Computational Method for Identifying Malonylation Sites by Using Random Forest Algorithm.

RNA editing is a post-transcriptional RNA process that provides RNA and protein complexity for regulating gene expression in eukaryotes. It is challenging to predict RNA editing by computational methods. In this study, we developed a novel method to predict RNA editing based on a random forest method. A careful feature selection procedure was performed based on the Maximum Relevance Minimum Redundancy (mRMR) and Incremental Feature Selection (IFS) algorithms. Eighteen optimal features were selected from the 77 features in our dataset and used to construct a final predictor. The accuracy and MCC (Matthews correlation coefficient) values for the training dataset were 0.866 and 0.742, respectively; for the testing dataset, the accuracy and MCC were 0.876 and 0.576, respectively. The performance was higher using 18 features than all 77, suggesting that a small feature set was sufficient to achieve accurate prediction. Analysis of the 18 features was performed and may shed light on the mechanism and dominant factors of RNA editing, providing a basis for future experimental validation.

Protein malonylation, a reversible post-translational modification of lysine residues, is associated with various biological functions, such as cellular regulation and pathogenesis. In proteomics, to improve our understanding of the mechanisms of malonylation at the molecular level,the identification of malonylation sites via an efficient methodology is essential. However, experimental identification of malonylated substrates via mass spectrometry is time-consuming, labor-intensive, and expensive. Although numerous methods have been developed to predict malonylation sites in mammalian proteins, the computational resource for identifying plant malonylation sites is very limited. In this study, a hybrid model incorporating multiple convolutional neural networks (CNNs) with physicochemical properties, evolutionary information,and sequenced-based features was developed for identifying protein malonylation sites in mammals. For plant malonylation, multiple CNNs and random forests were integrated into a secondary modeling phase using a support vector machine. The independent testing has demonstrated that the mammalian and plant malonylation models can yield the area under the receiver operating characteristic curves (AUC) at 0.943 and 0.772, respectively. The proposed scheme has been implemented as a web-based tool, Kmalo (https://fdblab.csie.ncu.edu.tw/kmalo/home.html), which can help facilitate the functional investigation of protein malonylation on mammals and plants.

RF-MaloSite and DL-Malosite: Methods based on random forest and deep learning to identify malonylation sites

Lysine acetylation, as one type of post-translational modifications (PTM), plays key roles in cellular regulations and can be involved in a variety of human diseases. However, it is often high-cost and time-consuming to use traditional experimental approaches to identify the lysine acetylation sites. Therefore, effective computational methods should be developed to predict the acetylation sites. In this study, we developed a position-specific method for epsilon lysine acetylation site prediction. Sequences of acetylated proteins were retrieved from the UniProt database. Various kinds of features such as position specific scoring matrix (PSSM), amino acid factors (AAF), and disorders were incorporated. A feature selection method based on mRMR (Maximum Relevance Minimum Redundancy) and IFS (Incremental Feature Selection) was employed. Finally, 319 optimal features were selected from total 541 features. Using the 319 optimal features to encode peptides, a predictor was constructed based on dagging. As a result, an accuracy of 69.56% with MCC of 0.2792 was achieved. We analyzed the optimal features, which suggested some important factors determining the lysine acetylation sites. We developed a position-specific method for epsilon lysine acetylation site prediction. A set of optimal features was selected. Analysis of the optimal features provided insights into the mechanism of lysine acetylation sites, providing guidance of experimental validation.

Feature-rank-code-based classifiers have been proposed recently in order to reduce the complexity for electronic nose system (ENS). The performance of these classifiers is degraded when the discriminatory information of gases lie in the actual feature values not in the ranks of features. To overcome the problem, a gas identification system based on a simple distance measure in combination with different type of features is proposed. In order to improve the computational cost of the existing ENS, a novel combination of optimum subset of features is proposed. To achieve the aim of low computational cost, a large feature vector is recursively reduced to a small number of features without compromising the classification accuracy of the system. Discrete binary particle swarm optimization, a metaheuristic for global search is used in a recursive setup to select the optimum subset of features for classification. Euclidian distance is used as a similarity measure for identification of different industrial gases. The proposed system is tested for the identification of 13 different industrial gases, namely, C3H8, Cl2, CO, CO2, SO2, NO2, NH3, C2H4O, C3H6O, C2H4, C2H6O, C7H8, and CH4. These gases are contained in three different data sets; two among these data sets are acquired experimentally in a laboratory setup, while one of these data sets is taken from the University of California at Irvine machine learning repository. Results reveal that the computational cost and the memory requirement of an ENS can be significantly reduced by combining different type of features. An average classification accuracy of 98.17% is achieved by the proposed system with an average 69.04% reduction in memory requirement using only three to five features.

BackgroundStructural flexibility is an important characteristic of proteins because it is often associated with their function. The movement of a polypeptide segment in a protein can be broken down into two types of motions: internal and external ones. The former is deformation of the segment itself, but the latter involves only rotational and translational motions as a rigid body. Normal Model Analysis (NMA) can derive these two motions, but its application remains limited because it necessitates the gathering of complete structural information.ResultsIn this work, we present a novel method for predicting two kinds of protein motions in ordered structures. The prediction uses only information from the amino acid sequence. We prepared a dataset of the internal and external motions of segments in many proteins by application of NMA. Subsequently, we analyzed the relation between thermal motion assessed from X-ray crystallographic B-factor and internal/external motions calculated by NMA. Results show that attributes of amino acids related to the internal motion have different features from those related to the B-factors, although those related to the external motion are correlated strongly with the B-factors. Next, we developed a method to predict internal and external motions from amino acid sequences based on the Random Forest algorithm. The proposed method uses information associated with adjacent amino acid residues and secondary structures predicted from the amino acid sequence. The proposed method exhibited moderate correlation between predicted internal and external motions with those calculated by NMA. It has the highest prediction accuracy compared to a naïve model and three published predictors.ConclusionsFinally, we applied the proposed method predicting the internal motion to a set of 20 proteins that undergo large conformational change upon protein-protein interaction. Results show significant overlaps between the predicted high internal motion regions and the observed conformational change regions.

In this work, we aim to show that machine learning algorithms are promising tools for the identification of nuclear data that contribute to increased errors in transport simulations. We demonstrate this through an application of a machine learning algorithm (Random Forest) to the Whisper/MCNP6 criticality validation library to identify nuclear data that are associated with an increase of the bias (simulated-experimental ) in the calculations. Specifically, the sensitivity profiles (with respect to nuclear data) of solution benchmarks are used to predict the bias, and SHapley Additive exPlanations (SHAP) are used to explain how the sensitivities are related to the predicted bias. The SHAP values can be interpreted as sensitivity coefficients of the machine learning model to the sensitivities that are used to make predictions of bias. Using the SHAP values, we can identify specific subsets of nuclear data that have the highest probability of influencing bias. We demonstrate the utility of this method by showing how SHAP values were used to identify an inconsistency in the inelastic scattering nuclear data. The methodology presented here is not limited to transport problems and can be applied to other simulations if there are experimental measurements to compare against, simulations of those experimental measurements, and the ability to calculate sensitivities of the model output with respect to the data inputs.

Identification of DNA-binding proteins from only sequence information is one of the most challenging problems in the field of genome annotation. DNA-binding proteins play an important role in various biological processes such as DNA replication, repair, transcription and splicing. Existing experimental techniques for identifying DNA-binding proteins are time-consuming and expensive. Thus, prediction of DNA-binding proteins from sequences alone using computational methods can be useful to quickly annotate and guide the experimental process. Most of the methods developed for predicting DNA-binding proteins use the information from the evolutionary profile, called the position-specific scoring matrix (PSSM) profile, alone and the accuracies of such methods have been limited. Here, we propose a method, called StackDPPred, which utilizes features extracted from PSSM and residue specific contact-energy to help train a stacking based machine learning method for the effective prediction of DNA-binding proteins. Based on benchmark sequences of 1063 (518 DNA-binding and 545 non DNA-binding) proteins and using jackknife validation, StackDPPred achieved an ACC of 89.96%, MCC of 0.799 and AUC of 94.50%. This outcome outperforms several state-of-the-art approaches. Furthermore, when tested on recently designed two independent test datasets, StackDPPred outperforms existing approaches consistently. The proposed StackDPPred can be used for effective prediction of DNA-binding proteins from sequence alone. Online server is at http://bmll.cs.uno.edu/add and code-data is at http://cs.uno.edu/∼tamjid/Software/StackDPPred/code_data.zip. Supplementary data are available at Bioinformatics online.

Background:Protein fold prediction is a fundamental step in Structural Bioinformatics. The tertiary structure of a protein determines its function and to predict its tertiary structure, fold prediction serves an important role. Protein fold is simply the arrangement of the secondary structure elements relative to each other in space. A number of studies have been carried out till date by different research groups working worldwide in this field by using the combination of different benchmark datasets, different types of descriptors, features and classification techniques.Objective:In this study, we have tried to put all these contributions together, analyze their study and to compare different techniques used by them.Methods:Different features are derived from protein sequence, its secondary structure, different physicochemical properties of amino acids, domain composition, Position Specific Scoring Matrix, profile and threading techniques.Conclusion:Combination of these different features can improve classification accuracy to a large extent. With the help of this survey, one can know the most suitable feature/attribute set and classification technique for this multi-class protein fold classification problem.

Cancerlectins have an inhibitory effect on the growth of cancer cells and are currently being employed as therapeutic agents. The accurate identification of the cancerlectins should provide insight into the molecular mechanisms of cancers. In this study, a new computational method based on the RF (Random Forest) algorithm is proposed for further improving the performance of identifying cancerlectins. Hybrid feature space before feature selection is developed by combining different individual feature spaces, CTD (Composition, Transition, and Distribution), PseAAC (Pseudo Amino Acid Composition), PSSM (Position-Specific Scoring Matrix), and disorder. The SMOTE (Synthetic Minority Oversampling Technique) is applied to solve the imbalanced data problem. To reduce feature redundancy and computation complexity, we propose a two-step feature selection process to select informative features. A 5-fold cross-validation technique is used for the evaluation of various prediction strategies. The proposed method achieves a sensitivity of 0.779, a specificity of 0.717, an accuracy of 0.748, and an MCC (Matthew's Correlation Coefficient) of 0.497. The prediction results are also compared with other existing methods on the same dataset using 5-fold cross-validation. The comparison results demonstrate the high effectiveness of our method for predicting cancerlectins.

Scareware is a recent type of malicious software that may pose financial and privacy-related threats to novice users. Traditional countermeasures, such as anti-virus software, require regular updates and often lack the capability of detecting novel (unseen) instances. This paper presents a scareware detection method that is based on the application of machine learning algorithms to learn patterns in extracted variable length opcode sequences derived from instruction sequences of binary files. The patterns are then used to classify software as legitimate or scareware but they may also reveal interpretable behavior that is unique to either type of software. We have obtained a large number of real world scareware applications and designed a data set with 550 scareware instances and 250 benign instances. The experimental results show that several common data mining algorithms are able to generate accurate models from the data set. The Random Forest algorithm is shown to outperform the other algorithms in the experiment. Essentially, our study shows that, even though the differences between scareware and legitimate software are subtler than between, say, viruses and legitimate software, the same type of machine learning approach can be used in both of these dissimilar cases.

Proteinases play critical roles in both intra and extracellular processes by binding and cleaving their protein substrates. The cleavage can either be non-specific as part of degradation during protein catabolism or highly specific as part of proteolytic cascades and signal transduction events. Identification of these targets is extremely challenging. Current computational approaches for predicting cleavage sites are very limited since they mainly represent the amino acid sequences as patterns or frequency matrices. In this work, we developed a novel predictor based on Random Forest algorithm (RF) using maximum relevance minimum redundancy (mRMR) method followed by incremental feature selection (IFS). The features of physicochemical/biochemical properties, sequence conservation, residual disorder, amino acid occurrence frequency, secondary structure and solvent accessibility were utilized to represent the peptides concerned. Here, we compared existing prediction tools which are available for predicting possible cleavage sites in candidate substrates with ours. It is shown that our method makes much more reliable predictions in terms of the overall prediction accuracy. In addition, this predictor allows the use of a wide range of proteinases.

Post-translational modifications (PTMs) are critical regulators of bacterial biofilm formation, but the role of lysine malonylation (Kmal) in biofilm formation is still poorly understood. In this study, we analyzed the dynamic changes of protein malonylation of Staphylococcus aureus (S. aureus) DC15 during biofilm formation based on antibody affinity enrichment combined with quantitative proteomics. Quantitative profiling identified 2,833 malonylated sites across 788 proteins, with significant enrichment in biofilm-associated proteins. Twelve conserved motifs, including Kmal******R and Kmal****R (* represents any amino acid residue), dominated the malonyl proteome landscape in S. aureus. The combined analysis of modified and quantitative proteomics revealed the quorum-sensing system as a key regulatory hub in S. aureus biofilm formation. In particular, the response regulator, AgrA, showed decreased expression but increased malonylation at the K2, K11, and K216 sites during S. aureus biofilm formation, suggesting functional compensation. Structural and phylogenetic analysis showed that the key malonylation sites (K216) of protein AgrA were evolutionarily conserved in Gram-positive pathogens including Bacillus cereus. Molecular docking analysis found that antimicrobial peptide BCp12 and natural compound chlorogenic acid could bind with the malonylation sites in AgrA (ΔG = -6.888 and -5.302 kcal/mol, respectively). This study provides a new perspective for understanding the general rules of bacterial biofilm formation and developing broad-spectrum anti-biofilm drugs.

In the postgenomic era, the large-scale data, such as genome sequences, mRNA sequences, and protein sequences, increase rapidly. It is desired to develop the computational approaches that can derive and analyze useful information from them to promote the development of biomedicine and drug design. Meanwhile, in order to understand how proteinprotein interactions and other complex interactions in a living system get integrated in complex nonlinear networks and regulate cell function, a new discipline, called "Systems Biology", is created.

Cell transplantation is an effective method for compensating for the loss of liver function and improve patient survival. However, given that hepatocytes cultivated in vitro have diverse developmental processes and physiological features, obtaining hepatocytes that can properly function in vivo is difficult. In the present study, we present an advanced computational analysis on single-cell transcriptional profiling to resolve the heterogeneity of the hepatocyte differentiation process in vitro and to mine biomarkers at different periods of differentiation. We obtained a batch of compressed and effective classification features with the Boruta method and ranked them using the Max-Relevance and Min-Redundancy method. Some key genes were identified during the in vitro culture of hepatocytes, including CD147, which not only regulates terminally differentiated cells in the liver but also affects cell differentiation. PPIA, which encodes a CD147 ligand, also appeared in the identified gene list, and the combination of the two proteins mediated multiple biological pathways. Other genes, such as TMSB10, TMEM176B, and CD63, which are involved in the maturation and differentiation of hepatocytes and assist different hepatic cell types in performing their roles were also identified. Then, several classifiers were trained and evaluated to obtain optimal classifiers and optimal feature subsets, using three classification algorithms (random forest, k-nearest neighbor, and decision tree) and the incremental feature selection method. The best random forest classifier with a 0.940 Matthews correlation coefficient was constructed to distinguish different hepatic cell types. Finally, classification rules were created for quantitatively describing hepatic cell types. In summary, This study provided potential targets for cell transplantation associated liver disease treatment strategies by elucidating the process and mechanism of hepatocyte development at both qualitative and quantitative levels.