FAQs

Onboarding with Tesorai Search and Tesorai Chat [beta] is fast and intuitive. Tesorai Search is cloud-based, so there’s nothing to install – just drag and drop your files into a user-friendly interface. Tesorai Chat [beta] makes exploration even easier with an interactive, conversational experience. You can start generating visualizations in seconds.

‍

You won’t need to. Software updates will be automatic. We continuously add new features and improvements behind the scenes, so you’re always using the latest version. We also welcome your feedback and feature suggestions to help shape what comes next.

Tesorai currently provides two types of output:

1. Search Results Dashboard:
   For each job, you’ll receive:
   
   • Downloadable tables for PSMs, peptides, proteins, and quantification results
   • An interactive dashboard with diagnostic plots such as:
     
     • Target/decoy score distributions
     • Annotated spectra
     • Venn diagrams comparing results to other search tools
     • Searchable PSM, peptide, and protein tables

To view the dashboard and download your results, go to the Jobs tab and click the job name or the report icon.

2. Tesorai Chat (Beta):
   Our new beta feature lets you interact with your data using natural language — ask questions, generate plots, and visualize results directly from your search output. It’s an early version, and we’re actively improving it based on user feedback.

To access Chat (Beta), go to the Jobs tab and click the chat icon all the way on the right side of each job’s row, or within the dashboard by clicking on a button in the upper-right corner.

‍

Tesorai Search includes free pre-loaded credits so you can get started right away. We are committed to offering a monthly allotment of free credits for all users. While the number of free credits may adjust over time, early users will have their tier locked in at the time of sign-up. For larger scale projects needing more credits, feel free to reach out to us.

Tesorai Chat [beta] is free while in beta. We encourage you to try it out and share your feedback so we can build a platform that truly supports your work. After the beta period, we will continue to provide free credits to support academic and research use, with affordable pricing available for users who need more credits.

By using Tesorai tools, you avoid the hidden costs of traditional workstation software – no installations, no maintenance, and no long wait times. Our cloud-based platform is designed to save you time and effort, so you can stay focused on your research.

For custom needs or volume-based pricing, feel free to contact us at info@tesorai.com. We’re happy to help you find the most cost-effective solution.

Tesorai Search currently supports DDA, TMT, and DIA datasets from major instrument vendors including Thermo, Bruker, and SCIEX. *note* Bruker DDA files need to be converted to mzML and uploaded in a zipped form. Bruker DIA datasets are not currently supported.

Let us know about your specific needs. You can sign up to receive updates on upcoming releases and soft launch dates.

‍

Tesorai Search currently provides core elements as output: PSM and peptide identification tables, as well as a report with a few data diagnostic plots. Here are a few features that we’ll be adding soon: protein inference, quantification, and support for TMT data and additional post-translational modification. Let us know what you would like to see added next: feedback@tesorai.com.

‍

Tesorai Search is designed to handle a wide range of experimental setups and excels in several challenging use cases.

It performs particularly well on:

• Datasets with larger search space, such as in immunopeptidomics
• Data acquired using varied collision energies and fragmentation methods
• Datasets with low signal-to-noise spectra, such as plasma samples

Note that when comparing to other tools, the total protein or peptide counts may not be the appropriate metric. With current tools, the identification accuracy (or, correctness) can be compromised due to the inaccurate control of the false-discovery rates [Freestone et al] [https://www.nature.com/articles/s41592-025-02719-x]. Our model does not suffer from this “double-dipping” issue, because it is entirely pre-trained with decoys used only for FDR estimation (exactly what they were supposed to be used for).

Speed and scalability are central to our mission. Tesorai Search is built on cloud-native infrastructure that scales dynamically with your data, allowing us to process datasets significantly faster than conventional tools. Instead of waiting hours or days, you can expect most results in under an hour – even for large-scale projects.

‍

Estimated DDA processing times (with standard FASTA files):

• Small datasets (up to 10 raw files): ~40 minutes
• Medium datasets (10–100 raw files): ~45 minutes
• Large datasets (100+ raw files): ~1 hour (e.g., 500 raw files processed in under 50 minutes)

*note* Processing DIA datasets can be 2-3x slower. Processing time can also depend on factors like raw file size, number of spectra, FASTA complexity, and digestion enzymes – but our flexible cloud approach ensures performance keeps up with your needs. If you have specific requirements or timelines, our technical team is happy to advise and support you directly.

‍

We currently set the following limits on file sizes: 300MB for fasta files and 30GB for raw files which should cover most needs. If you have larger files or specific requirements that exceed this limitation, we encourage you to reach out to us directly.

The time it takes to upload data to Tesorai Search generally depends on a few key factors, including the size of the files you are uploading and the current internet conditions. While the actual upload speed is influenced by your internet bandwidth, our platform is optimized to handle uploads as efficiently as possible. For example, for a dataset with 5 files and 1 Gb in size each, and on a typical 50 Mbps upload internet speed, the data upload would only take a couple of minutes.

Tesorai Search does not limit the number of files you can upload and process. You have the flexibility to upload and process as many files as you need. However, there is a size limit of 5 GB per individual file; note that this is temporary as we continue to expand our computational framework. If you have larger files or specific requirements that exceed this limitation, we encourage you to reach out to us directly.

‍

No need for installation; Tesorai Search is web-based, unlike many other tools that require installation and frequent updates on workstations. If your organization requires an on-prem solution, please reach out to info@tesorai.com.

‍

Mass spectrometers collect a massive amount of spectral data but the majority of those mass spectra remain unidentified or unannotated - current algorithms can fail to identify up to 80% of tandem spectra. Tesorai Search leverages the most recent AI advances to enable users to increase identification of peptides and analytes in their samples despite these challenges. Other tools, such as Percolator, have also attempted to leverage other machine learning approaches for rescoring, boosting peptide and protein identification rates. But the results from recent tools that rely on boosting rates with the use of Percolator come at a cost, as they are trained to separate the targets from the decoys, which can lead to inaccurate control of the false-discovery rate [Freestone et al] [https://www.nature.com/articles/s41592-025-02719-x]. 

‍

In contrast, Tesorai Search increases peptide identification without needing Percolator. Our advanced approach to peptide-spectrum matching is based on a pre-trained large deep learning model which does not utilize decoys during training and does not require training a new model for every new sample. We trained the Tesorai model on over 100M real peptide-spectrum pairs and demonstrate that the approach performs robustly across a wide range of use-cases including standard trypsin-digested human samples, immunopeptidomics, and metaproteomics, single-cell and isobaric-labeled samples. In addition to providing robust FDR control, our method increases identifications by 20% or more compared to other advanced methods. [See our presentation from ASMS for more details here.] 

‍

Yes – the current version can help identification of protein modifications, as long as they’re included in the search fasta file. The standard, sample-preparation modifications such as cysteine carbamylation, methionine oxidation, deamidation, phosphorylation, and acetylation are also supported by default. Other PTMs, such as ubiquitination, glycosylation and more are being added as we speak and will become available soon. 

‍

Downloading images and tables is easy:

• Images:
  • For interactive Plotly images, simply click the save icon in the upper-right corner.
    
    
  • For standard, non-interactive images, right-click on the image and select "Save."
    
    
  • If you need higher resolution images for reports or publications, just ask Chat to generate one for you. You can also request stylistic changes, such as adjusting fonts or colors.
• Tables:
  •  You can copy or download tables by clicking the respective buttons below each table.

Yes, you can see the executed code by clicking on the “See code” button underneath each response.

Ensuring accuracy is a top priority for us, and we’re dedicated to continuous improvement. Achieving 99% accuracy is relatively straightforward, but the final 1% requires innovation and effort. To ensure accuracy, we’ve taken several steps:

1. Focused Scope: We’ve narrowed the Chat’s focus to proteomics rather than broader fields. By specializing, we can ensure deeper expertise and better accuracy.
2. Leveraging Existing Top-Tier LLMs: Chat utilizes advanced language models (like ChatGPT), but we enhance them by integrating custom-built code and tools. This approach minimizes the risk of "hallucinations" or incorrect information.
3. Continuous Testing: We’ve assembled a large dataset of queries with known correct responses. Every change we make is rigorously tested using this dataset before any new features reach you.
4. Transparency: The code that generates responses is made visible to you, so you can validate the accuracy of the information yourself.

This approach allows us to maintain a high level of accuracy while continually improving as we learn from real-world use.

It’s a wide range. We recommend checking out our overview video here: docs.tesorai.com/demo

To help you get started, we've pre-populated your job with a few example queries and answers to show you what’s possible. Tesorai Chat can assist with a wide range of analyses, including:

• QC Analyses: Plotting peptide or protein counts per sample, calculating coefficients of variation for quantification, creating clustered heatmaps, and generating PCA plots.
• Secondary Analyses: Conducting differential expression analyses, applying various data normalization techniques, and performing missing value imputation.
• Tertiary Analyses: Putting results into context by exploring biological pathways, protein interactions, diseases, or drugs through gene set enrichment analysis.

Additionally, Tesorai Chat can act as a mentor by suggesting best approaches or offering multiple options for your analysis needs. We’ve seen Chat handle a wide variety of tasks, so feel free to ask challenging questions or test its capabilities. You might be surprised by its answers. And don’t forget to share your feedback, whether it impresses you or falls short. Your input helps us improve!

Tesorai Chat [beta] is still in active development, which means you're getting early access while we continue to improve it. We're focused on making it more robust, reliable, and useful based on how it performs for real users. Your feedback plays a key role in shaping what comes next, so try it out and let us know what works and what doesn’t!

We use Google Cloud Storage (GCS) to store your data, which is designed with multiple layers of protection. Here are several key measures we take to safeguard your information:

• Robust Encryption: All data stored on GCS is encrypted at rest and in transit. This means your data is encrypted before it is written to disk and is also protected as it travels between our servers and GCS, preventing unauthorized access.
  ‍
• Compliance and Certifications: GCS complies with major security standards and certifications such as ISO 27001, which helps protect data from security threats or breaches. By complying with these standards, we ensure that our security measures meet international security guidelines.
  ‍
• Access Controls: We implement strict access controls and auditing capabilities. Access to data is tightly controlled and limited to authorized personnel only, based on their role. We also use advanced identity and access management policies to prevent unauthorized access.
  ‍
• Regular Security Audits: We regularly review and update our security practices. This includes conducting security audits and vulnerability scans to ensure that our defenses remain effective against new threats.
  ‍
• Data Redundancy: GCS provides high durability via data redundancy. This means your data is automatically replicated across multiple locations to prevent data loss due to hardware failures or other incidents.

By leveraging Google Cloud's robust infrastructure and adhering to best practices, we ensure that your data is secure and protected at all times. If you have any more questions about our data security measures, please feel free to contact us.

‍

No, we do not share your data with third parties. Our commitment to your privacy and data security is paramount. Here is how we handle your data:

• Strict Privacy Policy: We adhere to a strict privacy policy that prohibits the sharing of your data with any external companies or third parties. This ensures that your personal and business data remains confidential and is used solely to enhance your experience with our service.

• Internal Use Only: Any data collected from you is used exclusively for internal purposes, such as improving our services, providing support, and making informed decisions that benefit our user community. We do not sell, rent, or trade your information with any external entities.

• We value your trust and are committed to protecting your data with the highest standards of privacy and security. If you have any further questions or concerns about how we handle your data, please feel free to reach out to our support team.

‍

Yes, we offer a range of custom services tailored to your specific needs. This includes validating targets, identifying novel biomarkers, and developing AI models to enhance your research. Whether you're working on drug discovery, diagnostics, or other areas of life sciences, our team can collaborate with you to design solutions that meet your unique requirements. If you'd like to discuss your project in more detail, please contact us at info@tesorai.com.

Yes, we have several advanced AI models that are either completed or in development but not yet released on our public platform. Some of our specialized work includes models for prioritizing hits from affinity purification or proximity labeling mass spectrometry, chemoproteomics, immunogenicity prediction, and a method for cleaning signals from high-throughput screening techniques that use plate formats. For more details or to discuss these models further, please reach out to us at info@tesorai.com.

We partner with biotech and life science teams who want to get more out of their data, move faster, and make smarter decisions. Whether you’re exploring uncharted biology or validating a promising signal, our AI platform gives you the speed and depth you need to get there.

Teams we support include:‍

• Discovery teams hunting for novel targets
• Biomarker teams pinpointing and validating disease-associated signals
• Translational research groups turning lab insights into clinical impact
• Preclinical teams refining assays and experimental designs
• Core facilities managing and interpreting large-scale datasets

By working across these groups, we help connect insights from early research through translational studies, accelerating the path from discovery to impact.

Yes, we can install and operate both Search and Chat within your local or cloud environment. However, the specifics will depend on the configuration of your infrastructure. Please contact us at info@tesorai.com to discuss your setup, and we’ll work with you to find the best solution.

Tesorai is pronounced /ˌtɛs.əˈraɪ/ — tess-uh-rye.

Our fish is inspired by the deep sea – a vast dark space where a complex ecosystem exists. Our logo is a friendly take on a deep-sea lanternfish, navigating uncharted waters and, in our fictional world, helping to illuminate hidden insights. Just like our platform, it’s designed to explore complexity and bring clarity where it’s hardest to find.

Tesorai is inspired by the Italian word tesoro, meaning “treasure,” combined with AI – our core technology. We chose the name to reflect what our platform does best: uncover valuable insights hidden deep within complex datasets. Just like finding treasure, making sense of biological data can be difficult without having a guide or map to assist. Tesorai brings those together, helping you discover what matters faster and with more confidence.