Prediction of donor splice sites using random forest with a new sequence encoding approach

Abstract

BackgroundDetection of splice sites plays a key role for predicting the gene structure and thus development of efficient analytical methods for splice site prediction is vital. This paper presents a novel sequence encoding approach based on the adjacent di-nucleotide dependencies in which the donor splice site motifs are encoded into numeric vectors. The encoded vectors are then used as input in Random Forest (RF), Support Vector Machines (SVM) and Artificial Neural Network (ANN), Bagging, Boosting, Logistic regression, kNN and Naïve Bayes classifiers for prediction of donor splice sites.ResultsThe performance of the proposed approach is evaluated on the donor splice site sequence data of Homo sapiens, collected from Homo Sapiens Splice Sites Dataset (HS3D). The results showed that RF outperformed all the considered classifiers. Besides, RF achieved higher prediction accuracy than the existing methods viz., MEM, MDD, WMM, MM1, NNSplice and SpliceView, while compared using an independent test dataset.ConclusionBased on the proposed approach, we have developed an online prediction server (MaLDoSS) to help the biological community in predicting the donor splice sites. The server is made freely available at http://cabgrid.res.in:8080/maldoss. Due to computational feasibility and high prediction accuracy, the proposed approach is believed to help in predicting the eukaryotic gene structure.Electronic supplementary materialThe online version of this article (doi:10.1186/s13040-016-0086-4) contains supplementary material, which is available to authorized users.

Differential Architecture Search in Deep Learning for DNA Splice Site Classification

“…The ML based techniques can predict non-canonical sites as well by appropriate training. Different ML approaches has been used such as Support Vector Machines (SVM) [16,17,18,19] Random Forest (RF) [20], Decision Trees (DT) [21], Naïve Bayesian (NB) [22], Markov Model [23] and AdaBoost [24] to identify splice or non-splice sites. Among them SVM models have been used very often due to their capability to handle high-dimensional datasets.…”

Thorough in silico and in vitro cDNA analysis of 21 putativeBRCA1andBRCA2splice variants and a complex tandem duplication inBRCA2allowing the identification of activated cryptic splice donor sites inBRCA2exon 11

“…Due to complex dependencies existing among the bases around splice sites, none of the frequently used programs perfectly predict the impact on pre-mRNA splicing. Learning algorithms such as AdaBoost (Pashaei, Yilmaz, Ozen, & Aydin, 2016) and Random Forest (Meher, Sahu, & Rao, 2016) are now emerging and need to be validated for their use in research and clinical practice.…”

Special Protein Molecules Computational Identification

“…Matrix metalloproteinase (MMP) are key factors for the degradation of extracellular matrix components and modification of cytokines, protease inhibitors, and cell surface signaling systems [103][104][105][106]. Polymorphisms on the MMP-9 promoter can affect the development of visceral involvement in Korean people with BD [107].…”

“…The independent test dataset was frequently constructed to evaluate the performances of protein function predictors in recent years [99][100][101][102][103][104]. To construct a valid set of data for building the predictor of each family, the datasets of the training, testing and independent test were generated by a strictly defined process after the data collection described in Section 2.1.…”