Search

Identifying whether a pentatricopeptide repeat (PPR) exists in an amino acid is a significant task in the field of bioinformatics. To address this problem, an identification method that combines an optimal feature set selection framework and machine learning algorithms is proposed to recognize the PPR coding genes and proteins in the sequence of amino acid. The original 188-dimensional (D) features are obtained using a feature extraction method, which is successively optimised through a covariance analysis, max-relevant-max-distance processing, and principal component analysis to reduce it to an optimal feature set that has fewer but more expressive features. Four machine learning methods are then used to serve as the classifiers for the identification task. The final number of feature data dimensions is reduced from 188 to only 10, and according to the experimental results from support vector machine methods, the loss of the AUC and the F 1 values are only 3.26% and 10.1%, respectively. Moreover, after applying the J48, random forest, and naïve Bayes methods as classifiers, it was also found that the optimal feature set with 10 dimensions has an almost equivalent performance for a 10-fold validation test. Identifying whether a pentatricopeptide repeat (PPR) exists in an amino acid is a significant task in the field of bioinformatics. To address this problem, an identification method that combines an optimal feature set selection framework and machine learning algorithms is proposed to recognise the PPR coding genes and proteins in the sequence of an amino acid. The original 188-dimensional (D) features are obtained using a feature extraction method, which is successively optimised through a covariance analysis, max-relevant-max-distance processing, and a principal component analysis to reduce it to an optimal feature set that has fewer but more expressive features. Four machine learning methods are then used to serve as the classifiers for the identification task. The final number of feature data dimensions is reduced from 188 to only 10, and according to the experimental results from support vector machine methods, the loss of the AUC and F 1 the value are only 3.26% and 10.1%, respectively. Moreover, after applying the J48, random forest, and naïve Bayes methods as classifiers, it was also found that the optimal feature set with 10 dimensions has an almost equivalent performance for a 10-fold validation test Image, graphical abstract [ABSTRACT FROM AUTHOR]

In online learning, the contribution of old samples to a model decreases as time passes, and old samples gradually become invalid. Although the Online Sequential Extreme Learning Machine (OS-ELM) can avoid the repetitive training of old samples, invalid samples are still used, which goes against improving the accuracy of an OS-ELM model. The Online Sequence Extreme Learning Machine with Forgetting Mechanism (FOS-ELM) timely discards invalid samples, but it does not consider the differences among valid samples and then has the limitation on boosting the accuracy and generalization. To solve this issue, the Memory Degradation Based OS-ELM (MDOS-ELM) is proposed in this paper. The MDOS-ELM adjusts the weights of the old and new samples in real time by a self-adaptive memory factor, and simultaneously discards invalid samples. The self-adaptive memory factor is determined by two elements. One is the similarity between the new and old samples, and the other is the prediction errors of the current training samples on the previous model. The performance of the proposed MDOS-ELM is validated on both regression and classification datasets which include an artificial dataset and twenty-two real-world dataset. The results demonstrate that the MDOS-ELM model outperforms the OS-ELM and the FOS-ELM models on the accuracy and generalization. [ABSTRACT FROM AUTHOR]

Coming with the big data era, the filtering of uninformative data becomes emerging. To this end, ranking the high dimensionality features plays an important role. However, most of the state-of-art methods focus on improving the classification accuracy while the stability of the dimensionality reduction is simply ignored. In this paper, we proposed a Max-Relevance-Max-Distance (MRMD) feature ranking method, which balances accuracy and stability of feature ranking and prediction task. In order to prove the effectiveness on big data, we tested our method on two different datasets. The first one is image classification, which is a benchmark dataset with high dimensionality, while the second one is protein–protein interaction prediction data, which comes from our previous private research and has massive instances. Experiments prove that our method maintained the accuracy together with the stability on both two big datasets. Moreover, our method runs faster than other filtering and wrapping methods, such as mRMR and Information Gain. [ABSTRACT FROM AUTHOR]

In this paper, we consider the problem of hierarchical image classification with multiple semantic views of object categories. A novel method is proposed for computing an image-semantic measure by determining the weights for the semantic similarity among the concepts of each view. After obtaining the new image-semantic measure, we construct a semantic hierarchy with the existing method called TRUST-ME. For the hierarchical classification, we translate the classification task with a learned taxonomy into a structured support vector machine (SVM) learning framework. We demonstrate our method on VOC2010 and a subset of the Animals with Attributes dataset, and show that the structured SVM using the weighted semantic hierarchy provides better accuracy. [ABSTRACT FROM AUTHOR]

Abstract N6-methyladenosine (m6A), as one of the most well-studied RNA modifications, has been found to be involved with a wide range of biological processes. Recently, diverse computational methods have been developed for automated identification of m6A sites within RNAs. To identify m6A sites accurately, one of the major challenges is to extract informative features to describe characteristics of m6A sites. However, existing feature representation methods are usually hand-crafted based, and cannot capture discriminative information of m6A sites. In this paper, we develop a m6A site predictor, named DeepM6APred. In this predictor, we propose to use a deep learning based feature descriptor with deep belief network (DBN) to extract high-level latent features. By integrating the deep features with traditional handcrafted features, we train a classification model based on support vector machine and successfully improve the predictive ability of m6A sites. Experimental results on a benchmark dataset show that our proposed method outperforms the state-of-the-art predictors, at least 2% higher in terms of Matthew's correlation coefficient (MCC). Moreover, a webserver that implements the DeepM6APred is established, which is currently available at the website: http://server.malab.cn/DeepM6APred. It is expected to be a useful tool to assist biologists to reveal the functional mechanisms of m6A sites. [ABSTRACT FROM AUTHOR]

While content-based image annotation and retrieval have been active research topics over the past decade, their correlation is not well exploited until recently. We argue that offline annotation and online retrieval models should be regarded as a unified long-term learner to reinforce each other. Based on this viewpoint, this paper presents an annotation-retrieval reinforcement framework, in which a dual-structured learning model is presented: the keyword-image association is learned by semantic manifold modeling while the semantic correlation between keywords is learned by Image-Word Net modeling. In keyword-image association modeling level, to effectively model keyword-image manifold, we present a manifold co-training algorithm to address the sample insufficiency problem. In manifold-based image annotation, we view annotation process as semantic feature reduction in keyword space, based on which a Biased Fisher Discriminant Analysis (BFDA) algorithm is presented for Eigen feature (keyword) selection. In semantic correlation modeling level, a novel Image-Word Net is learned from annotation training set and users' retrieval log for (1) irrelevant annotated keyword pruning; (2) semantic-level retrieval enhancement. In retrieval, our framework can effectively reveal user target by improving traditional content-based relevance feedback to linguistic-level interaction using annotation information, based on which BFDA is adopted for keyword selection. Finally, user interaction logs are adopted for manifold model updating and annotation refinement. As presented in our experiments, proposed method outperforms state-of-the-art annotation and retrieval algorithms in COREL Image databases with over 10,000 general-purpose images. [ABSTRACT FROM AUTHOR]