Cargando…
Delineating the impact of machine learning elements in pre-microRNA detection
Gene regulation modulates RNA expression via transcription factors. Post-transcriptional gene regulation in turn influences the amount of protein product through, for example, microRNAs (miRNAs). Experimental establishment of miRNAs and their effects is complicated and even futile when aiming to est...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
PeerJ Inc.
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5374968/ https://www.ncbi.nlm.nih.gov/pubmed/28367373 http://dx.doi.org/10.7717/peerj.3131 |
_version_ | 1782518975782977536 |
---|---|
author | Saçar Demirci, Müşerref Duygu Allmer, Jens |
author_facet | Saçar Demirci, Müşerref Duygu Allmer, Jens |
author_sort | Saçar Demirci, Müşerref Duygu |
collection | PubMed |
description | Gene regulation modulates RNA expression via transcription factors. Post-transcriptional gene regulation in turn influences the amount of protein product through, for example, microRNAs (miRNAs). Experimental establishment of miRNAs and their effects is complicated and even futile when aiming to establish the entirety of miRNA target interactions. Therefore, computational approaches have been proposed. Many such tools rely on machine learning (ML) which involves example selection, feature extraction, model training, algorithm selection, and parameter optimization. Different ML algorithms have been used for model training on various example sets, more than 1,000 features describing pre-miRNAs have been proposed and different training and testing schemes have been used for model establishment. For pre-miRNA detection, negative examples cannot easily be established causing a problem for two class classification algorithms. There is also no consensus on what ML approach works best and, therefore, we set forth and established the impact of the different parts involved in ML on model performance. Furthermore, we established two new negative datasets and analyzed the impact of using them for training and testing. It was our aim to attach an order of importance to the parts involved in ML for pre-miRNA detection, but instead we found that all parts are intricately connected and their contributions cannot be easily untangled leading us to suggest that when attempting ML-based pre-miRNA detection many scenarios need to be explored. |
format | Online Article Text |
id | pubmed-5374968 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | PeerJ Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-53749682017-03-31 Delineating the impact of machine learning elements in pre-microRNA detection Saçar Demirci, Müşerref Duygu Allmer, Jens PeerJ Bioinformatics Gene regulation modulates RNA expression via transcription factors. Post-transcriptional gene regulation in turn influences the amount of protein product through, for example, microRNAs (miRNAs). Experimental establishment of miRNAs and their effects is complicated and even futile when aiming to establish the entirety of miRNA target interactions. Therefore, computational approaches have been proposed. Many such tools rely on machine learning (ML) which involves example selection, feature extraction, model training, algorithm selection, and parameter optimization. Different ML algorithms have been used for model training on various example sets, more than 1,000 features describing pre-miRNAs have been proposed and different training and testing schemes have been used for model establishment. For pre-miRNA detection, negative examples cannot easily be established causing a problem for two class classification algorithms. There is also no consensus on what ML approach works best and, therefore, we set forth and established the impact of the different parts involved in ML on model performance. Furthermore, we established two new negative datasets and analyzed the impact of using them for training and testing. It was our aim to attach an order of importance to the parts involved in ML for pre-miRNA detection, but instead we found that all parts are intricately connected and their contributions cannot be easily untangled leading us to suggest that when attempting ML-based pre-miRNA detection many scenarios need to be explored. PeerJ Inc. 2017-03-29 /pmc/articles/PMC5374968/ /pubmed/28367373 http://dx.doi.org/10.7717/peerj.3131 Text en ©2017 Saçar Demirci and Allmer http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited. |
spellingShingle | Bioinformatics Saçar Demirci, Müşerref Duygu Allmer, Jens Delineating the impact of machine learning elements in pre-microRNA detection |
title | Delineating the impact of machine learning elements in pre-microRNA detection |
title_full | Delineating the impact of machine learning elements in pre-microRNA detection |
title_fullStr | Delineating the impact of machine learning elements in pre-microRNA detection |
title_full_unstemmed | Delineating the impact of machine learning elements in pre-microRNA detection |
title_short | Delineating the impact of machine learning elements in pre-microRNA detection |
title_sort | delineating the impact of machine learning elements in pre-microrna detection |
topic | Bioinformatics |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5374968/ https://www.ncbi.nlm.nih.gov/pubmed/28367373 http://dx.doi.org/10.7717/peerj.3131 |
work_keys_str_mv | AT sacardemircimuserrefduygu delineatingtheimpactofmachinelearningelementsinpremicrornadetection AT allmerjens delineatingtheimpactofmachinelearningelementsinpremicrornadetection |