Phylo Launches Target Atlas to Speed Up Target Prioritization

Hundreds of AI agents curate and synthesize evidence across thousands of target–disease assessments, with the first disease-specific application developed with The Michael J. Fox Foundation Targets to Therapies initiative

SOUTH SAN FRANCISCO, Calif., Sept. 29, 2026 /PRNewswire/ -- Phylo today launched Target Atlas, an agentic target-prioritization app built on Biomni Lab, the company's Integrated Biology Environment. Target Atlas can cut the evidence-gathering behind target reviews from months of work by teams of scientists to days, creating a shared record that links findings to their sources and can be updated as new research appears. AI agents apply consistent analyses across targets, while scientists decide which evidence matters and how much weight it should carry. Teams can change those weights to see how their own criteria alter the rankings.

Free with a Biomni account, the public edition of Target Atlas spans thousands of target–disease assessments, presented through source-linked target profiles and interactive 2x2 plots.

Only about one in ten drug programs that enter clinical development is approved (Hay et al., Nature Biotechnology, 2014). Target choice is one of the earliest and least expensive points at which to change a drug program—and one of the most costly to get wrong—yet the evidence needed to choose well is fragmented across genetics, expression, clinical activity, safety, tractability, biomarkers, competition, and the literature, and changes continuously. Drug mechanisms with human genetic support are associated with an estimated 2.6-fold higher probability of success from Phase 1 to approval (Minikel et al., Nature, 2024). The finding supports a broader premise: stronger, converging evidence at target selection should improve the odds of clinical success, underscoring the value of a current, auditable evidence layer.

The Michael J. Fox Foundation's Targets to Therapies (T2T) Initiative established a transparent Parkinson's target-prioritization framework through community nominations, expert panels, curated scorecards, and a published methodology (Vaiana et al., npj Parkinson's Disease, 2025). MJFF's Parkinson's edition of Target Atlas makes that expert framework openly explorable and connects it to source-linked analyses that can be refreshed as new evidence emerges.

"The Michael J. Fox Foundation's single, urgent goal remains to find better therapies and a cure for people and families with Parkinson's. Expanding the number of well-characterized, druggable targets is a critical part of the puzzle," said Gaia Skibinski, VP, Head of Translational Therapeutics at The Michael J. Fox Foundation for Parkinson's Research. "As the pace of technology and science evolve, we look forward to exploring how emerging tools in AI, like Phylo's Target Atlas, can help researchers move promising targets toward potential new Parkinson's treatments."

"The T2T initiative is exactly the kind of multi-database, multi-expert prioritization that takes a community months to do by hand. Target Atlas shows that agents can assemble and score that evidence in days and keep it current — without replacing the expert judgment that decides which evidence matters. Our collaboration demonstrates what becomes possible when a foundation's expert framework is connected to a continuously updateable evidence layer, and our goal is to bring that model to every major disease," said Kexin Huang, Ph.D., Co-founder and CEO of Phylo.

Because target prioritization spans scientists, team leads, and senior R&D leaders, Target Atlas gives teams a shared, source-linked view for comparing evidence and aligning on decisions. Across diseases, versioned computational skills turn evidence from databases, papers, and disease datasets into dashboards and source-linked profiles that record source, date, coverage, and missingness. Researchers can compare targets in interactive 2x2 plots, inspect the evidence behind each result, and use chat to explore the evidence or edit private views.

MJFF's Parkinson's edition is one application of the broader Target Atlas, which Phylo plans to expand across all major diseases in the public edition over time. Available by annual license for a governed Biomni deployment, the enterprise edition of Target Atlas enables 20,000-plus targets per selected disease, proprietary data integration, target-pair dashboards, and AI/ML-based scoring.

Phylo is seeking foundations, consortia, and patient organizations to sponsor additional disease editions published free to their communities, with each organization's framework represented in scoring.

Target Atlas, including the MJFF Parkinson's edition, is available today at https://biomni.phylo.bio. R&D leaders can request an Enterprise demonstration, and foundations and consortia can discuss sponsoring a disease, by reaching out to [email protected].

About Phylo

Phylo's mission is to bring the best agentic intelligence to every biomedical scientist. Its enterprise-grade AI platform, Biomni Lab, is the first Integrated Biology Environment—a unified workspace where scientists collaborate with AI agents across literature research, experimental design, biological data analysis, and scientific decision-making.

Biomni Lab is now used by leading global biopharma, including Chugai Pharmaceutical and Ono Pharmaceutical.

Phylo is based in South San Francisco, and raised a $13.5 million seed round co-led by Andreessen Horowitz (a16z) and Menlo Ventures' Anthology Fund with Anthropic.

For more information, visit phylo.bio. To learn more about Biomni Lab, visit biomni.phylo.bio.

About The Michael J. Fox Foundation's Targets to Therapies Initiative

The Michael J. Fox Foundation for Parkinson's Research (MJFF) launched its Targets to Therapies Initiative in 2024 to expand promising, druggable biological targets in the Parkinson's disease translational pipeline. It combines community-sourced nominations with expert panel-guided prioritization and validation roadmaps, drawing on MJFF datasets and collaborations with Aligning Science Across Parkinson's (ASAP), including the Collaborative Research Network, Parkinson's Progression Markers Initiative, and Global Parkinson's Genetics Program.

SOURCE Phylo, Inc.