Machine Learning Applications for Mass Spectrometry-Based Metabolomics

Metabolites, Journal Year: 2020, Volume and Issue: 10(6), P. 243 - 243

Published: June 13, 2020

The metabolome of an organism depends on environmental factors and intracellular regulation provides information about the physiological conditions. Metabolomics helps to understand disease progression in clinical settings or estimate metabolite overproduction for metabolic engineering. most popular analytical metabolomics platform is mass spectrometry (MS). However, MS data analysis complicated, since metabolites interact nonlinearly, structures themselves are complex. Machine learning methods have become immensely statistical due inherent nonlinear representation ability process large heterogeneous rapidly. In this review, we address recent developments using machine processing spectra show how generates new biological insights. particular, supervised has great potential research because supply quantitative predictions. We review here commonly used tools, such as random forest, support vector machines, artificial neural networks, genetic algorithms. During steps, help peak picking, normalization, missing imputation. For knowledge-driven analysis, contributes biomarker detection, classification regression, biochemical pathway identification, carbon flux determination. Of important relevance combination different omics identify contributions various regulatory levels. Our overview publications also highlights that quality determines quality, but adds challenge choosing right model data. applied MS-based ease can decisions, guide engineering, stimulate fundamental discoveries.

Language: Английский

---

A guide for the diagnosis of rare and undiagnosed disease: beyond the exome

Genome Medicine, Journal Year: 2022, Volume and Issue: 14(1)

Published: Feb. 28, 2022

Abstract Rare diseases affect 30 million people in the USA and more than 300–400 worldwide, often causing chronic illness, disability, premature death. Traditional diagnostic techniques rely heavily on heuristic approaches, coupling clinical experience from prior rare disease presentations with medical literature. A large number of patients remain undiagnosed for years many even die without an accurate diagnosis. In recent years, gene panels, microarrays, exome sequencing have helped to identify molecular cause such diseases. These technologies allowed diagnoses a sizable proportion (25–35%) patients, actionable findings. However, these undiagnosed. this review, we focus that can be adopted if is unrevealing. We discuss benefits whole genome additional benefit may offered by long-read technology, pan-genome reference, transcriptomics, metabolomics, proteomics, methyl profiling. highlight computational methods help regionally distant similar phenotypes or genetic mutations. Finally, describe approaches automate accelerate genomic analysis. The strategies discussed here are intended serve as guide clinicians researchers next steps when encountering non-diagnostic exomes.

Language: Английский

---

Network analysis methods for studying microbial communities: A mini review

Computational and Structural Biotechnology Journal, Journal Year: 2021, Volume and Issue: 19, P. 2687 - 2698

Published: Jan. 1, 2021

Microorganisms including bacteria, fungi, viruses, protists and archaea live as communities in complex contiguous environments. They engage numerous inter- intra- kingdom interactions which can be inferred from microbiome profiling data. In particular, network-based approaches have proven helpful deciphering microbial interaction patterns. Here we give an overview of state-of-the-art methods to infer intra-kingdom ranging simple correlation- conditional dependence-based methods. We highlight common biases encountered profiles discuss mitigation strategies employed by different tools their trade-off with increased computational complexity. Finally, current limitations that motivate further method development inter-kingdom robustly comprehensively characterize environments the future.

Language: Английский

---

Multi-omics integration in biomedical research – A metabolomics-centric review

Analytica Chimica Acta, Journal Year: 2020, Volume and Issue: 1141, P. 144 - 162

Published: Oct. 22, 2020

Language: Английский

---

Machine learning for multi-omics data integration in cancer

iScience, Journal Year: 2022, Volume and Issue: 25(2), P. 103798 - 103798

Published: Jan. 22, 2022

Multi-omics data analysis is an important aspect of cancer molecular biology studies and has led to ground-breaking discoveries. Many efforts have been made develop machine learning methods that automatically integrate omics data. Here, we review tools categorized as either general-purpose or task-specific, covering both supervised unsupervised for integrative multi-omics We benchmark the performance five approaches using from Cancer Cell Line Encyclopedia, reporting accuracy on type classification mean absolute error drug response prediction, evaluating runtime efficiency. This provides recommendations researchers regarding suitable method selection their specific applications. It should also promote development novel methodologies integration, which will be essential discovery, clinical trial design, personalized treatments.

Language: Английский

---

Unraveling negative biotic interactions determining soil microbial community assembly and functioning

The ISME Journal, Journal Year: 2021, Volume and Issue: 16(1), P. 296 - 306

Published: July 28, 2021

Abstract Microbial communities play important roles in all ecosystems and yet a comprehensive understanding of the ecological processes governing assembly these is missing. To address role biotic interactions between microorganisms for functioning soil microbiota, we used top-down manipulation approach based on removal various populations natural microbial community. We hypothesized that certain groups will strongly affect relative fitness many others, therefore unraveling contribution shaping microbiome. Here show 39% dominant bacterial taxa across treatments were subjected to competitive during recolonization, highlighting importance soil. Moreover, our allowed identification community rule as exemplified by exclusion members Bacillales Proteobacteriales. Modified resulted greater changes activities related N- than C-cycling. Our can provide new promising avenue study complex well links composition ecosystem function.

Language: Английский

---

Undisclosed, unmet and neglected challenges in multi-omics studies

Nature Computational Science, Journal Year: 2021, Volume and Issue: 1(6), P. 395 - 402

Published: June 21, 2021

Language: Английский

---

Aberrant gut-microbiota-immune-brain axis development in premature neonates with brain damage

Cell Host & Microbe, Journal Year: 2021, Volume and Issue: 29(10), P. 1558 - 1572.e6

Published: Sept. 3, 2021

Language: Английский

---

Causal integration of multi‐omics data with prior knowledge to generate mechanistic hypotheses

Molecular Systems Biology, Journal Year: 2021, Volume and Issue: 17(1)

Published: Jan. 1, 2021

Language: Английский

---

Omics sciences for systems biology in Alzheimer’s disease: State-of-the-art of the evidence

Ageing Research Reviews, Journal Year: 2021, Volume and Issue: 69, P. 101346 - 101346

Published: April 27, 2021

Language: Английский

---