Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data

Abstract Several disorders are related to amyloid aggregation of proteins, for example Alzheimer’s or Parkinson’s diseases. Amyloid proteins form fibrils of aggregated beta structures. This is preceded by formation of oligomers—the most cytotoxic species. Determining amyloidogenicity is tedious and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Natalia Szulc, Michał Burdukiewicz, Marlena Gąsior-Głogowska, Jakub W. Wojciechowski, Jarosław Chilimoniuk, Paweł Mackiewicz, Tomas Šneideris, Vytautas Smirnovas, Malgorzata Kotulska
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1b581be9c50f488f8323d496d600981b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1b581be9c50f488f8323d496d600981b
record_format	dspace
spelling	oai:doaj.org-article:1b581be9c50f488f8323d496d600981b2021-12-02T13:41:23ZBioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data10.1038/s41598-021-86530-62045-2322https://doaj.org/article/1b581be9c50f488f8323d496d600981b2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-86530-6https://doaj.org/toc/2045-2322Abstract Several disorders are related to amyloid aggregation of proteins, for example Alzheimer’s or Parkinson’s diseases. Amyloid proteins form fibrils of aggregated beta structures. This is preceded by formation of oligomers—the most cytotoxic species. Determining amyloidogenicity is tedious and costly. The most reliable identification of amyloids is obtained with high resolution microscopies, such as electron microscopy or atomic force microscopy (AFM). More frequently, less expensive and faster methods are used, especially infrared (IR) spectroscopy or Thioflavin T staining. Different experimental methods are not always concurrent, especially when amyloid peptides do not readily form fibrils but oligomers. This may lead to peptide misclassification and mislabeling. Several bioinformatics methods have been proposed for in-silico identification of amyloids, many of them based on machine learning. The effectiveness of these methods heavily depends on accurate annotation of the reference training data obtained from in-vitro experiments. We study how robust are bioinformatics methods to weak supervision, encountering imperfect training data. AmyloGram and three other amyloid predictors were applied. The results proved that a certain degree of misannotation in the reference data can be eliminated by the bioinformatics tools, even if they belonged to their training set. The computational results are supported by new experiments with IR and AFM methods.Natalia SzulcMichał BurdukiewiczMarlena Gąsior-GłogowskaJakub W. WojciechowskiJarosław ChilimoniukPaweł MackiewiczTomas ŠneiderisVytautas SmirnovasMalgorzata KotulskaNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Natalia Szulc Michał Burdukiewicz Marlena Gąsior-Głogowska Jakub W. Wojciechowski Jarosław Chilimoniuk Paweł Mackiewicz Tomas Šneideris Vytautas Smirnovas Malgorzata Kotulska Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
description	Abstract Several disorders are related to amyloid aggregation of proteins, for example Alzheimer’s or Parkinson’s diseases. Amyloid proteins form fibrils of aggregated beta structures. This is preceded by formation of oligomers—the most cytotoxic species. Determining amyloidogenicity is tedious and costly. The most reliable identification of amyloids is obtained with high resolution microscopies, such as electron microscopy or atomic force microscopy (AFM). More frequently, less expensive and faster methods are used, especially infrared (IR) spectroscopy or Thioflavin T staining. Different experimental methods are not always concurrent, especially when amyloid peptides do not readily form fibrils but oligomers. This may lead to peptide misclassification and mislabeling. Several bioinformatics methods have been proposed for in-silico identification of amyloids, many of them based on machine learning. The effectiveness of these methods heavily depends on accurate annotation of the reference training data obtained from in-vitro experiments. We study how robust are bioinformatics methods to weak supervision, encountering imperfect training data. AmyloGram and three other amyloid predictors were applied. The results proved that a certain degree of misannotation in the reference data can be eliminated by the bioinformatics tools, even if they belonged to their training set. The computational results are supported by new experiments with IR and AFM methods.
format	article
author	Natalia Szulc Michał Burdukiewicz Marlena Gąsior-Głogowska Jakub W. Wojciechowski Jarosław Chilimoniuk Paweł Mackiewicz Tomas Šneideris Vytautas Smirnovas Malgorzata Kotulska
author_facet	Natalia Szulc Michał Burdukiewicz Marlena Gąsior-Głogowska Jakub W. Wojciechowski Jarosław Chilimoniuk Paweł Mackiewicz Tomas Šneideris Vytautas Smirnovas Malgorzata Kotulska
author_sort	Natalia Szulc
title	Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
title_short	Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
title_full	Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
title_fullStr	Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
title_full_unstemmed	Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
title_sort	bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1b581be9c50f488f8323d496d600981b
work_keys_str_mv	AT nataliaszulc bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT michałburdukiewicz bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT marlenagasiorgłogowska bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT jakubwwojciechowski bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT jarosławchilimoniuk bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT pawełmackiewicz bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT tomassneideris bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT vytautassmirnovas bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata AT malgorzatakotulska bioinformaticsmethodsforidentificationofamyloidogenicpeptidesshowrobustnesstomisannotatedtrainingdata
_version_	1718392541823369216

Bioinformatics methods for identification of amyloidogenic peptides show robustness to misannotated training data

Ejemplares similares