Dataset Information

Improvements to Casanovo, a deep learning de novo peptide sequencer

ABSTRACT: Casanovo is a state-of-the-art deep learning model for de novo peptide sequencing from mass spec- trometry proteomics data. Here we report on a series of enhancements to Casanovo, aimed at improving the interpretability of the scores assigned to predicted peptides, generalizing the software for use in database search, speeding up training and prediction runtimes, and providing workflows and visual- ization tools to facilitate adoption of Casanovo and interpretation of its results. Our goal is to make Casanovo accurate and easy to use for applications such as metaproteomics, antibody sequencing, im- munopeptidomics, and discovery of novel peptide sequences in standard proteomics analyses. Casanovo is available as open source at https://github.com/Noble-Lab/casanovo. The raw data and search results can also be viewed at: https://limelight.yeastrc.org/limelight/d/pg/project/165

ORGANISM(S): Homo Sapiens Mus Musculus Saccharomyces Cerevisiae

SUBMITTER: Chris Hsu

PROVIDER: PXD066485 | panorama | Wed Jul 23 00:00:00 BST 2025

REPOSITORIES: PanoramaPublic

ACCESS DATA

Similar Datasets

Project description:Although current mass spectrometry (MS)-based proteomics identifies and quantifies thousands of proteins and (modified) peptides, only a minority of them are subjected to in-depth downstream analysis. With the advent of automated processing workflows, biologically or clinically important results within a study are rarely validated by visualization of the underlying raw information. Although several tools for this are in principle available, they are often not integrated into the overall analysis nor readily extendable with new approaches. To remedy this, we developed AlphaViz, an open-source Python package to superimpose output from common analysis workflows on the raw data for quick and easy visualization and validation of protein and peptide identifications. AlphaViz takes advantage of recent breakthroughs in the deep learning-assisted prediction of experimental peptide properties to allow manual assessment of the expected and measured peptide result deviation. We focused on the visualization of the 4-dimensional data cuboid provided by Bruker TimsTOF instruments, where the ion mobility dimension, besides intensity and retention time, can be predicted and used for verification. We illustrate how AlphaViz can quickly validate or invalidate peptide identifications regardless of the score given to them by automated workflows. Furthermore, we provide a â€˜predict modeâ€™ that can locate peptides present in the raw data but not reported by the search engine. This is illustrated with dilution series and the recovery of missing values from experimental replicates. Applied to phosphoproteomics of the EGF-signaling pathway, we show how key signaling nodes can be validated to enhance confidence for downstream interpretation or follow-up experiments. AlphaViz follows accepted standards for open-source software development, including extensive documentation, testing and continuous integration. It features an easy-to-install graphical user interface for end-users and a modular Python package for bioinformaticians. We hope that AlphaViz can help to make validation of critical proteomics results a standard feature in MS-based proteomics.

Dataset Information

Improvements to Casanovo, a deep learning de novo peptide sequencer

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets