H. Ismail

RF-Phos: A Novel General Phosphorylation Site Prediction Tool Based on Random Forest

Protein phosphorylation is one of the most widespread regulatory mechanisms in eukaryotes. Over the past decade, phosphorylation site prediction has emerged as an important problem in the field of bioinformatics. Here, we report a new method, termed Random Forest-based Phosphosite predictor 2.0 (RF-Phos 2.0), to predict phosphorylation sites given only the primary amino acid sequence of a protein as input. RF-Phos 2.0, which uses random forest with sequence and structural features, is able to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation and an independent dataset, RF-Phos 2.0 compares favorably to other popular mammalian phosphosite prediction methods, such as PhosphoSVM, GPS2.1, and Musite.

Effect of probiotic supplementation on growth and global gene expression in dairy cows

ABSTRACT Use of probiotic supplements as a non-chemical approach to promote health has increased in animal production. The present study evaluated the effect of oral probiotic administration on growth and global gene expression profile in dairy cows. Lactating Holstein-Friesian cows received a daily dose (50 ml) of a commercial probiotic (containing Lactobacillus acidophilus, Saccharomyces cerevisiae, Enterococcus faecium, Aspergillus oryza and Bacillus subtilis) for 60 days. A microarray experiment was performed with blood collected at day-0 and day-60. Although probiotic supplementation had no effect on body weight, PCV and total protein concentration in plasma (P > 0.05), per cent lymphocyte count increased (P < 0.05), and per cent neutrophil count decreased (P < 0.05) in probiotic-treated animals. Gene expression analysis identified 10,859 differentially expressed genes, 1168 up-regulated and 9691 down-regulated genes, respectively, following probiotic treatment. Single experiment pathway analysis identified 87 bovine pathways impacted by probiotic treatment. These pathways included the Toll-like receptor (TLR), inflammation response and Wingless signalling pathways. Oral administration of probiotics to dairy cows had a systemic effect on global gene expression, such as on genes involved in immunity and homeostasis. The results of this study show that the utilization of probiotics in animal agriculture impacts genes important to dairy cow health and production.

Phosphorylation sites prediction using Random Forest

Protein phosphorylation is one of the most widespread regulatory mechanisms in eukaryotes. Over the past decade, phosphorylation site prediction has emerged as an important problem in the field of bioinformatics. Here, we report a new method, termed Random Forest-based Phosphosite predictor 1.0 (RF-Phos 1.0), to predict phosphorylation sites given only the primary amino acid sequence of a protein as input. RF-Phos 1.0, which uses random forest classifiers to integrate various sequence and structural features, is able to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation and an independent dataset, RF-Phos 1.0 compares favorably to other existing phosphosite prediction methods, such as PhosphoSVM, GPS2.1 and Musite.

Transcriptional profiling of the effect of lipopolysaccharide (LPS) pretreatment in blood from probiotics-treated dairy cows

Probiotic supplements are beneficial for animal health and rumen function; and lipopolysaccharides (LPS) from gram negative bacteria have been associated with inflammatory diseases. In this study the transcriptional profile in whole blood collected from probiotics-treated cows was investigated in response to stimulation with lipopolysaccharides (LPS) in vitro. Microarray experiment was performed between LPS-treated and control samples using the Agilent one-color bovine v2 bovine (v2) 4x44K array slides. Global gene expression analysis identified 13,658 differentially expressed genes (fold change cutoff ≥ 2, P < 0.05), 3816 upregulated genes and 9842 downregulated genes in blood in response to LPS. Treatment with LPS resulted in increased expression of TLR4 (Fold change (FC) = 3.16) and transcription factor NFkB (FC = 5.4) and decreased the expression of genes including TLR1 (FC = − 2.54), TLR3 (FC = − 2.43), TLR10 (FC = − 3.88), NOD2 (FC = − 2.4), NOD1 (FC = − 2.45) and pro-inflammatory cytokine IL1B (− 3.27). The regulation of the genes involved in inflammation signaling pathway suggests that probiotics may stimulate the innate immune response of animal against parasitic and bacterial infections. We have provided a detailed description of the experimental design, microarray experiment and normalization and analysis of data which have been deposited into NCBI Gene Expression Omnibus (GEO): GSE75240.

RF-NR: Random forest based approach for improved classification of Nuclear Receptors

The Nuclear Receptor (NR) superfamily plays an important role in key biological, developmental, and physiological processes. Developing a method for the classification of NR proteins is an important step towards understanding the structure and functions of the newly discovered NR protein. The recent studies on NR classification are either unable to achieve optimum accuracy or are not designed for all the known NR subfamilies. In this study, we developed RF-NR, which is a Random Forest based approach for improved classification of nuclear receptors. The RF-NR can predict whether a query protein sequence belongs to one of the eight NR subfamilies or it is a non-NR sequence. The RF-NR uses spectrum-like features namely: Amino Acid Composition, Di-peptide Composition, and Tripeptide Composition. Benchmarking on two independent datasets with varying sequence redundancy reduction criteria, the RF-NR achieves better (or comparable) accuracy than other existing methods. The added advantage of our approach is that we can also obtain biological insights about the important features that are required to classify NR subfamilies. RF-NR is freely available at http://bcb.ncat.edu/RF_NR/.

CNN-BLPred: A Convolutional neural network based predictor for β-Lactamases (BL) and their classes

BackgroundThe β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory.ResultsWe addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms.Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend.ConclusionsWe implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

RF-Phos: Random forest-based prediction of phosphorylation sites

It is estimated that about 30% of the proteins in the human proteome are regulated by phosphorylation. In recent years, phosphorylation site prediction has been investigated in the field of bioinformatics. This has become necessary due to the challenges associated with experimental methods. Previously, we developed a random forest-based method, termed Random Forest-based Phosphosite predictor (RF-Phos 1.0), to predict phosphorylation sites in proteins given only the amino acid sequence of a protein as input. Here, we report an improved version of this method, termed RF-Phos 1.1 that employs additional sequence-driven features to identify putative sites of phosphorylation across many protein families. In side-by-side comparisons based on 10-fold cross validation analysis and an independent dataset, RF-Phos 1.1 performs comparably to or better than other existing phosphosite prediction methods, such as PhosphoSVM, GPS2.1 and Musite.