Nearest neighbor search aims at obtaining the samples in the database with the smallest distances from them to the queries, which is a basic task in a range of fields, including computer vision and data mining. Hashing is one of the most widely used methods for its computational and storage efficiency. With the development of deep learning, deep hashing methods show more advantages than traditional methods. In this survey, we detailedly investigate current deep hashing algorithms including deep supervised hashing and deep unsupervised hashing. Specifically, we categorize deep supervised hashing methods into pairwise methods, ranking-based methods, pointwise methods as well as quantization according to how measuring the similarities of the learned hash codes. Moreover, deep unsupervised hashing is categorized into similarity reconstruction-based methods, pseudo-label-based methods, and prediction-free self-supervised learning-based methods based on their semantic learning manners. We also introduce three related important topics including semi-supervised deep hashing, domain adaption deep hashing, and multi-modal deep hashing. Meanwhile, we present some commonly used public datasets and the scheme to measure the performance of deep hashing algorithms. Finally, we discuss some potential research directions in conclusion.

Motivation: Direct analysis of microbial communities in the environment and human body has become more convenient and reliable owing to the advancements of high-throughput sequencing techniques for 16S rRNA gene profiling. Inferring the correlation relationship among members of microbial communities is of fundamental importance for genomic survey study. Traditional Pearson correlation analysis treating the observed data as absolute abundances of the microbes may lead to spurious results because the data only represent relative abundances. Special care and appropriate methods are required prior to correlation analysis for these compositional data. Results: In this article, we first discuss the correlation definition of latent variables for compositional data. We then propose a novel method called CCLasso based on least squares with $ℓ1$ penalty to infer the correlation network for latent variables of compositional data from metagenomic data. An effective alternating direction algorithm from augmented Lagrangian method is used to solve the optimization problem. The simulation results show that CCLasso outperforms existing methods, e.g. SparCC, in edge recovery for compositional data. It also compares well with SparCC in estimating correlation network of microbe species from the Human Microbiome Project. Availability and implementation: CCLasso is open source and freely available from https://github.com/huayingfang/CCLasso under GNU LGPL v3. Contact:dengmh@pku.edu.cn Supplementary information: Supplementary data are available at Bioinformatics online.

Cell-cell communication (CCC) is critical for determining cell fates and functions in multicellular organisms. With the advent of single-cell RNA-sequencing (scRNA-seq) and spatial transcriptomics (ST), an increasing number of CCC inference methods have been developed. Nevertheless, a thorough comparison of their performances is yet to be conducted. To fill this gap, we developed a systematic benchmark framework called ESICCC to evaluate 18 ligand-receptor (LR) inference methods and five ligand/receptor-target inference methods using a total of 116 data sets, including 15 ST data sets, 15 sets of cell line perturbation data, two sets of cell type–specific expression/proteomics data, and 84 sets of sampled or unsampled scRNA-seq data. We evaluated and compared the agreement, accuracy, robustness, and usability of these methods. Regarding accuracy evaluation, RNAMagnet, CellChat, and scSeqComm emerge as the three best-performing methods for intercellular ligand-receptor inference based on scRNA-seq data, whereas stMLnet and HoloNet are the best methods for predicting ligand/receptor-target regulation using ST data. To facilitate the practical applications, we provide a decision-tree-style guideline for users to easily choose best tools for their specific research concerns in CCC inference, and develop an ensemble pipeline CCCbank that enables versatile combinations of methods and databases. Moreover, our comparative results also uncover several critical influential factors for CCC inference, such as prior interaction information, ligand-receptor scoring algorithm, intracellular signaling complexity, and spatial relationship, which may be considered in the future studies to advance the development of new methodologies.

Single-cell RNA sequencing (scRNA-seq) allows researchers to study cell heterogeneity at the cellular level. A crucial step in analyzing scRNA-seq data is to cluster cells into subpopulations to facilitate subsequent downstream analysis. However, frequent dropout events and increasing size of scRNA-seq data make clustering such high-dimensional, sparse and massive transcriptional expression profiles challenging. Although some existing deep learning-based clustering algorithms for single cells combine dimensionality reduction with clustering, they either ignore the distance and affinity constraints between similar cells or make some additional latent space assumptions like mixture Gaussian distribution, failing to learn cluster-friendly low-dimensional space. Therefore, in this paper, we combine the deep learning technique with the use of a denoising autoencoder to characterize scRNA-seq data while propose a soft self-training K-means algorithm to cluster the cell population in the learned latent space. The self-training procedure can effectively aggregate the similar cells and pursue more cluster-friendly latent space. Our method, called ‘scziDesk’, alternately performs data compression, data reconstruction and soft clustering iteratively, and the results exhibit excellent compatibility and robustness in both simulated and real data. Moreover, our proposed method has perfect scalability in line with cell size on large-scale datasets.

Motivation: In recent years, high-throughput sequencing technologies have made large-scale protein sequences accessible. However, their functional annotations usually rely on low-throughput and pricey experimental studies. Computational prediction models offer a promising alternative to accelerate this process. Graph neural networks have shown significant progress in protein research, but capturing long-distance structural correlations and identifying key residues in protein graphs remains challenging. Results: In the present study, we propose a novel deep learning model named Hierarchical graph transformEr with contrAstive Learning (HEAL) for protein function prediction. The core feature of HEAL is its ability to capture structural semantics using a hierarchical graph Transformer, which introduces a range of super-nodes mimicking functional motifs to interact with nodes in the protein graph. These semantic-aware super-node embeddings are then aggregated with varying emphasis to produce a graph representation. To optimize the network, we utilized graph contrastive learning as a regularization technique to maximize the similarity between different views of the graph representation. Evaluation of the PDBch test set shows that HEAL-PDB, trained on fewer data, achieves comparable performance to the recent state-of-the-art methods, such as DeepFRI. Moreover, HEAL, with the added benefit of unresolved protein structures predicted by AlphaFold2, outperforms DeepFRI by a significant margin on Fmax, AUPR, and Smin metrics on PDBch test set. Additionally, when there are no experimentally resolved structures available for the proteins of interest, HEAL can still achieve better performance on AFch test set than DeepFRI and DeepGOPlus by taking advantage of AlphaFold2 predicted structures. Finally, HEAL is capable of finding functional sites through class activation mapping. Availability and implementation: Implementations of our HEAL can be found at https://github.com/ZhonghuiGu/HEAL.

Background: The development of high-throughput technologies has produced several large scale protein interaction data sets for multiple species, and significant efforts have been made to analyze the data sets in order to understand protein activities. Considering that the basic units of protein interactions are domain interactions, it is crucial to understand protein interactions at the level of the domains. The availability of many diverse biological data sets provides an opportunity to discover the underlying domain interactions within protein interactions through an integration of these biological data sets. Results: We combine protein interaction data sets from multiple species, molecular sequences, and gene ontology to construct a set of high-confidence domain-domain interactions. First, we propose a new measure, the expected number of interactions for each pair of domains, to score domain interactions based on protein interaction data in one species and show that it has similar performance as the E-value defined by Riley et al. [1]. Our new measure is applied to the protein interaction data sets from yeast, worm, fruitfly and humans. Second, information on pairs of domains that coexist in known proteins and on pairs of domains with the same gene ontology function annotations are incorporated to construct a high-confidence set of domain-domain interactions using a Bayesian approach. Finally, we evaluate the set of domain-domain interactions by comparing predicted domain interactions with those defined in iPfam database [2, 3] that were derived based on protein structures. The accuracy of predicted domain interactions are also confirmed by comparing with experimentally obtained domain interactions from H. pylori [4]. As a result, a total of 2,391 high-confidence domain interactions are obtained and these domain interactions are used to unravel detailed protein and domain interactions in several protein complexes. Conclusion: Our study shows that integration of multiple biological data sets based on the Bayesian approach provides a reliable framework to predict domain interactions. By integrating multiple data sources, the coverage and accuracy of predicted domain interactions can be significantly increased.