The company's core strategy is "data-first," believing the true long-term differentiator in AI drug discovery is generating unique, high-quality experimental data, not just innovating on model architecture, which they see as prone to commoditization when trained on public data.
Public datasets primarily show successful protein interactions, starving AI models of crucial "negative data"—plausible but incorrect interactions. A-Alpha Bio finds that providing this data on what fails is just as important for training predictive and generalizable models.
The issue with public protein affinity databases isn't just a lack of data, but a lack of interoperability. Data aggregated from different labs using varied methods, buffers, and conditions creates a "messy" dataset that hinders an AI's ability to learn generalizable rules, a problem solved by standardized assays.
Instead of developing its own drugs, A-Alpha Bio strategically chose to provide data and services to the entire ecosystem. They believe they can have a broader impact on thousands of therapeutic programs by addressing the industry's data needs rather than focusing on a few internal assets.
Contrary to the belief that AI will replace experimentation, A-Alpha Bio's CEO argues that as models improve, the industry becomes "hungrier" for high-quality wet lab validation data. Better computation creates a greater need for ground-truth data to train, validate, and refine the models.
While AI offers some time savings, A-Alpha Bio's CEO argues this is minimal in the overall drug development timeline. The transformative impact is AI's ability to engineer therapeutics with novel properties, like binding to previously inaccessible epitopes, that traditional discovery methods could never find.