ProTstab - Predictor for cellular protein stability

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

Standard

ProTstab - Predictor for cellular protein stability. / Yang, Yang; Ding, Xuesong; Zhu, Guanchen; Niroula, Abhishek; Lv, Qiang; Vihinen, Mauno.

I: BMC Genomics, Vol. 20, Nr. 1, 804, 04.11.2019.

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

Harvard

APA

CBE

MLA

Vancouver

Author

Yang, Yang ; Ding, Xuesong ; Zhu, Guanchen ; Niroula, Abhishek ; Lv, Qiang ; Vihinen, Mauno. / ProTstab - Predictor for cellular protein stability. I: BMC Genomics. 2019 ; Vol. 20, Nr. 1.

RIS

TY - JOUR

T1 - ProTstab - Predictor for cellular protein stability

AU - Yang, Yang

AU - Ding, Xuesong

AU - Zhu, Guanchen

AU - Niroula, Abhishek

AU - Lv, Qiang

AU - Vihinen, Mauno

PY - 2019/11/4

Y1 - 2019/11/4

N2 - Background: Stability is one of the most fundamental intrinsic characteristics of proteins and can be determined with various methods. Characterization of protein properties does not keep pace with increase in new sequence data and therefore even basic properties are not known for far majority of identified proteins. There have been some attempts to develop predictors for protein stabilities; however, they have suffered from small numbers of known examples. Results: We took benefit of results from a recently developed cellular stability method, which is based on limited proteolysis and mass spectrometry, and developed a machine learning method using gradient boosting of regression trees. ProTstab method has high performance and is well suited for large scale prediction of protein stabilities. Conclusions: The Pearson's correlation coefficient was 0.793 in 10-fold cross validation and 0.763 in independent blind test. The corresponding values for mean absolute error are 0.024 and 0.036, respectively. Comparison with a previously published method indicated ProTstab to have superior performance. We used the method to predict stabilities of all the remaining proteins in the entire human proteome and then correlated the predicted stabilities to protein chain lengths of isoforms and to localizations of proteins.

AB - Background: Stability is one of the most fundamental intrinsic characteristics of proteins and can be determined with various methods. Characterization of protein properties does not keep pace with increase in new sequence data and therefore even basic properties are not known for far majority of identified proteins. There have been some attempts to develop predictors for protein stabilities; however, they have suffered from small numbers of known examples. Results: We took benefit of results from a recently developed cellular stability method, which is based on limited proteolysis and mass spectrometry, and developed a machine learning method using gradient boosting of regression trees. ProTstab method has high performance and is well suited for large scale prediction of protein stabilities. Conclusions: The Pearson's correlation coefficient was 0.793 in 10-fold cross validation and 0.763 in independent blind test. The corresponding values for mean absolute error are 0.024 and 0.036, respectively. Comparison with a previously published method indicated ProTstab to have superior performance. We used the method to predict stabilities of all the remaining proteins in the entire human proteome and then correlated the predicted stabilities to protein chain lengths of isoforms and to localizations of proteins.

KW - Machine learning

KW - Prediction

KW - Protein stability

KW - Proteome properties

U2 - 10.1186/s12864-019-6138-7

DO - 10.1186/s12864-019-6138-7

M3 - Article

VL - 20

JO - BMC Genomics

JF - BMC Genomics

SN - 1471-2164

IS - 1

M1 - 804

ER -