Retention time prediction using neural networks increases identifications in crosslinking mass spectrometry

Abstract

Crosslinking mass spectrometry has developed into a robust technique that is increasingly used to investigate the interactomes of organelles and cells. However, the incomplete and noisy information in the mass spectra of crosslinked peptides limits the numbers of protein–protein interactions that can be confidently identified. Here, we leverage chromatographic retention time information to aid the identification of crosslinked peptides from mass spectra. Our Siamese machine learning model xiRT achieves highly accurate retention time predictions of crosslinked peptides in a multi-dimensional separation of crosslinked E. coli lysate. Importantly, supplementing the search engine score with retention time features leads to a substantial increase in protein–protein interactions without affecting confidence. This approach is not limited to cell lysates and multi-dimensional separation but also improves considerably the analysis of crosslinked multiprotein complexes with a single chromatographic dimension. Retention times are a powerful complement to mass spectrometric information to increase the sensitivity of crosslinking mass spectrometry analyses.

Improved Peptide Backbone Fragmentation Is the Primary Advantage of MS-Cleavable Crosslinkers

“…For self-CSMs, only 29% more CSMs were identified with DSSO than with BS3 (Figure S10), indicating that self-CSMs are approaching exhaustive coverage at the given experimental detection limit. Similar results were seen when including retention time data of heteromeric and self-CSMs …”

“…Similar results were seen when including retention time data of heteromeric and self-CSMs. 22 To investigate the effect of the cleaved crosslinker fragments on the overall crosslink search performance, we performed another search in which the DSSO crosslinker was treated as noncleavable. In this search, only 1866 heteromeric CSMs were identified (−74%).…”

“…This would lead to an explosion of the search space. However, there are multiple large-scale studies that have successfully employed a noncleavable crosslinker despite these assumptions. ,,, These are based on a detailed understanding of how crosslinked peptides fragment that offered a computational solution to knowing the individual peptide masses which was then implemented in the search algorithm xiSEARCH 3 . In light of the successful usages of both types of crosslinkers, we decided to compare their spectral information to understand any costs and benefits.…”

Accurate Retention Time Prediction Based on Monolinked Peptide Information to Confidently Identify Cross-Linked Peptides

“…In this study, we further found that the retention time can act as an extra dimension to dramatically reduce the false positive hits. Retention time has reported to be a useful feature in the application of MS-based proteomics. − We just noticed that a recent paper also used retention time prediction to increase identification of cross-linked peptides . Herein, we found that the monolinked peptides carried out the information on the retention time of the corresponding cross-linked pairs, and the retention time of cross-linked peptides can be well predicted by the use of the retention time of the monolinked peptides.…”

Yeast Display Enables Identification of Covalent Single Domain Antibodies Against Botulinum Neurotoxin Light Chain A

“…Larger datasets that include both crosslinking efficiency and crosslinking site(s) of antibody variants bearing crosslinkable groups are needed to enable data-driven approaches to covalent antibody engineering. [77][78][79][80][81][82] Future endeavors using the high throughput yeast-display screening tools reported here can be complemented by mechanistic investigations of successful crosslinkable antibodies using mass spectrometry 37,38,62,65,[83][84][85][86][87][88] and structural 61 characterizations. Ongoing work in our laboratories seeks to identify the residues on LC/A that are directly involved in crosslinking using mass spectrometry (these technically demanding experiments require further methodological development and refinement to enable their application in the sdAb-LC/A system).…”