iPTREE-STAB: interpretable decision tree based method for predicting protein stability changes upon mutations

Huang, Liang-Tsung; Gromiha, M. Michael; Ho, Shinn-Ying

doi:10.1093/bioinformatics/btm100

Cited by 149 publications

(100 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These programs predict features such as the secondary structure, transmembrane regions, and the relative solvent accessibilities of the amino acids based on the amino acid sequence of the given protein. Protein stability was examined using the I-Mutant-3 (33) and MuPro (34) programs, also implemented in PON-P, and an additional program called iPTREE-STAB (35).…”

Section: In Silico Pathogenicity Predictionmentioning

confidence: 99%

HOXB13 G84E Mutation in Finland: Population-Based Analysis of Prostate, Breast, and Colorectal Cancer Risk

Laitinen

Wahlfors

Saaristo

et al. 2013

Cancer Epidemiology, Biomarkers &Amp; Prevention

View full text Add to dashboard Cite

Background: A recently identified germline mutation G84E in HOXB13 was shown to increase the risk of prostate cancer. In a family-based analysis by The International Consortium for Prostate Cancer Genetics (ICPCG), the G84E mutation was most prevalent in families from the Nordic countries of Finland (22.4%) and Sweden (8.2%).Methods: To further investigate the importance of G84E in the Finns, we determined its frequency in more than 4,000 prostate cancer cases and 5,000 controls. In addition, 986 breast cancer and 442 colorectal cancer (CRC) cases were studied. Genotyping was conducted using TaqMan, MassARRAY iPLEX, and sequencing. Statistical analyses were conducted using Fisher exact test, and overall survival was analyzed using Cox modeling.Results: The frequency of the G84E mutation was significantly higher among patients with prostate cancer and highest among patients with a family history of the disease, hereditary prostate cancer [8.4% vs. 1.0% in controls; OR 8.8; 95% confidence interval (CI), 4.9-15.7]. The mutation contributed significantly to younger age ( 55 years) at onset and high prostate-specific antigen (PSA; !20 ng/mL) at diagnosis. An association with increased prostate cancer risk in patients with prior benign prostate hyperplasia (BPH) diagnosis was also revealed. No statistically significant evidence for a contribution in CRC risk was detected, but a suggestive role for the mutation was observed in familial BRCA1/2-negative breast cancer.Conclusions: These findings confirm an increased cancer risk associated with the G84E mutation in the Finnish population, particularly for early-onset prostate cancer and cases with substantially elevated PSA.Impact: This study confirms the overall importance of the HOXB13 G84E mutation in prostate cancer susceptibility. Cancer Epidemiol Biomarkers Prev; 22(3); 452-60. Ó2012 AACR.

show abstract

Section: In Silico Pathogenicity Predictionmentioning

confidence: 99%

HOXB13 G84E Mutation in Finland: Population-Based Analysis of Prostate, Breast, and Colorectal Cancer Risk

Laitinen

Wahlfors

Saaristo

et al. 2013

Cancer Epidemiology, Biomarkers &Amp; Prevention

View full text Add to dashboard Cite

show abstract

“…. This kind of low-level rule-with conditions referring to specific amino acids in specific positionswas also discovered by Huang et al [27], with the difference that in this case, the rules predict protein stability changes upon mutations. Although the rules discovered in the previous two works do not give as much insight about the data as rules having higher level attributes, they were still considered interpretable by the authors, and they were found to be useful to guide "wetlab" experiments because the explicit sequence features that caused the prediction to be made are identified, and therefore, a specific mutation can be made to validate the prediction.…”

Section: Examples Of Discovered Knowledge Represented By Comprehensibmentioning

confidence: 67%

On the Importance of Comprehensible Classification Models for Protein Function Prediction

Freitas

Wieser

Apweiler

2010

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Abstract-The literature on protein function prediction is currently dominated by works aimed at maximizing predictive accuracy, ignoring the important issues of validation and interpretation of discovered knowledge, which can lead to new insights and hypotheses that are biologically meaningful and advance the understanding of protein functions by biologists. The overall goal of this paper is to critically evaluate this approach, offering a refreshing new perspective on this issue, focusing not only on predictive accuracy but also on the comprehensibility of the induced protein function prediction models. More specifically, this paper aims to offer two main contributions to the area of protein function prediction. First, it presents the case for discovering comprehensible protein function prediction models from data, discussing in detail the advantages of such models, namely, increasing the confidence of the biologist in the system's predictions, leading to new insights about the data and the formulation of new biological hypotheses, and detecting errors in the data. Second, it presents a critical review of the pros and cons of several different knowledge representations that can be used in order to support the discovery of comprehensible protein function prediction models.

show abstract

“…The 4-fold and 20-fold cross-validation tests yielded the accuracy of 81.4% and 82.1% for discriminating the stability of protein mutants. The sensitivity and specificity are 75.3% and 84.5%, respectively [42]. Further, our method could predict the stability of protein mutants with the correlation coefficient of 0.70.…”

Section: Prediction Of Protein Stabilitymentioning

confidence: 80%

Sequence Based Prediction of Protein Mutant Stability and Discrimination of Thermophilic Proteins

Gromiha

Huang

Lai

2008

Pattern Recognition in Bioinformatics

View full text Add to dashboard Cite

Abstract. Prediction of protein stability upon amino acid substitution and discrimination of thermophilic proteins from mesophilic ones are important problems in designing stable proteins. We have developed a classification rule generator using the information about wild-type, mutant, three neighboring residues and experimentally observed stability data. Utilizing the rules, we have developed a method based on decision tree for discriminating the stabilizing and destabilizing mutants and predicting protein stability changes upon single point mutations, which showed an accuracy of 82% and a correlation of 0.70, respectively. In addition, we have systematically analyzed the characteristic features of amino acid residues in 3075 mesophilic and 1609 thermophilic proteins belonging to 9 and 15 families, respectively, and developed methods for discriminating them. The method based on neural network could discriminate them at the 5-fold cross-validation accuracy of 89% in a dataset of 4684 proteins and 91% in a test set of 707 proteins.

show abstract

iPTREE-STAB: interpretable decision tree based method for predicting protein stability changes upon mutations

Abstract: Dataset and other details are given.

Cited by 149 publications

References 13 publications

HOXB13 G84E Mutation in Finland: Population-Based Analysis of Prostate, Breast, and Colorectal Cancer Risk

HOXB13 G84E Mutation in Finland: Population-Based Analysis of Prostate, Breast, and Colorectal Cancer Risk

On the Importance of Comprehensible Classification Models for Protein Function Prediction

Sequence Based Prediction of Protein Mutant Stability and Discrimination of Thermophilic Proteins

Contact Info

Product

Resources

About