The Open Discovery Challenge introduces a computational leaderboard for scoring AI-designed malaria drug candidates across six dimensions: whole-cell activity, target binding, selectivity, ADMET properties, novelty, and synthetic feasibility. Its authors documented fourteen validation defects uncovered during development, including early scoring models that rejected already-approved drugs or overweighted molecular mass. Reference compounds such as the clinical candidate DSM265 and inert controls like caffeine are kept visible on the public leaderboard so outside researchers can independently verify the scoring system’s integrity.
