Cargando…

Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data

Pectinolytic enzymes are a variety of enzymes involved in breaking down pectin, a complex and abundant plant cell-wall polysaccharide. In nature, pectinolytic enzymes play an essential role in allowing bacteria and fungi to depolymerize and utilize pectin. In addition, pectinases have been widely ap...

Descripción completa

Detalles Bibliográficos
Autores principales: Peng, Mao, de Vries, Ronald P.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Microbiology Society 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8767319/
https://www.ncbi.nlm.nih.gov/pubmed/34874247
http://dx.doi.org/10.1099/mgen.0.000674
_version_ 1784634710949888000
author Peng, Mao
de Vries, Ronald P.
author_facet Peng, Mao
de Vries, Ronald P.
author_sort Peng, Mao
collection PubMed
description Pectinolytic enzymes are a variety of enzymes involved in breaking down pectin, a complex and abundant plant cell-wall polysaccharide. In nature, pectinolytic enzymes play an essential role in allowing bacteria and fungi to depolymerize and utilize pectin. In addition, pectinases have been widely applied in various industries, such as the food, wine, textile, paper and pulp industries. Due to their important biological function and increasing industrial potential, discovery of novel pectinolytic enzymes has received global interest. However, traditional enzyme characterization relies heavily on biochemical experiments, which are time consuming, laborious and expensive. To accelerate identification of novel pectinolytic enzymes, an automatic approach is needed. We developed a machine learning (ML) approach for predicting pectinases in the industrial workhorse fungus, Aspergillus niger. The prediction integrated a diverse range of features, including evolutionary profile, gene expression, transcriptional regulation and biochemical characteristics. Results on both the training and the independent testing dataset showed that our method achieved over 90 % accuracy, and recalled over 60 % of pectinolytic genes. Application of the ML model on the A. niger genome led to the identification of 83 pectinases, covering both previously described pectinases and novel pectinases that do not belong to any known pectinolytic enzyme family. Our study demonstrated the tremendous potential of ML in discovery of new industrial enzymes through integrating heterogeneous (post-) genomimcs data.
format Online
Article
Text
id pubmed-8767319
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Microbiology Society
record_format MEDLINE/PubMed
spelling pubmed-87673192022-01-19 Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data Peng, Mao de Vries, Ronald P. Microb Genom Research Articles Pectinolytic enzymes are a variety of enzymes involved in breaking down pectin, a complex and abundant plant cell-wall polysaccharide. In nature, pectinolytic enzymes play an essential role in allowing bacteria and fungi to depolymerize and utilize pectin. In addition, pectinases have been widely applied in various industries, such as the food, wine, textile, paper and pulp industries. Due to their important biological function and increasing industrial potential, discovery of novel pectinolytic enzymes has received global interest. However, traditional enzyme characterization relies heavily on biochemical experiments, which are time consuming, laborious and expensive. To accelerate identification of novel pectinolytic enzymes, an automatic approach is needed. We developed a machine learning (ML) approach for predicting pectinases in the industrial workhorse fungus, Aspergillus niger. The prediction integrated a diverse range of features, including evolutionary profile, gene expression, transcriptional regulation and biochemical characteristics. Results on both the training and the independent testing dataset showed that our method achieved over 90 % accuracy, and recalled over 60 % of pectinolytic genes. Application of the ML model on the A. niger genome led to the identification of 83 pectinases, covering both previously described pectinases and novel pectinases that do not belong to any known pectinolytic enzyme family. Our study demonstrated the tremendous potential of ML in discovery of new industrial enzymes through integrating heterogeneous (post-) genomimcs data. Microbiology Society 2021-12-07 /pmc/articles/PMC8767319/ /pubmed/34874247 http://dx.doi.org/10.1099/mgen.0.000674 Text en © 2021 The Authors https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License.
spellingShingle Research Articles
Peng, Mao
de Vries, Ronald P.
Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data
title Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data
title_full Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data
title_fullStr Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data
title_full_unstemmed Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data
title_short Machine learning prediction of novel pectinolytic enzymes in Aspergillus niger through integrating heterogeneous (post-) genomics data
title_sort machine learning prediction of novel pectinolytic enzymes in aspergillus niger through integrating heterogeneous (post-) genomics data
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8767319/
https://www.ncbi.nlm.nih.gov/pubmed/34874247
http://dx.doi.org/10.1099/mgen.0.000674
work_keys_str_mv AT pengmao machinelearningpredictionofnovelpectinolyticenzymesinaspergillusnigerthroughintegratingheterogeneouspostgenomicsdata
AT devriesronaldp machinelearningpredictionofnovelpectinolyticenzymesinaspergillusnigerthroughintegratingheterogeneouspostgenomicsdata