Skip to content
AI.info

The Pulse

Tesorai raises $5.3 million for AI analysis of research data

Tesorai has raised $5.3 million in seed funding to expand its work on AI tools that process raw life sciences data. The company plans to extend its platform beyond proteins and work with more research and biopharmaceutical customers.

Tesorai raises $5.3 million for AI analysis of research data

Tesorai has raised $5.3 million in seed funding to expand its AI tools for analyzing raw life sciences data, bringing its total funding to $8 million, the company said on Nov. 18. Its platform processes data from new experiments and past studies so researchers can search and compare results.

Source prnewswire.com

The San Diego company plans to use the funding to work with more biopharmaceutical and research customers, build partnerships across the life sciences tools industry and extend its platform beyond proteins to other molecular data. It also plans to catalog more public repositories and supply processed data to companies building AI models of biology.

Investors include Perplexity Fund, IQT, South Central Ventures, New Stack Ventures, NextGen Venture Partners, f7 Ventures, VitalStage Ventures and ZAKA.

Processing the underlying data

Tesorai works with raw experimental data held in public repositories, institutional archives and company databases. Rather than indexing research papers or collecting existing analyses, its approach reprocesses the underlying data and harmonizes results across studies for comparison.

Tesorai Search processes raw mass spectrometry data in the cloud, including data from new experiments and older studies. The company says its patented model has processed thousands of files and terabytes of data in a few hours, work it says previously took months.

Tesorai Chat runs downstream analyses through conversational prompts and can also be used through a connector to large language models. Tesorai Trove is a catalog of thousands of curated, structured public proteomics datasets that researchers can use to validate and compare results against past studies. Researchers can try the platform for free.

Tests on published studies

In a test described by the company, its team reprocessed raw files from five public brain studies and recovered p-tau217, an Alzheimer's marker that none of the original studies had reported. The marker was one of seven proteins in an Alzheimer's panel published in JAMA Neurology on Aug. 10.

The researchers posted their analysis as a preprint three weeks later. In another August preprint, they reported that adding protein data helped a small single-cell AI model match or beat larger models trained only on RNA data across multiple benchmarks. One of the models used for comparison was more than 40 times its size.

Founders and customers

Tesorai was founded by former Google and Verily leaders. Its co-founders are CEO Melissa Miao, chief technology officer Peter Cimermancic and chief scientific officer Charlie Kim, who worked together at Alphabet's life sciences company Verily.

There, Kim launched and led the Molecular Science program, Miao led business initiatives and strategic partnerships, and Cimermancic led AI teams. Tesorai says it has signed contracts with biopharmaceutical and research organizations since its pre-seed round, collaborated with institutions including MD Anderson Cancer Center, NYU and the Michael J. Fox Foundation, and received its first U.S. patent for an AI model.

Source

  1. PR Newswire

Related stories

Explore

More articles