Dataset Information

Machine Learning-Based Retention Time Prediction of Trimethylsilyl Derivatives of Metabolites

ABSTRACT: In gas chromatography-mass spectrometry-based untargeted metabolomics, metabolites are identified by comparing mass spectra and chromatographic retention time with reference databases or standard materials. In that sense, machine learning has been used to predict the retention time of metabolites lacking reference data. However, the retention time prediction of trimethylsilyl derivatives of metabolites, typically analyzed in untargeted metabolomics using gas chromatography, has been poorly explored. Here, we provide a rationalized framework for machine learning-based retention time prediction of trimethylsilyl derivatives of metabolites in gas chromatography. We compared different machine learning paradigms, in addition to exploring the influence of the computational molecular structure representation to train the prediction models: fingerprint class and fingerprint calculation software. Our study challenged predicted retention time when using chemical ionization and electron impact ionization sources in simulated and real cases, demonstrating a good correct identity ranking capability by machine learning, despite observing a limited false identity filtering power in cases where a spectrum or a monoisotopic mass match to multiple candidates. Specifically, machine learning prediction yielded median absolute and relative retention index (relative retention time) errors of 37.1 retention index units and 2%, respectively. In addition, fingerprint class and fingerprint calculation software, as well as the molecular structural similarity between the training and test or real case sets, showed to be critical modulators of the prediction performance. Finally, we leveraged the structural similarity between the training and test or real case set to determine the probability that the prediction error is below a specific threshold. Overall, our study demonstrates that predicted retention time can provide insights into the true structure of unknown metabolites by ranking from the most to the least plausible molecular identity, and sets the guidelines to assess the confidence in metabolite identification using predicted retention time data.

INSTRUMENT(S): Gas Chromatography MS - positive

SUBMITTER: Sara Martinez de Cripan

PROVIDER: MTBLS2841 | MetaboLights | 2022-05-26

REPOSITORIES: MetaboLights

ACCESS DATA

Dataset's files

Source:

Items per page:

1 - 5 of 7

Publications

Machine Learning-Based Retention Time Prediction of Trimethylsilyl Derivatives of Metabolites.

de Cripan Sara M SM Cereto-Massagué Adrià A Herrero Pol P Barcaru Andrei A Canela Núria N Domingo-Almenara Xavier X

Biomedicines 20220411 4

In gas chromatography-mass spectrometry-based untargeted metabolomics, metabolites are identified by comparing mass spectra and chromatographic retention time with reference databases or standard materials. In that sense, machine learning has been used to predict the retention time of metabolites lacking reference data. However, the retention time prediction of trimethylsilyl derivatives of metabolites, typically analyzed in untargeted metabolomics using gas chromatography, has been poorly explo ...[more]

PMID: 35453629

Similar Datasets

Project description:Abstract: Crosslinking mass spectrometry (Crosslinking MS) has developed into a robust technique that is increasingly used to investigate the interactomes of organelles and cells. However, the incomplete and noisy information contained in spectra limits especially the identification of heteromeric protein-protein interactions (PPIs) from the many theoretically possible PPIs. We successfully leveraged here chromatographic retention time (RT) to complement the mass spectrometry-centric identification process. For this, we first made crosslinked peptides amenable to RT prediction, through a Siamese neural network, and then added RT information to the identification process. Our multi-task machine learning model xiRT achieved highly accurate predictions in a multi-dimensional separation experiment of crosslinked E. coli lysate conducted for this study. We combined strong cation exchange (SCX), hydrophilic strong anion exchange (hSAX) and reversed-phase (RP) chromatography and reached R^2 0.94 in RP and a margin of error of 1 fraction for hSAX in 94%, and SCX in 85% of the cases. Importantly, supplementing the search engine score with retention time features led to a 1.4-fold increase in PPIs, at 1% PPI false discovery rate (FDR). We also demonstrated the value of this approach for the more routine analysis of multiprotein complexes. In the Fanconi anaemia monoubiquitin ligase complex, an increase of 1.7-fold in heteromeric residue-pairs was achieved at 1% residue-pair FDR, solely using reversed-phase RT. Retention times therefore proved to be a powerful complement to mass spectrometric information to improve the identification of crosslinked peptides. We envision xiRT to supplement search engines in their scoring routines to increase the sensitivity of Crosslinking MS analyses especially for protein-protein interactions. Conclusion: Using a Siamese network architecture, we succeeded in bringing RT prediction into the Crosslinking MS field, independent of separation setup and search software. Our open source application xiRT introduces the concept of multi-task learning to achieve multi-dimensional chromatographic retention time prediction, and may use any peptide sequence-dependent measure including for example collision cross section or isoelectric point. The black-box character of the neural network was reduced by means of interpretable machine learning that revealed individual amino acid contributions towards the separation behavior. The RT predictions – even when using only the RP dimension – complement mass spectrometric information to enhance the identification of heteromeric crosslinks in multiprotein complex and proteome-wide studies. Overfitting does not account for this gain as known false target matches from an entrapment database did not increase. Leveraging additional information sources may help to address the mass-spectrometric identification challenge of heteromeric crosslinks.

			Action	DRS
	MTBLS2841	Other
	FILES	Other
	a_MTBLS2841_GC-MS_positive__metabolite_profiling.txt	Txt
	files-all.json	Other
	i_Investigation.txt	Txt