SUMMARY: Identifying molecular cancer subtypes from multi-omics data is an important step in the personalized medicine. We introduce CancerSubtypes, an R package for identifying cancer subtypes using multi-omics data, including gene expression, miRNA expression and DNA methylation data. CancerSubtypes integrates four main computational methods which are highly cited for cancer subtype identification and provides a standardized framework for data pre-processing, feature selection, and result follow-up analyses, including results computing, biology validation and visualization. The input and output of each step in the framework are packaged in the same data format, making it convenience to compare different methods. The package is useful for inferring cancer subtypes from an input genomic dataset, comparing the predictions from different well-known methods and testing new subtype discovery methods, as shown with different application scenarios in the Supplementary Material. AVAILABILITY AND IMPLEMENTATION: The package is implemented in R and available under GPL-2 license from the Bioconductor website (http://bioconductor.org/packages/CancerSubtypes/). CONTACT: [email protected] or [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Randomised controlled trials (RCTs) are the most effective approach to causal discovery, but in many circumstances it is impossible to conduct RCTs. Therefore, observational studies based on passively observed data are widely accepted as an alternative to RCTs. However, in observational studies, prior knowledge is required to generate the hypotheses about the cause-effect relationships to be tested, and hence they can only be applied to problems with available domain knowledge and a handful of variables. In practice, many datasets are of high dimensionality, which leaves observational studies out of the opportunities for causal discovery from such a wealth of data sources. In another direction, many efficient data mining methods have been developed to identify associations among variables in large datasets. The problem is that causal relationships imply associations, but the reverse is not always true. However, we can see the synergy between the two paradigms here. Specifically, association rule mining can be used to deal with the high-dimensionality problem, whereas observational studies can be utilised to eliminate noncausal associations. In this article, we propose the concept of causal rules (CRs) and develop an algorithm for mining CRs in large datasets. We use the idea of retrospective cohort studies to detect CRs based on the results of association rule mining. Experiments with both synthetic and real-world datasets have demonstrated the effectiveness and efficiency of CR mining. In comparison with the commonly used causal discovery methods, the proposed approach generally is faster and has better or competitive performance in finding correct or sensible causes. It is also capable of finding a cause consisting of multiple variables—a feature that other causal discovery methods do not possess.

MOTIVATION: microRNAs (miRNAs) are known to play an essential role in the post-transcriptional gene regulation in plants and animals. Currently, several computational approaches have been developed with a shared aim to elucidate miRNA-mRNA regulatory relationships. Although these existing computational methods discover the statistical relationships, such as correlations and associations between miRNAs and mRNAs at data level, such statistical relationships are not necessarily the real causal regulatory relationships that would ultimately provide useful insights into the causes of gene regulations. The standard method for determining causal relationships is randomized controlled perturbation experiments. In practice, however, such experiments are expensive and time consuming. Our motivation for this study is to discover the miRNA-mRNA causal regulatory relationships from observational data. RESULTS: We present a causality discovery-based method to uncover the causal regulatory relationship between miRNAs and mRNAs, using expression profiles of miRNAs and mRNAs without taking into consideration the previous target information. We apply this method to the epithelial-to-mesenchymal transition (EMT) datasets and validate the computational discoveries by a controlled biological experiment for the miR-200 family. A significant portion of the regulatory relationships discovered in data is consistent with those identified by experiments. In addition, the top genes that are causally regulated by miRNAs are highly relevant to the biological conditions of the datasets. The results indicate that the causal discovery method effectively discovers miRNA regulatory relationships in data. Although computational predictions may not completely replace intervention experiments, the accurate and reliable discoveries in data are cost effective for the design of miRNA experiments and the understanding of miRNA-mRNA regulatory relationships.

Discovering causal relationships in large databases of observational data is challenging. The pioneering work in this area was rooted in the theory of Bayesian network (BN) learning, which however, is a NP-complete problem. Hence several constraint-based algorithms have been developed to efficiently discover causations in large databases. These methods usually use the idea of BN learning, directly or indirectly, and are focused on causal relationships with single cause variables. In this paper, we propose an approach to mine causal rules in large databases of binary variables. Our method expands the scope of causality discovery to causal relationships with multiple cause variables, and we utilise partial association tests to exclude noncausal associations, to ensure the high reliability of discovered causal rules. Furthermore an efficient algorithm is designed for the tests in large databases. We assess the method with a set of real-world diagnostic data. The results show that our method can effectively discover interesting causal rules in large databases.

Prognostic prediction is important in medical domain, because it can be used to select an appropriate treatment for a patient by predicting the patient's clinical outcomes. For high-dimensional data, a normal prognostic method undergoes two steps: feature selection and prognosis analysis. Recently, the L₁-L₂-norm Support Vector Machine (L₁-L₂ SVM) has been developed as an effective classification technique and shown good classification performance with automatic feature selection. In this paper, we extend L₁-L₂ SVM for regression analysis with automatic feature selection. We further improve the L₁-L₂ SVM for prognostic prediction by utilizing the information of censored data as constraints. We design an efficient solution to the new optimization problem. The proposed method is compared with other seven prognostic prediction methods on three realworld data sets. The experimental results show that the proposed method performs consistently better than the medium performance. It is more efficient than other algorithms with the similar performance.

Ordinal regression has wide applications in many domains where the human evaluation plays a major role. Most current ordinal regression methods are based on Support Vector Machines (SVM) and suffer from the problems of ignoring the global information of the data and the high computational complexity. Linear Discriminant Analysis (LDA) and its kernel version, Kernel Discriminant Analysis (KDA), take into consideration the global information of the data together with the distribution of the classes for classification, but they have not been utilized for ordinal regression yet. In this paper, we propose a novel regression method by extending the Kernel Discriminant Learning using a rank constraint. The proposed algorithm is very efficient since the computational complexity is significantly lower than other ordinal regression methods. We demonstrate experimentally that the proposed method is capable of preserving the rank of data classes in a projected data space. In comparison to other benchmark ordinal regression methods, the proposed method is competitive in accuracy.

In most complex classification problems, many types of features have been captured or extracted. Feature fusion is used to combine features for better classification and to reduce data dimensionality. Kernel-based feature fusion methods are very effective for classification, but they do not reduce data dimensionality. In this brief, we propose an effective feature fusion method using locally linear embedding (LLE). The proposed method overcomes the limitations of LLE, which could not handle different types of features and is inefficient for classification. We propose an efficient algorithm to solve the optimization problem in obtaining weights of different features, and design an efficient method for LLE-based classification. In comparison to other kernel-based feature fusion methods, the proposed method fuses features to a significantly lower dimensional feature space with the same discriminant power. We have conducted experiments to demonstrate the effectiveness of the proposed feature fusion method.

In this paper an effective method of using SVM classifier for multiple feature classification is proposed. Compared with traditional combination methods where all needed base classifiers should be trained before the decision combination, the proposed approach is to train individual classifiers and combine the decisions of these base classifiers at the same time. Thus the complexity of the training can be reduced because our proposed method involves solving only one optimization problem while several optimization problems should be solved for traditional methods. Furthermore, during the combination, our proposed approach takes into account both a base classifier's performance on the training data and its generalization ability while traditional combination approaches consider only a base classifier's performance on the training data. The experiments proved the efficiency of our proposed approach

Most robot grippers can hardly be applied to space service due to their devoid of the ability of outputting large force, autonomously making decision and sensing the environment. In this paper, a space underactuated gripper which can stably grasp various objects based on fewer actuators, large force and autonomous decision and multisensory information feedback is introduced. Firstly, the versatile grasping patterns of the gripper with characteristics of underactuation are presented. The multiple sensors are mounted on the gripper including PVDF contact force sensors, a line structure light sensor which detects grasped object approximate shape and volume, and a wrist force sensor which detects the grasped object mass. Secondly, autonomous grasping which is characterized by autonomous decision-making and control is focused on. Control strategies are also proposed to make proper prosthetics and stable grasping according to force sensors information. The grasping rules are extracted from original experiment sample data. Through fuzzy neural network, grasping map is established among comprehensive fuzzy features, including grasping task and object features, and the grasping patterns. Finally, the experimental results demonstrate that the gripper can achieve autonomous and stable grasping

Lidar is an active remote sensing instrument, but its effective range is often limited by signal-to-noise (SNR) ratio. The reason is that noises or fluctuations always strongly affect the measured results. To resolve this problem, a novel approach of using least-squares support vector machine (LS-SVM) to reconstruct the Lidar signal is proposed in this paper. LS-SVM has been proven as robust to noisy data; the Lidar signal, which is strongly corrupted by noises or fluctuations, can be thought as a function of distance. So detecting Lidar signals from high noisy regime can be regarded as a robust regression procedure which involves estimating the underlying relationship from detected signal data set. To apply the LS-SVM on Lidar signal regression, firstly the noises in Lidar signal is analyzed and then the traditional LS-SVM algorithm is modified to incorporate the a priori knowledge of the Lidar signal in the training of LS-SVM. The experimental results demonstrate the effectiveness and efficiency of our approach.

The noise in a Lidar signal is analyzed first, and then a novel method that applies least-square support vector machine (LS-SVM) to denoising Lidar signals is proposed. In order to improve the performance of denoising, the a priori knowledge about Lidar signals is also incorporated in the training of the LS-SVM. Finally, the experimental results demonstrate the effectiveness and efficiency of our approach.

The LS-SVM ensemble is proposed to improve the performance of the single LS-SVM. During the constructing of the LS-SVM ensemble, bagging algorithm is used because it is more suitable than boosting algorithm in high noise regime. Furthermore, in This work a novel aggregation method of the LS-SVM ensemble is also proposed. Traditionally the aggregation of the ensemble always uses all the available individual LS-SVM, while our approach can exclude the ones which may degrade the performance of the ensemble. Finally, the simulating results demonstrate the effectiveness and efficiency of our approach.

We propose a new approach by combining support vector clustering (SVC) with a two layered neural network for multiclass classification problems. This new approach is not only capable of improving the performance of the traditional SVC, but also, compared to support vector machines (SVM), can reduce the computational complexity and get better performance in the case of multiclass problems. Finally, the experimental results demonstrate the effectiveness and efficiency of our approach.