Neural network-based taxonomic clustering for metagenomics

Essinger, Steven D.; Polikar, Robi; Rosen, Gail

doi:10.1109/ijcnn.2010.5596644

Cited by 5 publications

(6 citation statements)

References 18 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the first techniques of de novo genome binning used self-organizing maps, a type of neural network [311]. Essinger et al [331] used Adaptive Resonance Theory to cluster similar genomic fragments and showed that it had better performance than k-means. However, other methods based on interpolated Markov models [332] have performed better than these early genome binners.…”

Section: Metagenomicsmentioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2018

J. R. Soc. Interface.

Self Cite

1,598

1,001

View full text Add to dashboard Cite

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems—patient classification, fundamental biological processes and treatment of patients—and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

show abstract

Section: Metagenomicsmentioning

confidence: 99%

Opportunities and obstacles for deep learning in biology and medicine

Ching

Himmelstein

Beaulieu‐Jones

et al. 2018

J. R. Soc. Interface.

Self Cite

1,598

1,001

View full text Add to dashboard Cite

show abstract

“…The one-hot encoding of a sequence is a limited method with respect to the goal of grouping it with others (binning). Various methods perform binning using autoencoders but relying on one-hot encoding [ 102 103 ] or reference database annotations only [ 104 ]. However, these methods are now outperformed by methods that provide better sequence representations.…”

Section: Resultsmentioning

confidence: 99%

“…This vector is then projected into a latent space, thereby producing a novel data visualization. These points can be grouped through clustering algorithms such as k-medoids or k-means based on their proximity in the embedding space [ 104 108 ]. These groups and their population will form the abundance table.…”

Section: Resultsmentioning

confidence: 99%

Deep learning methods in metagenomics: a review

Roy,

Prifti,

Belda

et al. 2024

Microbial Genomics

View full text Add to dashboard Cite

The ever-decreasing cost of sequencing and the growing potential applications of metagenomics have led to an unprecedented surge in data generation. One of the most prevalent applications of metagenomics is the study of microbial environments, such as the human gut. The gut microbiome plays a crucial role in human health, providing vital information for patient diagnosis and prognosis. However, analysing metagenomic data remains challenging due to several factors, including reference catalogues, sparsity and compositionality. Deep learning (DL) enables novel and promising approaches that complement state-of-the-art microbiome pipelines. DL-based methods can address almost all aspects of microbiome analysis, including novel pathogen detection, sequence classification, patient stratification and disease prediction. Beyond generating predictive models, a key aspect of these methods is also their interpretability. This article reviews DL approaches in metagenomics, including convolutional networks, autoencoders and attention-based models. These methods aggregate contextualized data and pave the way for improved patient care and a better understanding of the microbiome’s key role in our health.

show abstract

“…The latent representations of all sequences constitute a spatial distribution of the data, with each point representing an individual sequence. These points can be grouped through clustering algorithms such as k-medoids or k-means ( [84] [80]). Once clustered, these sequences aggregate into groups representing their proximity in the embedding space, and therefore hopefully their real proximity.…”

Section: Classification Of Reads Computing An Abundance Matrix By Gro...mentioning

confidence: 99%

Deep learning methods in metagenomics: a review

Roy

Prifti

Zucker

2023

Preprint

View full text Add to dashboard Cite

The ever decreasing cost of sequencing and the multiplication of potential applications for the study of metagenomes have led to an unprecedented increase in the volume of data generated. One of the most prevalent applications of metagenomics is the study of microbial environments, such as the human gut. The gut microbiome has been shown to play an important role in human health, providing critical information for patient diagnosis and prognosis. However, the analysis of metagenomic data remains challenging for many reasons, including reference catalogs, sparsity and compositionality of the data, to name a few. Deep learning (DL) enables novel and promising approaches that complement state-of-the-art microbiome pipelines. In fact, DL-based methods can address almost all aspects of microbiome analysis, including novel pathogen detection, sequence classification, patient stratification, and disease prediction. Beyond the generation of predictive models, a key aspect of such methods remains their interpretability. In this article, we provide a systematic review of deep learning approaches in metagenomics, whether based on convolutional networks, autoencoders, or attention-based models. These methods aggregate contextualized data and pave the way for improved patient care and a better understanding of the key role the microbiome plays in our health.

show abstract

Neural network-based taxonomic clustering for metagenomics

Cited by 5 publications

References 18 publications

Opportunities and obstacles for deep learning in biology and medicine

Opportunities and obstacles for deep learning in biology and medicine

Deep learning methods in metagenomics: a review

Deep learning methods in metagenomics: a review

Contact Info

Product

Resources

About