TB-3756 · REV B · Technical newsheet
Device profile
Tesorai Raises $5.3M to Re-Mine Raw Molecular Data at Scale
Tesorai raised $5.3M in seed funding to standardize raw molecular data for AI analysis, including a p-tau217 finding from reprocessed Alzheimer's studies.
By Sophie Lindqvist4 min read752 words
Features
- Tesorai raised $5.3 million in seed funding, bringing total funding to $8 million.
- In August 2026, reanalysis of five public brain studies identified p-tau217, unreported in the originals; findings are in a non-peer-reviewed preprint.
- A second August 2026 preprint reports a small single-cell AI model matching models more than 40 times larger when trained with protein data.
- The company has partnered with MD Anderson, NYU and the Michael J. Fox Foundation, and holds its first U.S. patent.
- Founders Miao, Cimermancic and Kim previously worked together at Verily, Alphabet's life sciences company.

Tesorai, a San Diego AI company for life sciences research, has raised $5.3 million in seed funding, bringing its total to $8 million. The round includes Perplexity Fund, IQT, South Central Ventures, New Stack Ventures, NextGen Venture Partners, f7 Ventures, VitalStage Ventures and ZAKA.
The company's pitch is straightforward: process the raw experimental data behind studies rather than the published conclusions, and standardize it so results across studies become searchable and comparable. That matters because scientific datasets sit scattered across public repositories, institutional archives and private databases, with differing processing methods and documentation that make cross-study comparison hard.
"Every experiment produces far more data than its paper can report, and most of it is never revisited," said Melissa Miao, co-founder and CEO. "Our platform reclaims the value of experiments that have already been done and amplifies each new experiment with the relevant evidence that already exists."
What does the platform actually do?
Three components make up the system. Tesorai Search processes raw molecular data. Tesorai Chat lets researchers run analyses through conversational prompts. Tesorai Trove is a catalog of structured research datasets (organized, comparable collections of experiment outputs) that enables comparison with previous experiments.
According to Tesorai, the platform has processed thousands of files containing terabytes of experimental data within hours, versus workflows that previously took months. That's a vendor claim without published test conditions, so treat it as a datasheet figure until independent benchmarks appear.
Where's the proof point?
The company's most concrete demonstration comes from Alzheimer's disease research. In August 2026, Tesorai researchers reprocessed raw data from five publicly available brain studies to probe a protein panel described in a JAMA Neurology paper. The reanalysis identified phosphorylated tau 217, or p-tau217 (an established Alzheimer's biomarker), which none of the original five studies had reported.
Tesorai published the findings in a research preprint. Worth noting: preprint findings have not undergone peer review, so the result is illustrative rather than confirmed.
"Life science R&D is accelerating and becoming increasingly autonomous, which makes it more important to extract as much insight as possible from every experiment," said Charlie Kim, co-founder and chief scientific officer. "Tesorai does this for a lab's new data and for thousands of published studies. The gains compound as each experiment builds on the last, and ultimately, this helps the industry develop better medicines faster."
Can reprocessed data train better AI models?
A second August 2026 preprint suggests yes. Company researchers reported that incorporating protein data let a relatively small single-cell AI model match or outperform larger models trained only on RNA data across several benchmarks. One of the comparison models was more than 40 times larger. Those findings are preliminary and have not been independently established through peer review.
"The quality of data and metadata a model learns from can matter as much as the size of the dataset, and much of the data that biology's AI models need has already been collected," said Peter Cimermancic, co-founder and CTO.
Who is behind it, and who's buying?
Miao, Cimermancic and Kim founded Tesorai after working together at Verily, Alphabet's life sciences company. Kim established and led Verily's Molecular Science program, Miao handled business initiatives and strategic partnerships, and Cimermancic led AI teams.
Since its pre-seed round, Tesorai has signed contracts with biopharmaceutical and research organizations and worked with MD Anderson Cancer Center, New York University and the Michael J. Fox Foundation. The company has also received its first U.S. patent covering one of its AI models.
"AI has the potential to dramatically accelerate scientific research, but its impact will depend on access to high-quality experimental data," said Joanna Lee Shevelenko, co-founder and general partner of Perplexity Fund. "Tesorai is building the infrastructure to make that data usable at scale, giving scientists and AI systems a stronger foundation for advancing research."
What changes for the field?
The seed money funds three moves: deeper work with biopharma companies and research organizations, new partnerships with life sciences technology providers, and extension of the platform beyond protein analysis to other molecular data types. Longer term, Tesorai plans to expand its catalog of public research datasets and supply processed molecular data to organizations building AI models for biological applications.
The open question is whether reanalysis pipelines like this one can clear peer review and regulatory-grade validation consistently, or whether they remain a fast triage layer on top of existing experimental archives.
via citybiz.co (Source)
Filed under
- tesorai
- life-sciences-ai
- molecular-data
- data-reanalysis
- alzheimer-s-disease
More from Sophie Lindqvist
Show full bio
News editor covering regulation, policy and their impact on Instruments, test and measurement at Testbench Report.
110 articles
Application notes
- NIST Backs White House 'Golden Age' Plan with Open Repositories
- Biomatter Closes $18M Series A to Build Enzyme Design Facility
- Emerson's Nigel AI Writes LabVIEW Code From a Prompt
- BrightAI Raises $97M for Global Infrastructure Inspection AI
- Danaher and Nvidia pair instruments with AI for autonomous science