ADAPTIVE: leArning DAta-dePendenT, concIse molecular VEctors for fast, accurate metabolite identification from tandem mass spectra

Abstract

Motivation Metabolite identification is an important task in metabolomics to enhance the knowledge of biological systems. There have been a number of machine learning-based methods proposed for this task, which predict a chemical structure of a given spectrum through an intermediate (chemical structure) representation called molecular fingerprints. They usually have two steps: (i) predicting fingerprints from spectra; (ii) searching chemical compounds (in database) corresponding to the predicted fingerprints. Fingerprints are feature vectors, which are usually very large to cover all possible substructures and chemical properties, and therefore heavily redundant, in the sense of having many molecular (sub)structures irrelevant to the task, causing limited predictive performance and slow prediction. Results We propose ADAPTIVE, which has two parts: learning two mappings (i) from structures to molecular vectors and (ii) from spectra to molecular vectors. The first part learns molecular vectors for metabolites from given data, to be consistent with both spectra and chemical structures of metabolites. In more detail, molecular vectors are generated by a model, being parameterized by a message passing neural network, and parameters are estimated by maximizing the correlation between molecular vectors and the corresponding spectra in terms of Hilbert-Schmidt Independence Criterion. Molecular vectors generated by this model are compact and importantly adaptive (specific) to both given data and task of metabolite identification. The second part uses input output kernel regression (IOKR), the current cutting-edge method of metabolite identification. We empirically confirmed the effectiveness of ADAPTIVE by using a benchmark data, where ADAPTIVE outperformed the original IOKR in both predictive performance and computational efficiency. Availability and implementation The code will be accessed through http://www.bic.kyoto-u.ac.jp/pathway/tools/ADAPTIVE after the acceptance of this article.

Recent Developments along the Analytical Process for Metabolomics Workflows

“…Recently, a new type of relevant and promising information has been included in some tools: the biological relationships between different metabolites in an organism (MassTRIX, GNPS, xMSannotator, BioCAn, NAP, ADAPTIVE, MetDNA, MolNetEnhancer, or MetNet) (see Figure , category 4). In the last 2 years, new metabolite identification tools have explored this approach, discarding the putative annotations not related to the other features and including evidence to confirm the annotations based on a significant number of connections among all the features present in a sample.…”

Network-based strategies in metabolomics data analysis and interpretation: from molecular networking to biological interpretation

“…Moreover, the recent success of molecular networking strategies has fired an exciting search for new methods of establishing structural relationships between mass spectra features. The recent development of MS2LDA [72] is a great example of how alternative metrics can be complementary to the already well-established spectra similarity, and the popularization of machine learning algorithms is providing some promising results in this area [123,124].…”

Probabilistic framework for integration of mass spectrum and retention time information in small molecule identification

“…In recent years, numerous powerful approaches ( Nguyen et al , 2018a ; Schymanski et al., 2017 ) to predict molecular structure annotations for MS 2 spectra have been developed ( Allen et al , 2014 ; Brouard et al , 2016 ; Dührkop et al , 2015 , 2019 ; Nguyen et al., 2018 b, 2019 ; Ruttkies et al., 2016 , 2019 ). Typically, these methods output a ranked list of molecular structure candidates, that can be shown to human experts, or further post-processed, e.g.…”