scholarly journals Decontaminating eukaryotic genome assemblies with machine learning

2017 ◽  
Vol 18 (1) ◽  
Author(s):  
Janna L. Fierst ◽  
Duncan A. Murdock
Keyword(s):  
Machine Learning ◽  
Eukaryotic Genome ◽  
Genome Assemblies

scholarly journals A machine-learning approach to combined evidence validation of genome assemblies

2008 ◽  
Vol 24 (6) ◽  
pp. 744-750 ◽  
Author(s):  
Jeong-Hyeon Choi ◽  
Sun Kim ◽  
Haixu Tang ◽  
Justen Andrews ◽  
Don G. Gilbert ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Genome Assemblies

scholarly journals Identifying contamination with advanced visualization and analysis practices: metagenomic approaches for eukaryotic genome assemblies

PeerJ ◽  
2016 ◽  
Vol 4 ◽  
pp. e1839 ◽  
Author(s):  
Tom O. Delmont ◽  
A. Murat Eren
Keyword(s):  
High Throughput Sequencing ◽  
Draft Genome ◽  
Cost Effective ◽  
Single Copy ◽  
Eukaryotic Genome ◽  
Sequencing Data ◽  
Bacterial Genomes ◽  
Long Read ◽  
Domains Of Life ◽  
Genome Assemblies

High-throughput sequencing provides a fast and cost-effective mean to recover genomes of organisms from all domains of life. However, adequate curation of the assembly results against potential contamination of non-target organisms requires advanced bioinformatics approaches and practices. Here, we re-analyzed the sequencing data generated for the tardigradeHypsibius dujardini,and created a holistic display of the eukaryotic genome assembly using DNA data originating from two groups and eleven sequencing libraries. By using bacterial single-copy genes, k-mer frequencies, and coverage values of scaffolds we could identify and characterize multiple near-complete bacterial genomes from the raw assembly, and curate a 182 Mbp draft genome forH. dujardinisupported by RNA-Seq data. Our results indicate that most contaminant scaffolds were assembled from Moleculo long-read libraries, and most of these contaminants have differed between library preparations. Our re-analysis shows that visualization and curation of eukaryotic genome assemblies can benefit from tools designed to address the needs of today’s microbiologists, who are constantly challenged by the difficulties associated with the identification of distinct microbial genomes in complex environmental metagenomes.

scholarly journals EvalDNA: a machine learning-based tool for the comprehensive evaluation of mammalian genome assembly quality

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Madolyn L. MacDonald ◽  
Kelvin H. Lee
Keyword(s):  
Machine Learning ◽  
Quality Assessment ◽  
Genome Assembly ◽  
Reference Genome ◽  
Chinese Hamster ◽  
Mammalian Genome ◽  
Quality Score ◽  
Assessment Tools ◽  
Supervised Machine Learning ◽  
Genome Assemblies

Abstract Background To select the most complete, continuous, and accurate assembly for an organism of interest, comprehensive quality assessment of assemblies is necessary. We present a novel tool, called Evaluation of De Novo Assemblies (EvalDNA), which uses supervised machine learning for the quality scoring of genome assemblies and does not require an existing reference genome for accuracy assessment. Results EvalDNA calculates a list of quality metrics from an assembled sequence and applies a model created from supervised machine learning methods to integrate various metrics into a comprehensive quality score. A well-tested, accurate model for scoring mammalian genome sequences is provided as part of EvalDNA. This random forest regression model evaluates an assembled sequence based on continuity, completeness, and accuracy, and was able to explain 86% of the variation in reference-based quality scores within the testing data. EvalDNA was applied to human chromosome 14 assemblies from the GAGE study to rank genome assemblers and to compare EvalDNA to two other quality evaluation tools. In addition, EvalDNA was used to evaluate several genome assemblies of the Chinese hamster genome to help establish a better reference genome for the biopharmaceutical manufacturing community. EvalDNA was also used to assess more recent human assemblies from the QUAST-LG study completed in 2018, and its ability to score bacterial genomes was examined through application on bacterial assemblies from the GAGE-B study. Conclusions EvalDNA enables scientists to easily identify the best available genome assembly for their organism of interest without requiring a reference assembly. EvalDNA sets itself apart from other quality assessment tools by producing a quality score that enables direct comparison among assemblies from different species.

scholarly journals Read coverage as an indicator of misassembly in a short-read based genome assembly

2019 ◽  
Author(s):  
Peipei Wang ◽  
Fanrui Meng ◽  
Bethany M. Moore ◽  
Shin-Han Shiu
Keyword(s):  
Machine Learning ◽  
Great Majority ◽  
Significant Advance ◽  
High Coverage ◽  
Short Read ◽  
Sequencing Technologies ◽  
Long Read ◽  
Genomic Regions ◽  
Genome Assemblies ◽  
Simple Sequence

ABSTRACTAvailability of genome sequences has led to significant advance in biology. With few exceptions, the great majority of existing genome assemblies are derived from short read sequencing technologies with highly uneven read coverages indicative of sequencing and assembly issues. In tomato, 0.6% (5.1 Mb) and 9.7% (79.6 Mb) of short-read based assembly had significantly higher and lower coverage compared to background, respectively. We established machine learning models capable of predicting genomic regions with variable coverages and found that high coverage regions tend to have lower simple sequence repeat but higher tandem gene densities compared to background regions. To determine if the high coverage regions were misassembled, we examined a recently available long-read based assembly and found that 27.8% (1.41 Mb) of high coverage regions were potentially mis-assembled of duplicate sequences, compared to 1.4% in background regions. In addition, using a machine learning model that can distinguish correctly and incorrectly assembled high coverage regions, we found that misassembled, high coverage regions tend to be flanked by simple sequence repeats, pseudogenes, and transposon elements. Our study provides insights on the causes of variable coverage regions and a quantitative assessment of factors contributing to misassembly when using short reads.

scholarly journals Identifying contamination with advanced visualization and analysis practices: metagenomic approaches for eukaryotic genome assemblies

2016 ◽  
Author(s):  
Tom O Delmont ◽  
A. Murat Eren
Keyword(s):  
High Throughput Sequencing ◽  
Draft Genome ◽  
Cost Effective ◽  
Single Copy ◽  
Eukaryotic Genome ◽  
Metagenomic Data ◽  
Sequencing Data ◽  
Long Read ◽  
Domains Of Life ◽  
Genome Assemblies

High-throughput sequencing provides a fast and cost effective mean to recover genomes of organisms from all domains of life. However, adequate curation of the assembly results against potential contamination of non-target organisms requires advanced bioinformatics approaches and practices. Here, we re-analyzed the sequencing data generated for the tardigrade Hypsibius dujardini using approaches routinely employed by microbial ecologists who reconstruct bacterial and archaeal genomes from metagenomic data. We created a holistic display of the eukaryotic genome assembly using DNA data originating from two groups and eleven sequencing libraries. By using bacterial single-copy genes, k-mer frequencies, and coverage values of scaffolds we could identify and characterize multiple near-complete bacterial genomes, and curate a 182 Mbp draft genome for H. dujardini supported by RNA-Seq data. Our results indicate that most contaminant scaffolds were assembled from Moleculo long-read libraries, and most of these contaminants have differed between library preparations. Our re-analysis shows that visualization and curation of eukaryotic genome assemblies can benefit from tools designed to address the needs of today’s microbiologists, who are constantly challenged by the difficulties associated with the identification of distinct microbial genomes in complex environmental metagenomes.

scholarly journals Identifying contamination with advanced visualization and analysis practices: metagenomic approaches for eukaryotic genome assemblies

2016 ◽  
Author(s):  
Tom O Delmont ◽  
A. Murat Eren
Keyword(s):  
High Throughput Sequencing ◽  
Draft Genome ◽  
Cost Effective ◽  
Single Copy ◽  
Eukaryotic Genome ◽  
Metagenomic Data ◽  
Sequencing Data ◽  
Long Read ◽  
Domains Of Life ◽  
Genome Assemblies

High-throughput sequencing provides a fast and cost effective mean to recover genomes of organisms from all domains of life. However, adequate curation of the assembly results against potential contamination of non-target organisms requires advanced bioinformatics approaches and practices. Here, we re-analyzed the sequencing data generated for the tardigrade Hypsibius dujardini using approaches routinely employed by microbial ecologists who reconstruct bacterial and archaeal genomes from metagenomic data. We created a holistic display of the eukaryotic genome assembly using DNA data originating from two groups and eleven sequencing libraries. By using bacterial single-copy genes, k-mer frequencies, and coverage values of scaffolds we could identify and characterize multiple near-complete bacterial genomes, and curate a 182 Mbp draft genome for H. dujardini supported by RNA-Seq data. Our results indicate that most contaminant scaffolds were assembled from Moleculo long-read libraries, and most of these contaminants have differed between library preparations. Our re-analysis shows that visualization and curation of eukaryotic genome assemblies can benefit from tools designed to address the needs of today’s microbiologists, who are constantly challenged by the difficulties associated with the identification of distinct microbial genomes in complex environmental metagenomes.

Sign in / Sign up

Export Citation Format

Share Document