Predicting DNA binding proteins using support vector machine with hybrid fractal features

UMAP-DBP: An Improved DNA-Binding Proteins Prediction Method Based on Uniform Manifold Approximation and Projection

DNA-binding proteins play a vital role in cellular processes. It is an extremely urgent to develop a high-throughput method for efficiently identifying DNA-binding proteins. According to the current research situation, some methods in machine learning and deep learning show excellent computational speed and accuracy, which are worthy of application. In this work, a novel predictor was proposed to predict DNA binding proteins called UMAP-DBP. Firstly, the feature extraction of primary protein sequence was realized based on physicochemical distance transformation, Profile-based auto-cross covariance and General series correlation pseudo amino acid composition. Secondly, uniform manifold approximation and projection (UMAP) and feature importance score methods were used for feature selection; there is a progressive relationship between them. Finally, the Adaboost operation engine with jackknife test were adopted for predicting DNA-binding proteins. For the jackknife test on the BP1075 and BP594, we obtained an overall accuracy of 82.97% and 82.14%, Cohen's kappa (CK) of 0.66 and 0.64, respectively. The results illustrate that a feasible method has been developed for predicting DNA-binding proteins by UMAP and Adaboost. This is the first study in which UMAP has been successfully applied to identify DNA-binding proteins. All the datasets and codes are accessible at https://github.com/Wang-Jinyue/UMAP-DBP .

Small-Angle Scattering and Multifractal Analysis of DNA Sequences

The arrangement of A, C, G and T nucleotides in large DNA sequences of many prokaryotic and eukaryotic cells exhibit long-range correlations with fractal properties. Chaos game representation (CGR) of such DNA sequences, followed by a multifractal analysis, is a useful way to analyze the corresponding scaling properties. This approach provides a powerful visualization method to characterize their spatial inhomogeneity, and allows discrimination between mono- and multifractal distributions. However, in some cases, two different arbitrary point distributions, may generate indistinguishable multifractal spectra. By using a new model based on multiplicative deterministic cascades, here it is shown that small-angle scattering (SAS) formalism can be used to address such issue, and to extract additional structural information. It is shown that the box-counting dimension given by multifractal spectra can be recovered from the scattering exponent of SAS intensity in the fractal region. This approach is illustrated for point distributions of CGR data corresponding to Escherichia coli, Phospholamban and Mouse mitochondrial DNA, and it is shown that for the latter two cases, SAS allows extraction of the fractal iteration number and the scaling factor corresponding to "ACGT" square, or to recover the number of bases. The results are compared with a model based on multiplicative deterministic cascades, and respectively with one which takes into account the existence of forbidden sequences in DNA. This allows a classification of the DNA sequences in terms of random and deterministic fractals structures emerging in CGR.

Integrating sequence and gene expression information predicts genome-wide DNA-binding proteins and suggests a cooperative mechanism

DNA-binding proteins (DBPs) perform diverse biological functions ranging from transcription to pathogen sensing. Machine learning methods can not only identify DBPs de novo but also provide insights into their DNA-recognition dynamics. However, it remains unclear whether available methods that can accurately predict DNA-binding sites in known DBPs can also identify novel DBPs. Moreover, sequence information is blind to the cellular- and disease-specific contexts of DBP activities, whereas the under-utilized knowledge from public gene expression data offers great promise. To address these issues, we have developed novel methods for predicting DBPs by integrating sequence and gene expression-derived features and applied them to explore human, mouse and Arabidopsis proteomes. While our sequence-based models outperformed the gene expression-based ones, some proteins with weaker DBP-like sequence features were correctly predicted by gene expression-based features, suggesting that these proteins acquire a tangible DBP functionality in a conducive gene expression environment. Analysis of motif enrichment among the co-expressed genes of top 100 candidates DBPs from hitherto unannotated genes provides further avenues to explore their functional associations.

Prediction of RNA-protein interactions using conjoint triad feature and chaos game representation

RNA-protein interactions (RPIs) play a very important role in a wide range of post-transcriptional regulations, and identifying whether a given RNA-protein pair can form interactions or not is a vital prerequisite for dissecting the regulatory mechanisms of functional RNAs. Currently, expensive and time-consuming biological assays can only determine a very small portion of all RPIs, which calls for computational approaches to help biologists efficiently and correctly find candidate RPIs. Here, we integrated a successful computing algorithm, conjoint triad feature (CTF), and another method, chaos game representation (CGR), for representing RNA-protein pairs and by doing so developed a prediction model based on these representations and random forest (RF) classifiers. When testing two benchmark datasets, RPI369 and RPI2241, the combined method (CTF+CGR) showed some superiority compared with four existing tools. Especially on RPI2241, the CTF+CGR method improved prediction accuracy (ACC) from 0.91 (the best record of all published works) to 0.95. When independently testing a newly constructed dataset, RPI1449, which only contained experimentally validated RPIs released between 2014 and 2016, our method still showed some generalization capability with an ACC of 0.75. Accordingly, we believe that our hybrid CTF+CGR method will be an important tool for predicting RPIs in the future.

Identification of DNA-binding proteins by combining auto-cross covariance transformation and ensemble learning

DNA-binding proteins play a pivotal role in various intra- and extra-cellular activities ranging from DNA replication to gene expression control. With the rapid development of next generation of sequencing technique, the number of protein sequences is unprecedentedly increasing. Thus it is necessary to develop computational methods to identify the DNA-binding proteins only based on the protein sequence information. In this study, a novel method called iDNA-KACC is presented, which combines the Support Vector Machine (SVM) and the auto-cross covariance transformation. The protein sequences are first converted into profile-based protein representation, and then converted into a series of fixed-length vectors by the auto-cross covariance transformation with Kmer composition. The sequence order effect can be effectively captured by this scheme. These vectors are then fed into Support Vector Machine (SVM) to discriminate the DNA-binding proteins from the non DNA-binding ones. iDNA-KACC achieves an overall accuracy of 75.16% and Matthew correlation coefficient of 0.5 by a rigorous jackknife test. Its performance is further improved by employing an ensemble learning approach, and the improved predictor is called iDNA-KACC-EL. Experimental results on an independent dataset shows that iDNA-KACC-EL outperforms all the other state-of-the-art predictors, indicating that it would be a useful computational tool for DNA binding protein identification. .

DNA-binding protein prediction using plant specific support vector machines: validation and application of a new genome annotation tool

There are currently 151 plants with draft genomes available but levels of functional annotation for putative protein products are low. Therefore, accurate computational predictions are essential to annotate genomes in the first instance, and to provide focus for the more costly and time consuming functional assays that follow. DNA-binding proteins are an important class of proteins that require annotation, but current computational methods are not applicable for genome wide predictions in plant species. Here, we explore the use of species and lineage specific models for the prediction of DNA-binding proteins in plants. We show that a species specific support vector machine model based on Arabidopsis sequence data is more accurate (accuracy 81%) than a generic model (74%), and based on this we develop a plant specific model for predicting DNA-binding proteins. We apply this model to the tomato proteome and demonstrate its ability to perform accurate high-throughput prediction of DNA-binding proteins. In doing so, we have annotated 36 currently uncharacterised proteins by assigning a putative DNA-binding function. Our model is publically available and we propose it be used in combination with existing tools to help increase annotation levels of DNA-binding proteins encoded in plant genomes.

PSSP-RFE: accurate prediction of protein structural class by recursive feature extraction from PSI-BLAST profile, physical-chemical property and functional annotations

Protein structure prediction is critical to functional annotation of the massively accumulated biological sequences, which prompts an imperative need for the development of high-throughput technologies. As a first and key step in protein structure prediction, protein structural class prediction becomes an increasingly challenging task. Amongst most homological-based approaches, the accuracies of protein structural class prediction are sufficiently high for high similarity datasets, but still far from being satisfactory for low similarity datasets, i.e., below 40% in pairwise sequence similarity. Therefore, we present a novel method for accurate and reliable protein structural class prediction for both high and low similarity datasets. This method is based on Support Vector Machine (SVM) in conjunction with integrated features from position-specific score matrix (PSSM), PROFEAT and Gene Ontology (GO). A feature selection approach, SVM-RFE, is also used to rank the integrated feature vectors through recursively removing the feature with the lowest ranking score. The definitive top features selected by SVM-RFE are input into the SVM engines to predict the structural class of a query protein. To validate our method, jackknife tests were applied to seven widely used benchmark datasets, reaching overall accuracies between 84.61% and 99.79%, which are significantly higher than those achieved by state-of-the-art tools. These results suggest that our method could serve as an accurate and cost-effective alternative to existing methods in protein structural classification, especially for low similarity datasets.