MolDiscovery › Научные исследования в СПбГУ

Standard

MolDiscovery : learning mass spectrometry fragmentation of small molecules. / Cao, Liu; Guler, Mustafa; Tagirdzhanov, Azat; Lee, Yi Yuan; Gurevich, Alexey; Mohimani, Hosein.

в: Nature Communications, Том 12, № 1, 3718, 17.06.2021.

Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование

Author

Cao, Liu ; Guler, Mustafa ; Tagirdzhanov, Azat ; Lee, Yi Yuan ; Gurevich, Alexey ; Mohimani, Hosein. / MolDiscovery : learning mass spectrometry fragmentation of small molecules. в: Nature Communications. 2021 ; Том 12, № 1.

BibTeX

@article{5b538156c6904bac9e0c9a103d739b5c,

title = "MolDiscovery: learning mass spectrometry fragmentation of small molecules",

abstract = "Identification of small molecules is a critical task in various areas of life science. Recent advances in mass spectrometry have enabled the collection of tandem mass spectra of small molecules from hundreds of thousands of environments. To identify which molecules are present in a sample, one can search mass spectra collected from the sample against millions of molecular structures in small molecule databases. The existing approaches are based on chemistry domain knowledge, and they fail to explain many of the peaks in mass spectra of small molecules. Here, we present molDiscovery, a mass spectral database search method that improves both efficiency and accuracy of small molecule identification by learning a probabilistic model to match small molecules with their mass spectra. A search of over 8 million spectra from the Global Natural Product Social molecular networking infrastructure shows that molDiscovery correctly identify six times more unique small molecules than previous methods.",

keywords = "Algorithms, Bacteria/isolation & purification, Benchmarking, Computer Simulation, Databases, Chemical, High-Throughput Screening Assays/methods, Humans, Lipids/isolation & purification, Metabolomics/methods, Models, Statistical, Plants/metabolism, Secondary Metabolism, Small Molecule Libraries/analysis, Software, Tandem Mass Spectrometry/methods, SEARCH, DATABASES, DISCOVERY, IMPACT, GENOMICS, COMPREHENSIVE RESOURCE, SPECTRA",

author = "Liu Cao and Mustafa Guler and Azat Tagirdzhanov and Lee, {Yi Yuan} and Alexey Gurevich and Hosein Mohimani",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s).",

year = "2021",

month = jun,

day = "17",

doi = "10.1038/s41467-021-23986-0",

language = "English",

volume = "12",

journal = "Nature Communications",

issn = "2041-1723",

publisher = "Nature Publishing Group",

number = "1",

}

RIS

TY - JOUR

T1 - MolDiscovery

T2 - learning mass spectrometry fragmentation of small molecules

AU - Cao, Liu

AU - Guler, Mustafa

AU - Tagirdzhanov, Azat

AU - Lee, Yi Yuan

AU - Gurevich, Alexey

AU - Mohimani, Hosein

PY - 2021/6/17

Y1 - 2021/6/17

N2 - Identification of small molecules is a critical task in various areas of life science. Recent advances in mass spectrometry have enabled the collection of tandem mass spectra of small molecules from hundreds of thousands of environments. To identify which molecules are present in a sample, one can search mass spectra collected from the sample against millions of molecular structures in small molecule databases. The existing approaches are based on chemistry domain knowledge, and they fail to explain many of the peaks in mass spectra of small molecules. Here, we present molDiscovery, a mass spectral database search method that improves both efficiency and accuracy of small molecule identification by learning a probabilistic model to match small molecules with their mass spectra. A search of over 8 million spectra from the Global Natural Product Social molecular networking infrastructure shows that molDiscovery correctly identify six times more unique small molecules than previous methods.

AB - Identification of small molecules is a critical task in various areas of life science. Recent advances in mass spectrometry have enabled the collection of tandem mass spectra of small molecules from hundreds of thousands of environments. To identify which molecules are present in a sample, one can search mass spectra collected from the sample against millions of molecular structures in small molecule databases. The existing approaches are based on chemistry domain knowledge, and they fail to explain many of the peaks in mass spectra of small molecules. Here, we present molDiscovery, a mass spectral database search method that improves both efficiency and accuracy of small molecule identification by learning a probabilistic model to match small molecules with their mass spectra. A search of over 8 million spectra from the Global Natural Product Social molecular networking infrastructure shows that molDiscovery correctly identify six times more unique small molecules than previous methods.

KW - Algorithms

KW - Bacteria/isolation & purification

KW - Benchmarking

KW - Computer Simulation

KW - Databases, Chemical

KW - High-Throughput Screening Assays/methods

KW - Humans

KW - Lipids/isolation & purification

KW - Metabolomics/methods

KW - Models, Statistical

KW - Plants/metabolism

KW - Secondary Metabolism

KW - Small Molecule Libraries/analysis

KW - Software

KW - Tandem Mass Spectrometry/methods

KW - SEARCH

KW - DATABASES

KW - DISCOVERY

KW - IMPACT

KW - GENOMICS

KW - COMPREHENSIVE RESOURCE

KW - SPECTRA

UR - http://www.scopus.com/inward/record.url?scp=85108167749&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/e5781f2a-c192-3f57-bcea-01d517f1a63a/

U2 - 10.1038/s41467-021-23986-0

DO - 10.1038/s41467-021-23986-0

M3 - Article

C2 - 34140479

AN - SCOPUS:85108167749

VL - 12

JO - Nature Communications

JF - Nature Communications

SN - 2041-1723

IS - 1

M1 - 3718

ER -

ID: 84852016

MolDiscovery: learning mass spectrometry fragmentation of small molecules

Standard

Harvard

APA

Vancouver

Author

BibTeX

RIS