Zero-shot-capable identification of phage-host relationships with whole-genome sequence representation by contrastive learning.

Accurately identifying phage-host relationships from their genome sequences is still challenging, especially for those phages and hosts with less homologous sequences. In this work, focusing on identifying the phage-host relationships at the species and genus level, we propose a contrastive learning based approach to learn whole-genome sequence embeddings that can take account of phage-host interactions (PHIs). Contrastive learning is used to make phages infecting the same hosts close to each other in the new representation space. Specifically, we rephrase whole-genome sequences with frequency chaos game representation (FCGR) and learn latent embeddings that 'encapsulate' phages and host relationships through contrastive learning. The contrastive learning method works well on the imbalanced dataset. Based on the learned embeddings, a proposed pipeline named CL4PHI can predict known hosts and unseen hosts in training. We compare our method with two recently proposed state-of-the-art learning-based methods on their benchmark datasets. The experiment results demonstrate that the proposed method using contrastive learning improves the prediction accuracy on known hosts and demonstrates a zero-shot prediction capability on unseen hosts. In terms of potential applications, the rapid pace of genome sequencing across different species has resulted in a vast amount of whole-genome sequencing data that require efficient computational methods for identifying phage-host interactions. The proposed approach is expected to address this need by efficiently processing whole-genome sequences of phages and prokaryotic hosts and capturing features related to phage-host relationships for genome sequence representation. This approach can be used to accelerate the discovery of phage-host interactions and aid in the development of phage-based therapies for infectious diseases.

biotextgraph: graphical summarization of functional similarities from textual information.

SUMMARY: Functional interpretation of biological entities such as differentially expressed genes is one of the fundamental analyses in bioinformatics. The task can be addressed by using biological pathway databases with enrichment analysis (EA). However, textual description of biological entities in public databases is less explored and integrated in existing tools and it has a potential to reveal new mechanisms. Here, we present a new R package biotextgraph for graphical summarization of omics' textual description data which enables assessment of functional similarities of the lists of biological entities. We illustrate application examples of annotating gene identifiers in addition to EA. The results suggest that the visualization based on words and inspection of biological entities with text can reveal a set of biologically meaningful terms that could not be obtained by using biological pathway databases alone. The results suggest the usefulness of the package in the routine analysis of omics-related data. The package also offers a web-based application for convenient querying. AVAILABILITY AND IMPLEMENTATION: The package, documentation, and web server are available at: https://github.com/noriakis/biotextgraph.

Investigation of the BERT model on nucleotide sequences with non-standard pre-training and evaluation of different k-mer embeddings.

MOTIVATION: In recent years, pre-training with the transformer architecture has gained significant attention. While this approach has led to notable performance improvements across a variety of downstream tasks, the underlying mechanisms by which pre-training models influence these tasks, particularly in the context of biological data, are not yet fully elucidated. RESULTS: In this study, focusing on the pre-training on nucleotide sequences, we decompose a pre-training model of Bidirectional Encoder Representations from Transformers (BERT) into its embedding and encoding modules to analyze what a pre-trained model learns from nucleotide sequences. Through a comparative study of non-standard pre-training at both the data and model levels, we find that a typical BERT model learns to capture overlapping-consistent k-mer embeddings for its token representation within its embedding module. Interestingly, using the k-mer embeddings pre-trained on random data can yield similar performance in downstream tasks, when compared with those using the k-mer embeddings pre-trained on real biological sequences. We further compare the learned k-mer embeddings with other established k-mer representations in downstream tasks of sequence-based functional prediction. Our experimental results demonstrate that the dense representation of k-mers learned from pre-training can be used as a viable alternative to one-hot encoding for representing nucleotide sequences. Furthermore, integrating the pre-trained k-mer embeddings with simpler models can achieve competitive performance in two typical downstream tasks. AVAILABILITY AND IMPLEMENTATION: The source code and associated data can be accessed at https://github.com/yaozhong/bert_investigation.

Genome analysis through image processing with deep learning models.

Genomic sequences are traditionally represented as strings of characters: A (adenine), C (cytosine), G (guanine), and T (thymine). However, an alternative approach involves depicting sequence-related information through image representations, such as Chaos Game Representation (CGR) and read pileup images. With rapid advancements in deep learning (DL) methods within computer vision and natural language processing, there is growing interest in applying image-based DL methods to genomic sequence analysis. These methods involve encoding genomic information as images or integrating spatial information from images into the analytical process. In this review, we summarize three typical applications that use image processing with DL models for genome analysis. We examine the utilization and advantages of these image-based approaches.

Identification of bacteriophage genome sequences with representation learning.

MOTIVATION: Bacteriophages/phages are the viruses that infect and replicate within bacteria and archaea, and rich in human body. To investigate the relationship between phages and microbial communities, the identification of phages from metagenome sequences is the first step. Currently, there are two main methods for identifying phages: database-based (alignment-based) methods and alignment-free methods. Database-based methods typically use a large number of sequences as references; alignment-free methods usually learn the features of the sequences with machine learning and deep learning models. RESULTS: We propose INHERIT which uses a deep representation learning model to integrate both database-based and alignment-free methods, combining the strengths of both. Pre-training is used as an alternative way of acquiring knowledge representations from existing databases, while the BERT-style deep learning framework retains the advantage of alignment-free methods. We compare INHERIT with four existing methods on a third-party benchmark dataset. Our experiments show that INHERIT achieves a better performance with the F1-score of 0.9932. In addition, we find that pre-training two species separately helps the non-alignment deep learning model make more accurate predictions. AVAILABILITY AND IMPLEMENTATION: The codes of INHERIT are now available in: https://github.com/Celestial-Bai/INHERIT. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A novel approach to quantify calcifications of thyroid nodules in US images based on deep learning: predicting the risk of cervical lymph node metastasis in papillary thyroid cancer patients.

OBJECTIVE: Based on ultrasound (US) images, this study aimed to detect and quantify calcifications of thyroid nodules, which are regarded as one of the most important features in US diagnosis of thyroid cancer, and to further investigate the value of US calcifications in predicting the risk of lymph node metastasis (LNM) in papillary thyroid cancer (PTC). METHODS: Based on the DeepLabv3+ networks, 2992 thyroid nodules in US images were used to train a model to detect thyroid nodules, of which 998 were used to train a model to detect and quantify calcifications. A total of 225 and 146 thyroid nodules obtained from two centers, respectively, were used to test the performance of these models. A logistic regression method was used to construct the predictive models for LNM in PTCs. RESULTS: Calcifications detected by the network model and experienced radiologists had an agreement degree of above 90%. The novel quantitative parameters of US calcification defined in this study showed a significant difference between PTC patients with and without cervical LNM (p < 0.05). The calcification parameters were beneficial to predicting the LNM risk in PTC patients. The LNM prediction model using these calcification parameters combined with patient age and other US nodular features showed a higher specificity and accuracy than the calcification parameters alone. CONCLUSIONS: Our models not only detect the calcifications automatically, but also have value in predicting cervical LNM risk of PTC patients, thereby making it possible to investigate the relationship between calcifications and highly invasive PTC in detail. CLINICAL RELEVANCE STATEMENT: Due to the high association of US microcalcifications with thyroid cancers, our model will contribute to the differential diagnosis of thyroid nodules in daily practice. KEY POINTS: • We developed an ML-based network model for automatically detecting and quantifying calcifications within thyroid nodules in US images. • Three novel parameters for quantifying US calcifications were defined and verified. • These US calcification parameters showed value in predicting the risk of cervical LNM in PTC patients.

Functional Restoration of Bacteriomes and Viromes by Fecal Microbiota Transplantation.

BACKGROUND & AIMS: Fecal microbiota transplantation (FMT) is an effective therapy for recurrent Clostridioides difficile infection (rCDI). However, the overall mechanisms underlying FMT success await comprehensive elucidation, and the safety of FMT has recently become a serious concern because of the occurrence of drug-resistant bacteremia transmitted by FMT. We investigated whether functional restoration of the bacteriomes and viromes by FMT could be an indicator of successful FMT. METHODS: The human intestinal bacteriomes and viromes from 9 patients with rCDI who had undergone successful FMT and their donors were analyzed. Prophage-based and CRISPR spacer-based host bacteria-phage associations in samples from recipients before and after FMT and in donor samples were examined. The gene functions of intestinal microorganisms affected by FMT were evaluated. RESULTS: Metagenomic sequencing of both the viromes and bacteriomes revealed that FMT does change the characteristics of intestinal bacteriomes and viromes in recipients after FMT compared with those before FMT. In particular, many Proteobacteria, the fecal abundance of which was high before FMT, were eliminated, and the proportion of Microviridae increased in recipients. Most temperate phages also behaved in parallel with the host bacteria that were altered by FMT. Furthermore, the identification of bacterial and viral gene functions before and after FMT revealed that some distinctive pathways, including fluorobenzoate degradation and secondary bile acid biosynthesis, were significantly represented. CONCLUSIONS: The coordinated action of phages and their host bacteria restored the recipients' intestinal flora. These findings show that the restoration of intestinal microflora functions reflects the success of FMT.

HEAL: an automated deep learning framework for cancer histopathology image analysis.

MOTIVATION: Digital pathology supports analysis of histopathological images using deep learning methods at a large-scale. However, applications of deep learning in this area have been limited by the complexities of configuration of the computational environment and of hyperparameter optimization, which hinder deployment and reduce reproducibility. RESULTS: Here, we propose HEAL, a deep learning-based automated framework for easy, flexible and multi-faceted histopathological image analysis. We demonstrate its utility and functionality by performing two case studies on lung cancer and one on colon cancer. Leveraging the capability of Docker, HEAL represents an ideal end-to-end tool to conduct complex histopathological analysis and enables deep learning in a broad range of applications for cancer image analysis. AVAILABILITY AND IMPLEMENTATION: The docker image of HEAL is available at https://hub.docker.com/r/docurdt/heal and related documentation and datasets are available at http://heal.erc.monash.edu.au. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Enhancing breakpoint resolution with deep segmentation model: A general refinement method for read-depth based structural variant callers.

Read-depths (RDs) are frequently used in identifying structural variants (SVs) from sequencing data. For existing RD-based SV callers, it is difficult for them to determine breakpoints in single-nucleotide resolution due to the noisiness of RD data and the bin-based calculation. In this paper, we propose to use the deep segmentation model UNet to learn base-wise RD patterns surrounding breakpoints of known SVs. We integrate model predictions with an RD-based SV caller to enhance breakpoints in single-nucleotide resolution. We show that UNet can be trained with a small amount of data and can be applied both in-sample and cross-sample. An enhancement pipeline named RDBKE significantly increases the number of SVs with more precise breakpoints on simulated and real data. The source code of RDBKE is freely available at https://github.com/yaozhong/deepIntraSV.

An integrated AI model to improve diagnostic accuracy of ultrasound and output known risk features in suspicious thyroid nodules.

OBJECTIVES: From the viewpoint of ultrasound (US) physicians, an ideal thyroid US computer-assisted diagnostic (CAD) system for thyroid cancer should perform well in suspicious thyroid nodules with atypical risk features and be able to output explainable results. This study aims to develop an explainable US CAD model for suspicious thyroid nodules. METHODS: A total of 2992 solid or almost-solid thyroid nodules were analyzed retrospectively. All nodules had pathological results (1070 malignancies and 1992 benignities) confirmed by ultrasound-guided fine-needle aspiration cytology and histopathology after thyroidectomy. A deep learning model (ResNet50) and a multiple risk features learning ensemble model (XGBoost) were used to train the US images of 2794 thyroid nodules. Then, an integrated AI model was generated by combining both models. The diagnostic accuracies of the three AI models (ResNet50, XGBoost, and the integrated model) were predicted in a testing set including 198 thyroid nodules and compared to the diagnostic efficacy of five ultrasonographers. RESULTS: The accuracy of the integrated model was 76.77%, while the mean accuracy of the ultrasonographers was 68.38%. Of the risk features, microcalcifications showed the highest contribution to the diagnosis of malignant nodules. CONCLUSIONS: The integrated AI model in our study can improve the diagnostic accuracy of suspicious thyroid nodules and output the known risk features simultaneously, thus aiding in training young ultrasonographers by linking the explainable results to their clinical experience and advancing the acceptance of AI diagnosis for thyroid cancer in clinical practice. KEY POINTS: • We developed an artificial intelligence (AI) diagnosis model based on both deep learning and multiple risk feature ensemble learning methods. • The AI diagnosis model showed higher diagnostic accuracy for suspicious thyroid nodules than ultrasonographers. • The AI diagnosis model showed partial explainability by outputting the known risk features, thus aiding young ultrasonic doctors in increasing the diagnostic level for thyroid cancer.

Nanopore basecalling from a perspective of instance segmentation.

BACKGROUND: Nanopore sequencing is a rapidly developing third-generation sequencing technology, which can generate long nucleotide reads of molecules within a portable device in real-time. Through detecting the change of ion currency signals during a DNA/RNA fragment's pass through a nanopore, genotypes are determined. Currently, the accuracy of nanopore basecalling has a higher error rate than the basecalling of short-read sequencing. Through utilizing deep neural networks, the-state-of-the art nanopore basecallers achieve basecalling accuracy in a range from 85% to 95%. RESULT: In this work, we proposed a novel basecalling approach from a perspective of instance segmentation. Different from previous approaches of doing typical sequence labeling, we formulated the basecalling problem as a multi-label segmentation task. Meanwhile, we proposed a refined U-net model which we call UR-net that can model sequential dependencies for a one-dimensional segmentation task. The experiment results show that the proposed basecaller URnano achieves competitive results on the in-species data, compared to the recently proposed CTC-featured basecallers. CONCLUSION: Our results show that formulating the basecalling problem as a one-dimensional segmentation task is a promising approach, which does basecalling and segmentation jointly.

Sequence-specific bias correction for RNA-seq data using recurrent neural networks.

BACKGROUND: The recent success of deep learning techniques in machine learning and artificial intelligence has stimulated a great deal of interest among bioinformaticians, who now wish to bring the power of deep learning to bare on a host of bioinformatical problems. Deep learning is ideally suited for biological problems that require automatic or hierarchical feature representation for biological data when prior knowledge is limited. In this work, we address the sequence-specific bias correction problem for RNA-seq data redusing Recurrent Neural Networks (RNNs) to model nucleotide sequences without pre-determining sequence structures. The sequence-specific bias of a read is then calculated based on the sequence probabilities estimated by RNNs, and used in the estimation of gene abundance. RESULT: We explore the application of two popular RNN recurrent units for this task and demonstrate that RNN-based approaches provide a flexible way to model nucleotide sequences without knowledge of predetermined sequence structures. Our experiments show that training a RNN-based nucleotide sequence model is efficient and RNN-based bias correction methods compare well with the-state-of-the-art sequence-specific bias correction method on the commonly used MAQC-III data set. CONCLUSTIONS: RNNs provides an alternative and flexible way to calculate sequence-specific bias without explicitly pre-determining sequence structures.

[Exploration of the Essence of "Endogenous Turbidity" in Chinese Medicine].

The essence of endogenous turbidity in Chinese medicine (CM) is different from cream, fat, phlegm, retention, damp, toxicity, and stasis. Along with the development of modern scientific technologies and biology, researches on the essence of endogenous turbidity should keep pace with the time. Its material bases should be defined and new connotation endowed at the microscopic level. The essence of turbidity lies in abnormal functions of zang-fu organs. Sugar, fat, protein, and other nutrient substances cannot be properly decomposed, but into semi-finished products or intermediate metabolites. They are inactive and cannot participate in normal material syntheses and decomposition. They cannot be transformed to energy metabolism, but also cannot be synthesized as executive functioning of active proteins. If they cannot be degraded by autophagy-lysosome or ubiquitin-prosome into glucose, fatty acids, amino acids, and other basic nutrients to be used again, they will accumulate inside the human body and become endogenous turbidity. Therefore, endogenous turbidity is different from final metabolites such as urea, carbon dioxide, etc., which can transform vital qi. How to improve the function of zang-fu organs, enhance its degradation by autophagy-lysosome or ubiquitin-prosome is of great significance in normal operating of zang-fu organs and preventing the emergence and progress of related diseases.

Predicting cell types with supervised contrastive learning on cells and their types.

Single-cell RNA-sequencing (scRNA-seq) is a powerful technique that provides high-resolution expression profiling of individual cells. It significantly advances our understanding of cellular diversity and function. Despite its potential, the analysis of scRNA-seq data poses considerable challenges related to multicollinearity, data imbalance, and batch effect. One of the pivotal tasks in single-cell data analysis is cell type annotation, which classifies cells into discrete types based on their gene expression profiles. In this work, we propose a novel modeling formalism for cell type annotation with a supervised contrastive learning method, named SCLSC (Supervised Contrastive Learning for Single Cell). Different from the previous usage of contrastive learning in single cell data analysis, we employed the contrastive learning for instance-type pairs instead of instance-instance pairs. More specifically, in the cell type annotation task, the contrastive learning is applied to learn cell and cell type representation that render cells of the same type to be clustered in the new embedding space. Through this approach, the knowledge derived from annotated cells is transferred to the feature representation for scRNA-seq data. The whole training process becomes more efficient when conducting contrastive learning for cell and their types. Our experiment results demonstrate that the proposed SCLSC method consistently achieves superior accuracy in predicting cell types compared to five state-of-the-art methods. SCLSC also performs well in identifying cell types in different batch groups. The simplicity of our method allows for scalability, making it suitable for analyzing datasets with a large number of cells. In a real-world application of SCLSC to monitor the dynamics of immune cell subpopulations over time, SCLSC demonstrates a capability to discriminate cell subtypes of CD19+ B cells that were not present in the training dataset.

Microbial Gene Ontology informed deep neural network for microbe functionality discovery in human diseases.

The human microbiome plays a crucial role in human health and is associated with a number of human diseases. Determining microbiome functional roles in human diseases remains a biological challenge due to the high dimensionality of metagenome gene features. However, existing models were limited in providing biological interpretability, where the functional role of microbes in human diseases is unexplored. Here we propose to utilize a neural network-based model incorporating Gene Ontology (GO) relationship network to discover the microbe functionality in human diseases. We use four benchmark datasets, including diabetes, liver cirrhosis, inflammatory bowel disease, and colorectal cancer, to explore the microbe functionality in the human diseases. Our model discovered and visualized the novel candidates' important microbiome genes and their functions by calculating the important score of each gene and GO term in the network. Furthermore, we demonstrate that our model achieves a competitive performance in predicting the disease by comparison with other non-Gene Ontology informed models. The discovered candidates' important microbiome genes and their functions provide novel insights into microbe functional contribution.

Correction: Microbial Gene Ontology informed deep neural network for microbe functionality discovery in human diseases.

[This corrects the article DOI: 10.1371/journal.pone.0290307.].

A Versatile Hydrophilic and Antifouling Coating Based on Dopamine Modified Four-Arm Polyethylene Glycol by One-Step Synthesis Method.

A versatile hydrophilic and antifouling coating was designed and prepared based on catechol-modified four-arm polyethylene glycol. The dopamine (DA) molecules were grafted onto the end of the four-arm polyethylene glycol carboxyl (4A-PEG-COOH) through the amidation reaction, which was proven by 1H NMR and FTIR analysis, assisting the strong adhesion of PEG on the surface of various types of materials, including metallic, inorganic, and polymeric materials. The reduction of the water contact angle and the bacteria-repellent and protein-repellent effects indicated that the coating had good hydrophilicity and antifouling performance. Raman spectroscopy analysis demonstrated the affinity between the polymeric surface and water, which further confirmed the hydrophilicity of the coating. Finally, in vitro cytotoxicity assay demonstrated good biocompatibility of the coating layer.

Cav-1 deficiency promotes liver fibrosis in carbon tetrachloride (CCl4)-induced mice by regulation of oxidative stress and inflammation responses.

Caveolin-1 (Cav-1), as a membrane protein involved in the formation of caveolae, binds steroid receptors and endothelial nitric oxide synthase, limiting its translocation and activation. In the present study, we investigated the role of Cav-1 in the progression of hepatic fibrosis induced by carbon tetrachloride (CCl4) in murine animals. Therefore, the wild type (WT) and Cav-1-knockout (Cav-1-/-) mice were used in our study and subjected to CCl4. The results indicated that CCl4 induced the decrease of Cav-1 expression in liver tissue samples. And Cav-1-/- intensified CCl4-triggered hepatic injury, evidenced by the stronger hepatic histological alterations, serum aspartate aminotransferase (AST) and alanine aminotransferase (ALT) levels and liver terminal deoxynucleotidyl transferase dUTP nick end labeling (TUNEL)-positive cells. CCl4 led to oxidative stress, supported by the reduced superoxide dismutase (SOD) activity and glutathione (GSH) levels, as well as enhanced malondialdehyde (MDA) and O2- levels in liver samples. And the process was intensified by Cav-1-/-. Additionally, CCl4-caused hepatic inflammation was aggregated by Cav-1-/- via further increasing the secretion of pro-inflammatory cytokines. Moreover, CCl4-caused fibrosis was strengthened by Cav-1-/-, which was evidenced by the up-regulation of α-smooth muscle actin (α-SMA), collagen alpha 1 type 1 (Col1A1), lysyl oxidase (Lox) and transforming growth factor-ß1 (TGF-ß1) in liver tissues. Similar results were observed in TGF-ß1-stimulated hepatic stellate cells (HSCs) and LX-2 cells without Cav-1 expressions that in vitro, suppressing Cav-1 further accelerated TGF-ß1-induced oxidative stress, inflammation and fibrosis development. In conclusion, our results indicated that Cav-1 played an important role in CCl4-induced hepatic injury, which may be used as potential therapeutic target for hepatic fibrosis treatment.

The clinicopathologic and immunohistochemical features of villoglandular adenocarcinoma of uterine cervix.

AIM: Villoglandular adenocarcinoma (VGA) of the uterine cervix is a variant of endocervical adenocarcinoma. However, the clinicopathologic and immunohistochemical features of VGA are still unclear. The aim of this study was to investigate the clinicopathologic and immunohistochemical features of VGA. MATERIALS AND METHODS: A total of 20 VGA patients were identified among 852 patients diagnosed with cervical cancer and enrolled in this study. The immunohistochemical levels of Ki-67, P53, P16, progesterone receptor (PR), carcinoembryonic antigen (CEA), vimentin (Vim), and estrogen receptor (ER) were measured by immunohistochemistry. RESULTS: VGA was prevalent in younger women and presented favorable prognosis. Ki-67, P16, and CEA were highly expressed in VGA tissues, while PR expression was hardly to be detected. The positive rates of Ki-67, CEA, and P16 were 90.0%, 90.0%, and 85.0%, respectively, which were significantly higher compared with PR (5.0%, P < 0.001). In addition, the positive rates of P53, Vim, and ER in VGA tissues were 55.0%, 50.0%, and 40.0%, respectively. However, the expression levels of Ki-67, P53, P16, PR, CEA, Vim, and ER were not significantly associated with clinical features (P > 0.05). CONCLUSION: These data indicate that VGA is a rare cervical adenocarcinoma, which is prevalent in younger women, and presents favorable prognosis. Detection of Ki-67, P53, P16, PR, CEA, Vim, and ER would be beneficial for the diagnosis of VGA.

A novel ASXL1-OGT axis plays roles in H3K4 methylation and tumor suppression in myeloid malignancies.

ASXL1 plays key roles in epigenetic regulation of gene expression through methylation of histone H3K27, and disruption of ASXL1 drives myeloid malignancies, at least in part, via derepression of posterior HOXA loci. However, little is known about the identity of proteins that interact with ASXL1 and about the functions of ASXL1 in modulation of the active histone mark, such as H3K4 methylation. In this study, we demonstrate that ASXL1 is a part of a protein complex containing HCFC1 and OGT; OGT directly stabilizes ASXL1 by O-GlcNAcylation. Disruption of this novel axis inhibited myeloid differentiation and H3K4 methylation as well as H2B glycosylation and impaired transcription of genes involved in myeloid differentiation, splicing, and ribosomal functions; this has implications for myelodysplastic syndrome (MDS) pathogenesis, as each of these processes are perturbed in the disease. This axis is responsible for tumor suppression in the myeloid compartment, as reactivation of OGT induced myeloid differentiation and reduced leukemogenecity both in vivo and in vitro. Our data also suggest that MLL5, a known HCFC1/OGT-interacting protein, is responsible for gene activation by the ASXL1-OGT axis. These data shed light on the novel roles of the ASXL1-OGT axis in H3K4 methylation and activation of transcription.