Structural basis for directional chitin biosynthesis.

Chitin, the most abundant aminopolysaccharide in nature, is an extracellular polymer consisting of N-acetylglucosamine (GlcNAc) units1. The key reactions of chitin biosynthesis are catalysed by chitin synthase2-4, a membrane-integrated glycosyltransferase that transfers GlcNAc from UDP-GlcNAc to a growing chitin chain. However, the precise mechanism of this process has yet to be elucidated. Here we report five cryo-electron microscopy structures of a chitin synthase from the devastating soybean root rot pathogenic oomycete Phytophthora sojae (PsChs1). They represent the apo, GlcNAc-bound, nascent chitin oligomer-bound, UDP-bound (post-synthesis) and chitin synthase inhibitor nikkomycin Z-bound states of the enzyme, providing detailed views into the multiple steps of chitin biosynthesis and its competitive inhibition. The structures reveal the chitin synthesis reaction chamber that has the substrate-binding site, the catalytic centre and the entrance to the polymer-translocating channel that allows the product polymer to be discharged. This arrangement reflects consecutive key events in chitin biosynthesis from UDP-GlcNAc binding and polymer elongation to the release of the product. We identified a swinging loop within the chitin-translocating channel, which acts as a 'gate lock' that prevents the substrate from leaving while directing the product polymer into the translocating channel for discharge to the extracellular side of the cell membrane. This work reveals the directional multistep mechanism of chitin biosynthesis and provides a structural basis for inhibition of chitin synthesis.

Machine learning on protein-protein interaction prediction: models, challenges and trends.

Protein-protein interactions (PPIs) carry out the cellular processes of all living organisms. Experimental methods for PPI detection suffer from high cost and false-positive rate, hence efficient computational methods are highly desirable for facilitating PPI detection. In recent years, benefiting from the enormous amount of protein data produced by advanced high-throughput technologies, machine learning models have been well developed in the field of PPI prediction. In this paper, we present a comprehensive survey of the recently proposed machine learning-based prediction methods. The machine learning models applied in these methods and details of protein data representation are also outlined. To understand the potential improvements in PPI prediction, we discuss the trend in the development of machine learning-based methods. Finally, we highlight potential directions in PPI prediction, such as the use of computationally predicted protein structures to extend the data source for machine learning models. This review is supposed to serve as a companion for further improvements in this field.

Sequence Alignment/Map format: a comprehensive review of approaches and applications.

The Sequence Alignment/Map (SAM) format file is the text file used to record alignment information. Alignment is the core of sequencing analysis, and downstream tasks accept mapping results for further processing. Given the rapid development of the sequencing industry today, a comprehensive understanding of the SAM format and related tools is necessary to meet the challenges of data processing and analysis. This paper is devoted to retrieving knowledge in the broad field of SAM. First, the format of SAM is introduced to understand the overall process of the sequencing analysis. Then, existing work is systematically classified in accordance with generation, compression and application, and the involved SAM tools are specifically mined. Lastly, a summary and some thoughts on future directions are provided.

Prediction of multi-relational drug-gene interaction via Dynamic hyperGraph Contrastive Learning.

Drug-gene interaction prediction occupies a crucial position in various areas of drug discovery, such as drug repurposing, lead discovery and off-target detection. Previous studies show good performance, but they are limited to exploring the binding interactions and ignoring the other interaction relationships. Graph neural networks have emerged as promising approaches owing to their powerful capability of modeling correlations under drug-gene bipartite graphs. Despite the widespread adoption of graph neural network-based methods, many of them experience performance degradation in situations where high-quality and sufficient training data are unavailable. Unfortunately, in practical drug discovery scenarios, interaction data are often sparse and noisy, which may lead to unsatisfactory results. To undertake the above challenges, we propose a novel Dynamic hyperGraph Contrastive Learning (DGCL) framework that exploits local and global relationships between drugs and genes. Specifically, graph convolutions are adopted to extract explicit local relations among drugs and genes. Meanwhile, the cooperation of dynamic hypergraph structure learning and hypergraph message passing enables the model to aggregate information in a global region. With flexible global-level messages, a self-augmented contrastive learning component is designed to constrain hypergraph structure learning and enhance the discrimination of drug/gene representations. Experiments conducted on three datasets show that DGCL is superior to eight state-of-the-art methods and notably gains a 7.6% performance improvement on the DGIdb dataset. Further analyses verify the robustness of DGCL for alleviating data sparsity and over-smoothing issues.

Dimensionality reduction and visualization of single-cell RNA-seq data with an improved deep variational autoencoder.

Single-cell RNA sequencing (scRNA-seq) is a revolutionary breakthrough that determines the precise gene expressions on individual cells and deciphers cell heterogeneity and subpopulations. However, scRNA-seq data are much noisier than traditional high-throughput RNA-seq data because of technical limitations, leading to many scRNA-seq data studies about dimensionality reduction and visualization remaining at the basic data-stacking stage. In this study, we propose an improved variational autoencoder model (termed DREAM) for dimensionality reduction and a visual analysis of scRNA-seq data. Here, DREAM combines the variational autoencoder and Gaussian mixture model for cell type identification, meanwhile explicitly solving 'dropout' events by introducing the zero-inflated layer to obtain the low-dimensional representation that describes the changes in the original scRNA-seq dataset. Benchmarking comparisons across nine scRNA-seq datasets show that DREAM outperforms four state-of-the-art methods on average. Moreover, we prove that DREAM can accurately capture the expression dynamics of human preimplantation embryonic development. DREAM is implemented in Python, freely available via the GitHub website, https://github.com/Crystal-JJ/DREAM.

Learning spatial structures of proteins improves protein-protein interaction prediction.

Spatial structures of proteins are closely related to protein functions. Integrating protein structures improves the performance of protein-protein interaction (PPI) prediction. However, the limited quantity of known protein structures restricts the application of structure-based prediction methods. Utilizing the predicted protein structure information is a promising method to improve the performance of sequence-based prediction methods. We propose a novel end-to-end framework, TAGPPI, to predict PPIs using protein sequence alone. TAGPPI extracts multi-dimensional features by employing 1D convolution operation on protein sequences and graph learning method on contact maps constructed from AlphaFold. A contact map contains abundant spatial structure information, which is difficult to obtain from 1D sequence data directly. We further demonstrate that the spatial information learned from contact maps improves the ability of TAGPPI in PPI prediction tasks. We compare the performance of TAGPPI with those of nine state-of-the-art sequence-based methods, and TAGPPI outperforms such methods in all metrics. To the best of our knowledge, this is the first method to use the predicted protein topology structure graph for sequence-based PPI prediction. More importantly, our proposed architecture could be extended to other prediction tasks related to proteins.

Deep learning in retrosynthesis planning: datasets, models and tools.

In recent years, synthesizing drugs powered by artificial intelligence has brought great convenience to society. Since retrosynthetic analysis occupies an essential position in synthetic chemistry, it has received broad attention from researchers. In this review, we comprehensively summarize the development process of retrosynthesis in the context of deep learning. This review covers all aspects of retrosynthesis, including datasets, models and tools. Specifically, we report representative models from academia, in addition to a detailed description of the available and stable platforms in the industry. We also discuss the disadvantages of the existing models and provide potential future trends, so that more abecedarians will quickly understand and participate in the family of retrosynthesis planning.

Predicting ncRNA-protein interactions based on dual graph convolutional network and pairwise learning.

Noncoding RNAs (ncRNAs) have recently attracted considerable attention due to their key roles in biology. The ncRNA-proteins interaction (NPI) is often explored to reveal some biological activities that ncRNA may affect, such as biological traits, diseases, etc. Traditional experimental methods can accomplish this work but are often labor-intensive and expensive. Machine learning and deep learning methods have achieved great success by exploiting sufficient sequence or structure information. Graph Neural Network (GNN)-based methods consider the topology in ncRNA-protein graphs and perform well on tasks like NPI prediction. Based on GNN, some pairwise constraint methods have been developed to apply on homogeneous networks, but not used for NPI prediction on heterogeneous networks. In this paper, we construct a pairwise constrained NPI predictor based on dual Graph Convolutional Network (GCN) called NPI-DGCN. To our knowledge, our method is the first to train a heterogeneous graph-based model using a pairwise learning strategy. Instead of binary classification, we use a rank layer to calculate the score of an ncRNA-protein pair. Moreover, our model is the first to predict NPIs on the ncRNA-protein bipartite graph rather than the homogeneous graph. We transform the original ncRNA-protein bipartite graph into two homogenous graphs on which to explore second-order implicit relationships. At the same time, we model direct interactions between two homogenous graphs to explore explicit relationships. Experimental results on the four standard datasets indicate that our method achieves competitive performance with other state-of-the-art methods. And the model is available at https://github.com/zhuoninnin1992/NPIPredict.

Deep learning joint models for extracting entities and relations in biomedical: a survey and comparison.

The rapid development of biomedicine has produced a large number of biomedical written materials. These unstructured text data create serious challenges for biomedical researchers to find information. Biomedical named entity recognition (BioNER) and biomedical relation extraction (BioRE) are the two most fundamental tasks of biomedical text mining. Accurately and efficiently identifying entities and extracting relations have become very important. Methods that perform two tasks separately are called pipeline models, and they have shortcomings such as insufficient interaction, low extraction quality and easy redundancy. To overcome the above shortcomings, many deep learning-based joint name entity recognition and relation extraction models have been proposed, and they have achieved advanced performance. This paper comprehensively summarize deep learning models for joint name entity recognition and relation extraction for biomedicine. The joint BioNER and BioRE models are discussed in the light of the challenges existing in the BioNER and BioRE tasks. Five joint BioNER and BioRE models and one pipeline model are selected for comparative experiments on four biomedical public datasets, and the experimental results are analyzed. Finally, we discuss the opportunities for future development of deep learning-based joint BioNER and BioRE models.

Deep learning methods for biomedical named entity recognition: a survey and qualitative comparison.

The biomedical literature is growing rapidly, and the extraction of meaningful information from the large amount of literature is increasingly important. Biomedical named entity (BioNE) identification is one of the critical and fundamental tasks in biomedical text mining. Accurate identification of entities in the literature facilitates the performance of other tasks. Given that an end-to-end neural network can automatically extract features, several deep learning-based methods have been proposed for BioNE recognition (BioNER), yielding state-of-the-art performance. In this review, we comprehensively summarize deep learning-based methods for BioNER and datasets used in training and testing. The deep learning methods are classified into four categories: single neural network-based, multitask learning-based, transfer learning-based and hybrid model-based methods. They can be applied to BioNER in multiple domains, and the results are determined by the dataset size and type. Lastly, we discuss the future development and opportunities of BioNER methods.

Molecular design in drug discovery: a comprehensive review of deep generative models.

Deep generative models have been an upsurge in the deep learning community since they were proposed. These models are designed for generating new synthetic data including images, videos and texts by fitting the data approximate distributions. In the last few years, deep generative models have shown superior performance in drug discovery especially de novo molecular design. In this study, deep generative models are reviewed to witness the recent advances of de novo molecular design for drug discovery. In addition, we divide those models into two categories based on molecular representations in silico. Then these two classical types of models are reported in detail and discussed about both pros and cons. We also indicate the current challenges in deep generative models for de novo molecular design. De novo molecular design automatically is promising but a long road to be explored.

A model for predicting ncRNA-protein interactions based on graph neural networks and community detection.

Non-coding RNA (ncRNA) s play an considerable role in the current biological sciences, such as gene transcription, gene expression, etc. Exploring the ncRNA-protein interactions(NPI) is of great significance, while some experimental techniques are very expensive in terms of time consumption and labor cost. This has promoted the birth of some computational algorithms related to traditional statistics and artificial intelligence. However, these algorithms usually require the sequence or structural feature vector of the molecule. Although graph neural network (GNN) s has been widely used in recent academic and industrial researches, its potential remains unexplored in the field of detecting NPI. Hence, we present a novel GNN-based model to detect NPI in this paper, where the detecting problem of NPI is transformed into the graph link prediction problem. Specifically, the proposed method utilizes two groups of labels to distinguish two different types of nodes: ncRNA and protein, which alleviates the problem of over-coupling in graph network. Subsequently, ncRNA and protein embedding is initially optimized based on the cluster ownership relationship of nodes in the graph. Moreover, the model applies a self-attention mechanism to preserve the graph topology to reduce information loss during pooling. The experimental results indicate that the proposed model indeed has superior performance.

Minirmd: accurate and fast duplicate removal tool for short reads via multiple minimizers.

SUMMARY: Removing duplicate and near-duplicate reads, generated by high-throughput sequencing technologies, is able to reduce computational resources in downstream applications. Here we develop minirmd, a de novo tool to remove duplicate reads via multiple rounds of clustering using different length of minimizer. Experiments demonstrate that minirmd removes more near-duplicate reads than existing clustering approaches and is faster than existing multi-core tools. To the best of our knowledge, minirmd is the first tool to remove near-duplicates on reverse-complementary strand. AVAILABILITY AND IMPLEMENTATION: https://github.com/yuansliu/minirmd. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Hamming-shifting graph of genomic short reads: Efficient construction and its application for compression.

Graphs such as de Bruijn graphs and OLC (overlap-layout-consensus) graphs have been widely adopted for the de novo assembly of genomic short reads. This work studies another important problem in the field: how graphs can be used for high-performance compression of the large-scale sequencing data. We present a novel graph definition named Hamming-Shifting graph to address this problem. The definition originates from the technological characteristics of next-generation sequencing machines, aiming to link all pairs of distinct reads that have a small Hamming distance or a small shifting offset or both. We compute multiple lexicographically minimal k-mers to index the reads for an efficient search of the weight-lightest edges, and we prove a very high probability of successfully detecting these edges. The resulted graph creates a full mutual reference of the reads to cascade a code-minimized transfer of every child-read for an optimal compression. We conducted compression experiments on the minimum spanning forest of this extremely sparse graph, and achieved a 10 - 30% more file size reduction compared to the best compression results using existing algorithms. As future work, the separation and connectivity degrees of these giant graphs can be used as economical measurements or protocols for quick quality assessment of wet-lab machines, for sufficiency control of genomic library preparation, and for accurate de novo genome assembly.

Instance-based error correction for short reads of disease-associated genes.

BACKGROUND: Genomic reads from sequencing platforms contain random errors. Global correction algorithms have been developed, aiming to rectify all possible errors in the reads using generic genome-wide patterns. However, the non-uniform sequencing depths hinder the global approach to conduct effective error removal. As some genes may get under-corrected or over-corrected by the global approach, we conduct instance-based error correction for short reads of disease-associated genes or pathways. The paramount requirement is to ensure the relevant reads, instead of the whole genome, are error-free to provide significant benefits for single-nucleotide polymorphism (SNP) or variant calling studies on the specific genes. RESULTS: To rectify possible errors in the short reads of disease-associated genes, our novel idea is to exploit local sequence features and statistics directly related to these genes. Extensive experiments are conducted in comparison with state-of-the-art methods on both simulated and real datasets of lung cancer associated genes (including single-end and paired-end reads). The results demonstrated the superiority of our method with the best performance on precision, recall and gain rate, as well as on sequence assembly results (e.g., N50, the length of contig and contig quality). CONCLUSION: Instance-based strategy makes it possible to explore fine-grained patterns focusing on specific genes, providing high precision error correction and convincing gene sequence assembly. SNP case studies show that errors occurring at some traditional SNP areas can be accurately corrected, providing high precision and sensitivity for investigations on disease-causing point mutations.

Allowing mutations in maximal matches boosts genome compression performance.

MOTIVATION: A maximal match between two genomes is a contiguous non-extendable sub-sequence common in the two genomes. DNA bases mutate very often from the genome of one individual to another. When a mutation occurs in a maximal match, it breaks the maximal match into shorter match segments. The coding cost using these broken segments for reference-based genome compression is much higher than that of using the maximal match which is allowed to contain mutations. RESULTS: We present memRGC, a novel reference-based genome compression algorithm that leverages mutation-containing matches (MCMs) for genome encoding. MemRGC detects maximal matches between two genomes using a coprime double-window k-mer sampling search scheme, the method then extends these matches to cover mismatches (mutations) and their neighbouring maximal matches to form long and MCMs. Experiments reveal that memRGC boosts the compression performance by an average of 27% in reference-based genome compression. MemRGC is also better than the best state-of-the-art methods on all of the benchmark datasets, sometimes better by 50%. Moreover, memRGC uses much less memory and de-compression resources, while providing comparable compression speed. These advantages are of significant benefits to genome data storage and transmission. AVAILABILITY AND IMPLEMENTATION: https://github.com/yuansliu/memRGC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A deep learning ensemble approach to prioritize antiviral drugs against novel coronavirus SARS-CoV-2 for COVID-19 drug repurposing.

The alarming pandemic situation of Coronavirus infectious disease COVID-19, caused by the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), has become a critical threat to public health. The unexpected outbreak and unrealistic progression of COVID-19 have generated an utmost need to realize promising therapeutic strategies to fight the pandemic. Drug repurposing-an efficient drug discovery technique from approved drugs is an emerging tactic to face the immediate global challenge. It​ offers a time-efficient and cost-effective way to find potential therapeutic agents for the disease. Artificial Intelligence-empowered deep learning models enable the rapid identification of potentially repurposable drug candidates against diseases. This study presents a deep learning ensemble model to prioritize clinically validated anti-viral drugs for their potential efficacy against SARS-CoV-2. The method integrates the similarities of drug chemical structures and virus genome sequences to generate feature vectors. The best combination of features is retrieved by the convolutional neural network in a deep learning manner. The extracted deep features are classified by the extreme gradient boosting classifier to infer potential virus-drug associations. The method could achieve an AUC of 0.8897 with 0.8571 prediction accuracy and 0.8394 sensitivity under the fivefold cross-validation. The experimental results and case studies demonstrate the suggested deep learning ensemble system yields competitive results compared with the state-of-the-art approaches. The top-ranked drugs are released for further wet-lab researches.

Geochemical Characteristics of Heavy Metals in Soil and Blueberries of the Core Majiang Blueberry Production Area.

By using field survey, sampling, and indoor analysis, we analyzed the geochemical characteristics of heavy metals in the blueberries and soil of the core blueberry production area of Majiang in Guizhou, China. Analyses were based on national standards for soil pollution risk control on agricultural land (GB15618-2018) and pollution index limits in food (GB2762-2017/2012). The results demonstrated that heavy metal content in the soil profile of this area exceeds standards, but standards were exceeded mainly in the lower layer of the profile, and blueberry growth was not substantially affected. Except for in Lanmenggu, heavy metals in the cultivation soil layer of Majiang Blueberry Farms did not considerably exceed standards. The content of heavy metals in blueberry did not exceed the standard, so it was a safe fruit. These results can provide a reference for the safe cultivation of Majiang blueberries.

Fast detection of maximal exact matches via fixed sampling of query K-mers and Bloom filtering of index K-mers.

MOTIVATION: Detection of maximal exact matches (MEMs) between two long sequences is a fundamental problem in pairwise reference-query genome comparisons. To efficiently compare larger and larger genomes, reducing the number of indexed k-mers as well as the number of query k-mers has been adopted as a mainstream approach which saves the computational resources by avoiding a significant number of unnecessary matches. RESULTS: Under this framework, we proposed a new method to detect all MEMs from a pair of genomes. The method first performs a fixed sampling of k-mers on the query sequence, and adds these selected k-mers to a Bloom filter. Then all the k-mers of the reference sequence are tested by the Bloom filter. If a k-mer passes the test, it is inserted into a hash table for indexing. Compared with the existing methods, much less number of query k-mers are generated and much less k-mers are inserted into the index to avoid unnecessary matches, leading to an efficient matching process and memory usage savings. Experiments on large genomes demonstrate that our method is at least 1.8 times faster than the best of the existing algorithms. This performance is mainly attributed to the key novelty of our method that the fixed k-mer sampling must be conducted on the query sequence and the index k-mers are filtered from the reference sequence via a Bloom filter. AVAILABILITY AND IMPLEMENTATION: https://github.com/yuansliu/bfMEM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.