<i>B</i>‐factor profile prediction for RNA flexibility using support vector machines

Guruge, Ivantha; Taherzadeh, Ghazaleh; Zhan, Jian; Zhou, Yaoqi; Yang, Yuedong

doi:10.1002/jcc.25124

Cited by 15 publications

(18 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this application, we used SVR to construct the prediction model to estimate the cleavage probability of substrate cleavage sites for a given protease. Owing to its excellent generalization capabilities, SVR has recently been applied in a growing number of applications in bioinformatics and computational biology, including cleavage site prediction [15,29,30], residue accessible surface area [95], protein B-factor [96,97], half sphere exposure [98], disulfide connectivity [99], residue depth [54], torsion angles [29] and protein expression-level prediction [100]. It demonstrates competitive performance compared with other machine learning approaches, especially when dealing with realvalued prediction tasks.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites

Song

Wang

et al. 2018

Briefings in Bioinformatics

166

View full text Add to dashboard Cite

Regulation of proteolysis plays a critical role in a myriad of important cellular processes. The key to better understanding the mechanisms that control this process is to identify the specific substrates that each protease targets. To address this, we have developed iProt-Sub, a powerful bioinformatics tool for the accurate prediction of protease-specific substrates and their cleavage sites. Importantly, iProt-Sub represents a significantly advanced version of its successful predecessor, PROSPER. It provides optimized cleavage site prediction models with better prediction performance and coverage for more species-specific proteases (4 major protease families and 38 different proteases). iProt-Sub integrates heterogeneous sequence and structural features and uses a two-step feature selection procedure to further remove redundant and irrelevant features in an effort to improve the cleavage site prediction accuracy. Features used by iProt-Sub are encoded by 11 different sequence encoding schemes, including local amino acid sequence profile, secondary structure, solvent accessibility and native disorder, which will allow a more accurate representation of the protease specificity of approximately 38 proteases and training of the prediction models. Benchmarking experiments using cross-validation and independent tests showed that iProt-Sub is able to achieve a better performance than several existing generic tools. We anticipate that iProt-Sub will be a powerful tool for proteome-wide prediction of protease-specific substrates and their cleavage sites, and will facilitate hypothesis-driven functional interrogation of protease-specific substrate cleavage and proteolytic events.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites

Song

Wang

et al. 2018

Briefings in Bioinformatics

166

View full text Add to dashboard Cite

show abstract

“…Moreover, it is the lowest sequence identity cutoff allowed by the program CD-HIT [59]. This cutoff was also employed previously for establishing non-redundant RNA sequences [61,62] In addition to the HTlncRNA set as the negative set, we also included mRNAs from GENCODE V19 as the negative set. These mRNAs were randomly selected with <80% sequence similarity between each other and from selected HTlncRNAs and EVlncRNAs.…”

Section: Training and Test Datasets For Human Lncrnasmentioning

confidence: 99%

Predicting functional long non-coding RNAs validated by low throughput experiments

Zhou

Yang

Zhan

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

High-throughput techniques have uncovered hundreds and thousands of long non-coding RNAs (lncRNAs). Among them, only a small fraction has experimentally validated functions (EVlncRNAs) by low-throughput methods.What fraction of lncRNAs from high-throughput experiments (HTlncRNAs) is truly functional is an active subject of debate. Here, we developed the first method to distinguish EVlncRNAs from HTlncRNAs and mRNAs by using Support Vector Machines and found that EVlncRNAs can be well separated from HTlncRNAs and mRNAs with 0.6 for Matthews correlation coefficient, 64% for sensitivity, and 81% for precision for the independent human test set. The most discriminative features are related to sequence conservations at RNA (for separating from HTlncRNAs) and protein (for separating from mRNA) levels.The method is found to be robust as the human-RNA-trained model is applicable to independent mouse RNAs with similar accuracy and to a lesser extent to plant RNAs. The method can recover newly discovered EVlncRNAs with high sensitivity. Its application to randomly selected 2000 human HTlncRNAs indicates that a large number of functional lncRNAs are waiting to be validated.The method is expected to speed up and reduce the cost of the discovery by prioritizing potentially functional lncRNAs prior to experimental validation.EVlncRNA-pred is available as a web server at http://biophy.dzu.edu.cn/lncrnapred/index.html. All datasets used in this study can be obtained from the same website.

show abstract

“…Other than the above deterministic models, data-driven machine learning models are also considered in flexibility analysis [20][21][22][23][24][25][26][27][28][29], thanks to the accumulation of ever-increasing experimental data. In these learning models, biomolecular genetic, epigenetic, evolutional and structural information are extracted and used as features in machine learning models, such as support vector machine (SVM), random forest (RF), gradient boost tree (GBT) and artificial neural network (ANN).…”

Section: Introductionmentioning

confidence: 99%

“…In these learning models, biomolecular genetic, epigenetic, evolutional and structural information are extracted and used as features in machine learning models, such as support vector machine (SVM), random forest (RF), gradient boost tree (GBT) and artificial neural network (ANN). Among these learning models, an evolution-information-based learning model has been used in RNA flexibility analysis [27]. In this model, position-specific iterative basic local alignment search tool (PSI-BLAST) [30] is considered for homologous sequence identification.…”

Section: Introductionmentioning

confidence: 99%

“…The properties of the matrix are used as feature vectors and fed into various machine learning models. A Pearson correlation coefficient (PCC) value of 0.5028 between the test and predicted B-factor values has been achieved [27]. Further, more features from sequence-based information, including nucleotide acid one hot vector, predicted secondary structure, and predicted solvent accessibility, are considered in RNAbval model [29].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Weighted-persistent-homology-based machine learning for RNA flexibility analysis

2020

View full text Add to dashboard Cite

With the great significance of biomolecular flexibility in biomolecular dynamics and functional analysis, various experimental and theoretical models are developed. Experimentally, Debye-Waller factor, also known as B-factor, measures atomic mean-square displacement and is usually considered as an important measurement for flexibility. Theoretically, elastic network models, Gaussian network model, flexibility-rigidity model, and other computational models have been proposed for flexibility analysis by shedding light on the biomolecular inner topological structures. Recently, a topology-based machine learning model has been proposed. By using the features from persistent homology, this model achieves a remarkable high Pearson correlation coefficient (PCC) in protein B-factor prediction. Motivated by its success, we propose weighted-persistent-homology (WPH)-based machine learning (WPHML) models for RNA flexibility analysis. Our WPH is a newly-proposed model, which incorporate physical, chemical and biological information into topological measurements using a weight function. In particular, we use local persistent homology (LPH) to focus on the topological information of local regions. Our WPHML model is validated on a well-established RNA dataset, and numerical experiments show that our model can achieve a PCC of up to 0.5822. The comparison with the previous sequence-information-based learning models shows that a consistent improvement in performance by at least 10% is achieved in our current model.

show abstract

B‐factor profile prediction for RNA flexibility using support vector machines

Cited by 15 publications

References 37 publications

iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites

iProt-Sub: a comprehensive package for accurately mapping and predicting protease-specific substrates and cleavage sites

Predicting functional long non-coding RNAs validated by low throughput experiments

Weighted-persistent-homology-based machine learning for RNA flexibility analysis

Contact Info

Product

Resources

About