MOTIVATION: Electron tomography (ET) offers a unique capacity to image biological structures in situ. However, the resolution of ET reconstructed tomograms is not comparable to that of the single-particle cryo-EM. If many copies of the object of interest are present in the tomograms, their structures can be reconstructed in the tomogram, picked, aligned and averaged to increase the signal-to-noise ratio and improve the resolution, which is known as the subtomogram averaging. To date, the resolution improvement of the subtomogram averaging is still limited because each reconstructed subtomogram is of low reconstruction quality due to the missing wedge issue. RESULTS: In this article, we propose a novel computational model, the constrained reconstruction model (CRM), to better recover the information from the multiple subtomograms and compensate for the missing wedge issue in each of them. CRM is supposed to produce a refined reconstruction in the final turn of subtomogram averaging after alignment, instead of directly taking the average. We first formulate the averaging method and our CRM as linear systems, and prove that the solution space of CRM is no larger, and in practice much smaller, than that of the averaging method. We then propose a sparse Kaczmarz algorithm to solve the formulated CRM, and further extend the solution to the simultaneous algebraic reconstruction technique (SART). Experimental results demonstrate that CRM can significantly alleviate the missing wedge issue and improve the final reconstruction quality. In addition, our model is robust to the number of images in each tilt series, the tilt range and the noise level. AVAILABILITY AND IMPLEMENTATION: The codes of CRM-SIRT and CRM-SART are available at https://github.com/icthrm/CRM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We propose a framework for analyzing and comparing distributions without imposing any parametric assumptions via empirical likelihood methods. Our framework is used to study two fundamental statistical test problems: the two-sample test and the goodness-of-fit test. For the two-sample test, we need to determine whether two groups of samples are from different distributions; for the goodness-of-fit test, we examine how likely it is that a set of samples is generated from a known target distribution. Specifically, we propose empirical likelihood ratio (ELR) statistics for the two-sample test and the goodness-of-fit test, both of which are of linear time complexity and show higher power (i.e., the probability of correctly rejecting the null hypothesis) than the existing linear statistics for high-dimensional data. We prove the nonparametric Wilks’ theorems for the ELR statistics, which illustrate that the limiting distributions of the proposed ELR statistics are chi-square distributions. With these limiting distributions, we can avoid bootstraps or simulations to determine the threshold for rejecting the null hypothesis, which makes the ELR statistics more efficient than the recently proposed linear statistic, finite set Stein discrepancy (FSSD). We also prove the consistency of the ELR statistics, which guarantees that the test power goes to 1 as the number of samples goes to infinity. In addition, we experimentally demonstrate and theoretically analyze that FSSD has poor performance or even fails to test for high-dimensional data. Finally, we conduct a series of experiments to evaluate the performance of our ELR statistics as compared to state-of-the-art linear statistics.

Kernel selection is fundamental to the generalization performance of kernel-based learning algorithms. Approximate kernel selection is an efficient kernel selection approach that exploits the convergence property of the kernel selection criteria and the computational virtue of kernel matrix approximation. The convergence property is measured by the notion of approximate consistency. For the existing Nyström approximations, whose sampling distributions are independent of the specific learning task at hand, it is difficult to establish the strong approximate consistency. They mainly focus on the quality of the low-rank matrix approximation, rather than the performance of the kernel selection criterion used in conjunction with the approximate matrix. In this paper, we propose a novel Nyström approximate kernel selection algorithm by customizing a criterion-driven adaptive sampling distribution for the Nyström approximation, which adaptively reduces the error between the approximate and accurate criteria. We theoretically derive the strong approximate consistency of the proposed Nyström approximate kernel selection algorithm. Finally, we empirically evaluate the approximate consistency of our algorithm as compared to state-of-the-art methods.

Traditional online multitask learning only utilizes the firstorder information of the datastream. To remedy this issue, we propose a confidence weighted multitask learning algorithm, which maintains a Gaussian distribution over each task model to guide online learning process. The mean (covariance) of the Gaussian Distribution is a sum of a local component and a global component that is shared among all the tasks. In addition, this paper also addresses the challenge of active learning on the online multitask setting. Instead of requiring labels of all the instances, the proposed algorithm determines whether the learner should acquire a label by considering the confidence from its related tasks over label prediction. Theoretical results show the regret bounds can be significantly reduced. Empirical results demonstrate that the proposed algorithm is able to achieve promising learning efficacy, while simultaneously minimizing the labeling cost.

Discovering disease-gene association is a fundamental and critical biomedical task, which assists biologists and physicians to discover pathogenic mechanism of syndromes. With various clinical biomarkers measuring the similarities among genes and disease phenotypes, network-based semi-supervised learning (NSSL) has been commonly utilized by these studies to address this class-imbalanced large-scale data issue. However, most existing NSSL approaches are based on linear models and suffer from two major limitations: 1) They implicitly consider a local-structure representation for each candidate; 2) They are unable to capture nonlinear associations between diseases and genes. In this paper, we propose a new framework for disease-gene association task by combining Graph Convolutional Network (GCN) and matrix factorization, named GCN-MF. With the help of GCN, we could capture non-linear interactions and exploit measured similarities. Moreover, we define a margin control loss function to reduce the effect of sparsity. Empirical results demonstrate that the proposed deep learning algorithm outperforms all other state-of-the-art methods on most of metrics.

Motivation: Dual-axis electron tomography is an important 3 D macro-molecular structure reconstruction technology, which can reduce artifacts and suppress the effect of missing wedge. However, the fully automatic data process for dual-axis electron tomography still remains a challenge due to three difficulties: (i) how to track the mass of fiducial markers automatically; (ii) how to integrate the information from the two different tilt series; and (iii) how to cope with the inconsistency between the two different tilt series. Results: Here we develop a toolkit for fully automatic alignment of dual-axis electron tomography, with a simultaneous reconstruction procedure. The proposed toolkit and its workflow carries out the following solutions: (i) fully automatic detection and tracking of fiducial markers under large-field datasets; (ii) automatic combination of two different tilt series and global calibration of projection parameters; and (iii) inconsistency correction based on distortion correction parameters and the consequently simultaneous reconstruction. With all of these features, the presented toolkit can achieve accurate alignment and reconstruction simultaneously and conveniently under a single global coordinate system. Availability and implementation: The toolkit AuTom-dualx (alignment module dualxmauto and reconstruction module volrec_mltm) are accessible for general application at http://ear.ict.ac.cn, and the key source code is freely available under request. Supplementary information: Supplementary data are available at Bioinformatics online.

Kernel selection aims at choosing an appropriate kernel function for kernel-based learning algorithms to avoid either underfitting or overfitting of the resulting hypothesis. One of the main problems faced by kernel selection is the evaluation of the goodness of a kernel, which is typically difficult and computationally expensive. In this paper, we propose a randomized kernel selection approach to evaluate and select the kernel with the spectra of the specifically designed multilevel circulant matrices (MCMs), which is statistically sound and computationally efficient. Instead of constructing the kernel matrix, we construct the randomized MCM to encode the kernel function and all data points together with labels. We build a one-to-one correspondence between all candidate kernel functions and the spectra of the randomized MCMs by Fourier transform. We prove the statistical properties of the randomized MCMs and the randomized kernel selection criteria, which theoretically qualify the utility of the randomized criteria in kernel selection. With the spectra of the randomized MCMs, we derive a series of randomized criteria to conduct kernel selection, which can be computed in log-linear time and linear space complexity by fast Fourier transform (FFT). Experimental results demonstrate that our randomized kernel selection criteria are significantly more efficient than the existing classic and widely-used criteria while preserving similar predictive performance.

Traditional online learning on graphs adapts graph Laplacian into ridge regression, which may not guarantee reasonable accuracy when the data are adversarially generated. To solve this issue, we exploit an adaptive optimization framework for online classification on graphs. The derived model can achieve a min-max regret under an adversarial mechanism of data generation. To take advantage of the informative labels, we propose an adaptive large-margin update rule, which enjoys a lower regret than the algorithms using error-driven update rules. However, this algorithm assumes that the full information label is provided for each node, which is violated in many practical applications where labeling is expensive and the oracle may only tell whether the prediction is correct or not. To address this issue, we propose a bandit online algorithm on graphs. It derives per-instance confidence region of the prediction, from which the model can be learned adaptively to minimize the online regret. Experiments on benchmark graph datasets show that the proposed bandit algorithm outperforms state-of-the-art competitors, even sometimes beats the algorithms using full information label feedback.

This paper aims at improvement on the effectiveness of matrix decomposition (MD) methods for implicit feedback. We highlight two critical limitations of existing works. First, due to the large number of unlabeled feedback, most existing works employ a uniform weight to the missing data to reduce computational complexity. However, such a uniform assumption may rarely hold in real-world scenarios. Second, the commonly-used bilateral loss function might be infinite if the data point is mis-classified. Outliers may have such issues and misguide the learning process. We address the above two issues by learning a robust asymmetric learning model. By leveraging the cost-sensitive learning and capped unilateral loss function, our robust MD objective function integrates them into a joint formulation, where the low-rank basis for user/item profiles can be modeled in an effective and robust way. Particularly, a novel log-determinant function is employed to refine the nuclear norm with respect to the low-rank approximation. We derive an iterative re-weighted algorithm to efficiently minimize this MD objective, and also rigorously prove a lower error bound of the proposed algorithm compared to the 1-bit matrix completion method. Finally, we show the promising experimental results of our algorithm on benchmark recommendation datasets.

Recommender systems with implicit feedback (e.g. clicks and purchases) suffer from two critical limitations: 1) imbalanced labels may mislead the learning process of the conventional models that assign balanced weights to the classes; and 2) outliers with large reconstruction errors may dominate the objective function by the conventional $L_2$-norm loss. To address these issues, we propose a robust asymmetric recommendation model. It integrates cost-sensitive learning with capped unilateral loss into a joint objective function, which can be optimized by an iteratively weighted approach. To reduce the computational cost of low-rank approximation, we exploit the dual characterization of the nuclear norm to derive a min-max optimization problem and design a subgradient algorithm without performing full SVD. Finally, promising empirical results demonstrate the effectiveness of our algorithm on benchmark recommendation datasets.

Keyphrases that efficiently summarize a document’s content are used in various document processing and retrieval tasks. Current state-of-the-art techniques for keyphrase extraction operate at a phrase-level and involve scoring candidate phrases based on features of their component words.In this paper, we learn keyphrase taggers for research papers using token-based features incorporating linguistic, surface-form, and document-structure information through sequence labeling. We experimentally illustrate that using within document features alone, our tagger trained with ConditionalRandom Fields performs on-par with existing state-of-the-art systems that rely on information from Wikipedia and citation networks. In addition, we are also able to harness recent work on feature labeling to seamlessly incorporate expert knowledge and predictions from existing systems to enhance the extraction performance further. We highlight the modeling advantages of our keyphrase taggers and show significant performance improvements on two recently-compiled datasets of keyphrases from Computer Science research papers.

Multi-Task Learning (MTL) can enhance a classifier's generalization performance by learning multiple related tasks simultaneously. Conventional MTL works under the offline or batch setting, and suffers from expensive training cost and poor scalability. To address such inefficiency issues, online learning techniques have been applied to solve MTL problems. However, most existing algorithms of online MTL constrain task relatedness into a presumed structure via a single weight matrix, which is a strict restriction that does not always hold in practice. In this paper, we propose a robust online MTL framework that overcomes this restriction by decomposing the weight matrix into two components: The first one captures the low-rank common structure among tasks via a nuclear norm and the second one identifies the personalized patterns of outlier tasks via a group lasso. Theoretical analysis shows the proposed algorithm can achieve a sub-linear regret with respect to the best linear model in hindsight. Even though the above framework achieves good performance, the nuclear norm that simply adds all nonzero singular values together may not be a good low-rank approximation. To improve the results, we use a log-determinant function as a non-convex rank approximation. The gradient scheme is applied to optimize log-determinant function and can obtain a closed-form solution for this refined problem. Experimental results on a number of real-world applications verify the efficacy of our method.

Multi-Task Learning (MTL) can enhance the classifier's generalization performance by learning multiple related tasks simultaneously. Conventional MTL works under the offline or batch learning setting and suffers from the expensive training cost together with the poor scalability. To address such inefficiency issues, online learning technique has been applied to solve MTL problems. However, most existing algorithms for online MTL constrain task relatedness into a presumed structure via a single weight matrix, a strict restriction that does not always hold in practice. In this paper, we propose a general online MTL framework that overcomes this restriction by decomposing the weight matrix into two components: the first component captures the correlative structure among tasks in a low-rank subspace, and the second component identifies the personalized patterns for the outlier tasks. A projected gradient scheme is devised to learn such components adaptively. Theoretical analysis shows that the proposed algorithm can achieve a sub-linear regret with respect to the best linear model in hindsight. Experimental investigation on a number of real-world datasets also verifies the efficacy of our approach.

Traditional online learning for graph node classification adapts graph regularization into ridge regression, which may not be suitable when data is adversarially generated. To solve this issue, we propose a more general min-max optimization framework for online graph node classification. The derived online algorithm can achieve a min-max regret compared with the optimal linear model found offline. However, this algorithm assumes that the label is provided for every node, while label is scare and labeling is usually either too time-consuming or expensive in real-world applications. To save labeling effort, we propose a novel confidence-based query approach to prioritize the informative labels. Our theoretical result shows that an online algorithm learning on these selected labels can achieve comparable mistake bound with the fully-supervised online counterpart. To take full advantage of these labels, we propose an aggressive algorithm, which can update the model even if no error occurs. Theoretical analysis shows that the mistake bound of the proposed method, thanks to the aggressive update trials, is better than conservative competitor in expectation. We finally empirically evaluate it on several real-world graph databases. Encouraging experimental results further demonstrate the effectiveness of our method.

Traditional online learning algorithms are designed for vector data only, which assume that the labels of all the training examples are provided. In this paper, we study graph classification where only limited nodes are chosen for labelling by selective sampling. Particularly, we first adapt a spectral-based graph regularization technique to derive a novel online learning linear algorithm which can handle graph data, although it still queries the labels of all nodes and thus is not preferred, as labelling is typically time-consuming. To address this issue, we then propose a new confidence-based query method for selective sampling. The theoretical result shows that our online learning algorithm with a fraction of queried labels can achieve a mistake bound comparable with the one learning on all labels of the nodes. In addition, the algorithm based on our proposed query strategy can achieve a mistake bound better than the one based on other query methods. However, our algorithm is conservative to update the model whenever error happens, which obviously wastes training labels that are valuable for the model. To take advantage of these labels, we further propose a novel aggressive algorithm, which can update the model aggressively even if no error occurs. The theoretical analysis shows that our aggressive approach can achieve a mistake bound better than its conservative and fully-supervised counterpart, with substantially fewer queried times. We empirically evaluate our algorithm on several real-world graph datasets and the experimental results demonstrate that our method is highly effective.

One major problem of using location data collected from mobile cellular networks for mobility modelling is the oscillation phenomenon. An oscillation occurs when a mobile phone intermittently switches between cell towers instead of connecting to the nearest cell tower. For the purpose of mobility modeling, the location data needs to be cleansed to approximate the mobile device's actual location. However, this constitutes a challenge because the mobile device's true location is not known. In this paper, we study the oscillation resolution problem. We propose an algorithm framework called DECRE (Detect, Expand, Check, Remove) to detect and remove oscillation logs. To make informed decisions DECRE includes four steps: Detect, to identify log sequences that may contain oscillation using a few heuristics based on the concepts of stable period and moving at impossible speed, Expand, to look before and after suspicious records to gain more information, Check, to check whether a cell tower is observed repeatedly (which is a strong indication of oscillation), and Remove, resolving oscillation by selecting a cell tower to approximate the mobile device's actual location. Our experimental results on travel diaries show that our oscillation resolution approach is able to remove records that are far from mobile device's ground-truth locations, improve the quality of the location data, and performs better than an existing method. Our performance study on large scale cell tower data shows that the MapReduce implementation of our approach is able to process 1 Terabyte of cell tower data in five hours using a small cluster.

BACKGROUND: As a fundamental genomic element, meiotic recombination hotspot plays important roles in life sciences. Thus uncovering its regulatory mechanisms has broad impact on biomedical research. Despite the recent identification of the zinc finger protein PRDM9 and its 13-mer binding motif as major regulators for meiotic recombination hotspots, other regulators remain to be discovered. Existing methods for finding DNA sequence motifs of recombination hotspots often rely on the enrichment of co-localizations between hotspots and short DNA patterns, which ignore the cross-individual variation of recombination rates and sequence polymorphisms in the population. Our objective in this paper is to capture signals encoded in genetic variations for the discovery of recombination-associated DNA motifs. RESULTS: Recently, an algorithm called "LDsplit" has been designed to detect the association between single nucleotide polymorphisms (SNPs) and proximal meiotic recombination hotspots. The association is measured by the difference of population recombination rates at a hotspot between two alleles of a candidate SNP. Here we present an open source software tool of LDsplit, with integrative data visualization for recombination hotspots and their proximal SNPs. Applying LDsplit on SNPs inside an established 7-mer motif bound by PRDM9 we observed that SNP alleles preserving the original motif tend to have higher recombination rates than the opposite alleles that disrupt the motif. Running on SNP windows around hotspots each containing an occurrence of the 7-mer motif, LDsplit is able to guide the established motif finding algorithm of MEME to recover the 7-mer motif. In contrast, without LDsplit the 7-mer motif could not be identified. CONCLUSIONS: LDsplit is a software tool for the discovery of cis-regulatory DNA sequence motifs stimulating meiotic recombination hotspots by screening and narrowing down to hotspot associated SNPs. It is the first computational method that utilizes the genetic variation of recombination hotspots among individuals, opening a new avenue for motif finding. Tested on an established motif and simulated datasets, LDsplit shows promise to discover novel DNA motifs for meiotic recombination hotspots.

Genetic recombination is an essential event during the process of meiosis resulting in an exchange of segments between paired chromosomes. Estimating recombination rate is crucial for understanding the process of recombination. Experimental methods are normally difficult and limited to small scale estimations. Thus statistical methods using population genetics data are important for large-scale analysis. LDhat is an extensively used statistical method using rjMCMC algorithm to predict recombination rates. Due to the complexity of rjMCMC scheme, LDhat may take a long time for large SNP data sets. In addition, rjMCMC parameters should be manually defined in the original program which directly impact results. To address these issues, we designed an improved algorithm based on LDhat implementing MCMC convergence diagnostic algorithms to automatically predict values of parameters and monitor the mixing process. Then parallel computation methods were employed to further accelerate the new program. The new algorithms have been tested on ten samples from HapMap phase 2 data set. The results were compared with previous code and showed nearly identical output. However, our new methods achieved significant acceleration proving that they are more efficient and reliable for the estimation of recombination rates. The stand-alone package is freely available for download http://www.ntu.edu.sg/home/zhengjie/software/CPLDhat.

MOTIVATION: In silico methods provide efficient ways to predict possible interactions between drugs and targets. Supervised learning approach, bipartite local model (BLM), has recently been shown to be effective in prediction of drug-target interactions. However, for drug-candidate compounds or target-candidate proteins that currently have no known interactions available, its pure 'local' model is not able to be learned and hence BLM may fail to make correct prediction when involving such kind of new candidates. RESULTS: We present a simple procedure called neighbor-based interaction-profile inferring (NII) and integrate it into the existing BLM method to handle the new candidate problem. Specifically, the inferred interaction profile is treated as label information and is used for model learning of new candidates. This functionality is particularly important in practice to find targets for new drug-candidate compounds and identify targeting drugs for new target-candidate proteins. Consistent good performance of the new BLM-NII approach has been observed in the experiment for the prediction of interactions between drugs and four categories of target proteins. Especially for nuclear receptors, BLM-NII achieves the most significant improvement as this dataset contains many drugs/targets with no interactions in the cross-validation. This demonstrates the effectiveness of the NII strategy and also shows the great potential of BLM-NII for prediction of compound-protein interactions. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Identifying disease genes from human genome is an important but challenging task in biomedical research. Machine learning methods can be applied to discover new disease genes based on the known ones. Existing machine learning methods typically use the known disease genes as the positive training set P and the unknown genes as the negative training set N (non-disease gene set does not exist) to build classifiers to identify new disease genes from the unknown genes. However, such kind of classifiers is actually built from a noisy negative set N as there can be unknown disease genes in N itself. As a result, the classifiers do not perform as well as they could be. RESULT: Instead of treating the unknown genes as negative examples in N, we treat them as an unlabeled set U. We design a novel positive-unlabeled (PU) learning algorithm PUDI (PU learning for disease gene identification) to build a classifier using P and U. We first partition U into four sets, namely, reliable negative set RN, likely positive set LP, likely negative set LN and weak negative set WN. The weighted support vector machines are then used to build a multi-level classifier based on the four training sets and positive training set P to identify disease genes. Our experimental results demonstrate that our proposed PUDI algorithm outperformed the existing methods significantly. CONCLUSION: The proposed PUDI algorithm is able to identify disease genes more accurately by treating the unknown data more appropriately as unlabeled set U instead of negative set N. Given that many machine learning problems in biomedical research do involve positive and unlabeled data instead of negative data, it is possible that the machine learning methods for these problems can be further improved by adopting PU learning methods, as we have done here for disease gene identification. AVAILABILITY AND IMPLEMENTATION: The executable program and data are available at http://www1.i2r.a-star.edu.sg/~xlli/PUDI/PUDI.html.