Search

The smoothing issue leads to indistinguishable node representations, which poses a significant challenge in the field of graph learning. However, this issue also presents an opportunity to reveal underlying properties behind different types of nodes, which have been overlooked in previous studies. Through empirical and theoretical analysis of real-world node anomaly detection (NAD) datasets, we observe that anomalous and normal nodes show different patterns in the smoothing process, which can be leveraged to enhance NAD tasks. Motivated by these findings, in this paper, we propose a novel unsupervised NAD framework. Specifically, according to our theoretical analysis, we design a Smoothing Learning Component. Subsequently, we introduce a Smoothing-aware Spectral Graph Neural Network, which establishes the connection between the spectral space of graphs and the smoothing process. Additionally, we demonstrate that the Dirichlet Energy, which reflects the smoothness of a graph, can serve as coefficients for node representations across different dimensions of the spectral space. Building upon these observations and analyses, we devise a novel anomaly measure for the NAD task. Extensive experiments on 9 real-world datasets show that SmoothGNN outperforms the best rival by an average of 14.66% in AUC and 7.28% in Precision, with 75x running time speed-up, which validates the effectiveness and efficiency of our framework.

Prokaryotic viruses, which infect bacteria and archaea, are key players in microbial communities. Predicting the hosts of prokaryotic viruses helps decipher the dynamic relationship between microbes. Experimental methods for host prediction cannot keep pace with the fast accumulation of sequenced phages. Thus, there is a need for computational host prediction. Despite some promising results, computational host prediction remains a challenge because of the limited known interactions and the sheer amount of sequenced phages by high-throughput sequencing technologies. The state-of-the-art methods can only achieve 43\% accuracy at the species level. In this work, we formulate host prediction as link prediction in a knowledge graph that integrates multiple protein and DNA-based sequence features. Our implementation named CHERRY can be applied to predict hosts for newly discovered viruses and to identify viruses infecting targeted bacteria. We demonstrated the utility of CHERRY for both applications and compared its performance with 11 popular host prediction methods. To our best knowledge, CHERRY has the highest accuracy in identifying virus-prokaryote interactions. It outperforms all the existing methods at the species level with an accuracy increase of 37\%. In addition, CHERRY's performance on short contigs is more stable than other tools., Comment: 20 pages, 14 figures

Background: Prokaryotic viruses, which infect bacteria and archaea, are the most abundant and diverse biological entities in the biosphere. To understand their regulatory roles in various ecosystems and to harness the potential of bacteriophages for use in therapy, more knowledge of viral-host relationships is required. High-throughput sequencing and its application to the microbiome have offered new opportunities for computational approaches for predicting which hosts particular viruses can infect. However, there are two main challenges for computational host prediction. First, the empirically known virus-host relationships are very limited. Second, although sequence similarity between viruses and their prokaryote hosts have been used as a major feature for host prediction, the alignment is either missing or ambiguous in many cases. Thus, there is still a need to improve the accuracy of host prediction. Results: In this work, we present a semi-supervised learning model, named HostG, to conduct host prediction for novel viruses. We construct a knowledge graph by utilizing both virus-virus protein similarity and virus-host DNA sequence similarity. Then graph convolutional network (GCN) is adopted to exploit viruses with or without known hosts in training to enhance the learning ability. During the GCN training, we minimize the expected calibrated error (ECE) to ensure the confidence of the predictions. We tested HostG on both simulated and real sequencing data and compared its performance with other state-of-the-art methods specifcally designed for virus host classification (VHM-net, WIsH, PHP, HoPhage, RaFAH, vHULK, and VPF-Class). Conclusion: HostG outperforms other popular methods, demonstrating the efficacy of using a GCN-based semi-supervised learning approach. A particular advantage of HostG is its ability to predict hosts from new taxa., Comment: 16 pages, 14 figures

Motivation: Bacteriophages (aka phages), which mainly infect bacteria, play key roles in the biology of microbes. As the most abundant biological entities on the planet, the number of discovered phages is only the tip of the iceberg. Recently, many new phages have been revealed using high throughput sequencing, particularly metagenomic sequencing. Compared to the fast accumulation of phage-like sequences, there is a serious lag in taxonomic classification of phages. High diversity, abundance, and limited known phages pose great challenges for taxonomic analysis. In particular, alignment-based tools have difficulty in classifying fast accumulating contigs assembled from metagenomic data. Results: In this work, we present a novel semi-supervised learning model, named PhaGCN, to conduct taxonomic classification for phage contigs. In this learning model, we construct a knowledge graph by combining the DNA sequence features learned by convolutional neural network (CNN) and protein sequence similarity gained from gene-sharing network. Then we apply graph convolutional network (GCN) to utilize both the labeled and unlabeled samples in training to enhance the learning ability. We tested PhaGCN on both simulated and real sequencing data. The results clearly show that our method competes favorably against available phage classification tools., Comment: 15 pages, 10 figures

Motivation: With the development of third-generation sequencing technologies, people are able to obtain DNA sequences with lengths from 10s to 100s of kb. These long reads allow protein domain annotation without assembly, thus can produce important insights into the biological functions of the underlying data. However, the high error rate in third-generation sequencing data raises a new challenge to established domain analysis pipelines. The state-of-the-art methods are not optimized for noisy reads and have shown unsatisfactory accuracy of domain classification in third-generation sequencing data. New computational methods are still needed to improve the performance of domain prediction in long noisy reads. Results: In this work, we introduce ProDOMA, a deep learning model that conducts domain classification for third-generation sequencing reads. It uses deep neural networks with 3-frame translation encoding to learn conserved features from partially correct translations. In addition, we formulate our problem as an open-set problem and thus our model can reject unrelated DNA reads such as those from noncoding regions. In the experiments on simulated reads of protein coding sequences and real reads from the human genome, our model outperforms HMMER and DeepFam on protein domain classification. In summary, ProDOMA is a useful end-to-end protein domain analysis tool for long noisy reads without relying on error correction. Availability: The source code and the trained model are freely available at https://github.com/strideradu/ProDOMA. Contact: yannisun@cityu.edu.hk, Comment: 13 pages, 8 figures (three of them are gourped in Figre. 6)

Shotgun metagenomics has greatly advanced our understanding of microbial communities over the last decade. Metagenomic analyses often include assembly and genome binning, computationally daunting tasks especially for big data from complex environments such as soil and sediments. In many studies, however, only a subset of genes and pathways involved in specific functions are of interest; thus, it is not necessary to attempt global assembly. In addition, methods that target genes can be computationally more efficient and produce more accurate assembly by leveraging rich databases, especially for those genes that are of broad interest such as those involved in biogeochemical cycles, biodegradation, and antibiotic resistance or used as phylogenetic markers. Here, we review six gene-targeted assemblers with unique algorithms for extracting and/or assembling targeted genes: Xander, MegaGTA, SAT-Assembler, HMM-GRASPx, GenSeed-HMM, and MEGAN. We tested these tools using two datasets with known genomes, a synthetic community of artificial reads derived from the genomes of 17 bacteria, shotgun sequence data from a mock community with 48 bacteria and 16 archaea genomes, and a large soil shotgun metagenomic dataset. We compared assemblies of a universal single copy gene (rplB) and two N cycle genes (nifH and nirK). We measured their computational efficiency, sensitivity, specificity, and chimera rate and found Xander and MegaGTA, which both use a probabilistic graph structure to model the genes, have the best overall performance with all three datasets, although MEGAN, a reference matching assembler, had better sensitivity with synthetic and mock community members chosen from its reference collection. Also, Xander and MegaGTA are the only tools that include post-assembly scripts tuned for common molecular ecology and diversity analyses. Additionally, we provide a mathematical model for estimating the probability of assembling targeted genes in a metagenome for estimating requir

Little is known about the impact of drug resistance on recurrence in TB. We conducted a cohort study to measure the impact of multi-drug resistance (MDR) on TB recurrence over nine years in Henan Province China. We reviewed medical records and conducted field interviews of 100 MDR and 150 non-MDR TB patients who were treated between 2001 and 2002. We compared long-term recurrence rates, risk factors, and outcomes in 2010 for 234 individuals who could be followed up. About one third (29.5%, 69/234) suffered recurrence after completion of treatment. The overall recurrence rate was 35/1,000 patient-years (PY), with a much higher rate (65/1,000 PY) among MDR-TB patients. MDR (HR: 2.75; CI: 1.58-4.79) and patient annual household income less than 10,000 Yuan (HR: 2.05; CI 1.11-3.80) were associated with recurrence. The mean time for recurrence among MDR-TB patients was 5.7 years, compared to 7.2 years among non-MDR-TB patients. Among the recurrence group members, 61.3% died, and 18.8% had failed treatments. We believe that the high TB recurrence rate after 9 years suggests that a high cure rate cannot accurately predict long-term outcome. We recommend that TB surveillance and control should be strengthened with a focus on MDR-TB and directly observed treatment, to reduce TB recurrence and transmission of MDR-TB.

BACKGROUND: We conducted a cohort study to compare the characteristics of MDR-TB with non-MDR-TB patients and to measure long term (9-year) mortality rate and determine factors associated with death in China. METHODS: We reviewed the medical records of 250 TB cases from a 2001 survey to compare 100 MDR-TB patients with 150 non-MDR-TB patients who were treated in 2001-2002. Baseline attributes extracted from the records were compared between the two cohorts and long-term mortality and risk factors were determined at nine-year follow-up in 2010. RESULTS: Among the 234 patients successfully followed up, 63 (26.9%) were female and 171 (73.1 %) were male. MDR-TB patients had poorer socioeconomic status compared to non-MDRTB. Nine years after the diagnosis of TB, 69 or 29.5 % of the 234 patients had died (32 or 21.6 % of non-MDR-TB versus 37 or 43.0 % of MDR-TB) and the overall mortality rate was 39/1000 per year (PY) (27/1000 PY among non-MDR versus 63/1000 PY among MDR-TB). Factors associated with death included: MDR status (hazard ratio (HR): 1.86; CI: 1.09-3.13), limited education of primary school or lower (HR: 2.51; CI 1.34-4.70) and received TB treatment during the nine-year period (HR 1.82; 95 % CI 1.02-3.26). CONCLUSIONS: MDR-TB was a strong predictor for poor long-term outcome. High quality diagnosis and treatment must be ensured. Greater reimbursement or free treatment may be needed to provide access for the poor and vulnerable populations, and to increase treatment compliance.

BackgroundMetagenomics can provide important insight into microbial communities. However, assembling metagenomic datasets has proven to be computationally challenging. Current methods often assemble only fragmented partial genes.ResultsWe present a novel method for targeting assembly of specific protein-coding genes. This method combines a de Bruijn graph, as used in standard assembly approaches, and a protein profile hidden Markov model (HMM) for the gene of interest, as used in standard annotation approaches. These are used to create a novel combined weighted assembly graph. Xander performs both assembly and annotation concomitantly using information incorporated in this graph. We demonstrate the utility of this approach by assembling contigs for one phylogenetic marker gene and for two functional marker genes, first on Human Microbiome Project (HMP)-defined community Illumina data and then on 21 rhizosphere soil metagenomic datasets from three different crops totaling over 800 Gbp of unassembled data. We compared our method to a recently published bulk metagenome assembly method and a recently published gene-targeted assembler and found our method produced more, longer, and higher quality gene sequences.ConclusionXander combines gene assignment with the rapid assembly of full-length or near full-length functional genes from metagenomic data without requiring bulk assembly or post-processing to find genes of interest. HMMs used for assembly can be tailored to the targeted genes, allowing flexibility to improve annotation over generic annotation pipelines. This method is implemented as open source software and is available at https://github.com/rdpstaff/Xander_assembler.

Ribosomal Database Project (RDP; http://rdp.cme.msu.edu/) provides the research community with aligned and annotated rRNA gene sequence data, along with tools to allow researchers to analyze their own rRNA gene sequences in the RDP framework. RDP data and tools are utilized in fields as diverse as human health, microbial ecology, environmental microbiology, nucleic acid chemistry, taxonomy and phylogenetics. In addition to aligned and annotated collections of bacterial and archaeal small subunit rRNA genes, RDP now includes a collection of fungal large subunit rRNA genes. RDP tools, including Classifier and Aligner, have been updated to work with this new fungal collection. The use of high-throughput sequencing to characterize environmental microbial populations has exploded in the past several years, and as sequence technologies have improved, the sizes of environmental datasets have increased. With release 11, RDP is providing an expanded set of tools to facilitate analysis of high-throughput data, including both single-stranded and paired-end reads. In addition, most tools are now available as open source packages for download and local use by researchers with high-volume needs or who would like to develop custom analysis pipelines.