CARE 2.0: reducing false-positive sequencing error corrections using machine learning

Publikationstyp:
Zeitschriftenaufsatz
Metadaten:
Autoren
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000810679500002&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.1186/s12859-022-04754-3
Externe Identifier
  • Clarivate Analytics Document Solution ID: 2C2BI
  • PubMed Identifier: 35698033
ISSN
1471-2105
Ausgabe der Veröffentlichung
1
Zeitschrift
BMC BIOINFORMATICS
Schlüsselwörter
  • Next-generation sequencing
  • Error correction
  • Machine learning
Artikelnummer
ARTN 227
Datum der Veröffentlichung
2022
Status
Published
Titel
CARE 2.0: reducing false-positive sequencing error corrections using machine learning
Sub types
  • Article
Ausgabe der Zeitschrift
23

Datenquelle: Web of Science (Lite)

Andere Metadatenquellen:
Abstract
<jats:title>Abstract</jats:title><jats:sec><jats:title>Background</jats:title><jats:p>Next-generation sequencing pipelines often perform error correction as a preprocessing step to obtain cleaned input data. State-of-the-art error correction programs are able to reliably detect and correct the majority of sequencing errors. However, they also introduce new errors by making false-positive corrections. These correction mistakes can have negative impact on downstream analysis, such as<jats:italic>k</jats:italic>-mer statistics, de-novo assembly, and variant calling. This motivates the need for more precise error correction tools.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>We present CARE 2.0, a context-aware read error correction tool based on multiple sequence alignment targeting Illumina datasets. In addition to a number of newly introduced optimizations its most significant change is the replacement of CARE 1.0’s hand-crafted correction conditions with a novel classifier based on random decision forests trained on Illumina data. This results in up to two orders-of-magnitude fewer false-positive corrections compared to other state-of-the-art error correction software. At the same time, CARE 2.0 is able to achieve high numbers of true-positive corrections comparable to its competitors. On a simulated full human dataset with 914M reads CARE 2.0 generates only 1.2M false positives (FPs) (and 801.4M true positives (TPs)) at a highly competitive runtime while the best corrections achieved by other state-of-the-art tools contain at least 3.9M FPs and at most 814.5M TPs. Better de-novo assembly and improved<jats:italic>k</jats:italic>-mer analysis show the applicability of CARE 2.0 to real-world data.</jats:p></jats:sec><jats:sec><jats:title>Conclusion</jats:title><jats:p>False-positive corrections can negatively influence down-stream analysis. The precision of CARE 2.0 greatly reduces the number of those corrections compared to other state-of-the-art programs including BFC, Karect, Musket, Bcool, SGA, and Lighter. Thus, higher-quality datasets are produced which improve<jats:italic>k</jats:italic>-mer analysis and de-novo assembly in real-world datasets which demonstrates the applicability of machine learning techniques in the context of sequencing read error correction. CARE 2.0 is written in C++/CUDA for Linux systems and can be run on the CPU as well as on CUDA-enabled GPUs. It is available at<jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="uri" xlink:href="https://github.com/fkallen/CARE">https://github.com/fkallen/CARE</jats:ext-link>.</jats:p></jats:sec>
Autoren
DOI
10.1186/s12859-022-04754-3
eISSN
1471-2105
Ausgabe der Veröffentlichung
1
Zeitschrift
BMC Bioinformatics
Sprache
en
Artikelnummer
227
Online publication date
2022
Datum der Veröffentlichung
2022
Status
Published
Herausgeber
Springer Science and Business Media LLC
Herausgeber URL
http://dx.doi.org/10.1186/s12859-022-04754-3
Datum der Datenerfassung
2023
Titel
CARE 2.0: reducing false-positive sequencing error corrections using machine learning
Ausgabe der Zeitschrift
23

Datenquelle: Crossref

Abstract
<h4>Background</h4>Next-generation sequencing pipelines often perform error correction as a preprocessing step to obtain cleaned input data. State-of-the-art error correction programs are able to reliably detect and correct the majority of sequencing errors. However, they also introduce new errors by making false-positive corrections. These correction mistakes can have negative impact on downstream analysis, such as k-mer statistics, de-novo assembly, and variant calling. This motivates the need for more precise error correction tools.<h4>Results</h4>We present CARE 2.0, a context-aware read error correction tool based on multiple sequence alignment targeting Illumina datasets. In addition to a number of newly introduced optimizations its most significant change is the replacement of CARE 1.0's hand-crafted correction conditions with a novel classifier based on random decision forests trained on Illumina data. This results in up to two orders-of-magnitude fewer false-positive corrections compared to other state-of-the-art error correction software. At the same time, CARE 2.0 is able to achieve high numbers of true-positive corrections comparable to its competitors. On a simulated full human dataset with 914M reads CARE 2.0 generates only 1.2M false positives (FPs) (and 801.4M true positives (TPs)) at a highly competitive runtime while the best corrections achieved by other state-of-the-art tools contain at least 3.9M FPs and at most 814.5M TPs. Better de-novo assembly and improved k-mer analysis show the applicability of CARE 2.0 to real-world data.<h4>Conclusion</h4>False-positive corrections can negatively influence down-stream analysis. The precision of CARE 2.0 greatly reduces the number of those corrections compared to other state-of-the-art programs including BFC, Karect, Musket, Bcool, SGA, and Lighter. Thus, higher-quality datasets are produced which improve k-mer analysis and de-novo assembly in real-world datasets which demonstrates the applicability of machine learning techniques in the context of sequencing read error correction. CARE 2.0 is written in C++/CUDA for Linux systems and can be run on the CPU as well as on CUDA-enabled GPUs. It is available at https://github.com/fkallen/CARE .
Addresses
  • Department of Computer Science, Johannes Gutenberg University Mainz, Mainz, Germany. kallenborn@uni-mainz.de.
Autoren
DOI
10.1186/s12859-022-04754-3
eISSN
1471-2105
Externe Identifier
  • PubMed Identifier: 35698033
  • PubMed Central ID: PMC9195321
Funding acknowledgements
  • DeCoDeML Project by Rhein-Main-University Network:
  • Johannes Gutenberg-Universität Mainz:
Open access
true
ISSN
1471-2105
Ausgabe der Veröffentlichung
1
Zeitschrift
BMC bioinformatics
Schlüsselwörter
  • Humans
  • Sequence Alignment
  • Sequence Analysis, DNA
  • Algorithms
  • Software
  • High-Throughput Nucleotide Sequencing
  • Machine Learning
Sprache
eng
Medium
Electronic
Online publication date
2022
Open access status
Open Access
Paginierung
227
Datum der Veröffentlichung
2022
Status
Published
Publisher licence
CC BY
Datum der Datenerfassung
2022
Titel
CARE 2.0: reducing false-positive sequencing error corrections using machine learning.
Sub types
  • research-article
  • Journal Article
Ausgabe der Zeitschrift
23

Files

https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-022-04754-3 https://europepmc.org/articles/PMC9195321?pdf=render

Datenquelle: Europe PubMed Central

Abstract
BACKGROUND: Next-generation sequencing pipelines often perform error correction as a preprocessing step to obtain cleaned input data. State-of-the-art error correction programs are able to reliably detect and correct the majority of sequencing errors. However, they also introduce new errors by making false-positive corrections. These correction mistakes can have negative impact on downstream analysis, such as k-mer statistics, de-novo assembly, and variant calling. This motivates the need for more precise error correction tools. RESULTS: We present CARE 2.0, a context-aware read error correction tool based on multiple sequence alignment targeting Illumina datasets. In addition to a number of newly introduced optimizations its most significant change is the replacement of CARE 1.0's hand-crafted correction conditions with a novel classifier based on random decision forests trained on Illumina data. This results in up to two orders-of-magnitude fewer false-positive corrections compared to other state-of-the-art error correction software. At the same time, CARE 2.0 is able to achieve high numbers of true-positive corrections comparable to its competitors. On a simulated full human dataset with 914M reads CARE 2.0 generates only 1.2M false positives (FPs) (and 801.4M true positives (TPs)) at a highly competitive runtime while the best corrections achieved by other state-of-the-art tools contain at least 3.9M FPs and at most 814.5M TPs. Better de-novo assembly and improved k-mer analysis show the applicability of CARE 2.0 to real-world data. CONCLUSION: False-positive corrections can negatively influence down-stream analysis. The precision of CARE 2.0 greatly reduces the number of those corrections compared to other state-of-the-art programs including BFC, Karect, Musket, Bcool, SGA, and Lighter. Thus, higher-quality datasets are produced which improve k-mer analysis and de-novo assembly in real-world datasets which demonstrates the applicability of machine learning techniques in the context of sequencing read error correction. CARE 2.0 is written in C++/CUDA for Linux systems and can be run on the CPU as well as on CUDA-enabled GPUs. It is available at https://github.com/fkallen/CARE .
Date of acceptance
2022
Autoren
Autoren-URL
https://www.ncbi.nlm.nih.gov/pubmed/35698033
DOI
10.1186/s12859-022-04754-3
eISSN
1471-2105
Externe Identifier
  • PubMed Central ID: PMC9195321
Ausgabe der Veröffentlichung
1
Zeitschrift
BMC Bioinformatics
Schlüsselwörter
  • Error correction
  • Machine learning
  • Next-generation sequencing
  • Algorithms
  • High-Throughput Nucleotide Sequencing
  • Humans
  • Machine Learning
  • Sequence Alignment
  • Sequence Analysis, DNA
  • Software
Sprache
eng
Country
England
Paginierung
227
PII
10.1186/s12859-022-04754-3
Datum der Veröffentlichung
2022
Status
Published online
Datum, an dem der Datensatz öffentlich gemacht wurde
2022
Titel
CARE 2.0: reducing false-positive sequencing error corrections using machine learning.
Sub types
  • Journal Article
Ausgabe der Zeitschrift
23

Datenquelle: PubMed

Autoren
Zeitschrift
BMC Bioinform.
Artikelnummer
1
Paginierung
227 - 227
Datum der Veröffentlichung
2022
Titel
CARE 2.0: reducing false-positive sequencing error corrections using machine learning.
Ausgabe der Zeitschrift
23

Datenquelle: DBLP

Author's licence
CC-BY
Autoren
Hosting institution
Universitätsbibliothek Mainz
Sammlungen
  • DFG-491381577-G
Resource version
Published version
DOI
10.1186/s12859-022-04754-3
Funding acknowledgements
  • Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - Projektnummer 491381577
File(s) embargoed
false
Open access
true
ISSN
1471-2105
Zeitschrift
BMC bioinformatics
Schlüsselwörter
  • 004 Informatik
  • 004 Data processing
Sprache
eng
Open access status
Open Access
Paginierung
227
Datum der Veröffentlichung
2022
Public URL
https://openscience.ub.uni-mainz.de/handle/20.500.12030/8137
Herausgeber
Springer Nature
Datum der Datenerfassung
2022
Datum, an dem der Datensatz öffentlich gemacht wurde
2022
Zugang
Public
Titel
CARE 2.0 : reducing false-positive sequencing error corrections using machine learning
Ausgabe der Zeitschrift
23

Files

care_20__reducing_falsepositi-20221020145914717.pdf

Datenquelle: OPENSCIENCE.UB

Beziehungen:
Eigentum von

Werkzeuge