Rule-Based Knowledge Acquisition Method for Promoter Prediction in Human andDrosophilaSpecies

Abstract

The rapid and reliable identification of promoter regions is important when the number of genomes to be sequenced is increasing very speedily. Various methods have been developed but few methods investigate the effectiveness of sequence-based features in promoter prediction. This study proposes a knowledge acquisition method (named PromHD) based on if-then rules for promoter prediction in human and Drosophila species. PromHD utilizes an effective feature-mining algorithm and a reference feature set of 167 DNA sequence descriptors (DNASDs), comprising three descriptors of physicochemical properties (absorption maxima, molecular weight, and molar absorption coefficient), 128 top-ranked descriptors of 4-mer motifs, and 36 global sequence descriptors. PromHD identifies two feature subsets with 99 and 74 DNASDs and yields test accuracies of 96.4% and 97.5% in human and Drosophila species, respectively. Based on the 99- and 74-dimensional feature vectors, PromHD generates several if-then rules by using the decision tree mechanism for promoter prediction. The top-ranked informative rules with high certainty grades reveal that the global sequence descriptor, the length of nucleotide A at the first position of the sequence, and two physicochemical properties, absorption maxima and molecular weight, are effective in distinguishing promoters from non-promoters in human and Drosophila species, respectively.

A Review of Computational Intelligence Methods for Eukaryotic Promoter Prediction

“…Random Forest [19] Interval Position Vector Matrix -0.53 -SVM [55] Particle Swarm Optimization -0.62 0.62 SVM [5] GP 7-cross validation 0.86 0.90 FFNN [35] Mapping function 3-cross validation 0.90 0.90 PSVM [56] Markov model 5-cross validation 0.93 0.98 SVM [57] Sliding Window -0.69 -SVM [58] Markov Model ---SVM [59] Physicochemical properties 10-cross validation 0.96 0.98 * Under this column, the numbers appearing in the square brackets are reference numbers.…”

“…On the other hand, two other methods based on structural and physiochemical properties of DNA sequences shown greater accuracy in 2012 and 2014 respectively. [58,59] …”

Identification of Biomarkers for Esophageal Squamous Cell Carcinoma Using Feature Selection and Decision Tree Methods

“…Decision tree algorithms are useful methods to generate interpretable rules based on gene expressions for ESCC classification that are widely used in various classification and regression problems such as immunogenic peptides [ 17 ], promoters [ 18 ], and nongenotoxic hepatocarcinogenicity [ 19 ]. In this study, a decision tree method J48 implemented in WEKA [ 20 ], also known as C4.5 [ 21 ], is applied to construct decision tree classifiers and derive interpretable rules.…”

Temporal and spatial expression of Drosophila Neurexin during the life cycle visualized using a DNRX-Gal4/UAS-reporter

“…DNRX-Gal4 lines have been described in our previous publication (Sun et al, 2009). Analyses of dnrx promoter region were performed using the promoter prediction program (NNPP version 2.2, Berkeley Drosophila Genome Project, http://www.fruitfly.org/index.html) (Huang et al, 2014;Reese, 2001). The genomic fragment including the dnrx core promoter was amplified and cloned into the pPTGAL (Sharma et al, 2002) [12] vector.…”