Dataset Information

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

ABSTRACT: Motivation: Untargeted mass spectrometry (MS/MS) is a powerful method for detecting metabolites in biological samples. However, fast and accurate identification of the metabolites' structures from MS/MS spectra is still a great challenge.

Results: We present a new analysis method, called SubFragment-Matching (SF-Matching) that is based on the hypothesis that molecules with similar structural features will exhibit similar fragmentation patterns. We combine information on fragmentation patterns of molecules with shared substructures and then use random forest models to predict whether a given structure can yield a certain fragmentation pattern. These models can then be used to score candidate molecules for a given mass spectrum. For rapid identification, we pre-compute such scores for common biological molecular structure databases. Using benchmarking datasets, we find that our method has similar performance to CSI: FingerID and those very high accuracies can be achieved by combining our method with CSI: FingerID. Rarefaction analysis of the training dataset shows that the performance of our method will increase as more experimental data become available.

Availability and implementation: SF-Matching is available from http://www.bork.embl.de/Docu/sf_matching.

Supplementary information: Supplementary data are available at Bioinformatics online.

SUBMITTER: Li Y

PROVIDER: S-EPMC7703789 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Li Yuanyue Y Kuhn Michael M Gavin Anne-Claude AC Bork Peer P

Bioinformatics (Oxford, England) 20200201 4

<h4>Motivation</h4>Untargeted mass spectrometry (MS/MS) is a powerful method for detecting metabolites in biological samples. However, fast and accurate identification of the metabolites' structures from MS/MS spectra is still a great challenge.<h4>Results</h4>We present a new analysis method, called SubFragment-Matching (SF-Matching) that is based on the hypothesis that molecules with similar structural features will exhibit similar fragmentation patterns. We combine information on fragmentatio ...[more]

PMID: 31605112

Similar Datasets

Project description:PurposeComputed tomography (CT) is an effective method for detecting and characterizing lung nodules in vivo. With the growing use of chest CT, the detection frequency of lung nodules is increasing. Noninvasive methods to distinguish malignant from benign nodules have the potential to decrease the clinical burden, risk, and cost involved in follow-up procedures on the large number of false-positive lesions detected. This study examined the benefit of including perinodular parenchymal features in machine learning (ML) tools for pulmonary nodule assessment.MethodsLung nodule cases with pathology confirmed diagnosis (74 malignant, 289 benign) were used to extract quantitative imaging characteristics from computed tomography scans of the nodule and perinodular parenchyma tissue. A ML tool development pipeline was employed using k-medoids clustering and information theory to determine efficient predictor sets for different amounts of parenchyma inclusion and build an artificial neural network classifier. The resulting ML tool was validated using an independent cohort (50 malignant, 50 benign).ResultsThe inclusion of parenchymal imaging features improved the performance of the ML tool over exclusively nodular features (P < 0.01). The best performing ML tool included features derived from nodule diameter-based surrounding parenchyma tissue quartile bands. We demonstrate similar high-performance values on the independent validation cohort (AUC-ROC = 0.965). A comparison using the independent validation cohort with the Fleischner pulmonary nodule follow-up guidelines demonstrated a theoretical reduction in recommended follow-up imaging and procedures.ConclusionsRadiomic features extracted from the parenchyma surrounding lung nodules contain valid signals with spatial relevance for the task of lung cancer risk classification. Through standardization of feature extraction regions from the parenchyma, ML tool validation performance of 100% sensitivity and 96% specificity was achieved.

Project description:Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of > 100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model's prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets