Machine learning and deep learning applications in microbiome research

ISME Communications, Journal Year: 2022, Volume and Issue: 2(1)

Published: Oct. 6, 2022

Abstract The many microbial communities around us form interactive and dynamic ecosystems called microbiomes. Though concealed from the naked eye, microbiomes govern influence macroscopic systems including human health, plant resilience, biogeochemical cycling. Such feats have attracted interest scientific community, which has recently turned to machine learning deep methods interrogate microbiome elucidate relationships between its composition function. Here, we provide an overview of how latest studies harness inductive prowess artificial intelligence methods. We start by highlighting that data – being compositional, sparse, high-dimensional necessitates special treatment. then introduce traditional novel discuss their strengths applications. Finally, outlook pipelines, focusing on bottlenecks considerations address them.

Language: Английский

---

The microbiota–gut–brain axis: pathways to better brain health. Perspectives on what we know, what we need to investigate and how to put knowledge into practice

Cellular and Molecular Life Sciences, Journal Year: 2022, Volume and Issue: 79(2)

Published: Jan. 19, 2022

Abstract The gut and brain link via various metabolic signalling pathways, each with the potential to influence mental, cognitive health. Over past decade, involvement of microbiota in gut–brain communication has become focus increased scientific interest, establishing microbiota–gut–brain axis as a field research. There is growing number association studies exploring microbiota’s possible role memory, learning, anxiety, stress, neurodevelopmental neurodegenerative disorders. Consequently, attention now turning how can target nutritional therapeutic strategies for improved health well-being. However, while such that function are currently under development varying levels success, still very little yet known about triggers mechanisms underlying apparent on or most evidence comes from pre-clinical rather than well controlled clinical trials/investigations. Filling knowledge gaps requires standardised methodology human studies, including strong guidance specific areas axis, need more extensive biological sample analyses, identification relevant biomarkers. Other urgent requirements new advanced models vitro vivo mechanisms, greater omics technologies supporting bioinformatics resources (training, tools) efficiently translate study findings, targets populations. key building validated base rely increasing sharing multi-disciplinary collaborations, along continued public–private funding support. This will allow research move its next phase so we identify realistic opportunities modulate better

Language: Английский

---

Feature selection techniques for machine learning: a survey of more than two decades of research

Knowledge and Information Systems, Journal Year: 2023, Volume and Issue: 66(3), P. 1575 - 1637

Published: Dec. 1, 2023

Language: Английский

---

Altered Gut Microbiome Composition and Function Are Associated With Gut Barrier Dysfunction in Healthy Relatives of Patients With Crohn’s Disease

Gastroenterology, Journal Year: 2022, Volume and Issue: 163(5), P. 1364 - 1376.e10

Published: July 16, 2022

Language: Английский

---

Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician

Journal of Infection, Journal Year: 2023, Volume and Issue: 87(4), P. 287 - 294

Published: July 17, 2023

BackgroundArtificial intelligence (AI), machine learning and deep (including generative AI) are increasingly being investigated in the context of research management human infection.ObjectivesWe summarise recent potential future applications AI its relevance to clinical infection practice.Methods1,617 PubMed results were screened, with priority given trials, systematic reviews meta-analyses. This narrative review focusses on studies using prospectively collected real-world data validation, translational potential, such as novel drug discovery microbiome-based interventions.ResultsThere is some evidence utility applied laboratory diagnostics (e.g. digital culture plate reading, malaria diagnosis, antimicrobial resistance profiling), imaging analysis pulmonary tuberculosis diagnosis), decision support tools sepsis prediction, prescribing) public health outbreak COVID-19). Most date lack any validation or metrics. Significant heterogeneity study design reporting limits comparability. Many practical ethical issues exist, including algorithm transparency risk bias.ConclusionsInterest development AI-based for undoubtedly gaining pace, although appears much more modest.

Language: Английский

---

Gut bless you: The microbiota-gut-brain axis in irritable bowel syndrome

World Journal of Gastroenterology, Journal Year: 2022, Volume and Issue: 28(4), P. 412 - 431

Published: Jan. 19, 2022

Irritable bowel syndrome (IBS) is a common clinical label for medically unexplained gastrointestinal symptoms, recently described as disturbance of the microbiota-gut-brain axis. Despite decades research, pathophysiology this highly heterogeneous disorder remains elusive. However, dramatic change in understanding underlying pathophysiological mechanisms surfaced when importance gut microbiota protruded scientific picture. Are we getting any closer to IBS' etiology, or are drowning unspecific, conflicting data because possess limited tools unravel cluster secrets our concealing? In comprehensive review discussing some major important features IBS and their interaction with microbiota, microbiota-altering treatment such low FODMAP diet fecal transplantation, neuroimaging methods analyses, current future challenges big analysis IBS.

Language: Английский

---

Dealing with dimensionality: the application of machine learning to multi-omics data

Bioinformatics, Journal Year: 2023, Volume and Issue: 39(2)

Published: Jan. 11, 2023

Machine learning (ML) methods are motivated by the need to automate information extraction from large datasets in order support human users data-driven tasks. This is an attractive approach for integrative joint analysis of vast amounts omics data produced next generation sequencing and other -omics assays. A systematic assessment current literature can help identify key trends potential gaps methodology applications. We surveyed on ML multi-omic integration quantitatively explored goals, techniques involved this field. were particularly interested examining how researchers use deal with volume complexity these datasets.Our main finding that used those address challenges few samples many features. Dimensionality reduction reduce feature count alongside models also appropriately handle relatively samples. Popular include autoencoders, random forests vector machines. found field heavily influenced The Cancer Genome Atlas dataset, which accessible contains diverse experiments.All processing scripts available at GitLab repository: https://gitlab.com/polavieja_lab/ml_multi-omics_review/ or Zenodo: https://doi.org/10.5281/zenodo.7361807.Supplementary Bioinformatics online.

Language: Английский

---

Machine learning approaches in microbiome research: challenges and best practices

Frontiers in Microbiology, Journal Year: 2023, Volume and Issue: 14

Published: Sept. 22, 2023

Microbiome data predictive analysis within a machine learning (ML) workflow presents numerous domain-specific challenges involving preprocessing, feature selection, modeling, performance estimation, model interpretation, and the extraction of biological information from results. To assist decision-making, we offer set recommendations on algorithm pipeline creation evaluation, stemming COST Action ML4Microbiome. We compared suggested approaches multi-cohort shotgun metagenomics dataset colorectal cancer patients, focusing their in disease diagnosis biomarker discovery. It is demonstrated that use compositional transformations filtering methods as part preprocessing does not always improve model. In contrast, multivariate such Statistically Equivalent Signatures algorithm, was effective reducing classification error. When validated separate test dataset, this combination with random forest provided most accurate estimates. Lastly, showed how linear modeling by logistic regression coupled visualization techniques Individual Conditional Expectation (ICE) plots can yield interpretable results insights. These findings are significant for clinicians non-experts alike translational applications.

Language: Английский

---

A comprehensive overview of microbiome data in the light of machine learning applications: categorization, accessibility, and future directions

Frontiers in Microbiology, Journal Year: 2024, Volume and Issue: 15

Published: Feb. 13, 2024

Metagenomics, Metabolomics, and Metaproteomics have significantly advanced our knowledge of microbial communities by providing culture-independent insights into their composition functional potential. However, a critical challenge in this field is the lack standard comprehensive metadata associated with raw data, hindering ability to perform robust data stratifications consider confounding factors. In review, we categorize publicly available microbiome five types: shotgun sequencing, amplicon metatranscriptomic, metabolomic, metaproteomic data. We explore importance for reuse address challenges collecting standardized metadata. also, assess limitations collection existing public repositories metagenomic This review emphasizes vital role interpreting comparing datasets highlights need protocols fully leverage data's Furthermore, future directions implementation Machine Learning (ML) retrieval, offering promising avenues deeper understanding ecological roles. Leveraging these tools will enhance capabilities dynamics diverse ecosystems. Finally, emphasize crucial ML models development.

Language: Английский

---

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

Diagnostics, Journal Year: 2024, Volume and Issue: 14(5), P. 484 - 484

Published: Feb. 23, 2024

Healthcare-associated infections (HAIs) are the most common adverse events in healthcare and constitute a major global public health concern. Surveillance represents foundation for effective prevention control of HAIs, yet conventional surveillance is costly labor intensive. Artificial intelligence (AI) machine learning (ML) have potential to support development HAI algorithms understanding risk factors, improvement patient stratification as well prediction timely detection infections. AI-supported systems so far been explored clinical laboratory testing imaging diagnosis, antimicrobial resistance profiling, antibiotic discovery prediction-based decision tools terms HAIs. This review aims provide comprehensive summary current literature on AI applications field HAIs discuss future potentials this emerging technology infection practice. Following PRISMA guidelines, study examined articles databases including PubMed Scopus until November 2023, which were screened based inclusion exclusion criteria, resulting 162 included articles. By elucidating advancements field, we aim highlight report related issues shortcomings directions.

Language: Английский

---