Literature DB >> 32997169

MetFID: artificial neural network-based compound fingerprint prediction for metabolite annotation.

Ziling Fan1, Amber Alley2, Kian Ghaffari2, Habtom W Ressom3.   

Abstract

INTRODUCTION: Metabolite annotation is a critical and challenging step in mass spectrometry-based metabolomic profiling. In a typical untargeted MS/MS-based metabolomic study, experimental MS/MS spectra are matched against those in spectral libraries for metabolite annotation. Yet, existing spectral libraries comprise merely a marginal percentage of known compounds.
OBJECTIVE: The objective is to develop a method that helps rank putative metabolite IDs for analytes whose reference MS/MS spectra are not present in spectral libraries.
METHODS: We introduce MetFID, which uses an artificial neural network (ANN) trained for predicting molecular fingerprints based on experimental MS/MS data. To narrow the search space, MetFID retrieves candidates from metabolite databases using molecular formula or m/z value of the precursor ions of the analytes. The candidate whose fingerprint is most analogous to the predicted fingerprint is used for metabolite annotation. A comprehensive evaluation was performed by training MetFID using MS/MS spectra from the MoNA repository and NIST library and by testing with structure-disjoint MS/MS spectra from the NIST library, the CASMI 2016 dataset, and in-house MS/MS data from a cancer biomarker discovery study.
RESULTS: We observed that training separate models for distinct ranges of collision energies enhanced model performance compared to a single model that covers a wide range of collision energies. Using MetaboQuest to retrieve candidates, MetFID prioritized the correct putative ID in the first place rank for about 50% of the testing cases. Through the independent testing dataset, we demonstrated that MetFID has the potential to improve the accuracy of ranking putative metabolite IDs by more than 5% compared to other tools such as ChemDistiller, CSI:FingerID, and MetFrag.
CONCLUSION: MetFID offers a promising opportunity to enhance the accuracy of metabolite annotation by using ANN for molecular fingerprint prediction.

Entities:  

Keywords:  Artificial neural network; Metabolite identification; Metabolomics; Molecular fingerprint

Mesh:

Year:  2020        PMID: 32997169      PMCID: PMC9547616          DOI: 10.1007/s11306-020-01726-7

Source DB:  PubMed          Journal:  Metabolomics        ISSN: 1573-3882            Impact factor:   4.747


  30 in total

1.  MassBank: a public repository for sharing mass spectral data for life sciences.

Authors:  Hisayuki Horai; Masanori Arita; Shigehiko Kanaya; Yoshito Nihei; Tasuku Ikeda; Kazuhiro Suwa; Yuya Ojima; Kenichi Tanaka; Satoshi Tanaka; Ken Aoshima; Yoshiya Oda; Yuji Kakazu; Miyako Kusano; Takayuki Tohge; Fumio Matsuda; Yuji Sawada; Masami Yokota Hirai; Hiroki Nakanishi; Kazutaka Ikeda; Naoshige Akimoto; Takashi Maoka; Hiroki Takahashi; Takeshi Ara; Nozomu Sakurai; Hideyuki Suzuki; Daisuke Shibata; Steffen Neumann; Takashi Iida; Ken Tanaka; Kimito Funatsu; Fumito Matsuura; Tomoyoshi Soga; Ryo Taguchi; Kazuki Saito; Takaaki Nishioka
Journal:  J Mass Spectrom       Date:  2010-07       Impact factor: 1.982

2.  Target-decoy approach and false discovery rate: when things may go wrong.

Authors:  Nitin Gupta; Nuno Bandeira; Uri Keich; Pavel A Pevzner
Journal:  J Am Soc Mass Spectrom       Date:  2011-05-05       Impact factor: 3.109

3.  SIRIUS 4: a rapid tool for turning tandem mass spectra into metabolite structure information.

Authors:  Kai Dührkop; Markus Fleischauer; Marcus Ludwig; Alexander A Aksenov; Alexey V Melnik; Marvin Meusel; Pieter C Dorrestein; Juho Rousu; Sebastian Böcker
Journal:  Nat Methods       Date:  2019-03-18       Impact factor: 28.547

4.  MetFusion: integration of compound identification strategies.

Authors:  Michael Gerlich; Steffen Neumann
Journal:  J Mass Spectrom       Date:  2013-03       Impact factor: 1.982

5.  Metabolomic Analysis of Liver Tissues for Characterization of Hepatocellular Carcinoma.

Authors:  Alessia Ferrarini; Cristina Di Poto; Shisi He; Chao Tu; Rency S Varghese; Abdalla Kara Balla; Meth Jayatilake; Zhenzhi Li; Kian Ghaffari; Ziling Fan; Zaki A Sherif; Deepak Kumar; Alexander Kroemer; Mahlet G Tadesse; Habtom W Ressom
Journal:  J Proteome Res       Date:  2019-07-01       Impact factor: 4.466

Review 6.  A rough guide to metabolite identification using high resolution liquid chromatography mass spectrometry in metabolomic profiling in metazoans.

Authors:  David G Watson
Journal:  Comput Struct Biotechnol J       Date:  2013-02-15       Impact factor: 7.271

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

Authors:  Yuanyue Li; Michael Kuhn; Anne-Claude Gavin; Peer Bork
Journal:  Bioinformatics       Date:  2020-02-15       Impact factor: 6.937

8.  ChemDistiller: an engine for metabolite annotation in mass spectrometry.

Authors:  Ivan Laponogov; Noureddin Sadawi; Dieter Galea; Reza Mirnezami; Kirill A Veselkov
Journal:  Bioinformatics       Date:  2018-06-15       Impact factor: 6.937

9.  Computational mass spectrometry for small molecules.

Authors:  Kerstin Scheubert; Franziska Hufsky; Sebastian Böcker
Journal:  J Cheminform       Date:  2013-03-01       Impact factor: 5.514

10.  MetFrag relaunched: incorporating strategies beyond in silico fragmentation.

Authors:  Christoph Ruttkies; Emma L Schymanski; Sebastian Wolf; Juliane Hollender; Steffen Neumann
Journal:  J Cheminform       Date:  2016-01-29       Impact factor: 5.514

View more
  5 in total

1.  Deep kernel learning improves molecular fingerprint prediction from tandem mass spectra.

Authors:  Kai Dührkop
Journal:  Bioinformatics       Date:  2022-06-24       Impact factor: 6.931

Review 2.  New software tools, databases, and resources in metabolomics: updates from 2020.

Authors:  Biswapriya B Misra
Journal:  Metabolomics       Date:  2021-05-11       Impact factor: 4.290

3.  Convolutional Neural Network-Based Compound Fingerprint Prediction for Metabolite Annotation.

Authors:  Shijinqiu Gao; Hoi Yan Katharine Chau; Kuijun Wang; Hongyu Ao; Rency S Varghese; Habtom W Ressom
Journal:  Metabolites       Date:  2022-06-29

Review 4.  Strategies for structure elucidation of small molecules based on LC-MS/MS data from complex biological samples.

Authors:  Zhitao Tian; Fangzhou Liu; Dongqin Li; Alisdair R Fernie; Wei Chen
Journal:  Comput Struct Biotechnol J       Date:  2022-09-07       Impact factor: 6.155

5.  Comparative Analysis of Binary Similarity Measures for Compound Identification in MassSpectrometry-Based Metabolomics.

Authors:  Seongho Kim; Ikuko Kato; Xiang Zhang
Journal:  Metabolites       Date:  2022-07-26
  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.