Data Mining Practical Machine Learning Tools and Techniques

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8829812

Machine learning for multi-omics data integration in cancer

Fast and Accurate Bacterial Species Identification in Urine Specimens Using LC-MS/MS Mass Spectrometry and Machine Learning.

Biomarkers are crucial biological indicators in medical diagnostics and therapy. However, the process of biomarker discovery and validation is hindered by a lack of standardized protocols for analytical studies, storage and sample collection. Wearable chemical sensors provide a real-time, non-invasive alternative to typical laboratory blood analysis, and are an effective tool for exploring novel biomarkers in alternative body fluids, such as sweat, saliva, tears and interstitial fluid. These devices may enable remote at-home personalized health monitoring and substantially reduce the healthcare costs. This Review introduces criteria, strategies and technologies involved in biomarker discovery using wearable chemical sensors. Electrochemical and optical detection techniques are discussed, along with the materials and system-level considerations for wearable chemical sensors. Lastly, this Review describes how the large sets of temporal data collected by wearable sensors, coupled with modern data analysis approaches, would open the door for discovering new biomarkers towards precision medicine. 

/pdf/wearable-chemical-sensors-for-biomarker-discovery-in-the-1hkxiyze.pdf

Wearable chemical sensors for biomarker discovery in the omics era

The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.

https://www.mdpi.com/1422-0067/22/6/2903/pdf

Incorporating Machine Learning into Established Bioinformatics Frameworks.

Increased availability of high-throughput technologies has generated an ever-growing number of omics data that seek to portray many different but complementary biological layers including genomics, epigenomics, transcriptomics, proteomics, and metabolomics. New insight from these data have been obtained by machine learning algorithms that have produced diagnostic and classification biomarkers. Most biomarkers obtained to date however only include one omic measurement at a time and thus do not take full advantage of recent multi-omics experiments that now capture the entire complexity of biological systems. Multi-omics data integration strategies are needed to combine the complementary knowledge brought by each omics layer. We have summarized the most recent data integration methods/ frameworks into five different integration strategies: early, mixed, intermediate, late and hierarchical. In this mini-review, we focus on challenges and existing multi-omics integration strategies by paying special attention to machine learning applications.

Integration strategies of multi-omics data for machine learning analysis.

The identification of biomarker signatures in omics molecular profiling is usually performed to predict outcomes in a precision medicine context, such as patient disease susceptibility, diagnosis, prognosis, and treatment response. To identify these signatures, we have developed a biomarker discovery tool, called BioDiscML. From a collection of samples and their associated characteristics, i.e., the biomarkers (e.g., gene expression, protein levels, clinico-pathological data), BioDiscML exploits various feature selection procedures to produce signatures associated to machine learning models that will predict efficiently a specified outcome. To this purpose, BioDiscML uses a large variety of machine learning algorithms to select the best combination of biomarkers for predicting categorical or continuous outcomes from highly unbalanced datasets. The software has been implemented to automate all machine learning steps, including data pre-processing, feature selection, model selection, and performance evaluation. BioDiscML is delivered as a stand-alone program and is available for download at https://github.com/mickaelleclercq/BioDiscML.

/pdf/large-scale-automatic-feature-selection-for-biomarker-1f99cxlq6r.pdf

Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data.

Cost reduction of high-throughput technologies has enabled the monitoring of the same biological sample across multiple omics studies and multiple timepoints. The goal is to combine longitudinal multi-omics data to detect temporal relationships between molecules and interactions between omics layers. This can finally lead to uncover new regulation mechanisms and interactions that could be responsible for causing complex phenotype or disease. However multi-omics integration of diverse omics data is still challenging due to heterogeneous data and designs. Moreover, interpretation of multi-omics models is the key to understand biological systems. We propose a generic analytic and integration framework for multi-omics longitudinal datasets that consists of multi-omics kinetic clustering and multi-layer network-based analysis. This frame-work was successfully applied to two case studies with different experimental designs and omics data collected. The first case studied transcriptomic and proteomic changes during cell cycle in human HeLa cells, while the second focused on maize transcriptomic and metabolomic response to aphid feeding. Propagation analysis on multi-layer networks identifies regulatory mechanisms and function prediction for both case studies. Our framework has led to the identification of new multi-layer interactions involved in key biological functions that cannot be revealed with single omics analysis and interplay in the kinetics that could help identify novel biological mechanisms.

/pdf/interpretation-of-network-based-integration-from-multi-omics-k6w099ve8d.pdf

Interpretation of network-based integration from multi-omics longitudinal data

Network-based analysis of gene expression through co-expression networks can be used to investigate modular relationships occurring between genes performing different biological functions. An extended description of each of the network modules is therefore a critical step to understand the underlying processes contributing to a disease or a phenotype. Biological integration, topology study and conditions comparison (e.g. wild vs mutant) are the main methods to do so, but to date no tool combines them all into a single pipeline. Here we present GWENA, a new R package that integrates gene co-expression network construction and whole characterization of the detected modules through gene set enrichment, phenotypic association, hub genes detection, topological metric computation, and differential co-expression. To demonstrate its performance, we applied GWENA on two skeletal muscle datasets from young and old patients of GTEx study. Remarkably, we prioritized a gene whose involvement was unknown in the muscle development and growth. Moreover, new insights on the variations in patterns of co-expression were identified. The known phenomena of connectivity loss associated with aging was found coupled to a global reorganization of the relationships leading to expression of known aging related functions. GWENA is an R package available through Bioconductor (
 https://bioconductor.org/packages/release/bioc/html/GWENA.html
 ) that has been developed to perform extended analysis of gene co-expression networks. Thanks to biological and topological information as well as differential co-expression, the package helps to dissect the role of genes relationships in diseases conditions or targeted phenotypes. GWENA goes beyond existing packages that perform co-expression analysis by including new tools to fully characterize modules, such as differential co-expression, additional enrichment databases, and network visualization.

/pdf/gwena-gene-co-expression-networks-analysis-and-extended-nk93wa51kt.pdf

GWENA: gene co-expression networks analysis and extended modules characterization in a single Bioconductor package.

The microbiome, as a community of microorganisms and their structural elements, genomes, metabolites/signal molecules, has been shown to play an important role in human health, with significant beneficial applications for gut health. Skin microbiome has emerged as a new field with high potential to develop disruptive solutions to manage skin health and disease. Despite an incomplete toolbox for skin microbiome analyses, much progress has been made towards functional dissection of microbiomes and host-microbiome interactions. A standardized and robust investigation of the skin microbiome is necessary to provide accurate microbial information and set the base for a successful translation of innovations in the dermo-cosmetic field. This review provides an overview of how the landscape of skin microbiome research has evolved from method development (multi-omics/data-based analytical approaches) to the discovery and development of novel microbiome-derived ingredients. Moreover, it provides a summary of the latest findings on interactions between the microbiomes (gut and skin) and skin health/disease. Solutions derived from these two paths are used to develop novel microbiome-based ingredients or solutions acting on skin homeostasis are proposed. The most promising skin and gut-derived microbiome interventional strategies are presented, along with regulatory, safety, industrial, and technical challenges related to a successful translation of these microbiome-based concepts/technologies in the dermo-cosmetic industry.

/pdf/advances-in-microbiome-derived-solutions-and-methodologies-2qtq1zwu.pdf

Olivier Perin

Papers

Integration strategies of multi-omics data for machine learning analysis.

Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data.

Interpretation of network-based integration from multi-omics longitudinal data

GWENA: gene co-expression networks analysis and extended modules characterization in a single Bioconductor package.

Advances in Microbiome-Derived Solutions and Methodologies Are Founding a New Era in Skin Health and Care