Single-cell ATAC-seq (scATAC-seq) technology allows the interrogation of chromatin accessibility of individual cells. Dropout events occur while the sequencing data signals at some bona fide chromatin sites of individuals are not captured, and the curse of these dropouts in scATAC-seq data inevitably hinders downstream analysis. It remains a challenge to impute scATAC-seq data due to its high dimensionality, sparsity, and near-binarization properties. Herein, we propose IMATAC, a deep hierarchical network with denoising autoencoder for imputing scATAC-seq data in the form of peak by cell. The network embeds scATAC-seq data into a latent space by a deep hierarchical architecture at two different levels, including bottom level for local details and top level for global information, that helps to characterize the high-dimensional sparse scATAC-seq data. Besides, it is encouraged to learn to reconstruct the original scATAC-seq data from an artificially corrupted version through a denoising autoencoder, so as to acquire an ability to recover the missing values primarily relying on the cells under the same population with the help of a parallel multi-classifier. Using simulated and experimental data, the performance of IMATAC is demonstrated by a comparative analysis with the other competing methods. The results suggest that our method can achieve lower imputation errors, and benefit the downstream analysis, including heterogeneous clustering, differential analysis, and regulatory element discovery. Besides, the contributions of several important network modules in our IMATAC are investigated, and how well it can separate the dropout zeros from biological zeros are discussed.

Unconstrained Palmprint Recognition (UPR) shows engaging potential owing to its high hygiene and privacy. The unconstrained acquisition usually produces wide variations, against which deep methods resort to large samples that are unavailable in practice, however. We focus on Few-Shot UPR (FS-UPR), a more general problem, recognizing query samples given a few support samples per class. Because scarce samples insufficiently represent potential variations, the augmentation methods train independent hallucinators on large samples to generate more ones. Whereas, the hallucinators trained independently of Few-Shot Learning (FSL) are blind of generating promising samples to boost the downstream FSL. Moreover, training hallucinators requires large samples per class, unavailable from unconstrained palmprint databases. We aim to address FS-UPR via contrastive augmentation merely on the support samples. Observing the variations to betransferableacross samples, we exploit low-rank representation to disentangle support samples intoprinciplesandvariationsin embedding space and augment features by variation transfer. To this end, we devise anend-to-endDeep Low-Rank Representation Feature Augmentation Network (DLRR-FAN) to simultaneously learn the embedding space and augmentation features with guaranteedrealityanddiversity. Furthermore, a Contrastive Recognition Regularizer (CRR) is tailored to secure thediscriminabilityof augmentation features. During each training episode, the task motivates DLRR-FAN to augment such features that correct the biased prototypes towards upcoming query samples with variations unseen in the support samples, namelytask-drivenprototype correction. Extensive experiments on both the typical and extended FS-UPR tasks demonstrate the efficacy of DLRR-FAN versus the state-of-the-art methods.

Few-shot learning is challenging in unconstrained palmprint recognition, where the palmprint images are collected by unconstrained acquisitions, i.e., different imaging sensors, backgrounds, palm postures, and illumination conditions. Furthermore, due to the lack of unconstrained palmprint databases and sufficient intra-class samples, it is difficult to apply the classic few-shot techniques, such as pre-training, fine-tuning, and sample augmentation, to generalize the model. In this work, we propose a novel feature augmentation network (FAN) for few-shot unconstrained palmprint recognition. Without any external databases, FAN aims to simultaneously remove the image variations caused by the unconstrained acquisitions and augment their feature representation from only a few support samples. To this end, the proposed deep self-expression module first decouples the support images into their principle and variation features. Assuming that the variations are translational across palm-print samples, the variation-sharing module achieves feature augmentations by swapping and combining all pairs of principle and variation features. The augmented palmprint features generated by FAN enable more general representations of categorical prototypes for few-shot unconstrained palmprint recognition. Experimental results on the standard palmprint databases show that FAN can effectively represent the prototypes of palmprint images from only a few available samples, thus outperforming the state-of-the-art methods in unconstrained palmprint recognition.

Robustness enhancement and feature selection are the two crucial issues to be resolved in robust palmprint recognition. However, existing regression-based methods are insufficient to handle outliers and select significant features. From a statistical viewpoint, we present a general framework to intrinsically resolve the two issues. By investigating the role of outliers in the formation of coding errors, we devise a double-Laplacian mixture-error model to faithfully fit the error distribution. Additionally, we design a supervised group-sparse regularizer to enforce the locality and group sparsity of the codes. Integrating the two parts into the framework produces a nonconvex constrained problem, for which we develop an iteratively reweighted${l} _{ {1}}$-${l} _{{1}}$minimization algorithm by combining the majorization-minimization strategy and the alternating direction method of multipliers. The weighted vector learned from the error model and the local group sparsity enforced by the regularizer enable our method to better handle outliers and select more significant features than the state-of-the-art methods. Extensive experimental results verify the flexibility and robustness of our method to various contaminations.

In the classic algorithm, palmprint recognition requires extraction of palmprint features before classification and recognition, which will affect the recognition rate.To solve this problem, this paper uses the convolutional neural network (CNN) structure Alexnet to realize palmprint recognition.First, according to the characteristics of the geometric shape of palmprint, the ROI area of palmprint was cut out.Then the ROI area after processing is taken as input of convolutional neural network.Next the PRelu activation function is used to train the network to select the best learning rate and super parameters.Finally, the palmprint was classified and identified.The method was applied to PolyU Multi-Spectral Palmprint Image Database and PolyU 2D+3D Palmprint Database, and the recognition rate of a single spectrum was up to 99.99%.

Although the unimodal biometric recognition (such as face and palmprint) has higher convenience, its security is also relatively weak.The recognition accuracy is easy affected by many factors such as ambient light and recognition distance etc.To address this issue, we present a weighted multimodal biometric recognition algorithm with face and palmprint based on histogram of contourlet oriented gradient (HCOG) feature description.We employ the nonsubsampled contour transform (NSCT) to decompose the face and palmprint images, and the HOG method is adopted to extract the feature, which is named as HCOG feature.Then the dimension reduction process is applied on the HCOG feature and a novel weight value computation method is proposed to accomplish the multimodal biometric fusion recognition.Extensive experiments illustrate that our proposed weighted fusion recognition can achieve excellent recognition accuracy rates and outmatches the unimodal biometric recognition methods.

Accurate identification of functionally relevant variants against the ubiquitous background genetic variations is a significant challenge facing bioinformatics researchers and the challenge becomes more severe for non-coding variants. In this study, a novel computational method to identify candidate disease-associated non-coding single nucleotide polymorphisms (SNPs) of human genome is presented. To characterize SNPs, an extensive range of features, such as sequence context, DNA structure, evolutionary conservation and histone modification signals etc. are extracted. Then random forest is adopted to build the classifier model together with an ensemble method to deal with unbalanced data. 10-fold cross-validation result shows that the proposed method can achieve accuracy with the area under ROC curve (AUC) of 0.74. All the original data and the source matlab codes involved are available at https://sourceforge.net/projects/dissnp-predict/.