The METLIN Small Molecule Dataset for Machine Learning-based Retention Time prediction

Overview

Journal Nat Commun

Specialty Biology

Date 2019 Dec 22

PMID 31862874

Citations 54

Authors

Xavier Domingo-Almenara

Carlos Guijas

Elizabeth Billings

J Rafael Montenegro-Burke

Winnie Uritboonthai

Aries E Aisporna

Emily Chen

H Paul Benton

Gary Siuzdak

Affiliations

Soon will be listed here.

Abstract

Machine learning has been extensively applied in small molecule analysis to predict a wide range of molecular properties and processes including mass spectrometry fragmentation or chromatographic retention time. However, current approaches for retention time prediction lack sufficient accuracy due to limited available experimental data. Here we introduce the METLIN small molecule retention time (SMRT) dataset, an experimentally acquired reverse-phase chromatography retention time dataset covering up to 80,038 small molecules. To demonstrate the utility of this dataset, we deployed a deep learning model for retention time prediction applied to small molecule annotation. Results showed that in 70[Formula: see text] of the cases, the correct molecular identity was ranked among the top 3 candidates based on their predicted retention time. We anticipate that this dataset will enable the community to apply machine learning or first principles strategies to generate better models for retention time prediction.

Citing Articles

FIORA: Local neighborhood-based prediction of compound mass spectra from single fragmentation events.

Nowatzky Y, Russo F, Lisec J, Kister A, Reinert K, Muth T Nat Commun. 2025; 16(1):2298.

PMID: 40055306 PMC: 11889238. DOI: 10.1038/s41467-025-57422-4.

ROASMI: accelerating small molecule identification by repurposing retention data.

Sun F, Yin Y, Liu H, Shen L, Kang X, Xin G J Cheminform. 2025; 17(1):20.

PMID: 39953609 PMC: 11829455. DOI: 10.1186/s13321-025-00968-8.

Development of an Efficient and Generalized MTSCAM Model to Predict Liquid Chromatography Retention Times of Organic Compounds.

Fan M, Sang C, Li H, Wei Y, Zhang B, Xing Y Research (Wash D C). 2025; 8:0607.

PMID: 39925484 PMC: 11803058. DOI: 10.34133/research.0607.

Application of artificial intelligence to quantitative structure-retention relationship calculations in chromatography.

Xie J, Chen S, Zhao L, Dong X J Pharm Anal. 2025; 15(1):101155.

PMID: 39896319 PMC: 11782803. DOI: 10.1016/j.jpha.2024.101155.

Explicit relation between thin film chromatography and column chromatography conditions from statistics and machine learning.

Xu H, Wu W, Chen Y, Zhang D, Mo F Nat Commun. 2025; 16(1):832.

PMID: 39828717 PMC: 11743788. DOI: 10.1038/s41467-025-56136-x.

References

Guijas C, Montenegro-Burke J, Domingo-Almenara X, Palermo A, Warth B, Hermann G . METLIN: A Technology Platform for Identifying Knowns and Unknowns. Anal Chem. 2018; 90(5):3156-3164. PMC: 5933435. DOI: 10.1021/acs.analchem.7b04424. View

Broeckling C, Ganna A, Layer M, Brown K, Sutton B, Ingelsson E . Enabling Efficient and Confident Annotation of LC-MS Metabolomics Data through MS1 Spectrum and Time Prediction. Anal Chem. 2016; 88(18):9226-34. DOI: 10.1021/acs.analchem.6b02479. View

Sumner L, Amberg A, Barrett D, Beale M, Beger R, Daykin C . Proposed minimum reporting standards for chemical analysis Chemical Analysis Working Group (CAWG) Metabolomics Standards Initiative (MSI). Metabolomics. 2013; 3(3):211-221. PMC: 3772505. DOI: 10.1007/s11306-007-0082-2. View

Bach E, Szedmak S, Brouard C, Bocker S, Rousu J . Liquid-chromatography retention order prediction for metabolite identification. Bioinformatics. 2018; 34(17):i875-i883. DOI: 10.1093/bioinformatics/bty590. View

Samaraweera M, Hall L, Hill D, Grant D . Evaluation of an Artificial Neural Network Retention Index Model for Chemical Structure Identification in Nontargeted Metabolomics. Anal Chem. 2018; 90(21):12752-12760. PMC: 8378237. DOI: 10.1021/acs.analchem.8b03118. View

Lenselink E, Ten Dijke N, Bongers B, Papadatos G, van Vlijmen H, Kowalczyk W . Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set. J Cheminform. 2017; 9(1):45. PMC: 5555960. DOI: 10.1186/s13321-017-0232-0. View

Liu Z, Li Y, Han L, Li J, Liu J, Zhao Z . PDB-wide collection of binding data: current status of the PDBbind database. Bioinformatics. 2014; 31(3):405-12. DOI: 10.1093/bioinformatics/btu626. View

Cereto-Massague A, Ojeda M, Valls C, Mulero M, Garcia-Vallve S, Pujadas G . Molecular fingerprint similarity search in virtual screening. Methods. 2014; 71:58-63. DOI: 10.1016/j.ymeth.2014.08.005. View

Bajusz D, Racz A, Heberger K . Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?. J Cheminform. 2015; 7:20. PMC: 4456712. DOI: 10.1186/s13321-015-0069-3. View

10.

Wishart D, Djoumbou Feunang Y, Marcu A, Guo A, Liang K, Vazquez-Fresno R . HMDB 4.0: the human metabolome database for 2018. Nucleic Acids Res. 2017; 46(D1):D608-D617. PMC: 5753273. DOI: 10.1093/nar/gkx1089. View

11.

Allen F, Pon A, Wilson M, Greiner R, Wishart D . CFM-ID: a web server for annotation, spectrum prediction and metabolite identification from tandem mass spectra. Nucleic Acids Res. 2014; 42(Web Server issue):W94-9. PMC: 4086103. DOI: 10.1093/nar/gku436. View

12.

Creek D, Jankevics A, Breitling R, Watson D, Barrett M, Burgess K . Toward global metabolomics analysis with hydrophilic interaction liquid chromatography-mass spectrometry: improved metabolite identification by retention time prediction. Anal Chem. 2011; 83(22):8703-10. DOI: 10.1021/ac2021823. View

13.

Wang M, Carver J, Phelan V, Sanchez L, Garg N, Peng Y . Sharing and community curation of mass spectrometry data with Global Natural Products Social Molecular Networking. Nat Biotechnol. 2016; 34(8):828-837. PMC: 5321674. DOI: 10.1038/nbt.3597. View

14.

Eugster P, Boccard J, Debrus B, Breant L, Wolfender J, Martel S . Retention time prediction for dereplication of natural products (CxHyOz) in LC-MS metabolite profiling. Phytochemistry. 2014; 108:196-207. DOI: 10.1016/j.phytochem.2014.10.005. View

15.

Bouwmeester R, Martens L, Degroeve S . Comprehensive and Empirical Evaluation of Machine Learning Algorithms for Small Molecule LC Retention Time Prediction. Anal Chem. 2019; 91(5):3694-3703. DOI: 10.1021/acs.analchem.8b05820. View

16.

Aicheler F, Li J, Hoene M, Lehmann R, Xu G, Kohlbacher O . Retention Time Prediction Improves Identification in Nontargeted Lipidomics Approaches. Anal Chem. 2015; 87(15):7698-704. DOI: 10.1021/acs.analchem.5b01139. View

17.

Abate-Pella D, Freund D, Ma Y, Simon-Manso Y, Hollender J, Broeckling C . Retention projection enables accurate calculation of liquid chromatographic retention times across labs and methods. J Chromatogr A. 2015; 1412:43-51. PMC: 4556278. DOI: 10.1016/j.chroma.2015.07.108. View

18.

Axen S, Huang X, Caceres E, Gendelev L, Roth B, Keiser M . A Simple Representation of Three-Dimensional Molecular Structure. J Med Chem. 2017; 60(17):7393-7409. PMC: 6075869. DOI: 10.1021/acs.jmedchem.7b00696. View

19.

Bruderer T, Varesio E, Hopfgartner G . The use of LC predicted retention times to extend metabolites identification with SWATH data acquisition. J Chromatogr B Analyt Technol Biomed Life Sci. 2017; 1071:3-10. DOI: 10.1016/j.jchromb.2017.07.016. View

20.

Blazenovic I, Kind T, Sa M, Ji J, Vaniya A, Wancewicz B . Structure Annotation of All Mass Spectra in Untargeted Metabolomics. Anal Chem. 2019; 91(3):2155-2162. PMC: 11426395. DOI: 10.1021/acs.analchem.8b04698. View