Embryonic Ethanol but Not Cannabinoid Exposure Affects Zebrafish Cardiac Development via Agrin and Sonic Hedgehog Interaction.

Recent studies demonstrate the adverse effects of cannabinoids on development, including via pathways shared with ethanol exposure. Our laboratory has shown that both the nervous system and cardiac development are dependent on agrin modulation of sonic hedgehog (shh) and fibroblast growth factor (Fgf) signaling pathways. As both ethanol and cannabinoids impact these signaling molecules, we examined their role on zebrafish heart development. Zebrafish embryos were exposed to a range of ethanol and/or cannabinoid receptor 1 and 2 agonist concentrations in the absence or presence of morpholino oligonucleotides that disrupt agrin or shh expression. In situ hybridization was employed to analyze cardiac marker gene expression. Exposure to cannabinoid receptor agonists disrupted midbrain-hindbrain boundary development, but had no effect on heart development, as assessed by the presence of cardiac edema or the altered expression of cardiac marker genes. In contrast, exposure to 1.5% ethanol induced cardiac edema and the altered expression of cardiac marker genes. Combined exposure to agrin or shh morpholino and 0.5% ethanol disrupted the cmlc2 gene expression pattern, with the restoration of the normal expression following shh mRNA overexpression. These studies provide evidence that signaling pathways critical to heart development are sensitive to ethanol exposure, but not cannabinoids, during early zebrafish embryogenesis.

Automated, High-Throughput Protoplast Transfection for Gene Editing and Transgene Expression Studies.

In an era of cost-efficient gene synthesis and high-throughput construct assembly, the onus of scientific experimentation is on the rate of in vivo testing for the identification of top performing candidates or designs. Assay platforms that are relevant to the species of interest and in the tissue of choice are highly desirable. A protoplast isolation and transfection method that is compatible with a large repertoire of species and tissues would be the platform of choice. A necessary aspect of this high-throughput screening approach is the need to handle many delicate protoplast samples at the same time, which is a bottleneck for manual operation. Such bottlenecks can be mitigated with the use of automated liquid handlers for the execution of protoplast transfection steps. The method described within this chapter utilizes a 96-well head for simultaneous, high-throughput initiation of transfection. While initially developed and optimized for use with etiolated maize leaf protoplasts, the automated protocol has also been demonstrated to be compatible with other established protoplast systems, such as soybean immature embryo derived protoplast, similarly described within. This chapter also includes instructions for a sample randomization design to reduce the impact of edge effects, which might be present when microplates are used for fluorescence readout following transfection. We also describe a streamlined, expedient, and cost-effective protocol for determining gene editing efficiencies using the T7E1 endonuclease cleavage assay with a publicly available image analysis tool.

Clustering-Driven DGS-Based Micro-Doppler Feature Extraction for Automatic Dynamic Hand Gesture Recognition.

We propose in this work a dynamic group sparsity (DGS) based time-frequency feature extraction method for dynamic hand gesture recognition (HGR) using millimeter-wave radar sensors. Micro-Doppler signatures of hand gestures show both sparse and structured characteristics in time-frequency domain, but previous study only focus on sparsity. We firstly introduce the structured prior when modeling the micro-Doppler signatures in this work to further enhance the features of hand gestures. The time-frequency distributions of dynamic hand gestures are first modeled using a dynamic group sparse model. A DGS-Subspace Pursuit (DGS-SP) algorithm is then utilized to extract the corresponding features. Finally, the support vector machine (SVM) classifier is employed to realize the dynamic HGR based on the extracted group sparse micro-Doppler features. The experiment shows that the proposed method achieved 3.3% recognition accuracy improvement over the sparsity-based method and has a better recognition accuracy than CNN based method in small dataset.

Multi-Scale Capsule Attention Network and Joint Distributed Optimal Transport for Bearing Fault Diagnosis under Different Working Loads.

In recent years, intelligent fault diagnosis methods based on deep learning have developed rapidly. However, most of the existing work performs well under the assumption that training and testing samples are collected from the same distribution, and the performance drops sharply when the data distribution changes. For rolling bearings, the data distribution will change when the load and speed change. In this article, to improve fault diagnosis accuracy and anti-noise ability under different working loads, a transfer learning method based on multi-scale capsule attention network and joint distributed optimal transport (MSCAN-JDOT) is proposed for bearing fault diagnosis under different loads. Because multi-scale capsule attention networks can improve feature expression ability and anti-noise performance, the fault data can be better expressed. Using the domain adaptation ability of joint distribution optimal transport, the feature distribution of fault data under different loads is aligned, and domain-invariant features are learned. Through experiments that investigate bearings fault diagnosis under different loads, the effectiveness of MSCAN-JDOT is verified; the fault diagnosis accuracy is higher than that of other methods. In addition, fault diagnosis experiment is carried out in different noise environments to demonstrate MSCAN-JDOT, which achieves a better anti-noise ability than other transfer learning methods.

iEnhancer-GAN: A Deep Learning Framework in Combination with Word Embedding and Sequence Generative Adversarial Net to Identify Enhancers and Their Strength.

As critical components of DNA, enhancers can efficiently and specifically manipulate the spatial and temporal regulation of gene transcription. Malfunction or dysregulation of enhancers is implicated in a slew of human pathology. Therefore, identifying enhancers and their strength may provide insights into the molecular mechanisms of gene transcription and facilitate the discovery of candidate drug targets. In this paper, a new enhancer and its strength predictor, iEnhancer-GAN, is proposed based on a deep learning framework in combination with the word embedding and sequence generative adversarial net (Seq-GAN). Considering the relatively small training dataset, the Seq-GAN is designed to generate artificial sequences. Given that each functional element in DNA sequences is analogous to a "word" in linguistics, the word segmentation methods are proposed to divide DNA sequences into "words", and the skip-gram model is employed to transform the "words" into digital vectors. In view of the powerful ability to extract high-level abstraction features, a convolutional neural network (CNN) architecture is constructed to perform the identification tasks, and the word vectors of DNA sequences are vertically concatenated to form the embedding matrices as the input of the CNN. Experimental results demonstrate the effectiveness of the Seq-GAN to expand the training dataset, the possibility of applying word segmentation methods to extract "words" from DNA sequences, the feasibility of implementing the skip-gram model to encode DNA sequences, and the powerful prediction ability of the CNN. Compared with other state-of-the-art methods on the training dataset and independent test dataset, the proposed method achieves a significantly improved overall performance. It is anticipated that the proposed method has a certain promotion effect on enhancer related fields.

A deep learning framework combined with word embedding to identify DNA replication origins.

The DNA replication influences the inheritance of genetic information in the DNA life cycle. As the distribution of replication origins (ORIs) is the major determinant to precisely regulate the replication process, the correct identification of ORIs is significant in giving an insightful understanding of DNA replication mechanisms and the regulatory mechanisms of genetic expressions. For eukaryotes in particular, multiple ORIs exist in each of their gene sequences to complete the replication in a reasonable period of time. To simplify the identification process of eukaryote's ORIs, most of existing methods are developed by traditional machine learning algorithms, and target to the gene sequences with a fixed length. Consequently, the identification results are not satisfying, i.e. there is still great room for improvement. To break through the limitations in previous studies, this paper develops sequence segmentation methods, and employs the word embedding technique, 'Word2vec', to convert gene sequences into word vectors, thereby grasping the inner correlations of gene sequences with different lengths. Then, a deep learning framework to perform the ORI identification task is constructed by a convolutional neural network with an embedding layer. On the basis of the analysis of similarity reduction dimensionality diagram, Word2vec can effectively transform the inner relationship among words into numerical feature. For four species in this study, the best models are obtained with the overall accuracy of 0.975, 0.765, 0.885, 0.967, the Matthew's correlation coefficient of 0.940, 0.530, 0.771, 0.934, and the AUC of 0.975, 0.800, 0.888, 0.981, which indicate that the proposed predictor has a stable ability and provide a high confidence coefficient to classify both of ORIs and non-ORIs. Compared with state-of-the-art methods, the proposed predictor can achieve ORI identification with significant improvement. It is therefore reasonable to anticipate that the proposed method will make a useful high throughput tool for genome analysis.

Exogenous Melatonin Modulates the Physiological and Biochemical Mechanisms of Drought Tolerance in Tartary Buckwheat (Fagopyrum tataricum (L.) Gaertn).

Tartary buckwheat is one of the nutritious minor cereals and is grown in high-cold mountainous areas of arid and semi-arid zones where drought is a common phenomenon, potentially reducing the growth and yield. Melatonin, which is an amphiphilic low molecular weight compound, has been proven to exert significant effects in plants, under abiotic stresses, but its role in the Tartary buckwheat under drought stress remains unexplored. We evaluated the influence of melatonin supplementation on plant morphology and different physiological activities, to enhance tolerance to posed drought stress by scavenging reactive oxygen species (ROS) and alleviating lipid peroxidation. Drought stress decreased the plant growth and biomass production compared to the control. Drought also decreased Chl a, b, and the Fv/Fm ratio by 54%, 70%, and 8%, respectively, which was associated with the disorganized stomatal properties. Under drought stress, H2O2, O2•-, and malondialdehyde (MDA) contents increased by 2.30, 2.43, and 2.22-folds, respectively, which caused oxidative stress. In contrast, proline and soluble sugar content were increased by 84% and 39%, respectively. However, exogenous melatonin (100 µM) could improve plant growth by preventing ROS-induced oxidative damage by increasing photosynthesis, enzymatic antioxidants (superoxide dismutase, peroxidase, catalase, and ascorbate peroxidase), secondary metabolites like phenylalanine ammonialyase, phenolics, and flavonoids, total antioxidant scavenging (free radical DPPH scavenging), and maintaining relative water content and osmoregulation substances under water stress. Therefore, our study suggested that exogenous melatonin could accelerate drought resistance by enhancing photosynthesis and antioxidant defense in Tartary buckwheat plants.

Ethanol and Cannabinoids Regulate Zebrafish GABAergic Neuron Development and Behavior in a Sonic Hedgehog and Fibroblast Growth Factor-Dependent Mechanism.

BACKGROUND: Ethanol (EtOH) has diverse effects on nervous system development, which includes development and survival of GABAergic neurons in a sonic hedgehog (Shh) and fibroblast growth factor (Fgf)-dependent mechanism. Cannabinoids also function as inhibitors of Shh signaling, raising the possibility that EtOH and cannabinoids may interact to broadly disrupt neuronal function during brain development. METHODS: Zebrafish embryos were exposed to a range of EtOH and/or cannabinoid receptor 1 (CB1R) agonist concentrations at specific developmental stages, in the absence or presence of morpholino oligonucleotides that disrupt shh expression. In situ hybridization was employed to analyze glutamic acid decarboxylase (gad1) gene expression as a marker of GABAergic neuron differentiation, and zebrafish behavior was analyzed using the novel tank diving test as a measure of risk-taking behavior. RESULTS: Combined acute subthreshold EtOH and CB1R agonist exposure results in a marked reduction in gad1 mRNA expression in zebrafish forebrain. Consistent with the EtOH and cannabinoid effects on Shh signaling, fgf8 mRNA overexpression rescues the EtOH- and cannabinoid-induced decrease in gad1 gene expression and also prevents the changes in behavior induced by EtOH and cannabinoids. CONCLUSIONS: These studies provide evidence that forebrain GABAergic neuron development and zebrafish risk-taking behavior are sensitive to both EtOH and cannabinoid exposure in a Shh- and Fgf-dependent mechanism, and provide additional evidence that a signaling pathway involving Shh and Fgf crosstalk is a critical target of EtOH and cannabinoids in FASD.

Cannabinoids Exacerbate Alcohol Teratogenesis by a CB1-Hedgehog Interaction.

We tested whether cannabinoids (CBs) potentiate alcohol-induced birth defects in mice and zebrafish, and explored the underlying pathogenic mechanisms on Sonic Hedgehog (Shh) signaling. The CBs, Δ9-THC, cannabidiol, HU-210, and CP 55,940 caused alcohol-like effects on craniofacial and brain development, phenocopying Shh mutations. Combined exposure to even low doses of alcohol with THC, HU-210, or CP 55,940 caused a greater incidence of birth defects, particularly of the eyes, than did either treatment alone. Consistent with the hypothesis that these defects are caused by deficient Shh, we found that CBs reduced Shh signaling by inhibiting Smoothened (Smo), while Shh mRNA or a CB1 receptor antagonist attenuated CB-induced birth defects. Proximity ligation experiments identified novel CB1-Smo heteromers, suggesting allosteric CB1-Smo interactions. In addition to raising concerns about the safety of cannabinoid and alcohol exposure during early embryonic development, this study establishes a novel link between two distinct signaling pathways and has widespread implications for development, as well as diseases such as addiction and cancer.

Real-Time Photometric Calibrated Monocular Direct Visual SLAM.

To solve the illumination sensitivity problems of mobile ground equipment, an enhanced visual SLAM algorithm based on the sparse direct method was proposed in this paper. Firstly, the vignette and response functions of the input sequences were optimized based on the photometric formation of the camera. Secondly, the Shi-Tomasi corners of the input sequence were tracked, and optimization equations were established using the pixel tracking of sparse direct visual odometry (VO). Thirdly, the Levenberg-Marquardt (L-M) method was applied to solve the joint optimization equation, and the photometric calibration parameters in the VO were updated to realize the real-time dynamic compensation of the exposure of the input sequences, which reduced the effects of the light variations on SLAM's (simultaneous localization and mapping) accuracy and robustness. Finally, a Shi-Tomasi corner filtered strategy was designed to reduce the computational complexity of the proposed algorithm, and the loop closure detection was realized based on the oriented FAST and rotated BRIEF (ORB) features. The proposed algorithm was tested using TUM, KITTI, EuRoC, and an actual environment, and the experimental results show that the positioning and mapping performance of the proposed algorithm is promising.

Nutrient limitation and enzymolysis of phosphorus in Meiliang Bay, Lake Taihu, during algal blooms.

In this study, algal growth potential tests were performed in water samples collected from six sampling sites in Meiliang Bay, Lake Taihu. The potential release of soluble reactive phosphorus (SRP) by enzymatic hydrolysis of enzymatically hydrolyzable phosphorus (EHP) was simultaneously evaluated. Results show that all studied regions were in highly eutrophic states, with additional nitrogen (N) or phosphorus (P) inputs, inducing negligible further increase in algal growth. EHP in water could be rapidly transformed into SRP, further supporting the proliferation of algal blooms. The shortest EHP mineralization time was calculated as 69 minutes; therefore, limiting specific nutrient inputs alone in extremely eutrophic lakes can have a limited effect on suppressing the proliferation of algal blooms. Methods to establish a suitable environmental fate for excessive nitrogen and phosphorus nutrients may be more effective and provide more significant results. PRACTITIONER POINTS: N and P were no longer serving as the limiting factors in Meiliang Bay. Enzymatically hydrolysable phosphorus could be hydrolyzed into soluble reactive phosphorus in a very short period during algal blooms. Both enzymatically hydrolysable phosphorus and soluble reactive phosphorus are required to be curbed in practical eutrophication control.

Ethanol and cannabinoids interact to alter behavior in a zebrafish fetal alcohol spectrum disorder model.

BACKGROUND: Recent work suggests that endocannabinoids (eCBs) may signal through the sonic hedgehog signaling pathway. We therefore hypothesized that combined ethanol and eCB exposure during defined stages of zebrafish embryogenesis will produce deficits comparable to human fetal alcohol spectrum disorder (FASD). METHODS: Zebrafish embryos were exposed to ethanol or cannabinoid agonists alone or in combination at defined developmental stages and assessed for changes in brain morphology or expression of marker genes such as pax6a. Juvenile fish were then assessed for risk-taking/anxiety-like behavior using the novel tank dive test. RESULTS: Either chronic or acute exposure to high doses of the CB1R agonist ACEA resulted in FASD phenotypes. However, acute subthreshold doses of CB1R agonist alone, or combined with 0.5% ethanol, did not induce morphological phenotypes, but did induce dysmorphogenesis when combined with acute 1% ethanol. Phenotypes were rescued using the CB1R antagonist SR141716A. In addition, JZL195, a dual inhibitor of FAAH and MAGL, two degradative enzymes for eCBs, induced FASD phenotypes in the presence of subthreshold ethanol, confirming the activation of common signaling pathways by ethanol and eCBs. We next analyzed the effects of ethanol and CB1R agonist on juvenile zebrafish behavior and show that ACEA or ethanol alone did not alter behavior, but combined ACEA and ethanol increased risk-taking behavior. CONCLUSIONS: These studies demonstrate that pathological and behavioral phenotypes associated with FASD are induced by exposure to CB1R agonists and suggest that combined exposure to lower levels of alcohol and marijuana may be capable of inducing FASD-like morphological and behavioral impairments.

Predicting FAD Interacting Residues with Feature Selection and Comprehensive Sequence Descriptors.

The function of a flavoprotein is determined to a great extent by the binding sites on its surface that interacts with flavin adenine dinucleotide (FAD). Malfunction or dysregulation of FAD binding leads to a series of diseases. Therefore, accurately identifying FAD interacting residues (FIRs) provides insights into the molecular mechanisms of flavoprotein-related biological processes and disease progression. In this paper, a new computational method is proposed for identifying FIRs from protein sequences. Various sequence-derived discriminative features are explored. We analyze the distinctions of these features between FIRs and non-FIRs. We also investigate the predictive capabilities of both individual features and combinations of features. A relief algorithm followed by incremental feature selection (relief-IFS) is then adopted to search the optimal features. Finally, a random forest (RF) module is used to predict FIRs based on the optimal features. Using a 5-fold cross-validation test, the proposed method performs well, with a sensitivity of 0.847, a specificity of 0.933, an accuracy of 0.890, and a Matthews correlation coefficient (MCC) of 0.782, thereby outperforming previous methods. These results indicate that our method is relatively successful at predicting FIRs.

Using a Classifier Fusion Strategy to Identify Anti-angiogenic Peptides.

Anti-angiogenic peptides perform distinct physiological functions and potential therapies for angiogenesis-related diseases. Accurate identification of anti-angiogenic peptides may provide significant clues to understand the essential angiogenic homeostasis within tissues and develop antineoplastic therapies. In this study, an ensemble predictor is proposed for anti-angiogenic peptide prediction by fusing an individual classifier with the best sensitivity and another individual one with the best specificity. We investigate predictive capabilities of various feature spaces with respect to the corresponding optimal individual classifiers and ensemble classifiers. The accuracy and Matthew's Correlation Coefficient (MCC) of the ensemble classifier trained by Bi-profile Bayes (BpB) features are 0.822 and 0.649, respectively, which represents the highest prediction results among the investigated prediction models. Discriminative features are obtained from BpB using the Relief algorithm followed by the Incremental Feature Selection (IFS) method. The sensitivity, specificity, accuracy, and MCC of the ensemble classifier trained by the discriminative features reach up to 0.776, 0.888, 0.832, and 0.668, respectively. Experimental results indicate that the proposed method is far superior to the previous study for anti-angiogenic peptide prediction.

[Inhibitory Effects of Phosphate and Recovery on a Nitrification System].

The effect of phosphate concentration on nitrification was studied by using a stabilization nitrosation system, which was started up in a continuous flow reactor by inoculating sludge from a municipal wastewater treatment plant. The results showed that the nitrification system was started successfully after operating for 14 days. The conversion rate of ammonia nitrogen reached 92.2%, the nitrite accumulation rate was 73.66%, and the nitrite generation rate was 14.42 g·(m3·d)-1. There was no effect of phosphate concentration on the nitrosation system between 10 and 30 mg·L-1; and the conversion rate of ammonia nitrogen was decreased with the continuous increase in phosphate concentration. When the concentration of phosphate was 80 mg·L-1, with an ammonia conversion rate 13.6%, accumulation rate of nitrite of 18.19%, and nitrite generation rate of 0.54 g·(m3·d)-1, the reaction was severely inhibited. After reducing the influent phosphate concentration to 0, with the ammonia nitrogen conversion rate at more than 80%, nitrite accumulation rate improved to 86.96%, and the nitrite generation rate being 15.63 g·(m3·d)-1, the system recovered after operating for 14 days.

A Two-Step Feature Selection Method to Predict Cancerlectins by Multiview Features and Synthetic Minority Oversampling Technique.

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.

Comparison of molecular marker expression in early zebrafish brain development following chronic ethanol or morpholino treatment.

This study was undertaken to ascertain whether defined markers of early zebrafish brain development are affected by chronic ethanol exposure or morpholino knockdown of agrin, sonic hedgehog, retinoic acid, and fibroblast growth factors, four signaling molecules that are suggested to be ethanol sensitive. Zebrafish embryos were exposed to 2% ethanol from 6 to 24 hpf or injected with agrin, shha, aldh1a3, or fgf8a morpholinos. In situ hybridization was employed to analyze otx2, pax6a, epha4a, krx20, pax2a, fgf8a, wnt1, and eng2b expression during early brain development. Our results showed that pax6a mRNA expression was decreased in eye, forebrain, and hindbrain of both chronic ethanol exposed and select MO treatments. Epha4a expression in rhombomere R1 boundary was decreased in chronic ethanol exposure and aldh1a3 morphants, lost in fgf8a morphants, but largely unaffected in agrin and shha morphants. Ectopic pax6a and epha4a expression in midbrain was only found in fgf8a morphants. These results suggest that while chronic ethanol induces obvious morphological change in brain architecture, many molecular markers of these brain structures are relatively unaffected by ethanol exposure.

Long-term behavioral change as a result of acute ethanol exposure in zebrafish: Evidence for a role for sonic hedgehog but not retinoic acid signaling.

BACKGROUND: Developmental exposure to ethanol is recognized to produce long-term neurobehavioral impairment in multiple animal models. However, the molecular mechanisms underlying these deficits remain poorly understood. The present study was undertaken to ascertain whether two well-characterized targets of prenatal alcohol exposure, sonic hedgehog (Shh) and retinoic acid (RA), that induce the hallmark morphological phenotypes of fetal alcohol spectrum disorders (FASD), are involved in the generation of behavioral alterations as a result of alcohol exposure. METHODS: Zebrafish embryos were exposed to ethanol (0%, 1%, 3%) at either 8-10 or 24-27h post-fertilization (hpf) and then evaluated during adolescence in the novel tank dive test to assess anxiety and risk-taking behavior. Overt signs of dysmorphogenesis were also scored and behavioral and morphological changes were compared for embryos treated with alcohol alone or in combination with subthreshold doses of shh or alhh1a3 morpholinos (MOs). RESULTS: Ethanol treated fish displayed altered tank diving behavior that was not exacerbated by combined MO treatment. While treatment of embryos with either shha mRNA or RA prior to ethanol exposure only ameliorated the altered tank diving response in the case of shha mRNA overexpression, dysmorphogenesis was rescued by both treatments. CONCLUSION: These results suggest that the effects of ethanol exposure on changes in anxiety and risk-taking behavior in adolescent zebrafish is manifested by a blunting of Shh, but not RA, signaling during early development.

Sequence Based Prediction of Antioxidant Proteins Using a Classifier Selection Strategy.

Antioxidant proteins perform significant functions in maintaining oxidation/antioxidation balance and have potential therapies for some diseases. Accurate identification of antioxidant proteins could contribute to revealing physiological processes of oxidation/antioxidation balance and developing novel antioxidation-based drugs. In this study, an ensemble method is presented to predict antioxidant proteins with hybrid features, incorporating SSI (Secondary Structure Information), PSSM (Position Specific Scoring Matrix), RSA (Relative Solvent Accessibility), and CTD (Composition, Transition, Distribution). The prediction results of the ensemble predictor are determined by an average of prediction results of multiple base classifiers. Based on a classifier selection strategy, we obtain an optimal ensemble classifier composed of RF (Random Forest), SMO (Sequential Minimal Optimization), NNA (Nearest Neighbor Algorithm), and J48 with an accuracy of 0.925. A Relief combined with IFS (Incremental Feature Selection) method is adopted to obtain optimal features from hybrid features. With the optimal features, the ensemble method achieves improved performance with a sensitivity of 0.95, a specificity of 0.93, an accuracy of 0.94, and an MCC (Matthew's Correlation Coefficient) of 0.880, far better than the existing method. To evaluate the prediction performance objectively, the proposed method is compared with existing methods on the same independent testing dataset. Encouragingly, our method performs better than previous studies. In addition, our method achieves more balanced performance with a sensitivity of 0.878 and a specificity of 0.860. These results suggest that the proposed ensemble method can be a potential candidate for antioxidant protein prediction. For public access, we develop a user-friendly web server for antioxidant protein identification that is freely accessible at http://antioxidant.weka.cc.

Prediction of aptamer-protein interacting pairs using an ensemble classifier in combination with various protein sequence attributes.

BACKGROUND: Aptamer-protein interacting pairs play a variety of physiological functions and therapeutic potentials in organisms. Rapidly and effectively predicting aptamer-protein interacting pairs is significant to design aptamers binding to certain interested proteins, which will give insight into understanding mechanisms of aptamer-protein interacting pairs and developing aptamer-based therapies. RESULTS: In this study, an ensemble method is presented to predict aptamer-protein interacting pairs with hybrid features. The features for aptamers are extracted from Pseudo K-tuple Nucleotide Composition (PseKNC) while the features for proteins incorporate Discrete Cosine Transformation (DCT), disorder information, and bi-gram Position Specific Scoring Matrix (PSSM). We investigate predictive capabilities of various feature spaces. The proposed ensemble method obtains the best performance with Youden's Index of 0.380, using the hybrid feature space of PseKNC, DCT, bi-gram PSSM, and disorder information by 10-fold cross validation. The Relief-Incremental Feature Selection (IFS) method is adopted to obtain the optimal feature set. Based on the optimal feature set, the proposed method achieves a balanced performance with a sensitivity of 0.753 and a specificity of 0.725 on the training dataset, which indicates that this method can solve the imbalanced data problem effectively. To evaluate the prediction performance objectively, an independent testing dataset is used to evaluate the proposed method. Encouragingly, our proposed method performs better than previous study with a sensitivity of 0.738 and a Youden's Index of 0.451. CONCLUSIONS: These results suggest that the proposed method can be a potential candidate for aptamer-protein interacting pair prediction, which may contribute to finding novel aptamer-protein interacting pairs and understanding the relationship between aptamers and proteins.