Deep learning meets metabolomics: a methodological perspective

2020 ◽  
Author(s):  
Partho Sen ◽  
Santosh Lamichhane ◽  
Vivek B Mathema ◽  
Aidan McGlinchey ◽  
Alex M Dickens ◽  
...  
Keyword(s):  
Deep Learning ◽  
Biomarker Discovery ◽  
Metabolite Identification ◽  
Metabolomics Data ◽  
Metabolic Phenotyping ◽  
Metabolic Modelling ◽  
Actionable Knowledge ◽  
The Past ◽  
Genome Scale ◽  
Biological Outcomes

Abstract Deep learning (DL), an emerging area of investigation in the fields of machine learning and artificial intelligence, has markedly advanced over the past years. DL techniques are being applied to assist medical professionals and researchers in improving clinical diagnosis, disease prediction and drug discovery. It is expected that DL will help to provide actionable knowledge from a variety of ‘big data’, including metabolomics data. In this review, we discuss the applicability of DL to metabolomics, while presenting and discussing several examples from recent research. We emphasize the use of DL in tackling bottlenecks in metabolomics data acquisition, processing, metabolite identification, as well as in metabolic phenotyping and biomarker discovery. Finally, we discuss how DL is used in genome-scale metabolic modelling and in interpretation of metabolomics data. The DL-based approaches discussed here may assist computational biologists with the integration, prediction and drawing of statistical inference about biological outcomes, based on metabolomics data.

scholarly journals Metabolomics for personalized medicine: the input of analytical chemistry from biomarker discovery to point-of-care tests

2021 ◽  
Author(s):  
Florence Anne Castelli ◽  
Giulio Rosati ◽  
Christian Moguet ◽  
Celia Fuentes ◽  
Jose Marrugo-Ramírez ◽  
...  
Keyword(s):  
Analytical Chemistry ◽  
Personalized Medicine ◽  
Large Scale ◽  
Biomarker Discovery ◽  
Point Of Care ◽  
Metabolite Identification ◽  
Individual Characteristics ◽  
Molecular Signatures ◽  
Laboratory Equipment ◽  
Metabolomics Data

AbstractMetabolomics refers to the large-scale detection, quantification, and analysis of small molecules (metabolites) in biological media. Although metabolomics, alone or combined with other omics data, has already demonstrated its relevance for patient stratification in the frame of research projects and clinical studies, much remains to be done to move this approach to the clinical practice. This is especially true in the perspective of being applied to personalized/precision medicine, which aims at stratifying patients according to their risk of developing diseases, and tailoring medical treatments of patients according to individual characteristics in order to improve their efficacy and limit their toxicity. In this review article, we discuss the main challenges linked to analytical chemistry that need to be addressed to foster the implementation of metabolomics in the clinics and the use of the data produced by this approach in personalized medicine. First of all, there are already well-known issues related to untargeted metabolomics workflows at the levels of data production (lack of standardization), metabolite identification (small proportion of annotated features and identified metabolites), and data processing (from automatic detection of features to multi-omic data integration) that hamper the inter-operability and reusability of metabolomics data. Furthermore, the outputs of metabolomics workflows are complex molecular signatures of few tens of metabolites, often with small abundance variations, and obtained with expensive laboratory equipment. It is thus necessary to simplify these molecular signatures so that they can be produced and used in the field. This last point, which is still poorly addressed by the metabolomics community, may be crucial in a near future with the increased availability of molecular signatures of medical relevance and the increased societal demand for participatory medicine. Graphical abstract

scholarly journals From Samples to Insights into Metabolism: Uncovering Biologically Relevant Information in LC-HRMS Metabolomics Data

Metabolites ◽  
2019 ◽  
Vol 9 (12) ◽  
pp. 308 ◽  
Author(s):  
Julijana Ivanisevic ◽  
Elizabeth J. Want
Keyword(s):  
Statistical Power ◽  
Biomarker Discovery ◽  
Disease Onset ◽  
Metabolite Identification ◽  
Holistic Approach ◽  
Data Interpretation ◽  
Relevant Information ◽  
Metabolomics Data ◽  
Biologically Relevant ◽  
Key Steps

Untargeted metabolomics (including lipidomics) is a holistic approach to biomarker discovery and mechanistic insights into disease onset and progression, and response to intervention. Each step of the analytical and statistical pipeline is crucial for the generation of high-quality, robust data. Metabolite identification remains the bottleneck in these studies; therefore, confidence in the data produced is paramount in order to maximize the biological output. Here, we outline the key steps of the metabolomics workflow and provide details on important parameters and considerations. Studies should be designed carefully to ensure appropriate statistical power and adequate controls. Subsequent sample handling and preparation should avoid the introduction of bias, which can significantly affect downstream data interpretation. It is not possible to cover the entire metabolome with a single platform; therefore, the analytical platform should reflect the biological sample under investigation and the question(s) under consideration. The large, complex datasets produced need to be pre-processed in order to extract meaningful information. Finally, the most time-consuming steps are metabolite identification, as well as metabolic pathway and network analysis. Here we discuss some widely used tools and the pitfalls of each step of the workflow, with the ultimate aim of guiding the reader towards the most efficient pipeline for their metabolomics studies.

scholarly journals MetPC: Metabolite Pipeline Consisting of Metabolite Identification and Biomarker Discovery Under the Control of Two-Dimensional FDR

Metabolites ◽  
2019 ◽  
Vol 9 (5) ◽  
pp. 103
Author(s):  
Jaehwi Kim ◽  
Jaesik Jeong
Keyword(s):  
Expectation Maximization ◽  
Latent Variables ◽  
Biomarker Discovery ◽  
Metabolite Identification ◽  
Two Dimensional ◽  
Bioinformatics Tool ◽  
Metabolomics Data ◽  
False Discovery ◽  
Hierarchical Statistical Model ◽  
Complex Features

Due to the complex features of metabolomics data, the development of a unified platform, which covers preprocessing steps to data analysis, has been in high demand over the last few decades. Thus, we developed a new bioinformatics tool that includes a few of preprocessing steps and biomarker discovery procedure. For metabolite identification, we considered a hierarchical statistical model coupled with an Expectation–Maximization (EM) algorithm to take care of latent variables. For biomarker metabolite discovery, our procedure controls two-dimensional false discovery rate (fdr2d) when testing for multiple hypotheses simultaneously.

Artificial Intelligence and Human Rights: Four Realms of Discussion: Summary of Remarks

2020 ◽  
Vol 114 ◽  
pp. 242-245
Author(s):  
Jootaek Lee
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Decision Making ◽  
Deep Learning ◽  
Language Processing ◽  
Human Reasoning ◽  
The Past ◽  
Making Choices ◽  
Data Capturing ◽  
Intensive Procedures

The term, Artificial Intelligence (AI), has changed since it was first coined by John MacCarthy in 1956. AI, believed to have been created with Kurt Gödel's unprovable computational statements in 1931, is now called deep learning or machine learning. AI is defined as a computer machine with the ability to make predictions about the future and solve complex tasks, using algorithms. The AI algorithms are enhanced and become effective with big data capturing the present and the past while still necessarily reflecting human biases into models and equations. AI is also capable of making choices like humans, mirroring human reasoning. AI can help robots to efficiently repeat the same labor intensive procedures in factories and can analyze historic and present data efficiently through deep learning, natural language processing, and anomaly detection. Thus, AI covers a spectrum of augmented intelligence relating to prediction, autonomous intelligence relating to decision making, automated intelligence for labor robots, and assisted intelligence for data analysis.

scholarly journals Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3046
Author(s):  
Shervin Minaee ◽  
Mehdi Minaei ◽  
Amirali Abdolrashidi
Keyword(s):  
Deep Learning ◽  
Facial Expression ◽  
Facial Expression Recognition ◽  
Expression Recognition ◽  
Visualization Technique ◽  
Convolutional Network ◽  
The Past ◽  
Multiple Datasets ◽  
The Face ◽  
Traditional Approaches

Facial expression recognition has been an active area of research over the past few decades, and it is still challenging due to the high intra-class variation. Traditional approaches for this problem rely on hand-crafted features such as SIFT, HOG, and LBP, followed by a classifier trained on a database of images or videos. Most of these works perform reasonably well on datasets of images captured in a controlled condition but fail to perform as well on more challenging datasets with more image variation and partial faces. In recent years, several works proposed an end-to-end framework for facial expression recognition using deep learning models. Despite the better performance of these works, there are still much room for improvement. In this work, we propose a deep learning approach based on attentional convolutional network that is able to focus on important parts of the face and achieves significant improvement over previous models on multiple datasets, including FER-2013, CK+, FERG, and JAFFE. We also use a visualization technique that is able to find important facial regions to detect different emotions based on the classifier’s output. Through experimental results, we show that different emotions are sensitive to different parts of the face.

scholarly journals Integration of machine learning and genome-scale metabolic modeling identifies multi-omics biomarkers for radiation resistance

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Joshua E. Lewis ◽  
Melissa L. Kemp
Keyword(s):  
Machine Learning ◽  
Metabolic Flux ◽  
Metabolic Modeling ◽  
The Cancer Genome Atlas ◽  
Radiation Response ◽  
Metabolomics Data ◽  
Machine Learning Classifiers ◽  
Learning Classifiers ◽  
Metabolic Biomarkers ◽  
Genome Scale

AbstractResistance to ionizing radiation, a first-line therapy for many cancers, is a major clinical challenge. Personalized prediction of tumor radiosensitivity is not currently implemented clinically due to insufficient accuracy of existing machine learning classifiers. Despite the acknowledged role of tumor metabolism in radiation response, metabolomics data is rarely collected in large multi-omics initiatives such as The Cancer Genome Atlas (TCGA) and consequently omitted from algorithm development. In this study, we circumvent the paucity of personalized metabolomics information by characterizing 915 TCGA patient tumors with genome-scale metabolic Flux Balance Analysis models generated from transcriptomic and genomic datasets. Metabolic biomarkers differentiating radiation-sensitive and -resistant tumors are predicted and experimentally validated, enabling integration of metabolic features with other multi-omics datasets into ensemble-based machine learning classifiers for radiation response. These multi-omics classifiers show improved classification accuracy, identify clinical patient subgroups, and demonstrate the utility of personalized blood-based metabolic biomarkers for radiation sensitivity. The integration of machine learning with genome-scale metabolic modeling represents a significant methodological advancement for identifying prognostic metabolite biomarkers and predicting radiosensitivity for individual patients.

scholarly journals Feature Extraction for Finger-Vein-Based Identity Recognition

2021 ◽  
Vol 7 (5) ◽  
pp. 89
Author(s):  
George K. Sidiropoulos ◽  
Polixeni Kiratsa ◽  
Petros Chatzipetrou ◽  
George A. Papakostas
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Extraction Methods ◽  
Identity Recognition ◽  
Learning Framework ◽  
Finger Vein ◽  
The Past ◽  
Biometric Systems ◽  
Vein Recognition ◽  
Finger Vein Recognition

This paper aims to provide a brief review of the feature extraction methods applied for finger vein recognition. The presented study is designed in a systematic way in order to bring light to the scientific interest for biometric systems based on finger vein biometric features. The analysis spans over a period of 13 years (from 2008 to 2020). The examined feature extraction algorithms are clustered into five categories and are presented in a qualitative manner by focusing mainly on the techniques applied to represent the features of the finger veins that uniquely prove a human’s identity. In addition, the case of non-handcrafted features learned in a deep learning framework is also examined. The conducted literature analysis revealed the increased interest in finger vein biometric systems as well as the high diversity of different feature extraction methods proposed over the past several years. However, last year this interest shifted to the application of Convolutional Neural Networks following the general trend of applying deep learning models in a range of disciplines. Finally, yet importantly, this work highlights the limitations of the existing feature extraction methods and describes the research actions needed to face the identified challenges.

Beyond Deep Learning: An Econometric Example

2020 ◽  
Vol 28 (Supp01) ◽  
pp. 31-38 ◽  
Author(s):  
Ruofan Liao ◽  
Paravee Maneejuk ◽  
Songsak Sriboonchitta
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Prediction Models ◽  
Original Data ◽  
Parametric Model ◽  
Parametric Models ◽  
The Past ◽  
Currency Exchange ◽  
Currency Exchange Rate ◽  
Linear And Nonlinear

In the past, in many areas, the best prediction models were linear and nonlinear parametric models. In the last decade, in many application areas, deep learning has shown to lead to more accurate predictions than the parametric models. Deep learning-based predictions are reasonably accurate, but not perfect. How can we achieve better accuracy? To achieve this objective, we propose to combine neural networks with parametric model: namely, to train neural networks not on the original data, but on the differences between the actual data and the predictions of the parametric model. On the example of predicting currency exchange rate, we show that this idea indeed leads to more accurate predictions.

scholarly journals Laplacian networks: bounding indicator function smoothness for neural networks robustness

2021 ◽  
Vol 10 ◽  
Author(s):  
Carlos Lassance ◽  
Vincent Gripon ◽  
Antonio Ortega
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Supervised Learning ◽  
Indicator Function ◽  
Training Data ◽  
Theoretical Justification ◽  
The Past ◽  
Noisy Examples

For the past few years, deep learning (DL) robustness (i.e. the ability to maintain the same decision when inputs are subject to perturbations) has become a question of paramount importance, in particular in settings where misclassification can have dramatic consequences. To address this question, authors have proposed different approaches, such as adding regularizers or training using noisy examples. In this paper we introduce a regularizer based on the Laplacian of similarity graphs obtained from the representation of training data at each layer of the DL architecture. This regularizer penalizes large changes (across consecutive layers in the architecture) in the distance between examples of different classes, and as such enforces smooth variations of the class boundaries. We provide theoretical justification for this regularizer and demonstrate its effectiveness to improve robustness on classical supervised learning vision datasets for various types of perturbations. We also show it can be combined with existing methods to increase overall robustness.

scholarly journals Flying Free: A Research Overview of Deep Learning in Drone Navigation Autonomy

Drones ◽  
2021 ◽  
Vol 5 (2) ◽  
pp. 52
Author(s):  
Thomas Lee ◽  
Susan Mckeever ◽  
Jane Courtney
Keyword(s):  
Deep Learning ◽  
Research Work ◽  
Learning Approaches ◽  
Clear Definition ◽  
Top Down ◽  
Research Activity ◽  
Comprehensive Overview ◽  
The Past ◽  
Computer Vision Applications ◽  
Definition Of

With the rise of Deep Learning approaches in computer vision applications, significant strides have been made towards vehicular autonomy. Research activity in autonomous drone navigation has increased rapidly in the past five years, and drones are moving fast towards the ultimate goal of near-complete autonomy. However, while much work in the area focuses on specific tasks in drone navigation, the contribution to the overall goal of autonomy is often not assessed, and a comprehensive overview is needed. In this work, a taxonomy of drone navigation autonomy is established by mapping the definitions of vehicular autonomy levels, as defined by the Society of Automotive Engineers, to specific drone tasks in order to create a clear definition of autonomy when applied to drones. A top–down examination of research work in the area is conducted, focusing on drone navigation tasks, in order to understand the extent of research activity in each area. Autonomy levels are cross-checked against the drone navigation tasks addressed in each work to provide a framework for understanding the trajectory of current research. This work serves as a guide to research in drone autonomy with a particular focus on Deep Learning-based solutions, indicating key works and areas of opportunity for development of this area in the future.

Sign in / Sign up

Export Citation Format

Share Document