Denoising of Aligned Genomic Data

Fischer-Hwang, Irena; Ochoa, Idoia; Weissman, Tsachy; Hernáez, Mikel

doi:10.1101/590372

“…Earlier works on metagenomics binning achieved good performance by applying different strategies for clustering. However, they ignored the potential factors in real-world conditions that influence the quality of metagenomic short reads, such as the low total biomass of microbial-derived genomes in clinical isolates [12] and the imperfect genomic sequencing process, for example, base substitutions, insertions, and deletions [13]. As a consequence of the factors, metagenomic sequences are susceptible to the noise issue, such as contamination noise and alignment noise [12].…”

Section: Introductionmentioning

confidence: 99%

CLMB: deep contrastive learning for robust metagenomic binning

Zhang¹,

Jiang²,

Wang³

et al. 2021

Preprint

0

View full text Add to dashboard Cite

The reconstruction of microbial genomes from large metagenomic datasets is a critical procedure for finding uncultivated microbial populations and defining their microbial functional roles. To achieve that, we need to perform metagenomic binning, clustering the assembled contigs into draft genomes. Despite the existing computational tools, most of them neglect one important property of the metagenomic data, that is, the noise. To further improve the metagenomic binning step and reconstruct better metagenomes, we propose a deep Contrastive Learning framework for Metagenome Binning (CLMB), which can efficiently eliminate the disturbance of noise and produce more stable and robust results. Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data. Consequently, the trained model will be robust to noise and handle it implicitly during usage. CLMB outperforms the previous state-of-the-art binning methods significantly, recovering the most near-complete genomes on almost all the benchmarking datasets (up to 17% more reconstructed genomes compared to the second-best method). It also improves the performance of bin refinement, reconstructing 8-22 more high-quality genomes and 15-32 more middle-quality genomes than the second-best result. Impressively, in addition to being compatible with the binning refiner, single CLMB even recovers on average 15 more HQ genomes than the refiner of VAMB and Maxbin on the benchmarking datasets. On a real mother-infant microbiome dataset with 110 samples, CLMB is scalable and practical to recover 365 high-quality and middle-quality genomes (including 21 new ones), providing insights into the microbiome transmission. CLMB is open-source and available at https://github.com/zpf0117b/CLMB/.

show abstract

CLMB: Deep Contrastive Learning for Robust Metagenomic Binning

Zhang

¹

,

Jiang

²

,

Wang

³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

CLMB: deep contrastive learning for robust metagenomic binning

Zhang

¹

,

Jiang

²

,

Wang

³

et al. 2021

Preprint

View full text Add to dashboard Cite

The reconstruction of microbial genomes from large metagenomic datasets is a critical procedure for finding uncultivated microbial populations and defining their microbial functional roles. To achieve that, we need to perform metagenomic binning, clustering the assembled contigs into draft genomes. Despite the existing computational tools, most of them neglect one important property of the metagenomic data, that is, the noise. To further improve the metagenomic binning step and reconstruct better metagenomes, we propose a deep Contrastive Learning framework for Metagenome Binning (CLMB), which can efficiently eliminate the disturbance of noise and produce more stable and robust results. Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data. Consequently, the trained model will be robust to noise and handle it implicitly during usage. CLMB outperforms the previous state-of-the-art binning methods significantly, recovering the most near-complete genomes on almost all the benchmarking datasets (up to 17% more reconstructed genomes compared to the second-best method). It also improves the performance of bin refinement, reconstructing 8-22 more high-quality genomes and 15-32 more middle-quality genomes than the second-best result. Impressively, in addition to being compatible with the binning refiner, single CLMB even recovers on average 15 more HQ genomes than the refiner of VAMB and Maxbin on the benchmarking datasets. On a real mother-infant microbiome dataset with 110 samples, CLMB is scalable and practical to recover 365 high-quality and middle-quality genomes (including 21 new ones), providing insights into the microbiome transmission. CLMB is open-source and available at https://github.com/zpf0117b/CLMB/.

show abstract

Denoising of Aligned Genomic Data

Cited by 3 publications

References 31 publications

CLMB: deep contrastive learning for robust metagenomic binning

CLMB: deep contrastive learning for robust metagenomic binning

CLMB: Deep Contrastive Learning for Robust Metagenomic Binning

CLMB: deep contrastive learning for robust metagenomic binning

Contact Info

Product

Resources

About