iiinova — where your digital self keeps evolving

Tesorai @tesorai.bsky.social · 28/09/2026

What does it take for an AI agent to actually help with proteomics analysis? Today at #HUPO2026, we’re presenting our work developing + benchmarking agentic LLM frameworks for faster, more accessible proteomics analysis. 📌 PS01.003 🗓️ Mon · 1:15–3 PM 📍 Exhibit Hall

000

Tesorai @tesorai.bsky.social · 28/09/2026

We’re at #HUPO2026! 🇸🇬 Come find us at Innovation Row to see Tesorai Search, Chat + Trove in action. Bring us a dataset, give us a hard biological question, or just come talk proteomics. 📍 Suntec Singapore 📅 Sep 27–Oct 1

010

Tesorai @tesorai.bsky.social · 24/09/2026

Start with the question, not the dataset. Ask Tesorai Chat a biological question and let it help identify relevant public proteomics studies. Question → Discover → Analyze See it at HUPO 2026 next week. Come give us a hard biological question at Innovation Row. 🇸🇬 www.tesorai.com/hupo #HUPO2026

000

Tesorai @tesorai.bsky.social · 22/09/2026

"We’re heading to #HUPO2026 in Singapore! 🇸🇬 Find us at Innovation Row to see Tesorai Search, Chat + Trove in action. We’ll also be presenting new work on agentic AI for proteomics and Alzheimer’s disease across public brain proteomics cohorts. 📍 Suntec Singapore 📅 Sep 27–Oct 1"

021

Tesorai @tesorai.bsky.social · 17/09/2026

Deep proteome coverage with rigorous FDR control. New work with @mdanderson.bsky.social + @cityofhope.bsky.social benchmarked 12 acquisition + analysis workflows. nDIA + Tesorai Search: • 10,766 protein groups • Deepest coverage evaluated • ≤1% FDP www.tesorai.com/resources/na...

000

Tesorai @tesorai.bsky.social · 14/09/2026

Where is AI accelerating drug discovery, and where is the promise still ahead of reality? Tomorrow, Tesorai CSO @cckim47.bsky.social joins the Life Science and Bio panel at The Next Endeavor to discuss AI in drug discovery. 📅 Sept 15, 4 PM 📍 Google Bay View

000

Tesorai @tesorai.bsky.social · 10/09/2026

Not reported doesn’t mean not measured. p-tau217 wasn’t in the published protein summaries of 5 public brain proteomics cohorts. We reprocessed the raw spectra with Tesorai Search. p-tau217 was recovered in 4 of 5 cohorts. Old data can answer new questions. www.tesorai.com/resources/al...

000

Tesorai @tesorai.bsky.social · 08/09/2026

An Alzheimer’s study was published Aug 10. Using Trove, we tested its protein signature across 5 brain proteomics cohorts. With Search, we re-mined raw spectra for p-tau217. 25 days later, we posted a new preprint. The next study may already be in the public data. www.tesorai.com/resources/al...

000

Tesorai @tesorai.bsky.social · 03/09/2026

More peptide IDs shouldn’t mean a looser threshold. Tesorai Search separates model training from FDR estimation, reserving decoys for FDR estimation. Across 7 independent datasets, it identified up to 68% more peptides at 1% FDR vs. four widely used search engines. www.tesorai.com/resources/ho...

000

Tesorai @tesorai.bsky.social · 01/09/2026

Proteomics analysis starts with a scientific question, not an analysis pipeline. With Tesorai Chat, ask the question in plain language and work through the data checks, preparation, statistics, and results in the same conversation.

100

Tesorai @tesorai.bsky.social · 27/08/2026

Finding a relevant public dataset is only the beginning. With Trove, you can compare studies, check whether they’re actually compatible, and look for signals shared across datasets. Public proteomics data, put back to work.

010

Tesorai @tesorai.bsky.social · 25/08/2026

What if better data matters as much as a bigger model? Our new preprint: a 70M-parameter model trained with proteomics matched or exceeded RNA-only models up to 50× larger. 48,843 samples · 440 studies. Why we’re building Trove: put existing proteomics data back to work. tinyurl.com/yubucze5

000

Tesorai @tesorai.bsky.social · 20/08/2026

Personalized cancer vaccines are advancing. So is the need to identify the tumor antigens that matter. See how Tesorai Search supports immunopeptidomics with greater sensitivity and at scale. bit.ly/4gp3kRF

000

Tesorai @tesorai.bsky.social · 18/08/2026

Public proteomics data is abundant. Reusing it is another story. In our analysis of 439 datasets, 84% had essential metadata outside the data file. With Trove, we’re working to make public proteomics data easier to find, understand, and reuse. #Proteomics

010

Tesorai @tesorai.bsky.social · 13/08/2026

What biological signals hold up across independent studies? Tesorai Trove helps researchers evaluate and compare public proteomics datasets through a conversational workflow—making it easier to find results reproduced across studies. Here’s what that looks like in 23 seconds.

010

Tesorai @tesorai.bsky.social · 11/08/2026

Good data can outlive the question that generated it. Public proteomics datasets can be revisited with new hypotheses, new analyses, and new comparisons. That’s the idea behind Tesorai Trove: making the evidence behind published research easier to explore and reuse.

000

Tesorai @tesorai.bsky.social · 06/08/2026

Describe the visualization you need. Tesorai builds it from your proteomics data. Here, a natural language request becomes a custom, interactive plot of protein CV distributions, with options to download the figure or inspect the code. What would you visualize?

010

Tesorai @tesorai.bsky.social · 04/08/2026

We're proud to share our latest peer-reviewed research, now published in the Journal of Molecular Biology. Thanks to our collaborators, especially @mpibiochem.bsky.social and @jmolbiol.bsky.social. 📄 www.sciencedirect.com/science/arti...

021

Tesorai @tesorai.bsky.social · 30/07/2026

Differential expression tells you which proteins changed. Protein interaction networks help explain how those proteins work together, revealing the biological processes behind the results. What's your favorite follow-up analysis after differential expression?

000

Tesorai @tesorai.bsky.social · 28/07/2026

Better hit identification creates more opportunities for successful drug discovery. In a recent biotech collaboration, Tesorai Search identified 11 additional candidate hits, resulting in >30% more new hits than the existing workflow. Reference customer available for qualified prospective partners

020

Tesorai @tesorai.bsky.social · 23/07/2026

Volcano plots are great at identifying what's different between samples. They're not designed to explain why those differences exist. Biology starts after differential expression.

010

Tesorai @tesorai.bsky.social · 21/07/2026

Same public Parkinson's disease dataset. Same statistical threshold. Different search pipeline. Original analysis: 2 statistically significant proteins. Tesorai Search reanalysis: 9. What datasets deserve another look?

010

Tesorai @tesorai.bsky.social · 16/07/2026

What if quality control started with a question instead of a workflow? Here's a short demo of asking Tesorai for proteomics QC guidance in natural language. What workflow should we show next? #Proteomics #MassSpectrometry #AI

121

Tesorai @tesorai.bsky.social · 14/07/2026

The biology was always there. Better computational methods made it possible to find. In collaboration with UCSF, Tesorai identified 7,998 protein-verified RNA editing sites—an 18× increase over previous reports. Congrats @dlswaney.bsky.social, @petercim.bsky.social, and colleagues!

034

Tesorai @tesorai.bsky.social · 09/07/2026

Which proteins are changing between my experimental groups? Ask the question in natural language. Tesorai performs the statistical analysis and generates the volcano plot. What's the slowest step in your Olink analysis workflow?

011

Tesorai @tesorai.bsky.social · 07/07/2026

Tesorai completed the analysis in ~7 hours of compute time, enabling the work to be completed before an ARPA-H proposal deadline. "These analyses dramatically accelerated our time from preliminary hypothesis to in silico antigen confirmation." — Nathan Salomonis, PhD @nathansalomonis.bsky.social

021

Tesorai @tesorai.bsky.social · 07/07/2026

A collaborator needed to reprocess the public ImmunoVerse immunopeptidomics collection: • ~4,000 raw MS files (~4 TB) • Custom FASTAs with ~100,000 proteins • Search for non-canonical antigens Conventional workflows would have taken weeks to months.

010

Tesorai @tesorai.bsky.social · 07/07/2026

Some scientific opportunities can't wait weeks for analysis. 👇

010

Tesorai @tesorai.bsky.social · 02/07/2026

In a collaboration with researchers at Notre Dame and NYU, Tesorai Search identified 136% more high-confidence peptide identifications than standard search engines. Resulting analysis contributed to a pan-cancer atlas of 28,446 tumor-specific antigens. Publication: www.biorxiv.org/content/10.1...

021

Tesorai @tesorai.bsky.social · 02/07/2026

In immunopeptidomics, a missed peptide isn't just another data point. It could be a tumor-specific antigen that never gets investigated. That's why sensitivity matters.

031

Tesorai @tesorai.bsky.social · 02/07/2026

Some discoveries start with a single missed peptide. More peptide identifications don't just improve a metric—they can reveal biology that would otherwise remain hidden. 👇

111

Tesorai @tesorai.bsky.social · 30/06/2026

Many analysis workflows require exporting differential expression results into another tool for pathway analysis. With Tesorai, differential expression and GO enrichment happen in the same workflow—so you can move from proteins to biology without leaving the platform.

011

Tesorai @tesorai.bsky.social · 30/06/2026

GO enrichment groups proteins into biological functions and pathways. Instead of looking at individual proteins, you can begin identifying the biological processes underlying your experiment. That's often where interpretation begins.

011

Tesorai @tesorai.bsky.social · 30/06/2026

A volcano plot might identify hundreds of significant proteins. But researchers rarely care about a list of proteins. They want to understand: • Which pathways are changing? • Which biological processes are enriched? • What mechanisms may be driving the phenotype?

031

Tesorai @tesorai.bsky.social · 30/06/2026

A list of proteins isn't the answer. Biology is. Differential expression tells you what's changing. GO enrichment helps explain what those changes mean. In this example, inflammatory and cytokine signaling emerge as some of the most enriched biological processes. 👇

021

Reposted by Tesorai

Peter Cimermancic @petercim.bsky.social · 25/06/2026

I’ve been re-analyzing a public proteomics dataset and noticed that cancer profiles can look more similar to other cancers than to normal tissue profiles. Is that expected biology, or an artifact of analysis choices?

021

Tesorai @tesorai.bsky.social · 25/06/2026

Large-scale proteomics analysis shouldn't take weeks. Working with frankligy.bsky.social and Mark Yarmarkovich, Tesorai processed 2,500 immunopeptidomics files in under 5 hours—a workflow that previously required more than 4 weeks. Publication: www.biorxiv.org/content/10.1...

043

Tesorai @tesorai.bsky.social · 23/06/2026

Proteomics datasets have grown dramatically in size and complexity. Analysis infrastructure needs to evolve alongside the data.

043

Tesorai @tesorai.bsky.social · 12/11/2025

Honored to see our work highlighted by Dr. Yu-Ju Chen (Academia Sinica) in her #HUPO2025 plenary talk yesterday. We’re thrilled to support her and her team's groundbreaking research in proteomics and lung cancer.

122

Tesorai @tesorai.bsky.social · 11/11/2025

Incredible energy at #HUPO2025! Huge thanks to everyone who has been stopping by the Tesorai booth to see our live demos in action! We’re thrilled by the excitement, thoughtful conversations, and momentum around what we’re building. Grateful to be part of such a passionate proteomics community!

121

Tesorai @tesorai.bsky.social · 09/11/2025

We’re excited to share that Tesorai will be hosting a booth at the HUPO 2025 World Congress in Toronto! Find us at Innovation Row – Table TP3! Stop by for live demos of our AI-powered platform and try out Tesorai Chat in action.

113

Tesorai @tesorai.bsky.social · 20/08/2025

Intro to Tesorai (Search + Chat) If you're working with proteomics data and tired of writing custom code or clicking through clunky tools, we built something that can help. Tesorai lets you process raw mass spec files quickly. And explore your results just by asking questions in chat. Links below:

121

Tesorai @tesorai.bsky.social · 18/08/2025

We are in Barcelona! Excited to sponsor the 2025 Gordon Research Conference on Decoding Microproteins! Dejan will be presenting our poster - “Tesorai Search: Large pretrained model boosts identifications without the need for Percolator.” Come find us and say hi!

130

Tesorai @tesorai.bsky.social · 15/08/2025

Why We Built This: We started building Tesorai because we kept running into the same problem: mass spec analysis is still too challenging and tools can be difficult to use. We wanted something fast, reliable, and flexible enough to work with the questions scientists actually have.

141

Tesorai @tesorai.bsky.social · 04/08/2025

We're a small group of former Google/Verily engineers who’ve spent years building large-scale AI systems. Now we’re working on something different: building advanced AI to help scientists make more sense of raw mass spec proteomics data.

162

Reposted by Tesorai

Peter Cimermancic @petercim.bsky.social · 23/01/2025

#teammassspec does anyone have more info on what's behind the restrictions to sell mass spectrometers to China? www.bis.gov/press-releas...

bis.gov

Commerce Implements New Controls to Address National Security Risks Related to Biotechnology | Bureau of Industry and SecurityLock

044

Reposted by Tesorai

Peter Cimermancic @petercim.bsky.social · 23/12/2024

Interesting to see how improving identification accuracy in #massspectrometry #proteomics also improves the quantification precision. On the public LFQBench benchmark, Tesorai Search without MBR outperforms tools like MaxQuant, FragPipe, and AlphaPept even when they have MBR enabled!

152