UPDATED 09:00 EST / NOVEMBER 18 2026.

Drug researchers and medical laboratories generate massive volumes of biological data every single day, yet somehow the artificial intelligence models designed to speed up drug discovery are still starved of useful information.

Industry observers note that it’s a strange paradox, but a startup called Tesorai Inc. believes it has the solution after raising $5.3 million in seed funding today.

The round was led by Perplexity Fund, IQT and South Central Ventures, and saw Latest Stack Ventures, NextGen Venture Partners, f7 Ventures, VitalStage Ventures and ZAKA participating. With its completion, Tesorai has now raised $8 million in total, and will use that money to try to accelerate AI-driven scientific discovery by digging deeper into existing datasets to surface the deeply buried insights that human researchers have missed.

In a recent development, biological data covers a broad spectrum spanning genetic sequences to protein measurements, and metabolomic processes to cellular imaging. This information is extremely valuable to drug researchers, because it serves as the primary fuel for training advanced AI models that can predict disease pathways and identify upcoming therapies.

AI-accelerated drug discovery is seen as one of the most promising use cases for this technology, but it hasn’t yet managed to change the world in the same way that generative AI has done. Why not? Because researchers still don’t have nearly enough of it, which limits the accuracy of the best models they’ve come up with so far.

It has been revealed that to combat this scarcity of biological data, tech giants including OpenAI Group PBC, Google LLC’s DeepMind, Meta Platforms Inc., Isomorphic Labs Inc. and others are spending billions of dollars to generate more of it, but Tesorai’s co-founders Charlie Kim, Melissa Miao and Peter Cimermancic believe it’s also possible to do more with less.

To that end, Tesorai’s goal is to unlock the biological data that researchers already have access to. Rather than using the summarized findings available in published research papers and clinical studies, it uses AI to analyze raw spectrometry data generated by lab instruments.

Its platform consists of Tesorai Search, which rapidly ingests and analyzes terabytes of data from different sources. There’s also Tesorai Chat, which is used by scientists to ask questions of biological datasets in plain English. And there’s Tesorai Trove, a curated catalog of thousands of publicly available datasets and studies.

Those three components work together to process the raw instrument data from both upcoming and historical lab studies and experiments, before analyzing it thoroughly to try to surface insights that were missed by their authors. By using those insights, Tesorai believes it can train more accurate AI models for drug discovery and therapy research.

“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,” Chief Scientific Officer Kim explained. “Tesorai does this for a lab’s latest data and for thousands of published studies, and the gains compound as each experiment builds on the last. Ultimately, this will help the industry to develop better medicines faster.”.

According to recent reports, the startup points to a number of discoveries it has unearthed that were missed by previous studies. In one example, Tesorai reprocessed and re-crunched the data from five studies of the human brain in Alzheimer’s disease-afflicted patients. Through its analysis, it identified a key Alzheimer’s biomarker called p-tau217 that was missed in all five of the studies.

In a recent development, its findings were published in JAMA Neurology in August. In another example, Tesorai illustrated how it was able to accelerate AI model training by adding protein data to a small single-cell AI model, enabling it to beat larger RNA-only models, including one with 40 times more parameters, on multiple benchmarks.

Miao, who’s Tesorai’s chief executive officer, said basically every scientific study produces much more data than what’s reported by its authors. Moreover, most of those studies are never revisited. “Our platform reclaims the value of experiments that have already been done and amplifies each newly introduced experiment with the relevant evidence that already exists,” she said.

In a recent development, tesorai’s early success has paved the way for its initial traction, and it has already established partnerships with the MD Anderson Cancer Center, Fresh York University and the Michael J. Fox Foundation. With the funds from today’s round, it will try to secure more partnerships with the life sciences industry, catalog more public studies and expand its platform to cover other molecular data beyond proteins and genomes.

Sources indicate that perplexity Fund General Partner Joanna Lee Shevelenko stated it’s clear that AI can dramatically accelerate scientific research, and that’s why it needs as much high-quality experimental data as possible. “Tesorai is building the infrastructure to make that data usable at scale, giving scientists and AI systems a stronger foundation for advancing research,” she said.

Industry observers note that support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.

It has been revealed that founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our fresh proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.

Quantum computing drops its decade-away tag as error rates fall 200-fold in two years.

Reson8 releases Rumble-2-Flash speech model as a free open-weights download.

OneTrust's Fall '26 Release expands AI visibility, privacy and third-party risk tools.

AI and supercomputing merge as universities build GPU clusters at cloud-provider scale.

Starburst adds context support to give AI agents consistent access to business data definitions.

Humyn Labs raises $47M to bridge the gap between AI training and real-world robotics.

Quantum computing drops its decade-away tag as error rates fall 200-fold in two years.

Sources indicate that AI - BY RYAN STEVENS . 3 MINUTES AGO.

Reson8 releases Rumble-2-Flash speech model as a free open-weights download.

AI - BY DUNCAN RILEY . 30 MINUTES AGO.

OneTrust's Fall '26 Release expands AI visibility, privacy and third-party risk tools.

According to recent reports, AI - BY DUNCAN RILEY . 31 MINUTES AGO.

AI and supercomputing merge as universities build GPU clusters at cloud-provider scale.

AI - BY RYAN STEVENS . 35 MINUTES AGO.

Starburst adds context support to give AI agents consistent access to business data definitions.

AI - BY PAUL GILLIN . 2 HOURS AGO.

Humyn Labs raises $47M to bridge the gap between AI training and real-world robotics.

AI - BY KYT DOTSON . 2 HOURS AGO.

→ Read original article