Resources main page

Learn, Apply, Discover

Whether you're just getting started or going deep, explore how our approach can help you grow your research with confidence.

Tesorai Search: Cloud-based Database Search Engine Boosts Identifications for Mass Spectrometry Proteomics With a Pretrained Peptide-spectrum Deep-learning Model

Tesorai Search is now peer-reviewed and published in the Journal of Molecular Biology, detailing the model's design and benchmarking against other leading proteomics search engines.

Rapid Mechanistic Bridging of an Alzheimer's Disease Plasma Protein Staging Panel Across Brain Proteomics Cohorts

Five public brain proteomics cohorts, reprocessed on Tesorai, support a seven-protein blood panel for Alzheimer's staging, including recovered p-tau217. Presented at HUPO 2026.

Developing and Benchmarking Agentic LLM Frameworks for Accelerated and Accessible Proteomics Data Analysis

On a 94-case proteomics benchmark, Tesorai Chat reached 92.2% accuracy, ahead of Phylo, GPT-5.4 Codex, and Claude 4.6 Sonnet. Presented at HUPO 2026.

Integrating Narrow-Window DIA with AI-Powered Search Enables Deep and Reliable Functional Proteomics

Our collaborators at MD Anderson Cancer Center have deposited a preprint on bioRxiv benchmarking narrow-window DIA with Tesorai Search, achieving the deepest proteome coverage among 12 acquisition-analysis pipelines tested while maintaining rigorous FDR control.

Rapid Mechanistic Bridging of an Alzheimer's Disease Plasma Protein Staging Panel Across Brain Proteomics Cohorts

A new Tesorai preprint validates a proposed seven-protein blood biomarker panel for Alzheimer's staging by reanalyzing five independent brain proteomics cohorts, recovering a key biomarker, p-tau217, that was missing from the original studies.

Single-cell foundation models benefit from cross-modal training: adding proteomics data beats parameter scaling

Fine-tuning a single-cell foundation model on proteomics data matches or beats scaling to models over 40x larger — showing multimodal training can outperform parameter scaling alone.

Building a Pan-Cancer Atlas of Therapeutic T Cell Targets

How NYU researchers used large-scale immunopeptidomics and AI-enabled peptide identification to identify 28,446 tumor-specific antigens and accelerate therapeutic target discovery.

How Tesorai Works

How Tesorai Search gets more identifications without cutting corners on error control — the scoring model, the FDR methodology, and how it handles both DDA and DIA, in one place.

Education

View All

FDR, MBR, and Immunopeptidomics guide resource card graphic

FDR, Match-Between-Runs, and Immunopeptidomics: A Plain-Language Guide

Three concepts that determine whether you can trust your proteomics results — and what to look for when evaluating any search engine.

What Is Proteomics guide resource card graphic

What is Proteomics? A guide to Mass Spectrometry, Search Engines, and Data Acquisition

From how proteins are measured to why the software that analyzes the data matters as mush as the instrument that generates it.

Case Studies

View All

Building a Pan-Cancer Atlas of Therapeutic T Cell Targets

How NYU researchers used large-scale immunopeptidomics and AI-enabled peptide identification to identify 28,446 tumor-specific antigens and accelerate therapeutic target discovery.

Guangyuan (Frank) Li, PhD, NYU Langone Health

RNA Editing case study resource card graphic

Revealing the Functional Landscape of RNA Editing

How UCSF researchers used deep proteomics and AI-enabled peptide identification to map 7.998 protien-verified RNA editing sites - an 18-fold increase over previously reported evidence.

Jack Moen, PhD, UCSF

Publications

View All

Publication

Tesorai Search: Cloud-based Database Search Engine Boosts Identifications for Mass Spectrometry Proteomics With a Pretrained Peptide-spectrum Deep-learning Model

Tesorai Search is now peer-reviewed and published in the Journal of Molecular Biology, detailing the model's design and benchmarking against other leading proteomics search engines.

Scientific poster

Rapid Mechanistic Bridging of an Alzheimer's Disease Plasma Protein Staging Panel Across Brain Proteomics Cohorts

Five public brain proteomics cohorts, reprocessed on Tesorai, support a seven-protein blood panel for Alzheimer's staging, including recovered p-tau217. Presented at HUPO 2026.

Blog

View All

The Publication Bottleneck: Lossy compression in the Age of Omics

Valuable biological information is lost in the practice of publishing our work.

Differential proteomics: Unpacking the protein table

The "protein table" behind differential analysis hides aggregation choices that can quietly shape your results.

Media

View All

Development of a large pretrained model for Tesorai Search

Peter's lecture at MaxQuant Summer School 2024 describing the principles underlying how Search was built.

Building Tesorai - an interview with Peter

Tanja Janko with the ASEF spoke with Peter about the creation of Tesorai and the future of molecular analysis.

Learning Hub

View All

Demo video

See Tesorai Chat in action and watch examples of how it can make data visualization faster and easier.

Get started

Learn how to set up your first analysis with Tesorai Search. This guide walks you through uploading your data, running a search, and reviewing the results.