidates, and refine predictions through active learning. By continuously learning from new data, the platform can identify the most promising leads for laboratory testing, potentially reducing drug discovery timelines and costs.
The tool was co-developed through workshops held in Ghana and Switzerland, incorporating insights from global drug discovery experts. Its AI models are trained on diverse datasets from studies in malaria, tuberculosis, and neglected tropical diseases (NTDs), enabling users to benefit from cross-cutting research insights.
dd4gh is available free of charge to eligible researchers working on diseases that primarily affect LMIC populations, with partial funding from the Bill & Melinda Gates Foundation, a longtime MMV supporter.
Dr. Martin Fitchet, Chief Executive Officer of MMV, said the platform exemplifies the potential of global partnerships to overcome resource constraints. “By giving scientists in LMICs free access to advanced AI tools, we can accelerate the discovery of lifesaving medicines – led by the people closest to the diseases we are trying to defeat,” he said.
Researchers in resource-limited settings have long faced barriers to using high-end AI tools due to licensing costs. Caroline Maina, a PhD candidate at the University of Cape Town who participated in the Ghana workshop, noted, “Making dd4gh open access means more of us can explore new ideas and apply AI to finding treatments for diseases that are part of our everyday realities.”
Dr. Max Jakobs, Co-founder and CEO of deepmirror, added that the platform’s goal is to democratize drug discovery. “Access to advanced AI should not depend on where a scientist works or their laboratory’s resources. dd4gh enables researchers everywhere to become AI-powered drug discovery experts and accelerate the development of treatments for diseases that affect their communities.”
Scientists working on global health challenges can learn more about the platform and apply for access at www.dd4gh.ai.