MS datasets for proteomic context-aware modeling of protein palmitoylation

This repository contains datasets derived from mass spectrometry–based proteomics experiments used in the study on generative context-aware modeling of protein palmitoylation. The repository includes two datasets: HeLa, consisting of data derived from a previously published study by our laboratory (DOI: 10.1038/s41388-025-03604-9), and PANC-1, consisting of data generated by our laboratory using a unified data processing pipeline. The deposited files contain: Type Description File Proteome protein and peptide identification results from database searching Prot_proteins_Hela.tsv Prot_peptides_Hela.tsv Prot_proteins_PANC1.xlsx Prot_peptides_PANC1.xlsx Proteome protein abundance matrix Protein_Expression_Hela.csv Protein_Expression_PANC1.csv Palmitoylome protein and peptide identification results from database searching Palm_proteins_Hela.tsv Palm_peptides_Hela.tsv Palm_proteins_PANC1.xlsx Palm_peptides_PANC1.xlsx Palmitoylome corresponding palmitoylation site table Palmitoylayion_Site_Hela.csv Palmitoylayion_Site_PANC1.csv Raw mass spectrometry data have been submitted to the PRIDE repository and will be made publicly available upon completion of repository curation. The source code and trained model are available separately via the project's GitHub repository (https://github.com/kkkyj/GAN-Palm).