Analyses of combined Merkel cell carcinomas with neuroblastic components suggests that loss of T antigen expression in Merkel cell carcinoma may result in cell cycle arrest and neuroblastic transdifferentiation

Merkel cell carcinoma (MCC) is an aggressive skin cancer frequently caused by genomic integration of the Merkel cell polyomavirus (MCPyV). MCPyV-negative cases often present as combined MCCs, which represent a distinctive subset of tumors characterized by association of an MCC with a second tumor component, mostly squamous cell carcinoma. Up to now, only exceptional cases of combined MCC with neuroblastic differentiation have been reported. Herein we describe two additional combined MCCs with neuroblastic differentiation and provide comprehensive morphologic, immunohistochemical, transcriptomic, genetic and epigenetic characterization of these tumors, which both arose in elderly men and appeared as an isolated inguinal adenopathy. Microscopic examination revealed biphasic tumors combining a poorly differentiated high-grade carcinoma with a poorly differentiated neuroblastic component lacking signs of proliferation. Immunohistochemical investigation revealed keratin 20 and MCPyV T antigen (TA) in the MCC parts, while neuroblastic differentiation was confirmed in the other component in both cases. A clonal relation of the two components can be deduced from 20 and 14 shared acquired point mutations detected by whole exome analysis in both combined tumors, respectively. Spatial transcriptomics demonstrated a lower expression of stem cell marker genes such as SOX2 and MCM2 in the neuroblastic component. Interestingly, although the neuroblastic part lacked TA expression, the same genomic MCPyV integration and the same large T-truncating mutations were observed in both tumor parts. Given that neuronal transdifferentiation upon TA repression has been reported for MCC cell lines, the most likely scenario for the two combined MCC/neuroblastic tumors is that neuroblastic transdifferentiation resulted from loss of TA expression in a subset of MCC cells. Indeed, DNA methylation profiling suggests an MCC-typical cellular origin for the combined MCC/neuroblastomas. © 2024 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Blood virome research in myalgic encephalomyelitis/chronic fatigue syndrome: challenges and opportunities

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a debilitating disease with a complex clinical presentation and an unknown etiology. Various viral infections have been proposed as potential triggers of ME/CFS onset, but no specific pathogen has been identified in all cases of postinfectious ME/CFS. The symptomatology of the postacute sequelae of SARS-CoV-2, or long COVID, mirrors that of ME/CFS, with nearly half of long COVID patients meeting ME/CFS diagnostic criteria. The influx of newly diagnosed patients has reinvigorated interest in ME/CFS pathogenesis research, with an emphasis on viral triggers. This review summarizes the current understanding of ME/CFS research on viral triggers, including blood virome screening studies. To further elucidate the molecular basis of ME/CFS, there is a need to develop innovative bioinformatics tools capable of analyzing complex virome data and integrating multiomics information.

ViroISDC: a method for calling integration sites of hepatitis B virus based on feature encoding

BACKGROUND

Hepatitis B virus (HBV) integrates into human chromosomes and can lead to genomic instability and hepatocarcinogenesis. Current tools for HBV integration site detection lack accuracy and stability.

RESULTS

This study proposes a deep learning-based method, named ViroISDC, for detecting integration sites. ViroISDC generates corresponding grammar rules and encodes the characteristics of the language data to predict integration sites accurately. Compared with Lumpy, Pindel, Seeksv, and SurVirus, ViroISDC exhibits better overall performance and is less sensitive to sequencing depth and integration sequence length, displaying good reliability, stability, and generality. Further downstream analysis of integrated sites detected by ViroISDC reveals the integration patterns and features of HBV. It is observed that HBV integration exhibits specific chromosomal preferences and tends to integrate into cancerous tissue. Moreover, HBV integration frequency was higher in males than females, and high-frequency integration sites were more likely to be present on hepatocarcinogenesis- and anti-cancer-related genes, validating the reliability of the ViroISDC.

CONCLUSIONS

ViroISDC pipeline exhibits superior precision, stability, and reliability across various datasets when compared to similar software. It is invaluable in exploring HBV infection in the human body, holding significant implications for the diagnosis, treatment, and prognosis assessment of HCC.

Detection of wildtype Merkel cell polyomavirus genomic sequence and VP1 transcription in a subset of Merkel cell carcinoma

AIMS

Merkel cell carcinoma (MCC) is frequently caused by the Merkel cell polyomavirus (MCPyV). Characteristic for these virus-positive (VP) MCC is MCPyV integration into the host genome and truncation of the viral oncogene Large T antigen (LT), with full-length LT expression considered as incompatible with MCC growth. Genetic analysis of a VP-MCC/trichoblastoma combined tumour demonstrated that virus-driven MCC can arise from an epithelial cell. Here we describe two further cases of VP-MCC combined with an adnexal tumour, i.e. one trichoblastoma and one poroma.

METHODS AND RESULTS

Whole-genome sequencing of MCC/trichoblastoma again provided evidence of a trichoblastoma-derived MCC. Although an MCC-typical LT-truncating mutation was detected, we could not determine an integration site and we additionally detected a wildtype sequence encoding full-length LT. Similarly, Sanger sequencing of the combined MCC/poroma revealed coding sequences for both truncated and full-length LT. Moreover, in situ RNA hybridization demonstrated expression of a late region mRNA encoding the viral capsid protein VP1 in both combined as well as in a few cases of pure MCC.

CONCLUSION

The data presented here suggest the presence of wildtype MCPyV genomes and VP1 transcription in a subset of MCC.

Third-generation genome sequencing implicates medium-sized structural variants in chronic schizophrenia

Background

Schizophrenia (SCZ) is a heterogeneous psychiatric disorder, with significant contribution from genetic factors particularly for chronic cases with negative symptoms and cognitive deficits. To date, Genome Wide Association Studies (GWAS) and exome sequencing have associated SCZ with a number of single nucleotide polymorphisms (SNPs) and copy number variants (CNVs), but there is still missing heritability. Medium-sized structural variants (SVs) are difficult to detect using SNP arrays or second generation sequencing, and may account for part of the missing heritability of SCZ.

Aims and objectives

To identify SVs associated with severe chronic SCZ across the whole genome.

Study design

10 multiplex families with probands suffering from chronic SCZ with negative symptoms and cognitive deficits were recruited, with all their affected members demonstrating uni-lineal inheritance. Control subjects comprised one affected member from the affected lineage, and unaffected members from each paternal and maternal lineage.

Methods

Third generation sequencing was applied to peripheral blood samples from 10 probands and 5 unaffected controls. Bioinformatic tools were used to identify SVs from the long sequencing reads, with confirmation of findings in probands by short-read Illumina sequencing, Sanger sequencing and visual manual validation with Integrated Genome Browser.

Results

In the 10 probands, we identified and validated 88 SVs (mostly in introns and medium-sized), within 79 genes, which were absent in the 5 unaffected control subjects. These 79 genes were enriched in 20 biological pathways which were related to brain development, neuronal migration, neurogenesis, neuronal/synaptic function, learning/memory, and hearing. These identified SVs also showed evidence for enrichment of genes that are highly expressed in the adolescent striatum.

Conclusion

A substantial part of the missing heritability in SCZ may be explained by medium-sized SVs detectable only by third generation sequencing. We have identified a number of such SVs potentially conferring risk for SCZ, which implicate multiple brain-related genes and pathways. In addition to previously-identified pathways involved in SCZ such as neurodevelopment and neuronal/synaptic functioning, we also found novel evidence for enrichment in hearing-related pathways and genes expressed in the adolescent striatum.

MTAGCN: predicting miRNA-target associations in Camellia sinensis var. assamica through graph convolution neural network

Background

MircoRNAs (miRNAs) play a central role in diverse biological processes of Camellia sinensis var.assamica (CSA) through their associations with target mRNAs, including CSA growth, development and stress response. However, although the experiment methods of CSA miRNA-target identifications are costly and time-consuming, few computational methods have been developed to tackle the CSA miRNA-target association prediction problem.

Results

In this paper, we constructed a heterogeneous network for CSA miRNA and targets by integrating rich biological information, including a miRNA similarity network, a target similarity network, and a miRNA-target association network. We then proposed a deep learning framework of graph convolution networks with layer attention mechanism, named MTAGCN. In particular, MTAGCN uses the attention mechanism to combine embeddings of multiple graph convolution layers, employing the integrated embedding to score the unobserved CSA miRNA-target associations.

Discussion

Comprehensive experiment results on two tasks (balanced task and unbalanced task) demonstrated that our proposed model achieved better performance than the classic machine learning and existing graph convolution network-based methods. The analysis of these results could offer valuable information for understanding complex CSA miRNA-target association mechanisms and would make a contribution to precision plant breeding.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04819-3.

Comprehensive analysis of recessive carrier status using exome and genome sequencing data in 1543 Southern Chinese

Traditional carrier screening has been utilized for the detection of carriers of genetic disorders. Since a comprehensive assessment of the carrier frequencies of recessive conditions in the Southern Chinese population is not yet available, we performed a secondary analysis on the spectrum and carrier status for 315 genes causing autosomal recessive disorders in 1543 Southern Chinese individuals with next-generation sequencing data, 1116 with exome sequencing and 427 with genome sequencing data. Our data revealed that 1 in 2 people (47.8% of the population) was a carrier for one or more recessive conditions, and 1 in 12 individuals (8.30% of the population) was a carrier for treatable inherited conditions. In alignment with current American College of Obstetricians and Gynecologists (ACOG) pan-ethnic carrier recommendations, 1 in 26 individuals were identified as carriers of cystic fibrosis, thalassemia, and spinal muscular atrophy in the Southern Chinese population. When the >1% expanded carrier screening rate recommendation by ACOG was used, 11 diseases were found to meet the criteria in the Southern Chinese population. Approximately 1 in 3 individuals (35.5% of the population) were carriers of these 11 conditions. If the 1 in 200 carrier frequency threshold is used, and additional seven genes would meet the criteria, and 2 in 5 individuals (38.7% of the population) would be detected as a carrier. This study provides a comprehensive catalogue of the carrier spectrum and frequency in the Southern Chinese population and can serve as a reference for careful evaluation of the conditions to be included in expanded carrier screening for Southern Chinese people.

Isling: a tool for detecting integration of wild-type viruses and clinical vectors

Detecting viral and vector integration events is a key step when investigating interactions between viral and host genomes. This is relevant in several fields, including virology, cancer research and gene therapy. For example, investigating integrations of wild-type viruses such as human papillomavirus and hepatitis B virus has proven to be crucial for understanding the role of these integrations in cancer. Furthermore, identifying the extent of vector integration is vital for determining the potential for genotoxicity in gene therapies. To address these questions, we developed isling, the first tool specifically designed for identifying viral integrations in both wild-type and vector from next-generation sequencing data. Isling addresses complexities in integration behaviour including integration of fragmented genomes and integration junctions with ambiguous locations in a host or vector genome, and can also flag possible vector recombinations. We show that isling is up to 1.6-fold faster and up to 170% more accurate than other viral integration tools, and performs well on both simulated and real datasets. Isling is therefore an efficient and application-agnostic tool that will enable a broad range of investigations into viral and vector integration. These include comparisons between integrations of wild-type viruses and gene therapy vectors, as well as assessing the genotoxicity of vectors and understanding the role of viruses in cancer.

Genomic Landscapes of Epstein-Barr Virus in Pulmonary Lymphoepithelioma-like Carcinoma

Epstein-Barr virus (EBV) infection is associated with multiple malignancies, including pulmonary lymphoepithelioma-like carcinoma (pLELC), a particular subtype of primary lung cancer. However, the genomic characteristics of EBV related to pLELC remain unclear. Here, we obtained the whole-genome dataset of EBV isolated from 78 pLELC patients and 37 healthy controls using EBV-captured sequencing. Compared to the reference genome (NC_007605), a total of 3995 variations were detected across pLELC-derived EBV sequences, with the mutational hotspots located in latent genes. Combined with 180 published EBV sequences derived from healthy people in Southern China, we performed a genome-wide association study and identified 32 variations significantly related to pLELC (p < 2.56×10^-05, Bonferroni correction), with the top signal of SNP coordinate T7327C (OR = 1.22, p = 2.39×10^-15) locating in the origin of plasmid replication (OriP). The results of population structure analysis of EBV isolates in East Asian showed the EBV strains derived from pLELC were more similar to those from nasopharyngeal carcinoma (NPC) than other EBV-associated diseases. In addition, typical latency type-II infection were recognized for EBV of pLELC at both transcription and methylation levels. Taken together, we defined the global view of EBV genomic profiles in pLELC patients for the first time, providing new insights to deepening our understanding of this rare EBV-associated primary lung carcinoma. Importance Pulmonary lymphoepithelioma-like carcinoma (pLELC) is a rarely distinctive subtype of primary lung cancer closely associated with Epstein-Barr virus (EBV) infection. Here, we gave the first overview of pLELC-derived EBV at the level of genome, methylation and transcription. We obtained the EBV sequences dataset from 78 primary pLELC patients, and revealed the sequences diversity across EBV genome and detected variability in known immune epitopes. Genome-wide association analysis combining 217 healthy controls identifies significant variations related to the risk of pLELC. Meanwhile, we characterized the integration landscapes of EBV at the genome-wide level. These results provided new insight for understanding EBV's role in pLELC tumorigenesis.

Resolving complex structures at oncovirus integration loci with conjugate graph

Oncovirus integrations cause copy number variations and complex structural variations (SVs) on host genomes. However, the understanding of how inserted viral DNA impacts the local genome remains limited. The linear structure of the oncovirus integrated local genomic map (LGM) will lay the foundations to understand how oncovirus integrations emerge and compromise the host genome's functioning. We propose a conjugate graph model to reconstruct the rearranged LGM at integrated loci. Simulation tests prove the reliability and credibility of the algorithm. Applications of the algorithm to whole-genome sequencing data of human papillomavirus (HPV) and hepatitis B virus (HBV)-infected cancer samples gained biological insights on oncovirus integrations. We observed four affection patterns of oncovirus integrations from the HPV and HBV-integrated cancer samples, including the coding-frame truncation, hyper-amplification of tumor gene, the viral cis-regulation inserted at the single intron and at the intergenic region. We found that the focal duplicates and host SVs are frequent in the HPV-integrated LGMs, while the focal deletions are prevalent in HBV-integrated LGMs. Furthermore, with the results yields from our method, we found the enhanced microhomology-mediated end joining might lead to both HPV and HBV integrations and conjectured that the HPV integrations might mainly occur during the DNA replication process. The conjugate graph algorithm code and LGM construction pipeline, available at https://github.com/deepomicslab/FuseSV.

Current status of structural variation studies in plants

Structural variations (SVs) including gene presence/absence variations and copy number variations are a common feature of genomes in plants and, together with single nucleotide polymorphisms and epigenetic differences, are responsible for the heritable phenotypic diversity observed within and between species. Understanding the contribution of SVs to plant phenotypic variation is important for plant breeders to assist in producing improved varieties. The low resolution of early genetic technologies and inefficient methods have previously limited our understanding of SVs in plants. However, with the rapid expansion in genomic technologies, it is possible to assess SVs with an ever-greater resolution and accuracy. Here, we review the current status of SV studies in plants, examine the roles that SVs play in phenotypic traits, compare current technologies and assess future challenges for SV studies.

The Development of Machine Learning Methods in discriminating Secretory Proteins of Malaria Parasite

Malaria caused by Plasmodium falciparum is one of the major infectious diseases in the world. It is essential to exploit an effective method to predict secretory proteins of malaria parasites to develop effective cures and treatment. Biochemical assays can provide details for accurate identification of the secretory proteins, but these methods are expensive and time-consuming. In this paper, we summarized the machine learning-based identification algorithms and compared the construction strategies between different computational methods. Also, we discussed the use of machine learning to improve the ability of algorithms to identify proteins secreted by malaria parasites.

Recent development of machine learning methods in sumoylation sites prediction

Sumoylation of proteins is an important reversible post-translational modification of proteins and mediates a variety of cellular processes. Sumo-modified proteins can change their subcellular localization, activity and stability. In addition, it also plays an important role in various cellular processes such as transcriptional regulation and signal transduction. The abnormal sumoylation is involved in many diseases, including neurodegeneration and immune-related diseases, as well as the development of cancer. Therefore, identification of the sumoylation site (SUMO site) is fundamental to understanding their molecular mechanisms and regulatory roles. In contrast to labor-intensive and costly experimental approaches, computational prediction of sumoylation sites in silico also attracted much attention for its accuracy, convenience and speed. At present, many computational prediction models have been used to identify SUMO sites, but these contents have not been comprehensively summarized and reviewed. Therefore, the research progress of relevant models is summarized and discussed in this paper. We will briefly summarize the development of bioinformatics methods on sumoylation site prediction. We will mainly focus on the benchmark dataset construction, feature extraction, machine learning method, published results and online tools. We hope the review will provide more help for wet-experimental scholars.

Deciphering complex genome rearrangements in C. elegans using short-read whole genome sequencing

Genomic rearrangements cause congenital disorders, cancer, and complex diseases in human. Yet, they are still understudied in rare diseases because their detection is challenging, despite the advent of whole genome sequencing (WGS) technologies. Short-read (srWGS) and long-read WGS approaches are regularly compared, and the latter is commonly recommended in studies focusing on genomic rearrangements. However, srWGS is currently the most economical, accurate, and widely supported technology. In Caenorhabditis elegans (C. elegans), such variants, induced by various mutagenesis processes, have been used for decades to balance large genomic regions by preventing chromosomal crossover events and allowing the maintenance of lethal mutations. Interestingly, those chromosomal rearrangements have rarely been characterized on a molecular level. To evaluate the ability of srWGS to detect various types of complex genomic rearrangements, we sequenced three balancer strains using short-read Illumina technology. As we experimentally validated the breakpoints uncovered by srWGS, we showed that, by combining several types of analyses, srWGS enables the detection of a reciprocal translocation (eT1), a free duplication (sDp3), a large deletion (sC4), and chromoanagenesis events. Thus, applying srWGS to decipher real complex genomic rearrangements in model organisms may help designing efficient bioinformatics pipelines with systematic detection of complex rearrangements in human genomes.

A Survey for Predicting ATP Binding Residues of Proteins Using Machine Learning Methods

Protein-ligand interactions are necessary for majority protein functions. Adenosine-5'-triphosphate (ATP) is one such ligand that plays vital role as a coenzyme in providing energy for cellular activities, catalyzing biological reaction and signaling. Knowing ATP binding residues of proteins is helpful for annotation of protein function and drug design. However, due to the huge amounts of protein sequences influx into databases in the post-genome era, experimentally identifying ATP binding residues is cost-ineffective and time-consuming. To address this problem, computational methods have been developed to predict ATP binding residues. In this review, we briefly summarized the application of machine learning methods in detecting ATP binding residues of proteins. We expect this review will be helpful for further research.

Genome-wide mutational signatures revealed distinct developmental paths for human B cell lymphomas

Both somatic hypermutation (SHM) and class switch recombination (CSR) are initiated by activation-induced cytidine deaminase (AID). Dysregulation of these processes has been linked to B cell lymphomagenesis. Here we performed an in-depth analysis of diffuse large B cell lymphoma (DLBCL) and follicular lymphoma (FL) genomes. We characterized seven genomic mutational signatures, including two B cell tumor-specific signatures, one of which is novel and associated with aberrant SHM. We further identified two major mutational signatures (K1 and K2) of clustered mutations (kataegis) resulting from the activities of AID or error-prone DNA polymerase η, respectively. K1 was associated with the immunoglobulin (Ig) switch region mutations/translocations and the ABC subtype of DLBCL, whereas K2 was related to the Ig variable region mutations and the GCB subtype of DLBCL and FL. Similar patterns were also observed in chronic lymphocytic leukemia subtypes. Thus, alterations associated with aberrant CSR and SHM activities can be linked to distinct developmental paths for different subtypes of B cell lymphomas.

Machine Learning Methods in Prediction of Protein Palmitoylation Sites: A Brief Review

Protein palmitoylation is a fundamental and reversible post-translational lipid modification that involves a series of biological processes. Although a large number of experimental studies have explored the molecular mechanism behind the palmitoylation process, the computational methods has attracted much attention for its good performance in predicting palmitoylation sites compared with expensive and time-consuming biochemical experiments. The prediction of protein palmitoylation sites is helpful to reveal its biological mechanism. Therefore, the research on the application of machine learning methods to predict palmitoylation sites has become a hot topic in bioinformatics and promoted the development in the related fields. In this review, we briefly introduced the recent development in predicting protein palmitoylation sites by using machine learningbased methods and discussed their benefits and drawbacks. The perspective of machine learning-based methods in predicting palmitoylation sites was also provided. We hope the review could provide a guide in related fields.

Sequence-Based Deep Learning Frameworks on Enhancer-Promoter Interactions Prediction

Enhancer-promoter interactions (EPIs) in the human genome are of great significance to transcriptional regulation, which tightly controls gene expression. Identification of EPIs can help us better decipher gene regulation and understand disease mechanisms. However, experimental methods to identify EPIs are constrained by funds, time, and manpower, while computational methods using DNA sequences and genomic features are viable alternatives. Deep learning methods have shown promising prospects in classification and efforts that have been utilized to identify EPIs. In this survey, we specifically focus on sequence-based deep learning methods and conduct a comprehensive review of the literature. First, we briefly introduce existing sequence- based frameworks on EPIs prediction and their technique details. After that, we elaborate on the dataset, pre-processing means, and evaluation strategies. Finally, we concluded with the challenges these methods are confronted with and suggest several future opportunities. We hope this review will provide a useful reference for further studies on enhancer-promoter interactions.

HFS-SLPEE: A Novel Hierarchical Feature Selection and Second Learning Probability Error Ensemble Model for Precision Cancer Diagnosis

The emergence of high-throughput RNA-seq data has offered unprecedented opportunities for cancer diagnosis. However, capturing biological data with highly nonlinear and complex associations by most existing approaches for cancer diagnosis has been challenging. In this study, we propose a novel hierarchical feature selection and second learning probability error ensemble model (named HFS-SLPEE) for precision cancer diagnosis. Specifically, we first integrated protein-coding gene expression profiles, non-coding RNA expression profiles, and DNA methylation data to provide rich information; afterward, we designed a novel hierarchical feature selection method, which takes the CpG-gene biological associations into account and can select a compact set of superior features; next, we used four individual classifiers with significant differences and apparent complementary to build the heterogeneous classifiers; lastly, we developed a second learning probability error ensemble model called SLPEE to thoroughly learn the new data consisting of classifiers-predicted class probability values and the actual label, further realizing the self-correction of the diagnosis errors. Benchmarking comparisons on TCGA showed that HFS-SLPEE performs better than the state-of-the-art approaches. Moreover, we analyzed in-depth 10 groups of selected features and found several novel HFS-SLPEE-predicted epigenomics and epigenetics biomarkers for breast invasive carcinoma (BRCA) (e.g., TSLP and ADAMTS9-AS2), lung adenocarcinoma (LUAD) (e.g., HBA1 and CTB-43E15.1), and kidney renal clear cell carcinoma (KIRC) (e.g., IRX2 and BMPR1B-AS1).

DetectIS: a pipeline to rapidly detect exogenous DNA integration sites using DNA or RNA paired-end sequencing data

Motivation

Recombinant DNA technology is widely used for different applications in biology, medicine and bio-technology. Viral transduction and plasmid transfection are among the most frequently used techniques to generate recombinant cell lines. Many of these methods result in the random integration of the plasmid into the host genome. Rapid identification of the integration sites is highly desirable in order to characterize these engineered cell lines.

Results

We developed detectIS: a pipeline specifically designed to identify genomic integration sites of exogenous DNA, either a plasmid containing one or more transgenes or a virus. The pipeline is based on a Nextflow workflow combined with a Singularity image containing all the necessary software, ensuring high reproducibility and scalability of the analysis. We tested it on simulated datasets and RNA-seq data from a human sample infected with Hepatitis B virus. Comparisons with other state of the art tools show that our method can identify the integration site in different recombinant cell lines, with accurate results, lower computational demand and shorter execution times.

Availability and implementation

The Nextflow workflow, the Singularity image and a test dataset are available at https://github.com/AstraZeneca/detectIS.

Supplementary information

Supplementary data are available at Bioinformatics online.

ViR: a tool to solve intrasample variability in the prediction of viral integration sites using whole genome sequencing data

Background

Several bioinformatics pipelines have been developed to detect sequences from viruses that integrate into the human genome because of the health relevance of these integrations, such as in the persistence of viral infection and/or in generating genotoxic effects, often progressing into cancer. Recent genomics and metagenomics analyses have shown that viruses also integrate into the genome of non-model organisms (i.e., arthropods, fish, plants, vertebrates). However, rarely studies of endogenous viral elements (EVEs) in non-model organisms have gone beyond their characterization from reference genome assemblies. In non-model organisms, we lack a thorough understanding of the widespread occurrence of EVEs and their biological relevance, apart from sporadic cases which nevertheless point to significant roles of EVEs in immunity and regulation of expression. The concomitance of repetitive DNA, duplications and/or assembly fragmentations in a genome sequence and intrasample variability in whole-genome sequencing (WGS) data could determine misalignments when mapping data to a genome assembly. This phenomenon hinders our ability to properly identify integration sites.

Results

To fill this gap, we developed ViR, a pipeline which solves the dispersion of reads due to intrasample variability in sequencing data from both single and pooled DNA samples thus ameliorating the detection of integration sites. We tested ViR to work with both in silico and real sequencing data from a non-model organism, the arboviral vector Aedes albopictus. Potential viral integrations predicted by ViR were molecularly validated supporting the accuracy of ViR results.

Conclusion

ViR will open new venues to explore the biology of EVEs, especially in non-model organisms. Importantly, while we generated ViR with the identification of EVEs in mind, its application can be extended to detect any lateral transfer event providing an ad-hoc sequence to interrogate.

A deep learning framework for drug repurposing via emulating clinical trials on real-world patient data

Drug repurposing is an effective strategy to identify new uses for existing drugs, providing the quickest possible transition from bench to bedside. Real-world data, such as electronic health records and insurance claims, provide information on large cohorts of users for many drugs. Here we present an efficient and easily customized framework for generating and testing multiple candidates for drug repurposing using a retrospective analysis of real-world data. Building upon well-established causal inference and deep learning methods, our framework emulates randomized clinical trials for drugs present in a large-scale medical claims database. We demonstrate our framework on a coronary artery disease cohort of millions of patients. We successfully identify drugs and drug combinations that substantially improve the coronary artery disease outcomes but haven't been indicated for treating coronary artery disease, paving the way for drug repurposing.

The Computational Models of Drug-target Interaction Prediction

The identification of Drug-Target Interactions (DTIs) is an important process in drug discovery and medical research. However, the tradition experimental methods for DTIs identification are still time consuming, extremely expensive and challenging. In the past ten years, various computational methods have been developed to identify potential DTIs. In this paper, the identification methods of DTIs are summarized. What's more, several state-of-the-art computational methods are mainly introduced, containing network-based method and machine learning-based method. In particular, for machine learning-based methods, including the supervised and semisupervised models, have essential differences in the approach of negative samples. Although these effective computational models in identification of DTIs have achieved significant improvements, network-based and machine learning-based methods have their disadvantages, respectively. These computational methods are evaluated on four benchmark data sets via values of Area Under the Precision Recall curve (AUPR).

Analysis of Oncogene Protein Structure Using Small World Network Concept

Background:

The basic building block of a body is protein which is a complex system whose structure plays a key role in activation, catalysis, messaging and disease states. Therefore, careful investigation of protein structure is necessary for the diagnosis of diseases and for the drug designing. Protein structures are described at their different levels of complexity: primary (chain), secondary (helical), tertiary (3D), and quaternary structure. Analyzing complex 3D structure of protein is a difficult task but it can be analyzed as a network of interconnection between its component, where amino acids are considered as nodes and interconnection between them are edges.

Objective:

Many literature works have proven that the small world network concept provides many new opportunities to investigate network of biological systems. The objective of this paper is analyzing the protein structure using small world concept.

Methods:

Protein is analyzed using small world network concept, specifically where extreme condition is having a degree distribution which follows power law. For the correct verification of the proposed approach, dataset of the Oncogene protein structure is analyzed using Python programming.

Results:

Protein structure is plotted as network of amino acids (Residue Interaction Graph (RIG)) using distance matrix of nodes with given threshold, then various centrality measures (i.e., degree distribution, Degree-Betweenness correlation, and Betweenness-Closeness correlation) are calculated for 1323 nodes and graphs are plotted.

Conclusion:

Ultimately, it is concluded that there exist hubs with higher centrality degree but less in number, and they are expected to be robust toward harmful effects of mutations with new functions.

A Novel XGBoost Method to Identify Cancer Tissue-of-Origin Based on Copy Number Variations

The discovery of cancer of unknown primary (CUP) is of great significance in designing more effective treatments and improving the diagnostic efficiency in cancer patients. In the study, we develop an appropriate machine learning model for tracing the tissue of origin of CUP with high accuracy after feature engineering and model evaluation. Based on a copy number variation data consisting of 4,566 training cases and 1,262 independent validation cases, an XGBoost classifier is applied to 10 types of cancer. Extremely randomized tree (Extra tree) is used for dimension reduction so that fewer variables replace the original high-dimensional variables. Features with top 300 weights are selected and principal component analysis is applied to eliminate noise. We find that XGBoost classifier achieves the highest overall accuracy of 0.8913 in the 10-fold cross-validation for training samples and 0.7421 on independent validation datasets for predicting tumor tissue of origin. Furthermore, by contrasting various performance indices, such as precision and recall rate, the experimental results show that XGBoost classifier significantly improves the classification performance of various tumors with less prediction error, as compared to other classifiers, such as K-nearest neighbors (KNN), Bayes, support vector machine (SVM), and Adaboost. Our method can infer tissue of origin for the 10 cancer types with acceptable accuracy in both cross-validation and independent validation data. It may be used as an auxiliary diagnostic method to determine the actual clinicopathological status of specific cancer.

Identification of Cancerlectins By Using Cascade Linear Discriminant Analysis and Optimal g-gap Tripeptide Composition

Background:

Lectins are a diverse group of glycoproteins or glycoconjugate proteins that can be extracted from plants, invertebrates and higher animals. Cancerlectins, a kind of lectins, which play a key role in the process of tumor cells interacting with each other and are being employed as therapeutic agents. A full understanding of cancerlectins is significant because it provides a tool for the future direction of cancer therapy.

Objective:

To develop an accurate and practically useful timesaving tool to identify cancerlectins. A novel sequence-based method is proposed along with a correlative webserver to access the proposed tool.

Methods:

Firstly, protein features were extracted in a newly feature building way termed, g-gap tripeptide composition. After which a proposed cascade linear discriminant analysis (Cascade LDA) is used to alleviate the high dimensional difficulties with the Analysis Of Variance (ANOVA) as a feature importance criterion. Finally, Support Vector Machine (SVM) is used as the classifier to identify cancerlectins.

Results:

The proposed method achieved an accuracy of 91.34% with sensitivity of 89.89%, specificity of 92.48% and an 0.8318 Mathew’s correlation coefficient based on only 13 fusion features in jackknife cross validation, the result of which is superior to other published methods in this domain.

Conclusion:

In this study, a new method based only on primary structure of protein is proposed and experimental results show that it could be a promising tool to identify cancerlectins. An openaccess webserver is made available in this work to facilitate other related works.

White Blood Cell Image Segmentation Based on Color Component Combination and Contour Fitting

Background:

White Blood Cell (WBC) image segmentation plays a key role in cell morphology analysis. However, WBC segmentation is still a challenging task due to the diversity of WBCs under different staining conditions.

Objective:

In this paper, we propose a novel WBC segmentation method based on color component combination and contour fitting to segment WBC images accurately.

Methods:

Specifically, the proposed method first uses color component combination and image thresholding to achieve nucleus segmentation, then uses a color prior to remove image background, and extracts the initial WBC contour via Canny edge detection, and finally judges and closes the unclosed WBC contour by contour fitting. Accordingly, cytoplasm segmentation is achieved by subtracting the nucleus region from the WBC region.

Results:

Experimental results on 100 WBC images under rapid staining condition and 50 WBC images under standard staining condition showed that the proposed method improved segmentation accuracy of white blood cells under rapid and standard staining conditions.

Conclusion:

The proposed color component combination and contour fitting is effective in WBC segmentation task.

A random forest-based framework for genotyping and accuracy assessment of copy number variations

Detection of copy number variations (CNVs) is essential for uncovering genetic factors underlying human diseases. However, CNV detection by current methods is prone to error, and precisely identifying CNVs from paired-end whole genome sequencing (WGS) data is still challenging. Here, we present a framework, CNV-JACG, for Judging the Accuracy of CNVs and Genotyping using paired-end WGS data. CNV-JACG is based on a random forest model trained on 21 distinctive features characterizing the CNV region and its breakpoints. Using the data from the 1000 Genomes Project, Genome in a Bottle Consortium, the Human Genome Structural Variation Consortium and in-house technical replicates, we show that CNV-JACG has superior sensitivity over the latest genotyping method, SV², particularly for the small CNVs (≤1 kb). We also demonstrate that CNV-JACG outperforms SV² in terms of Mendelian inconsistency in trios and concordance between technical replicates. Our study suggests that CNV-JACG would be a useful tool in assessing the accuracy of CNVs to meet the ever-growing needs for uncovering the missing heritability linked to CNVs.

Prediction of the Disordered Regions of Intrinsically Disordered Proteins Based on the Molecular Functions

BACKGROUND

Intrinsically disordered proteins lack a well-defined three dimensional structure under physiological conditions while possessing the essential biological functions. They take part in various physiological processes such as signal transduction, transcription and posttranslational modifications and etc. The disordered regions are the main functional sites for intrinsically disordered proteins. Therefore, the research of the disordered regions has become a hot issue.

OBJECTIVE

In this paper, our motivation is to analysis of the features of disordered regions with different molecular functions and predict of different disordered regions using valid features.

METHODS

In this article, according to the different molecular function, we firstly divided intrinsically disordered proteins into six classes in DisProt database. Then, we extracted four features using bioinformatics methods, namely, Amino Acid Index (AAIndex), codon frequency (Codon), three kinds of protein secondary structure compositions (3PSS) and Chemical Shifts (CSs), and used these features to predict the disordered regions of the different functions by Support Vector Machine (SVM).

RESULTS

The best overall accuracy was 99.29% using the chemical shift (CSs) as feature. In feature fusion, the overall accuracy can reach 88.70% by using CSs+AAIndex as features. The overall accuracy was up to 86.09% by using CSs+AAIndex+Codon+3PSS as features.

CONCLUSION

We predicted and analyzed the disordered regions based on the molecular functions. The results showed that the prediction performance can be improved by adding chemical shifts and AAIndex as features, especially chemical shifts. Moreover, the chemical shift was the most effective feature in the prediction. We hoped that our results will be constructive for the study of intrinsically disordered proteins.

Comprehensive comparative analysis of methods and software for identifying viral integrations

Many viruses are capable of integrating in the human genome, particularly viruses involved in tumorigenesis. Viral integrations can be considered genetic markers for discovering virus-caused cancers and inferring cancer cell development. Next-generation sequencing (NGS) technologies have been widely used to screen for viral integrations in cancer genomes, and a number of bioinformatics tools have been developed to detect viral integrations using NGS data. However, there has been no systematic comparison of the methods or software. In this study, we performed a comprehensive comparative analysis of the designs, performance, functionality and limitations among the existing methods and software for detecting viral integrations. We further compared the sensitivity, precision and runtime of integration detection of four representative tools. Our analyses showed that each of the existing software had its own merits; however, none of them were sufficient for parallel or accurate virome-wide detection. After carefully evaluating the limitations shared by the existing methods, we proposed strategies and directions for developing virome-wide integration detection.

A Deep Learning Framework to Predict Tumor Tissue-of-Origin Based on Copy Number Alteration

Cancer of unknown primary site (CUPS) is a type of metastatic tumor for which the sites of tumor origin cannot be determined. Precise diagnosis of the tissue origin for metastatic CUPS is crucial for developing treatment schemes to improve patient prognosis. Recently, there have been many studies using various cancer biomarkers to predict the tissue-of-origin (TOO) of CUPS. However, only a very few of them use copy number alteration (CNA) to trance TOO. In this paper, a two-step computational framework called CNA_origin is introduced to predict the tissue-of-origin of a tumor from its gene CNA levels. CNA_origin set up an intellectual deep-learning network mainly composed of an autoencoder and a convolution neural network (CNN). Based on real datasets released from the public database, CNA_origin had an overall accuracy of 83.81% on 10-fold cross-validation and 79% on independent datasets for predicting tumor origin, which improved the accuracy by 7.75 and 9.72% compared with the method published in a previous paper. Our results suggested that the autoencoder model can extract key characteristics of CNA and that the CNN classifier model developed in this study can predict the origin of tumors robustly and effectively. CNA_origin was written in Python and can be downloaded from https://github.com/YingLianghnu/CNA_origin.

A Brief Survey for MicroRNA Precursor Identification Using Machine Learning Methods

MicroRNAs, a group of short non-coding RNA molecules, could regulate gene expression. Many diseases are associated with abnormal expression of miRNAs. Therefore, accurate identification of miRNA precursors is necessary. In the past 10 years, experimental methods, comparative genomics methods, and artificial intelligence methods have been used to identify pre-miRNAs. However, experimental methods and comparative genomics methods have their disadvantages, such as time-consuming. In contrast, machine learning-based method is a better choice. Therefore, the review summarizes the current advances in pre-miRNA recognition based on computational methods, including the construction of benchmark datasets, feature extraction methods, prediction algorithms, and the results of the models. And we also provide valid information about the predictors currently available. Finally, we give the future perspectives on the identification of pre-miRNAs. The review provides scholars with a whole background of pre-miRNA identification by using machine learning methods, which can help researchers have a clear understanding of progress of the research in this field.

Recent Advances in Computational Methods for Identifying Anticancer Peptides

Anticancer peptide (ACP) is a kind of small peptides that can kill cancer cells without damaging normal cells. In recent years, ACP has been pre-clinically used for cancer treatment. Therefore, accurate identification of ACPs will promote their clinical applications. In contrast to labor-intensive experimental techniques, a series of computational methods have been proposed for identifying ACPs. In this review, we briefly summarized the current progress in computational identification of ACPs. The challenges and future perspectives in developing reliable methods for identification of ACPs were also discussed. We anticipate that this review could provide novel insights into future researches on anticancer peptides.

A Survey for Predicting Enzyme Family Classes Using Machine Learning Methods

Enzymes are proteins that act as biological catalysts to speed up cellular biochemical processes. According to their main Enzyme Commission (EC) numbers, enzymes are divided into six categories: EC-1: oxidoreductase; EC-2: transferase; EC-3: hydrolase; EC-4: lyase; EC-5: isomerase and EC-6: synthetase. Different enzymes have different biological functions and acting objects. Therefore, knowing which family an enzyme belongs to can help infer its catalytic mechanism and provide information about the relevant biological function. With the large amount of protein sequences influxing into databanks in the post-genomics age, the annotation of the family for an enzyme is very important. Since the experimental methods are cost ineffective, bioinformatics tool will be a great help for accurately classifying the family of the enzymes. In this review, we summarized the application of machine learning methods in the prediction of enzyme family from different aspects. We hope that this review will provide insights and inspirations for the researches on enzyme family classification.

The Influence of Immune Heterogeneity on the Effectiveness of Immune Checkpoint Inhibitors in Multifocal Hepatocellular Carcinomas

PURPOSE

Immune checkpoint inhibitor therapy is emerging as the promising option for patients with advanced hepatocellular carcinoma. We aimed to investigate the heterogeneity of different tumor nodules of the same patient with multifocal hepatocellular carcinomas in response to immunotherapy and its molecular mechanisms.

EXPERIMENTAL DESIGN

We attained 45 surgical tumor samples including 33 small and 12 large nodules from 12 patients with multifocal hepatocellular carcinoma and evaluated genomic and immune heterogeneity among tumors through whole-genome sequencing and RNA sequencing. IHC was performed to validate the expression of immune markers. The responses to anti-programmed cell death protein-1 (PD-1) therapy in patients with multifocal hepatocellular carcinoma were evaluated.

RESULTS

The small and large tumors within the same patient presented with similar genomic characteristics, indicating their same genomic origin. We further found the small tumors had higher immune cell infiltration including more CD8⁺ T cells, M1 macrophages, and monocytes as compared with large tumors. Besides, the expression of interferon signature predictive of response to anti-PD-1 therapy was significantly upregulated in the small tumors. Moreover, the immune pathways were more vigorous along with less active proliferation pathways in the small tumors. In keeping with this, we found that small nodules were more sensitive to anti-PD-1 therapy than large nodules in patients with multifocal hepatocellular carcinoma.

CONCLUSIONS

The small tumors in patients with multifocal hepatocellular carcinoma had higher immune cell infiltration and upregulation of immune pathways as compared with the large tumors, which can partially explain the different responses of small and large tumors in the same case to anti-PD-1 therapy.

MVSC: A Multi-variation Simulator of Cancer Genome

BACKGROUND

Many forms of variations exist in the genome, which are the main causes of individual phenotypic differences. The detection of variants, especially those located in the tumor genome, still faces many challenges due to the complexity of the genome structure. Thus, the performance assessment of variation detection tools using next-generation sequencing platforms is urgently needed.

METHOD

We have created a software package called the Multi-Variation Simulator of Cancer genomes (MVSC) to simulate common genomic variants, including single nucleotide polymorphisms, small insertion and deletion polymorphisms, and structural variations (SVs), which are analogous to human somatically acquired variations. Three sets of variations embedded in genomic sequences in different periods were dynamically and sequentially simulated one by one.

RESULTS

In cancer genome simulation, complex SVs are important because this type of variation is characteristic of the tumor genome structure. Overlapping variations of different sizes can also coexist in the same genome regions, adding to the complexity of cancer genome architecture. Our results show that MVSC can efficiently simulate a variety of genomic variants that cannot be simulated by existing software packages.

CONCLUSION

The MVSC-simulated variants can be used to assess the performance of existing tools designed to detect SVs in next-generation sequencing data, and we also find that MVSC is memory and time-efficient compared with similar software packages.

A Review of Recent Advances and Research on Drug Target Identification Methods

BACKGROUND

From a therapeutic viewpoint, understanding how drugs bind and regulate the functions of their target proteins to protect against disease is crucial. The identification of drug targets plays a significant role in drug discovery and studying the mechanisms of diseases. Therefore the development of methods to identify drug targets has become a popular issue.

METHODS

We systematically review the recent work on identifying drug targets from the view of data and method. We compiled several databases that collect data more comprehensively and introduced several commonly used databases. Then divided the methods into two categories: biological experiments and machine learning, each of which is subdivided into different subclasses and described in detail.

RESULTS

Machine learning algorithms are the majority of new methods. Generally, an optimal set of features is chosen to predict successful new drug targets with similar properties. The most widely used features include sequence properties, network topological features, structural properties, and subcellular locations. Since various machine learning methods exist, improving their performance requires combining a better subset of features and choosing the appropriate model for the various datasets involved.

CONCLUSION

The application of experimental and computational methods in protein drug target identification has become increasingly popular in recent years. Current biological and computational methods still have many limitations due to unbalanced and incomplete datasets or imperfect feature selection methods.

Polyomavirus-Positive Merkel Cell Carcinoma Derived from a Trichoblastoma Suggests an Epithelial Origin of this Merkel Cell Carcinoma

Merkel cell carcinoma (MCC), an aggressive neuroendocrine carcinoma of the skin, is to date the only human cancer known to be frequently caused by a polyomavirus. However, it is a matter of debate which cells are targeted by the Merkel cell polyomavirus (MCPyV) to give rise to the phenotypically multifaceted MCC cells. To assess the lineage of origin of MCPyV-positive MCC, genetic analysis of a very rare tumor combining benign trichoblastoma and MCPyV-positive MCC was conducted by massive parallel sequencing. Although MCPyV was found to be integrated only in the MCC part, six somatic mutations were shared by both tumor components. The mutational overlap between the trichoblastoma and MCPyV-positive MCC parts of the combined tumor implies that MCPyV integration occurred in an epithelial tumor cell before MCC development. Therefore, our report demonstrates that MCPyV-positive MCC can derive from the epithelial lineage.

The Development of Machine Learning Methods in Cell-Penetrating Peptides Identification: A Brief Review

Background:

Cell-penetrating Peptides (CPPs) are important short peptides that facilitate cellular intake or uptake of various molecules. CPPs can transport drug molecules through the plasma membrane and send these molecules to different cellular organelles. Thus, CPP identification and related mechanisms have been extensively explored. In order to reveal the penetration mechanisms of a large number of CPPs, it is necessary to develop convenient and fast methods for CPPs identification.

Methods:

Biochemical experiments can provide precise details for accurately identifying CPP, but these methods are expensive and laborious. To overcome these disadvantages, several computational methods have been developed to identify CPPs. We have performed review on the development of machine learning methods in CPP identification. This review provides an insight into CPP identification.

Results:

We summarized the machine learning-based CPP identification methods and compared the construction strategies of 11 different computational methods. Furthermore, we pointed out the limitations and difficulties in predicting CPPs.

Conclusion:

In this review, the last studies on CPP identification using machine learning method were reported. We also discussed the future development direction of CPP recognition with computational methods.

Deregulated expression of NKL homeobox genes in T-cell lymphomas

Recently, we have presented a scheme, termed "NKL-code", which describes physiological expression patterns of NKL homeobox genes in early hematopoiesis and in lymphopoiesis including main stages of T-, B- and NK-cell development. Aberrant activity of these genes underlies the generation of hematological malignancies notably T-cell leukemia. Here, we searched for deregulated NKL homeobox genes in main entities of T-cell lymphomas comprising angioimmunoblastic T-cell lymphoma (AITL), anaplastic large cell lymphoma (ALCL), adult T-cell leukemia/lymphoma (ATLL), hepatosplenic T-cell lymphoma (HSTL), NK/T-cell lymphoma (NKTL) and peripheral T-cell lymphoma (PTCL). Our data revealed altogether 19 aberrantly overexpressed genes in these types, demonstrating deregulated NKL homeobox genes involvement in T-cell lymphomas as well. For detailed analysis we focused on NKL homeobox gene MSX1 which is normally expressed in NK-cells. MSX1 was overexpressed in subsets of HSTL patients and HSTL-derived sister cell lines DERL-2 and DERL-7 which served as models to characterize mechanisms of deregulation. We performed karyotyping, genomic and expression profiling, and whole genome sequencing to reveal mutated and deregulated gene candidates, including the fusion gene CD53-PDGFRB. Subsequent knockdown experiments allowed the reconstruction of an aberrant network involved in MSX1 deregulation, including chromatin factors AUTS2 and mutated histone HIST1H3B(K27M). The gene encoding AUTS2 is located at chromosome 7q11 and may represent a basic target of the HSTL hallmark aberration i(7q). Taken together, our findings highlight an oncogenic role for deregulated NKL homeobox genes in T-cell lymphoma and identify MSX1 as a novel player in HSTL, implicated in aberrant NK- and T-cell differentiation.

Uncovering Missing Heritability in Rare Diseases

The problem of 'missing heritability' affects both common and rare diseases hindering: discovery, diagnosis, and patient care. The 'missing heritability' concept has been mainly associated with common and complex diseases where promising modern technological advances, like genome-wide association studies (GWAS), were unable to uncover the complete genetic mechanism of the disease/trait. Although rare diseases (RDs) have low prevalence individually, collectively they are common. Furthermore, multi-level genetic and phenotypic complexity when combined with the individual rarity of these conditions poses an important challenge in the quest to identify causative genetic changes in RD patients. In recent years, high throughput sequencing has accelerated discovery and diagnosis in RDs. However, despite the several-fold increase (from ~10% using traditional to ~40% using genome-wide genetic testing) in finding genetic causes of these diseases in RD patients, as is the case in common diseases-the majority of RDs are also facing the 'missing heritability' problem. This review outlines the key role of high throughput sequencing in uncovering genetics behind RDs, with a particular focus on genome sequencing. We review current advances and challenges of sequencing technologies, bioinformatics approaches, and resources.

A virome-wide clonal integration analysis platform for discovering cancer viral etiology

Oncoviral infection is responsible for 12%–15% of cancer in humans. Convergent evidence from epidemiology, pathology, and oncology suggests that new viral etiologies for cancers remain to be discovered. Oncoviral profiles can be obtained from cancer genome sequencing data; however, widespread viral sequence contamination and noncausal viruses complicate the process of identifying genuine oncoviruses. Here, we propose a novel strategy to address these challenges by performing virome-wide screening of early-stage clonal viral integrations. To implement this strategy, we developed VIcaller, a novel platform for identifying viral integrations that are derived from any characterized viruses and shared by a large proportion of tumor cells using whole-genome sequencing (WGS) data. The sensitivity and precision were confirmed with simulated and benchmark cancer data sets. By applying this platform to cancer WGS data sets with proven or speculated viral etiology, we newly identified or confirmed clonal integrations of hepatitis B virus (HBV), human papillomavirus (HPV), Epstein-Barr virus (EBV), and BK Virus (BKV), suggesting the involvement of these viruses in early stages of tumorigenesis in affected tumors, such as HBV in TERT and KMT2B (also known as MLL4) gene loci in liver cancer, HPV and BKV in bladder cancer, and EBV in non-Hodgkin's lymphoma. We also showed the capacity of VIcaller to identify integrations from some uncharacterized viruses. This is the first study to systematically investigate the strategy and method of virome-wide screening of clonal integrations to identify oncoviruses. Searching clonal viral integrations with our platform has the capacity to identify virus-caused cancers and discover cancer viral etiologies.

A Brief Survey of Machine Learning Methods in Protein Sub-Golgi Localization

Background:

The location of proteins in a cell can provide important clues to their functions in various biological processes. Thus, the application of machine learning method in the prediction of protein subcellular localization has become a hotspot in bioinformatics. As one of key organelles, the Golgi apparatus is in charge of protein storage, package, and distribution.

Objective:

The identification of protein location in Golgi apparatus will provide in-depth insights into their functions. Thus, the machine learning-based method of predicting protein location in Golgi apparatus has been extensively explored. The development of protein sub-Golgi apparatus localization prediction should be reviewed for providing a whole background for the fields.

Method:

The benchmark dataset, feature extraction, machine learning method and published results were summarized.

Results:

We briefly introduced the recent progresses in protein sub-Golgi apparatus localization prediction using machine learning methods and discussed their advantages and disadvantages.

Conclusion:

We pointed out the perspective of machine learning methods in protein sub-Golgi localization prediction.

Identification of Genes Associated With Hirschsprung Disease, Based on Whole-Genome Sequence Analysis, and Potential Effects on Enteric Nervous System Development

BACKGROUND & AIMS

Hirschsprung disease, or congenital aganglionosis, is believed to be oligogenic-that is, caused by multiple genetic factors. We performed whole-genome sequence analyses of patients with Hirschsprung disease to identify genetic factors that contribute to disease development and analyzed the functional effects of these variants.

METHODS

We performed whole-genome sequence analyses of 443 patients with short-segment disease, recruited from hospitals in China and Vietnam, and 493 ethnically matched individuals without Hirschsprung disease (controls). We performed genome-wide association analyses and gene-based rare-variant burden tests to identify rare and common disease-associated variants and study their interactions. We obtained induced pluripotent stem cell (iPSC) lines from 4 patients with Hirschsprung disease and 2 control individuals, and we used these to generate enteric neural crest cells for transcriptomic analyses. We assessed the neuronal lineage differentiation capability of iPSC-derived enteric neural crest cells using an in vitro differentiation assay.

RESULTS

We identified 4 susceptibility loci, including 1 in the phospholipase D1 gene (PLD1) (P = 7.4 × 10^-7). The patients had a significant excess of rare protein-altering variants in genes previously associated with Hirschsprung disease and in the β-secretase 2 gene (BACE2) (P = 2.9 × 10^-6). The epistatic effects of common and rare variants across these loci provided a sensitized background that increased risk for the disease. In studies of the iPSCs, we observed common and distinct pathways associated with variants in RET that affect risk. In functional assays, we found variants in BACE2 to protect enteric neurons from apoptosis. We propose that alterations in BACE1 signaling via amyloid β precursor protein and BACE2 contribute to pathogenesis of Hirschsprung disease.

CONCLUSIONS

In whole-genome sequence analyses of patients with Hirschsprung disease, we identified rare and common variants associated with disease risk. Using iPSC cells, we discovered some functional effects of these variants.

Predicting Influenza Antigenicity by Matrix Completion With Antigen and Antiserum Similarity

The rapid mutation of influenza viruses especially on the two surface proteins hemagglutinin (HA) and neuraminidase (NA) has made them capable to escape from population immunity, which has become a key challenge for influenza vaccine design. Thus, it is crucial to predict influenza antigenic evolution and identify new antigenic variants in a timely manner. However, traditional experimental methods like hemagglutination inhibition (HI) assay to select vaccine strains are time and labor-intensive, while popular computational methods are less sensitive, which presents the need for more accurate algorithms. In this study, we have proposed a novel low-rank matrix completion model MCAAS to infer antigenic distances between antigens and antisera based on partially revealed antigenic distances, virus similarity based on HA protein sequences, and vaccine similarity based on vaccine strains. The model exploits the correlations of viruses and vaccines in serological tests as well as the ability of HAs from viruses and vaccine strains in inferring influenza antigenicity. We also compared the effects of comprehensive 65 amino acids substitution matrices in predicting influenza antigenicity. As a result, we applied MCAAS into H3N2 seasonal influenza virus data. Our model achieved a 10-fold cross validation root-mean-squared error (RMSE) of 0.5982, significantly outperformed existing computational methods like antigenic cartography, AntigenMap and BMCSI. We also constructed the antigenic map and studied the association between genetic and antigenic evolution of H3N2 influenza viruses. Finally, our analyses showed that homologous structure derived amino acid substitution matrix (HSDM) is most powerful in predicting influenza antigenicity, which is consistent with previous studies.

iRNA-2OM: A Sequence-Based Predictor for Identifying 2'-O-Methylation Sites in Homo sapiens

2'-O-methylation plays an important biological role in gene expression. Owing to the explosive increase in genomic sequencing data, it is necessary to develop a method for quickly and efficiently identifying whether a sequence contains the 2'-O-methylation site. As an additional method to the experimental technique, a computational method may help to identify 2'-O-methylation sites. In this study, based on the experimental 2'-O-methylation data of Homo sapiens, we proposed a support vector machine-based model to predict 2'-O-methylation sites in H. sapiens. In this model, the RNA sequences were encoded with the optimal features obtained from feature selection. In the fivefold cross-validation test, the accuracy reached 97.95%.