Protein Binding Site Prediction by Combining Hidden Markov Support Vector Machine and Profile-Based Propensities

Liu, Bin; Liu, Bingquan; Liu, Fule; Wang, Xiaolong

doi:10.1155/2014/464093

Cited by 11 publications

(9 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An alternative approach to using linear or non-linear combinations is to find the conditional probability

being interface or non-interface, where

are the properties of the residue under study. Conditional probability can be generated from the training sets using Bayesian methods [ 61–63 ], Hidden Markov Model [ 64 , 65 ] or Conditional Random Fields [ 66–68 ]. It has been argued that such probabilistic classifiers might offer an increased performance over the machine learning methods described above [ 62 , 67 ].…”

Section: Intrinsic-based Predictorsmentioning

confidence: 99%

Progress and challenges in predicting protein interfaces

Esmaielbeiki¹,

Krawczyk²,

Knapp³

et al. 2015

Brief Bioinform

125

120

View full text Add to dashboard Cite

The majority of biological processes are mediated via protein–protein interactions. Determination of residues participating in such interactions improves our understanding of molecular mechanisms and facilitates the development of therapeutics. Experimental approaches to identifying interacting residues, such as mutagenesis, are costly and time-consuming and thus, computational methods for this purpose could streamline conventional pipelines. Here we review the field of computational protein interface prediction. We make a distinction between methods which address proteins in general and those targeted at antibodies, owing to the radically different binding mechanism of antibodies. We organize the multitude of currently available methods hierarchically based on required input and prediction principles to provide an overview of the field.

show abstract

“…An alternative approach to using linear or non-linear combinations is to find the conditional probability

being interface or non-interface, where

Section: Intrinsic-based Predictorsmentioning

confidence: 99%

Progress and challenges in predicting protein interfaces

Esmaielbeiki¹,

Krawczyk²,

Knapp³

et al. 2015

Brief Bioinform

125

120

View full text Add to dashboard Cite

show abstract

“…Though several methods address the issue of protein-ligand interactions [ 22 – 27 , 30 – 32 ], the method reported here is particularly for membrane proteins. Since the features derived are from the dataset of membrane protein sequences, its performance is very poor for globular proteins.…”

Section: Resultsmentioning

confidence: 99%

Development of a Machine Learning Method to Predict Membrane Protein-Ligand Binding Residues Using Basic Sequence Information

Suresh

Gromiha

Suwa

2015

Advances in Bioinformatics

View full text Add to dashboard Cite

Locating ligand binding sites and finding the functionally important residues from protein sequences as well as structures became one of the challenges in understanding their function. Hence a Naïve Bayes classifier has been trained to predict whether a given amino acid residue in membrane protein sequence is a ligand binding residue or not using only sequence based information. The input to the classifier consists of the features of the target residue and two sequence neighbors on each side of the target residue. The classifier is trained and evaluated on a nonredundant set of 42 sequences (chains with at least one transmembrane domain) from 31 alpha-helical membrane proteins. The classifier achieves an overall accuracy of 70.7% with 72.5% specificity and 61.1% sensitivity in identifying ligand binding residues from sequence. The classifier performs better when the sequence is encoded by psi-blast generated PSSM profiles. Assessment of the predictions in the context of three-dimensional structures of proteins reveals the effectiveness of this method in identifying ligand binding sites from sequence information. In 83.3% (35 out of 42) of the proteins, the classifier identifies the ligand binding sites by correctly recognizing more than half of the binding residues. This will be useful to protein engineers in exploiting potential residues for functional assessment.

show abstract

“…For a prediction problem, a classifier can predict an individual instance into the following four categories: false positive (FP), true positive (TP), false negative (FN) and true negative (TN). As shown in previous studies 52 53 , the total prediction accuracy (ACC), Specificity (Sp), Sensitivity (Sn) and Mathew’s correlation coefficient (MCC) for assessment of the prediction system are given by:…”

Section: Methodsmentioning

confidence: 97%

iMiRNA-SSF: Improving the Identification of MicroRNA Precursors by Combining Negative Sets with Different Distributions

Chen

Wang

Liu

2016

Sci Rep

Self Cite

View full text Add to dashboard Cite

The identification of microRNA precursors (pre-miRNAs) helps in understanding regulator in biological processes. The performance of computational predictors depends on their training sets, in which the negative sets play an important role. In this regard, we investigated the influence of benchmark datasets on the predictive performance of computational predictors in the field of miRNA identification, and found that the negative samples have significant impact on the predictive results of various methods. We constructed a new benchmark set with different data distributions of negative samples. Trained with this high quality benchmark dataset, a new computational predictor called iMiRNA-SSF was proposed, which employed various features extracted from RNA sequences. Experimental results showed that iMiRNA-SSF outperforms three state-of-the-art computational methods. For practical applications, a web-server of iMiRNA-SSF was established at the website http://bioinformatics.hitsz.edu.cn/iMiRNA-SSF/.

show abstract

Protein Binding Site Prediction by Combining Hidden Markov Support Vector Machine and Profile-Based Propensities

Cited by 11 publications

References 44 publications

Progress and challenges in predicting protein interfaces

Progress and challenges in predicting protein interfaces

Development of a Machine Learning Method to Predict Membrane Protein-Ligand Binding Residues Using Basic Sequence Information

iMiRNA-SSF: Improving the Identification of MicroRNA Precursors by Combining Negative Sets with Different Distributions

Contact Info

Product

Resources

About