Short tandem repeats (STRs) represent one of the most polymorphic variations in the human genome, finding extensive applications in forensics, population genetics and medical genetics. In contrast to the traditional capillary electrophoresis (CE) method, genotyping STRs using massive parallel sequencing technology offers enhanced sensitivity and accuracy. However, current methods are mainly designed for target sequencing with higher coverage for a specific STR locus, thereby constraining the utility of STRs in low- and medium-coverage whole genome sequencing (WGS) data. Here, we introduce STRsensor, a method designed to type STR alleles in low-coverage WGS data and target sequencing data, achieving a significant high detection ratio and accuracy. STRsensor employs two methods for STR allele-typing: the Kmers-based method and the CIGAR-based method. Furthermore, by incorporating a model for PCR stutters, STRsensor greatly enhances the accuracy of STR allele typing. With simulation data, we demonstrate that STRsensor achieves a detection ratio of 100$\%$ and an accuracy of 99.37$\%$ for a 30$\times $ WGS data, outperforming the existing methods, such as STRait Razor, STRinNGS, and HipSTR. When applied to real target sequencing data from 687 individuals, STRsensor achieves a detection ratio of 99.64$\%$ and an accuracy of 99.99$\%$. Moreover, STRsensor is a computationally efficient method that runs 79 times faster than HipSTR and 10 000 times faster than STRinNGS. STRsensor is freely available on GitHub: https://github.com/ChenHuaLab/STRsensor.

Passive traffic monitoring can be used for network diagnosis and management in wireless networks by deploying wireless sniffers to monitor abnormal data traffic on different channels and locations. This motivates the spatial sniffer-channel assignment (SSCA) problem, i.e., assigning each wireless sniffer a proper operating channel and location to detect the target signals or data packets. The existing approaches for SSCA problems are usually designed for the scenarios where the behavior features of the target users are known. In this paper, we focus on a cognitive monitoring system without information about the users' activities. The wireless sniffers can be deployed to patrol different locations and meet a desirable detection probability requirement. Considering a dynamic network environment with a huge state space, we propose a novel deep reinforcement learning (DRL) approach to adapt the patrolling route for each wireless sniffer. Moreover, we employ Bayesian optimization to help explore the action space and thus improve the learning efficiency. Via numerical simulations, we show that the Bayesian optimization enhanced DRL approach can improve the detection performance and fast adapt the wireless sniffers' actions according to the environmental changes.

Illuminating interactions between proteins and small drug molecules is a long-standing challenge in the field of drug discovery. Despite the importance of understanding these interactions, most previous works are limited by hand-designed scoring functions and insufficient conformation sampling. The recently-proposed graph neural network-based methods provides alternatives to predict protein-ligand complex conformation in a one-shot manner. However, these methods neglect the geometric constraints of the complex structure and weaken the role of local functional regions. As a result, they might produce unreasonable conformations for challenging targets and generalize poorly to novel proteins. In this paper, we propose Trigonometry-Aware Neural networKs for binding structure prediction, TANKBind, that builds trigonometry constraint as a vigorous inductive bias into the model and explicitly attends to all possible binding sites for each protein by segmenting the whole protein into functional blocks. We construct novel contrastive losses with local region negative sampling to jointly optimize the binding interaction and affinity. Extensive experiments show substantial performance gains in comparison to state-of-the-art physics-based and deep learning-based methods on commonly-used benchmark datasets for both binding structure and affinity predictions with variant settings.

Retrosynthetic planning is a critical task in organic chemistry which identifies a series of reactions that can lead to the synthesis of a target product. The vast number of possible chemical transformations makes the size of the search space very big, and retrosynthetic planning is challenging even for experienced chemists. However, existing methods either require expensive return estimation by rollout with high variance, or optimize for search speed rather than the quality. In this paper, we propose Retro*, a neural-based A*-like algorithm that finds high-quality synthetic routes efficiently. It maintains the search as an AND-OR tree, and learns a neural search bias with off-policy data. Then guided by this neural network, it performs best-first search efficiently during new planning episodes. Experiments on benchmark USPTO datasets show that, our proposed method outperforms existing state-of-the-art with respect to both the success rate and solution quality, while being more efficient at the same time.

Global context is crucial for 3D point cloud scene understanding tasks. In this work, we extended the contextual encoding layer that was originally designed for 2D tasks to 3D Point Cloud scenarios. The encoding layer learns a set of code words in the feature space of the 3D point cloud to characterize the global semantic context, and then based on these code words, the method learns a global contextual descriptor to reweight the featuremaps accordingly. Moreover, compared to 2D scenarios, data sparsity becomes a major issue in 3D point cloud scenarios, and the performance of contextual encoding quickly saturates when the number of code words increases. To mitigate this problem, we further proposed a group contextual encoding method, which divides the channel into groups and then performs encoding on group-divided feature vectors. This method facilitates learning of global context in grouped subspace for 3D point clouds. We evaluate the effectiveness and generalizability of our method on three widely-studied 3D point cloud tasks. Experimental results have shown that the proposed method outperformed the VoteNet remarkably with 3 mAP on the benchmark of SUN-RGBD, with the metrics of mAP@ 0.25, and a much greater margin of 6.57 mAP on ScanNet with the metrics of mAP@ 0.5. Compared to the baseline of PointNet++, the proposed method leads to an accuracy of 86 %, outperforming the baseline by 1.5 %. Our proposed method have outperformed the non-grouping baseline methods across the board and establishes new state-of-the-art on these benchmarks.

Retrosynthesis is one of the fundamental problems in organic chemistry. The task is to identify reactants that can be used to synthesize a specified product molecule. Recently, computer-aided retrosynthesis is finding renewed interest from both chemistry and computer science communities. Most existing approaches rely on template-based models that define subgraph matching rules, but whether or not a chemical reaction can proceed is not defined by hard decision rules. In this work, we propose a new approach to this task using the Conditional Graph Logic Network, a conditional graphical model built upon graph neural networks that learns when rules from reaction templates should be applied, implicitly considering whether the resulting reaction would be both chemically feasible and strategic. We also propose an efficient hierarchical sampling to alleviate the computation cost. While achieving a significant improvement of 8.2% over current state-of-the-art methods on the benchmark dataset, our model also offers interpretations for the prediction.

Recent deep learning approaches for representation learning on graphs follow a neighborhood aggregation procedure. We analyze some important properties of these models, and propose a strategy to overcome those. In particular, the range of "neighboring" nodes that a node’s representation draws from strongly depends on the graph structure, analogous to the spread of a random walk. To adapt to local neighborhood properties and tasks, we explore an architecture – jumping knowledge (JK) networks – that flexibly leverages, for each node, different neighborhood ranges to enable better structure-aware representation. In a number of experiments on social, bioinformatics and citation networks, we demonstrate that our model achieves state-of-the-art performance. Furthermore, combining the JK framework with models like Graph Convolutional Networks, GraphSAGE and Graph Attention Networks consistently improves those models’ performance.

Optimization of high-dimensional black-box functions is an extremely challenging problem. While Bayesian optimization has emerged as a popular approach for optimizing black-box functions, its applicability has been limited to low-dimensional problems due to its computational and statistical challenges arising from high-dimensional settings. In this paper, we propose to tackle these challenges by (1) assuming a latent additive structure in the function and inferring it properly for more efficient and effective BO, and (2) performing multiple evaluations in parallel to reduce the number of iterations required by the method. Our novel approach learns the latent structure with Gibbs sampling and constructs batched queries using determinantal point processes. Experimental validations on both synthetic and real-world functions demonstrate that the proposed method outperforms the existing state-of-the-art approaches.

We study dual volume sampling, a method for selecting k columns from an n*m short and wide matrix (n <= k <= m) such that the probability of selection is proportional to the volume spanned by the rows of the induced submatrix. This method was proposed by Avron and Boutsidis (2013), who showed it to be a promising method for column subset selection and its multiple applications. However, its wider adoption has been hampered by the lack of polynomial time sampling algorithms. We remove this hindrance by developing an exact (randomized) polynomial time sampling algorithm as well as its derandomization. Thereafter, we study dual volume sampling via the theory of real stable polynomials and prove that its distribution satisfies the “Strong Rayleigh” property. This result has numerous consequences, including a provably fast-mixing Markov chain sampler that makes dual volume sampling much more attractive to practitioners. This sampler is closely related to classical algorithms for popular experimental design methods that are to date lacking theoretical analysis but are known to empirically work well.

Determinantal Point Processes (DPPs) are elegant probabilistic models of repulsion and diversity over discrete sets of items. But their applicability to large sets is hindered by expensive cubic-complexity matrix operations for basic tasks such as sampling. In light of this, we propose a new method for approximate sampling from discrete k-DPPs. Our method takes advantage of the diversity property of subsets sampled from a DPP, and proceeds in two stages: first it constructs coresets for the ground set of items; thereafter, it efficiently samples subsets based on the constructed coresets. As opposed to previous approaches, our algorithm aims to minimize the total variation distance to the original distribution. Experiments on both synthetic and real datasets indicate that our sampling algorithm works efficiently on large data sets, and yields more accurate samples than previous approaches.

The Nystrom method has long been popular for scaling up kernel methods. Its theoretical guarantees and empirical performance rely critically on the quality of the landmarks selected. We study landmark selection for Nystrom using Determinantal Point Processes (DPPs), discrete probability models that allow tractable generation of diverse samples. We prove that landmarks selected via DPPs guarantee bounds on approximation errors; subsequently, we analyze implications for kernel ridge regression. Contrary to prior reservations due to cubic complexity of DPP sampling, we show that (under certain conditions) Markov chain DPP sampling requires only linear time in the size of the data. We present several empirical results that support our theoretical analysis, and demonstrate the superior performance of DPP-based landmark selection compared with existing approaches.

We present a framework for accelerating a spectrum of machine learning algorithms that require computation of \emphbilinear inverse forms u^T A^-1u, where A is a positive definite matrix and u a given vector. Our framework is built on Gauss-type quadrature and easily scales to large, sparse matrices. Further, it allows retrospective computation of lower and upper bounds on u^T A^-1u, which in turn accelerates several algorithms. We prove that these bounds tighten iteratively and converge at a linear (geometric) rate. To our knowledge, ours is the first work to demonstrate these key properties of Gauss-type quadrature, which is a classical and deeply studied topic. We illustrate empirical consequences of our results by using quadrature to accelerate machine learning tasks involving determinantal point processes and submodular optimization, and observe tremendous speedups in several instances.

We study probability measures induced by set functions with constraints. Such measures arise in a variety of real-world settings, where prior knowledge, resource limitations, or other pragmatic considerations impose constraints. We consider the task of rapidly sampling from such constrained measures, and develop fast Markov chain samplers for them. Our first main result is for MCMC sampling from Strongly Rayleigh (SR) measures, for which we present sharp polynomial bounds on the mixing time. As a corollary, this result yields a fast mixing sampler for Determinantal Point Processes (DPPs), yielding (to our knowledge) the first provably fast MCMC sampler for DPPs since their inception over four decades ago. Beyond SR measures, we develop MCMC samplers for probabilistic models with hard constraints and identify sufficient conditions under which their chains mix rapidly. We illustrate our claims by empirically verifying the dependence of mixing times on the key factors governing our theoretical bounds.

Detecting similar question is a fundamental and essential research problem for constructing similar question dataset for the research of question-answering, short text similarity calculating, and sentence paragraphing. This paper explores the previous assumption about similar question detection and analyzes its existing problem. Afterwards, we propose an automated approach to detecting similar questions based on the calculation of question topical diversity using different ways of topical feature generation methods. The experiment dataset are Yahoo! 4,482,757 questions with answers. The results present that our approach achieves a precision of 74% and a recall of 74% as the best performance compared with baseline methods, demonstrating its effectiveness in similar question group detection.

Yuan Zhang, Chengtao Li, Regina Barzilay, Kareem Darwish. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

Both max-margin and Bayesian methods have been extensively studied in multi-task learning, but have rarely been considered together. We present Bayesian max-margin multi-task learning, which conjoins the two schools of methods, thus allowing the discriminative max-margin methods to enjoy the great flexibility of Bayesian methods on incorporating rich prior information as well as performing nonparametric Bayesian feature learning with the latent dimensionality resolved from data. We develop Gibbs sampling algorithms by exploring data augmentation to deal with the non-smooth hinge loss. For nonparametric models, our algorithms do not need to make mean-field assumptions or truncated approximation. Empirical results demonstrate superior performance than competitors in both multi-task classification and regression.

This paper deals with the problem of jointly mining topics, sentiments, and the association between them from online reviews in an unsupervised way. Previous methods often treat a sentiment as a special topic and assume a word is generated from a flat mixture of topics, where the discriminative performance of sentiment analysis is not satisfied. A key reason is that providing rich priors on the polarity of a word for the flat mixture is difficult as the polarity often depends on the topic. To solve the problem we propose a novel model. We decompose the generative process of a word's sentiment polarity to a two-level hierarchy: the first level determines whether a word is used as a sentiment word or just an ordinary topic word, and the second level (if the word is used as a sentiment word) determines the polarity of it. With the decomposition, we provide separate prior for the the first level to encourage the discrimination between sentiment words and ordinary topic words. This prior is relatively easy to obtain compared to the concrete prior of the word polarities. We construct the prior based on part-of-speech tags of words and embed the prior into the model. Experiments on four real online review data sets show that our model consistently outperforms previous methods in the task of sentiment analysis, and simultaneously performs well in the sub-tasks of discovering ordinary topics, sentiment-specific topics, and extracting topic-specific sentiment words.