SpotLink enables sensitive and precise identification of site non-specific cross-links at the proteome scale
Zhang, W.; Gong, P.; Shan, Y.; Zhao, L.; Hu, H.; Wei, Q.; Liang, Z.; Liu, C.; Zhang, L.; Zhang, Y.
Show abstract
We developed SpotLink software for identifying site non-specific cross-links at the proteome scale. Contributed by the dual pointer dynamic pruning (DPDP) algorithm and the quality control of cross-linking sites, SpotLink identified more than 3000 cross-links from human proteome database with rich site information in a few days. We demonstrated that SpotLink outperformed other approaches in terms of sensitivity and precision on a simulated dataset and a protein complexes dataset with known structures. Additionally, we discovered some valuable protein-protein interaction (PPI) information contained in the protein complexes dataset and HeLa dataset, indicating the unique identification advantages of site non-specific cross-linking. The excellent performance of SpotLink will increase the usage of site non-specific cross-linking in the near future. SpotLink is publicly available on GitHub [https://github.com/DICP1810/SpotLink].
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Spatially resolved profiling of protein conformation and interactions by biocompatible chemical cross-linking in living cells 95%
- AlphaPeptDeep: A modular deep learning framework to predict peptide properties for proteomics 95%
- Systematic detection of functional proteoform groups from bottom-up proteomic datasets 95%
Similar papers in this journal
- Deep-learning enables proteome-scale identification of phase-separated protein candidates from immunofluorescence images 95%
- PSTP: Decoding Latent Sequence Grammar for Protein Phase Separation through Transfer Learning and Attention 94%
- Predicting the structures of cyclic peptides containing unnatural amino acids by HighFold2 93%
Similar papers in this journal
- SHEPHARD: a modular and extensible software architecture for analyzing and annotating large protein datasets 95%
- Sitetack: A Deep Learning Model that Improves PTM Predictionby Using Known PTMs 93%
- PEPerMINT: Peptide Abundance Imputation in Mass Spectrometry-based Proteomics using Graph Neural Networks 93%
Similar papers in this journal
- O-Pair Search with MetaMorpheus for O-glycopeptide Characterization 94%
- Genomics 2 Proteins portal: A resource and discovery tool for linking genetic screening outputs to protein sequences and structures 93%
- Time-resolved cryo-EM using a combination of droplet microfluidics with on-demand jetting 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.