GFO: A data driven approach for optimizing the Gaussian function based similarity metric in computational biology

Lei, Jianbo; Yin, Jiang-Bo; Shen, Hong‐Bin

doi:10.1016/j.neucom.2012.07.003

Cited by 13 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are two important parameters, c and γ, that require optimization: c represents the cost factor controlling the trade-off for maximizing the margin and minimizing the error rate, and γ regulates model generalization. In order to optimize these parameters during model training, the grid-search strategy and the GFO 98 algorithm were used, as well as five-fold cross-validation on the training dataset, to fully optimize the model performance. In addition, we adopted the following strategies to avoid potential overfitting problems:

At each cross-validation step, addition of each of the features to train the model was achieved by using four folds of the dataset, validating the performance of the trained model on the singled-out fold of the dataset.

…”

Section: Methodsmentioning

confidence: 99%

Knowledge-transfer learning for prediction of matrix metalloprotease substrate-cleavage sites

Wang

Song

Marquez‐Lago

et al. 2017

Sci Rep

Self Cite

View full text Add to dashboard Cite

Matrix Metalloproteases (MMPs) are an important family of proteases that play crucial roles in key cellular and disease processes. Therefore, MMPs constitute important targets for drug design, development and delivery. Advanced proteomic technologies have identified type-specific target substrates; however, the complete repertoire of MMP substrates remains uncharacterized. Indeed, computational prediction of substrate-cleavage sites associated with MMPs is a challenging problem. This holds especially true when considering MMPs with few experimentally verified cleavage sites, such as for MMP-2, -3, -7, and -8. To fill this gap, we propose a new knowledge-transfer computational framework which effectively utilizes the hidden shared knowledge from some MMP types to enhance predictions of other, distinct target substrate-cleavage sites. Our computational framework uses support vector machines combined with transfer machine learning and feature selection. To demonstrate the value of the model, we extracted a variety of substrate sequence-derived features and compared the performance of our method using both 5-fold cross-validation and independent tests. The results show that our transfer-learning-based method provides a robust performance, which is at least comparable to traditional feature-selection methods for prediction of MMP-2, -3, -7, -8, -9 and -12 substrate-cleavage sites on independent tests. The results also demonstrate that our proposed computational framework provides a useful alternative for the characterization of sequence-level determinants of MMP-substrate specificity.

show abstract

…”

Section: Methodsmentioning

confidence: 99%

Knowledge-transfer learning for prediction of matrix metalloprotease substrate-cleavage sites

Wang

Song

Marquez‐Lago

et al. 2017

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The range values for C, γ , and ε were taken from the LIBSVM grid search [31] and extended to suit all methods assessed in this study. We also considered using a data-driven approach for optimising the kernel width parameter ( γ ) [32], however, for the relatively small size of our data set, the grid search was a sufficient solution.…”

Section: Methodsmentioning

confidence: 99%

In silico comparative characterization of pharmacogenomic missense variants

Seligman

Thusberg

et al. 2014

BMC Genomics

View full text Add to dashboard Cite

BackgroundMissense pharmacogenomic (PGx) variants refer to amino acid substitutions that potentially affect the pharmacokinetic (PK) or pharmacodynamic (PD) response to drug therapies. The PGx variants, as compared to disease-associated variants, have not been investigated as deeply. The ability to computationally predict future PGx variants is desirable; however, it is not clear what data sets should be used or what features are beneficial to this end. Hence we carried out a comparative characterization of PGx variants with annotated neutral and disease variants from UniProt, to test the predictive power of sequence conservation and structural information in discriminating these three groups.Results126 PGx variants of high quality from PharmGKB were selected and two data sets were created: one set contained 416 variants with structural and sequence information, and, the other set contained 1,265 variants with sequence information only. In terms of sequence conservation, PGx variants are more conserved than neutral variants and much less conserved than disease variants. A weighted random forest was used to strike a more balanced classification for PGx variants. Generally structural features are helpful in discriminating PGx variant from the other two groups, but still classification of PGx from neutral polymorphisms is much less effective than between disease and neutral variants.ConclusionsWe found that PGx variants are much more similar to neutral variants than to disease variants in the feature space consisting of residue conservation, neighboring residue conservation, number of neighbors, and protein solvent accessibility. Such similarity poses great difficulty in the classification of PGx variants and polymorphisms.

show abstract

“…The range values for C, γ , and ε were taken from the LIBSVM grid search [ 31 ] and extended to suit all methods assessed in this study. We also considered using a data-driven approach for optimising the kernel width parameter ( γ ) [ 32 ], however, for the relatively small size of our data set, the grid search was a sufficient solution.…”

Section: Methodsmentioning

confidence: 99%

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins

2014

View full text Add to dashboard Cite

BackgroundReliable prediction of stability changes induced by a single amino acid substitution is an important aspect of computational protein design. Several machine learning methods capable of predicting stability changes from the protein sequence alone have been introduced. Prediction performance of these methods is evaluated on mutations unseen during training. Nevertheless, different mutations of the same protein, and even the same residue, as encountered during training are commonly used for evaluation. We argue that a faithful evaluation can be achieved only when a method is tested on previously unseen proteins with low sequence similarity to the training set.ResultsWe provided experimental evidence of the limitations of the evaluation commonly used for assessing the prediction performance. Furthermore, we demonstrated that the prediction of stability changes in previously unseen non-homologous proteins is a challenging task for currently available methods. To improve the prediction performance of our previously proposed method, we identified features which led to over-fitting and further extended the model with new features. The new method employs Evolutionary And Structural Encodings with Amino Acid parameters (EASE-AA). Evaluated with an independent test set of more than 600 mutations, EASE-AA yielded a Matthews correlation coefficient of 0.36 and was able to classify correctly 66% of the stabilising and 74% of the destabilising mutations. For real-value prediction, EASE-AA achieved the correlation of predicted and experimentally measured stability changes of 0.51.ConclusionsCommonly adopted evaluation with mutations in the same protein, and even the same residue, randomly divided between the training and test sets lead to an overestimation of prediction performance. Therefore, stability changes prediction methods should be evaluated only on mutations in previously unseen non-homologous proteins. Under such an evaluation, EASE-AA predicts stability changes more reliably than currently available methods.Electronic supplementary materialThe online version of this article (doi:10.1186/1471-2164-15-S1-S4) contains supplementary material, which is available to authorized users.

show abstract

GFO: A data driven approach for optimizing the Gaussian function based similarity metric in computational biology

Cited by 13 publications

References 34 publications

Knowledge-transfer learning for prediction of matrix metalloprotease substrate-cleavage sites

Knowledge-transfer learning for prediction of matrix metalloprotease substrate-cleavage sites

In silico comparative characterization of pharmacogenomic missense variants

Towards sequence-based prediction of mutation-induced stability changes in unseen non-homologous proteins

Contact Info

Product

Resources

About