Dataset Information

MetaboRank: network-based recommendation system to interpret and enrich metabolomics results.

ABSTRACT:

Motivation

Metabolomics has shown great potential to improve the understanding of complex diseases, potentially leading to therapeutic target identification. However, no single analytical method allows monitoring all metabolites in a sample, resulting in incomplete metabolic fingerprints. This incompleteness constitutes a stumbling block to interpretation, raising the need for methods that can enrich those fingerprints. We propose MetaboRank, a new solution inspired by social network recommendation systems for the identification of metabolites potentially related to a metabolic fingerprint.

Results

MetaboRank method had been used to enrich metabolomics data obtained on cerebrospinal fluid samples from patients suffering from hepatic encephalopathy (HE). MetaboRank successfully recommended metabolites not present in the original fingerprint. The quality of recommendations was evaluated by using literature automatic search, in order to check that recommended metabolites could be related to the disease. Complementary mass spectrometry experiments and raw data analysis were performed to confirm these suggestions. In particular, MetaboRank recommended the overlooked ?-ketoglutaramate as a metabolite which should be added to the metabolic fingerprint of HE, thus suggesting that metabolic fingerprints enhancement can provide new insight on complex diseases.

Availability and implementation

Method is implemented in the MetExplore server and is available at www.metexplore.fr. A tutorial is available at https://metexplore.toulouse.inra.fr/com/tutorials/MetaboRank/2017-MetaboRank.pdf.

Supplementary information

Supplementary data are available at Bioinformatics online.

SUBMITTER: Frainay C

PROVIDER: S-EPMC6330003 | biostudies-literature | 2019 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

MetaboRank: network-based recommendation system to interpret and enrich metabolomics results.

Frainay Clément C Aros Sandrine S Chazalviel Maxime M Garcia Thomas T Vinson Florence F Weiss Nicolas N Colsch Benoit B Sedel Frédéric F Thabut Dominique D Junot Christophe C Jourdan Fabien F

Bioinformatics (Oxford, England) 20190101 2

<h4>Motivation</h4>Metabolomics has shown great potential to improve the understanding of complex diseases, potentially leading to therapeutic target identification. However, no single analytical method allows monitoring all metabolites in a sample, resulting in incomplete metabolic fingerprints. This incompleteness constitutes a stumbling block to interpretation, raising the need for methods that can enrich those fingerprints. We propose MetaboRank, a new solution inspired by social network rec ...[more]

PMID: 29982278

Similar Datasets

Project description:In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

Project description:BackgroundTraditional Chinese medicine (TCM) practitioners usually follow a 4-step evaluation process during patient diagnosis: observation, auscultation, olfaction, inquiry, pulse feeling, and palpation. The information gathered in this process, along with laboratory test results and other measurements such as vital signs, is recorded in the patient's electronic health record (EHR). In fact, all the information needed to make a treatment plan is contained in the EHR; however, only a seasoned TCM physician could use this information well to make a good treatment plan as the reasoning process is very complicated, and it takes years of practice for a medical graduate to master the reasoning skill. In this digital medicine era, with a deluge of medical data, ever-increasing computing power, and more advanced artificial neural network models, it is not only desirable but also readily possible for a computerized system to mimic the decision-making process of a TCM physician.ObjectiveThis study aims to develop an assistive tool that can predict prescriptions for inpatients in a hospital based on patients' clinical EHRs.MethodsClinical health records containing medical histories, as well as current symptoms and diagnosis information, were used to train a transformer-based neural network model using the corresponding physician's prescriptions as the target. This was accomplished by extracting relevant information, such as the patient's current illness, medicines taken, nursing care given, vital signs, examinations, and laboratory results from the patient's EHRs. The obtained information was then sorted chronologically to produce a sequence of data for the patient. These time sequence data were then used as input to a modified transformer network, which was chosen as a prescription prediction model. The output of the model was the prescription for the patient. The ultimate goal is for this tool to generate a prescription that matches what an expert TCM physician would prescribe. To alleviate the issue of overfitting, a generative adversarial network was used to augment the training sample data set by generating noise-added samples from the original training samples.ResultsIn total, 21,295 copies of inpatient electronic medical records from Guang'anmen Hospital were used in this study. These records were generated between January 2017 and December 2018, covering 6352 types of medicines. These medicines were sorted into 819 types of first-category medicines based on their class relationships. As shown by the test results, the performance of a fully trained transformer model can have an average precision rate of 80.58% and an average recall rate of 68.49%.ConclusionsAs shown by the preliminary test results, the transformer-based TCM prescription recommendation model outperformed the existing conventional methods. The extra training samples generated by the generative adversarial network help to overcome the overfitting issue, leading to further improved recall and precision rates.

Project description:Membranous glomerulonephritis (MGN) is one of the most frequent causes of nephrotic syndrome in adults. It is characterized by the thickening of the glomerular basement membrane in the renal tissue. The current diagnosis of MGN is based on renal biopsy and the detection of antibodies to the few podocyte antigens. Due to the limitations of the current diagnostic methods, including invasiveness and the lack of sensitivity of the current biomarkers, there is a requirement to identify more applicable biomarkers. The present study aimed to identify diagnostic metabolites that are involved in the development of the disease using topological features in the component‑reaction‑enzyme‑gene (CREG) network for MGN. Significant differential metabolites in MGN compared with healthy controls were identified using proton nuclear magnetic resonance and gas chromatography‑mass spectrometry techniques, and multivariate analysis. The CREG network for MGN was constructed, and metabolites with a high centrality and a striking fold‑change in patients, compared with healthy controls, were introduced as putative diagnostic biomarkers. In addition, a protein‑protein interaction (PPI) network, which was based on proteins associated with MGN, was built and analyzed using PPI analysis methods, including molecular complex detection and ClueGene Ontology. A total of 26 metabolites were identified as hub nodes in the CREG network, 13 of which had salient centrality and fold‑changes: Dopamine, carnosine, fumarate, nicotinamide D‑ribonucleotide, adenosine monophosphate, pyridoxal, deoxyguanosine triphosphate, L‑citrulline, nicotinamide, phenylalanine, deoxyuridine, tryptamine and succinate. A total of 13 subnetworks were identified using PPI analysis. In total, two of the clusters contained seed proteins (phenylalanine‑4‑hydroxlylase and cystathionine γ‑lyase) that were associated with MGN based on the CREG network. The following biological processes associated with MGN were identified using gene ontology analysis: 'Pyrimidine‑containing compound biosynthetic process', 'purine ribonucleoside metabolic process', 'nucleoside catabolic process', 'ribonucleoside metabolic process' and 'aromatic amino acid family metabolic process'. The results of the present study may be helpful in the diagnostic and therapeutic procedures of MGN. However, validation is required in the future.

Dataset Information

MetaboRank: network-based recommendation system to interpret and enrich metabolomics results.

Motivation

Results

Availability and implementation

Supplementary information

Publications

MetaboRank: network-based recommendation system to interpret and enrich metabolomics results.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets