Filters








769 Hits in 6.6 sec

Identification of metabolites from tandem mass spectra with a machine learning approach utilizing structural features

2019 Bioinformatics  
However, fast and accurate identification of the metabolites' structures from MS/MS spectra is still a great challenge.  ...  Untargeted mass spectrometry (MS/MS) is a powerful method for detecting metabolites in biological samples.  ...  assistance with the benchmark dataset, and Yan Ping Yuan for IT support.  ... 
doi:10.1093/bioinformatics/btz736 pmid:31605112 pmcid:PMC7703789 fatcat:ix4gmusqkndbvolrr4x6twavni

Identification of metabolites from tandem mass spectra with a machine learning approach utilizing structural features [article]

Yuanyue Li, Michael Kuhn, Anne-Claude Gavin, Peer Bork
2019 bioRxiv   pre-print
However, fast and accurate identification of the metabolites' structures from MS/MS spectra is still a great challenge.  ...  Untargeted mass spectrometry is a powerful method for detecting metabolites in biological samples.  ...  Here, we describe a new method called SF-Matching (SubFragment-Matching) to predict likely peaks in tandem mass spectra for small molecules using a machine learning approach.  ... 
doi:10.1101/573790 fatcat:rpkuju4utrhuhoq4denekryqlm

Metabolite identification and molecular fingerprint prediction through machine learning

M. Heinonen, H. Shen, N. Zamboni, J. Rousu
2012 Bioinformatics  
Results: We introduce a novel framework for prediction of molecular characteristics and identification of metabolites from tandem mass spectra using machine learning with the support vector machine.  ...  Our approach is to first predict a large set of molecular properties of the unknown metabolite from salient tandem mass spectral signals, and in the second step to use the predicted properties for matching  ...  Machine learning approaches for metabolite identification from MS/MS data have not been widely studied.  ... 
doi:10.1093/bioinformatics/bts437 pmid:22815355 fatcat:rb5uw7fq75dgznbwd3uvs4opqa

Software Tools and Approaches for Compound Identification of LC-MS/MS Data in Metabolomics

Ivana Blaženović, Tobias Kind, Jian Ji, Oliver Fiehn
2018 Metabolites  
The annotation of small molecules remains a major challenge in untargeted mass spectrometry-based metabolomics.  ...  Furthermore, the use of retention time models from liquid chromatography and the utility of collision cross-section modelling from ion mobility experiments are covered.  ...  It is based on a machine-learning approach including chemical rules andva is available for ESI MS/MS data as well as EI mass spectra.  ... 
doi:10.3390/metabo8020031 pmid:29748461 pmcid:PMC6027441 fatcat:lozwgydywrhvrctkxmemdmanxm

Recent advances and prospects of computational methods for metabolite identification: a review with emphasis on machine learning approaches

Dai Hai Nguyen, Canh Hao Nguyen, Hiroshi Mamitsuka
2018 Briefings in Bioinformatics  
Over many decades, many techniques with different approaches have been proposed for MS-based metabolite identification task, which can be divided into the following four groups: mass spectra database,  ...  In this review paper, we thoroughly survey currently available tools for metabolite identification with the focus on in silico fragmentation, and machine learning-based approaches.  ...  Machine learning-based metabolite identification Recently, several machine learning frameworks have been introduced to deal with the task of metabolite identification.  ... 
doi:10.1093/bib/bby066 pmid:30099485 fatcat:zqdzozintjayznjctttqn3nldi

Annotation: A Computational Solution for Streamlining Metabolomics Analysis

Xavier Domingo-Almenara, J. Rafael Montenegro-Burke, H. Paul Benton, Gary Siuzdak
2017 Analytical Chemistry  
For this reason, computational annotation is used to reveal the underlying metabolites monoisotopic masses, improving putative identification in addition to confirmation with tandem mass spectrometry.  ...  from each metabolite; (ii) annotation using ion adduction and mass distance among ion peaks; (iii) incorporation of biological knowledge such as biotransformations or pathways; (iv) tandem MS data; and  ...  Acknowledgments This work was partially supported by Ecosystems and Networks Integrated with Genes and Molecular Assemblies  ... 
doi:10.1021/acs.analchem.7b03929 pmid:29039932 pmcid:PMC5750104 fatcat:3m5ce4ltgrexbjkxcnoyejniui

Fast metabolite identification with Input Output Kernel Regression

Céline Brouard, Huibin Shen, Kai Dührkop, Florence d'Alché-Buc, Sebastian Böcker, Juho Rousu
2016 Bioinformatics  
In this work we propose to address the metabolite identification problem using a structured output prediction approach.  ...  Results: We use the Input Output Kernel Regression method to learn the mapping between tandem mass spectra and molecular structures.  ...  Conflict of Interest: none declared.  ... 
doi:10.1093/bioinformatics/btw246 pmid:27307628 pmcid:PMC4908330 fatcat:jvky2s7f6rcuvgovzhmnpcnkqe

Current status of retention time prediction in metabolite identification

Michael Witting, Sebastian Böcker
2020 Journal of Separation Science  
Metabolite identification is a crucial step in non-targeted metabolomics, but also represents one of its current bottlenecks.  ...  Here, we review the current state of retention time prediction in liquid chromatography-mass spectrometry-based metabolomics, with a focus on publications published after 2010.  ...  Evaluation of different machine learning approaches In most cases of published QSRR approaches for metabolomics, only one or two machine learning approaches are used for prediction.  ... 
doi:10.1002/jssc.202000060 pmid:32144942 fatcat:ek32njbvbbckjfm6icc4rgofby

Computational mass spectrometry for small molecules

Kerstin Scheubert, Franziska Hufsky, Sebastian Böcker
2013 Journal of Cheminformatics  
The identification of small molecules from mass spectrometry (MS) data remains a major challenge in the interpretation of MS data.  ...  This review covers the computational aspects of identifying small molecules, from the identification of a compound searching a reference spectral library, to the structural elucidation of unknowns.  ...  System (STIRS) [158] mixes a rule-based approach with some early machine learning techniques to obtain structural information from related EI spectra.  ... 
doi:10.1186/1758-2946-5-12 pmid:23453222 pmcid:PMC3648359 fatcat:r2l2i3tfi5hqfm7iidqxsza25e

Metabolite Identification through Machine Learning— Tackling CASMI Challenge Using FingerID

Huibin Shen, Nicola Zamboni, Markus Heinonen, Juho Rousu
2013 Metabolites  
Recent efforts in assembling large public mass spectral databases such as MassBank have opened the door for developing a new genre of metabolite identification methods that rely on machine learning as  ...  In short, FingerID learns to predict molecular fingerprints from a large collection of MS/MS spectra, and uses the predicted fingerprints to retrieve and rank candidate molecules from a given large molecular  ...  Acknowledgements This work was funded by the Academy of Finland grant 118653 (ALGODAN CoE) and in part by the IST Programme of the European Community, under the PASCAL2 Network of Excellence, IST-2007-  ... 
doi:10.3390/metabo3020484 pmid:24958002 pmcid:PMC3901273 fatcat:edvajxfbbrairaj6hy2rixslui

Supervised topic modeling for predicting molecular substructure from mass spectrometry

Gabriel K. Reder, Adamo Young, Jaan Altosaar, Jakub Rajniak, Noémie Elhadad, Michael Fischbach, Susan Holmes
2021 F1000Research  
A workhorse method for characterizing individual molecules in such untargeted metabolomics studies is tandem mass spectrometry (MS/MS).  ...  MS/MS spectra provide rich information about chemical composition. However, structural characterization from spectra corresponding to unknown molecules remains a bottleneck in metabolomics.  ...  Substructure identification benchmark As the output of machine learning methods for mass spectrometry data is typically inspected by a human in an experimental procedure, developing interpretable methods  ... 
doi:10.12688/f1000research.52549.1 fatcat:c7qfz4pvbngplo2eqtkfxj764i

METLIN: A Technology Platform for Identifying Knowns and Unknowns

Carlos Guijas, J. Rafael Montenegro-Burke, Xavier Domingo-Almenara, Amelia Palermo, Benedikt Warth, Gerrit Hermann, Gunda Koellensperger, Tao Huan, Winnie Uritboonthai, Aries E. Aisporna, Dennis W. Wolan, Mary E. Spilker (+2 others)
2018 Analytical Chemistry  
METLIN's high-resolution tandem mass spectrometry (MS/MS) database, which plays a key role in the identification process, has data generated from both reference standards and their labeled stable isotope  ...  METLIN originated as a database to characterize known metabolites and has since expanded into a technology platform for the identification of known and unknown metabolites and other chemical entities.  ...  ), a Scientific Focus Area Program at Lawrence Berkeley Laboratory for the U.S.  ... 
doi:10.1021/acs.analchem.7b04424 pmid:29381867 pmcid:PMC5933435 fatcat:xsikz52gifgd3p4ngcvd4kjhea

Linking genomics and metabolomics to chart specialized metabolic diversity

Justin J J van der Hooft, Hosein Mohimani, Anelize Bauermeister, Pieter C Dorrestein, Katherine R Duncan, Marnix H Medema
2020 Chemical Society Reviews  
Traditionally, the main discovery strategies have centered around the use of activity-guided fractionation of metabolite extracts.  ...  In recent years, genomic and metabolomic analyses of specialized metabolic diversity have been scaled up to study thousands of samples simultaneously.  ...  Other approaches use machine learning. For example, CSI:FingerID, enables the generation of fragmentation trees to match MS/MS spectra to candidate structures using support vector machines.  ... 
doi:10.1039/d0cs00162g pmid:32393943 fatcat:jjkyiefpsrdr5lpj5f6jjyyxnm

Workflows for automated downstream data analysis and visualization in large-scale computational mass spectrometry

Stephan Aiche, Timo Sachsenberg, Erhan Kenar, Mathias Walzer, Bernd Wiswedel, Theresa Kristl, Matthew Boyles, Albert Duschl, Christian G. Huber, Michael R. Berthold, Knut Reinert, Oliver Kohlbacher
2015 Proteomics  
label-free quantitation and identification of metabolites, and quality control for proteomics experiments.  ...  MS-based proteomics and metabolomics are rapidly evolving research fields driven by the development of novel instruments, experimental approaches, and analysis methods.  ...  approach [11] , and afterwards combines the identifications with the quantitative information extracted from the tandem mass tags reporter ions.  ... 
doi:10.1002/pmic.201400391 pmid:25604327 pmcid:PMC4415483 fatcat:d24pgxfo2nbohi5rwivnjcxsju

Managing of Unassigned Mass Spectrometric Data by Neural Network for Cancer Phenotypes Classification

Denis V. Petrovsky, Arthur T. Kopylov, Vladimir R. Rudnev, Alexander A. Stepanov, Liudmila I. Kulikova, Kristina A. Malsagova, Anna L. Kaysheva
2021 Journal of Personalized Medicine  
The development of machine learning methods for the intelligent analysis of raw mass spectrometric (HPLC-MS/MS) measurements without involving the stages of preprocessing and data identification seems  ...  However, the weak efficiency of computational algorithms in correlating tandem spectra to molecular components (proteins and metabolites) dramatically limits the use of "omics" profiling for the classification  ...  Conflicts of Interest: The authors declare no conflict of interest. The funder had a role in the samples collection and code development.  ... 
doi:10.3390/jpm11121288 pmid:34945760 pmcid:PMC8707435 fatcat:bne4mdol5fhjxmvymt6ycybuki
« Previous Showing results 1 — 15 out of 769 results