Search

Abstract Spread through air spaces (STAS) is a distinct invasion pattern in lung cancer, crucial for prognosis assessment and guiding surgical decisions. Histopathology is the gold standard for STAS detection, yet traditional methods are subjective, time-consuming, and prone to misdiagnosis, limiting large-scale applications. We present VERN, an image analysis model utilizing a feature-interactive Siamese graph encoder to predict STAS from lung cancer histopathological images. VERN captures spatial topological features with feature sharing and skip connections to enhance model training. Using 1,546 histopathology slides, we built a large single-cohort STAS lung cancer dataset. VERN achieved an AUC of 0.9215 in internal validation and AUCs of 0.8275 and 0.8829 in frozen and paraffin-embedded test sections, respectively, demonstrating clinical-grade performance. Validated on a single-cohort and three external datasets, VERN showed robust predictive performance and generalizability, providing an open platform ( http://plr.20210706.xyz:5000/ ) to enhance STAS diagnosis efficiency and accuracy.

Medical big data with artificial intelligence are vital in advancing digital medicine. However, the opaque and non-standardised nature embedded in most medical data extraction is prone to batch effects and has become a significant obstacle to reproducing previous works. This paper aims to develop an easy-to-use time-series multimodal data extraction pipeline, Quick-MIMIC, for standardised data extraction from MIMIC datasets. Our method can fully integrate different data structures into a time-series table, including structured, semi-structured, and unstructured data. We also introduce two additional modules to Quick-MIMIC, a pipeline parallelization method and data analysis methods, for reducing the data extraction time and presenting the characteristics of the extracted data intuitively. The extensive experimental results show that our pipeline can efficiently extract the needed data from the MIMIC dataset and convert it into the correct format for further analytic tasks.

Drawing parallels between linguistic constructs and cellular biology, Large Language Models (LLMs) have achieved success in diverse downstream applications for single-cell data analysis. However, to date, it still lacks methods to take advantage of LLMs to infer Ligand-Receptor (LR)-mediated cell-cell communications for spatially resolved transcriptomic data. Here, we propose SpaCCC to facilitate the inference of spatially resolved cell-cell communications, which relies on our fine-tuned single-cell LLM and functional gene interaction network to embed ligand and receptor genes into a unified latent space. The LR pairs with a significant closer distance in latent space are taken to be more likely to interact with each other. After that, the molecular diffusion and permutation test strategies are respectively employed to calculate the communication strength and filter out communications with low specificities. The benchmarked performance of SpaCCC is evaluated on real single-cell spatial transcriptomic datasets with superiority over other methods. SpaCCC also infers known LR pairs concealed by existing aggregative methods and then identifies communication patterns for specific cell types and their signaling pathways. Furthermore, SpaCCC provides various cell-cell communication visualization results at both single-cell and cell type resolution. In summary, SpaCCC provides a sophisticated and practical tool allowing researchers to decipher spatially resolved cell-cell communications and related communication patterns and signaling pathways based on spatial transcriptome data. SpaCCC is free and publicly available at https://github.com/jiboyalab/SpaCCC.

Abstract Major Depressive Disorder (MDD) is an affective disorder that can lead to persistent sadness and a decline in the quality of life, increasing the risk of suicide. Utilizing multimodal data such as electroencephalograms and patient interview audios can facilitate the timely detection of MDD. However, existing depression detection methods either consider only a single modality or do not fully account for the differences and similarities between modalities in multimodal approaches, potentially overlooking the latent information inherent in various modal data. To address these challenges, we propose EMO-GCN, a multimodal depression detection method based on an adaptive multi-graph neural network. By employing graph-based methods to model data from various modalities and extracting features from them, the potential correlations between modalities are uncovered. The model’s performance on the MODMA dataset is outstanding, achieving an accuracy (ACC) of 96.30%. Ablation studies further confirm the effectiveness of the model’s individual components.The experimental results of EMO-GCN demonstrate the application prospects of graph-based multimodal analysis in the field of mental health, offering new perspectives for future research.

Abstract DNA-protein interactions exert the fundamental structure of many pivotal biological processes, such as DNA replication, transcription, and gene regulation. However, accurate and efficient computational methods for identifying these interactions are still lacking. In this study, we propose a method ESM-DBP through refining the DNA-binding protein sequence repertory and domain-adaptive pretraining based the general protein language model. Our method considers the lacking exploration of general language model for DNA-binding protein domain-specific knowledge, so we screen out 170,264 DNA-binding protein sequences to construct the domain-adaptive language model. Experimental results on four downstream tasks show that ESM-DBP provides a better feature representation of DNA-binding protein compared to the original language model, resulting in improved prediction performance and outperforming the state-of-the-art methods. Moreover, ESM-DBP can still perform well even for those sequences with only a few homologous sequences. ChIP-seq on two predicted cases further support the validity of the proposed method.

Influenced by ChatGPT, artificial intelligence (AI) large models have witnessed a global upsurge in large model research and development. As people enjoy the convenience by this AI large model, more and more large models in subdivided fields are gradually being proposed, especially large models in radiology imaging field. This article first introduces the development history of large models, technical details, workflow, working principles of multimodal large models and working principles of video generation large models. Secondly, we summarize the latest research progress of AI large models in radiology education, radiology report generation, applications of unimodal and multimodal radiology. Finally, this paper also summarizes some of the challenges of large AI models in radiology, with the aim of better promoting the rapid revolution in the field of radiography.

MicroRNAs (miRNAs) play a crucial role in the prevention, prognosis, diagnosis, and treatment of complex diseases. Existing computational methods primarily focus on biologically relevant molecules directly associated with miRNA or disease, overlooking the fact that the human body is a highly complex system where miRNA or disease may indirectly correlate with various types of biomolecules. To address this, we propose a novel prediction model named MHGTMDA (miRNA and disease association prediction using heterogeneous graph transformer based on molecular heterogeneous graph). MHGTMDA integrates biological entity relationships of eight biomolecules, constructing a relatively comprehensive heterogeneous biological entity graph. MHGTMDA serves as a powerful molecular heterogeneity map transformer, capturing structural elements and properties of miRNAs and diseases, revealing potential associations. In a 5-fold cross-validation study, MHGTMDA achieved an area under the receiver operating characteristic curve of 0.9569, surpassing state-of-the-art methods by at least 3%. Feature ablation experiments suggest that considering features among multiple biomolecules is more effective in uncovering miRNA-disease correlations. Furthermore, we conducted differential expression analyses on breast cancer and lung cancer, using MHGTMDA to further validate differentially expressed miRNAs. The results demonstrate MHGTMDA’s capability to identify novel MDAs.

The metaverse is a process of virtualization and digitalization of the natural world, integrating various technologies.Virtual reality and blockchain are the underlying technologies for building the metaverse, but they are very different in data processing and computing power requirements.To solve the problems of data heterogeneity and computing power heterogeneity between blockchain and virtual reality, the concept of a ＆quot;meta-computing center＆quot; was described.The meta computing center, blockchain nodes, and edge servers formed a computing network in the hardware architecture.The meta computing center centrally processed the interaction between the virtual scene rendering data and virtual human objects.Digital assets and personal information were desensitized and stored on multiple distributed nodes using blockchain, and the edge server handled simple interaction.In terms of software architecture, a layered processing model was designed in combination with hardware architecture, and heterogeneous data such as model data and asset data were placed in different software layers for processing.Finally, the metaverse mall was designed based on the layered processing model, which provided some reference for future metaverse applications.

Abstract Background Considering the heterogeneity of tumors, it is a key issue in precision medicine to predict the drug response of each individual. The accumulation of various types of drug informatics and multi-omics data facilitates the development of efficient models for drug response prediction. However, the selection of high-quality data sources and the design of suitable methods remain a challenge. Methods In this paper, we design NeRD, a multidimensional data integration model based on the PRISM drug response database, to predict the cellular response of drugs. Four feature extractors, including drug structure extractor (DSE), molecular fingerprint extractor (MFE), miRNA expression extractor (mEE), and copy number extractor (CNE), are designed for different types and dimensions of data. A fully connected network is used to fuse all features and make predictions. Results Experimental results demonstrate the effective integration of the global and local structural features of drugs, as well as the features of cell lines from different omics data. For all metrics tested on the PRISM database, NeRD surpassed previous approaches. We also verified that NeRD has strong reliability in the prediction results of new samples. Moreover, unlike other algorithms, when the amount of training data was reduced, NeRD maintained stable performance. Conclusions NeRD’s feature fusion provides a new idea for drug response prediction, which is of great significance for precise cancer treatment.

Summary: Exploring early detection methods through comprehensive evaluation of DNA methylation for lung squamous cell carcinoma (LUSC) patients is of great significance. By using different machine learning algorithms for feature selection and model construction based on The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases, five methylation biomarkers in LUSC (along with mapped genes) were identified including cg14823851 (TBX4), cg02772121 (TRIM15), cg10424681 (C6orf201), cg12910906 (ARHGEF4), and cg20181079 (OR4D11), achieving extremely high sensitivity and specificity in distinguishing LUSC from normal samples in independent cohorts. Pyrosequencing assay verified DNA methylation levels, meanwhile qRT-PCR and immunohistochemistry results presented their accordant methylation-related gene expression statuses in paired LUSC and normal lung tissues. The five methylation-based biomarkers proposed in this study have great potential for the diagnosis of LUSC and could guide studies in methylation-regulated tumor development and progression.

Abstract Background Many of genome features which could help unravel the often complex post-speciation evolution of closely related species are obscured because of their location in chromosomal regions difficult to accurately characterize using standard genome analysis methods, including centromeres and repeat regions. Results Here, we analyze the genome evolution and diversification of two recently diverged sister cotton species based on nanopore long-read sequence assemblies and Hi-C 3D genome data. Although D genomes are conserved in gene content, they have diversified in gene order, gene structure, gene family diversification, 3D chromatin structure, long-range regulation, and stress-related traits. Inversions predominate among D genome rearrangements. Our results support roles for 5mC and 6mA in gene activation, and 3D chromatin analysis showed that diversification in proximal-vs-distal regulatory-region interactions shape the regulation of defense-related-gene expression. Using a newly developed method, we accurately positioned cotton centromeres and found that these regions have undergone obviously more rapid evolution relative to chromosome arms. We also discovered a cotton-specific LTR class that clarifies evolutionary trajectories among diverse cotton species and identified genetic networks underlying the Verticillium tolerance of Gossypium thurberi (e.g., SA signaling) and salt-stress tolerance of Gossypium davidsonii (e.g., ethylene biosynthesis). Finally, overexpression of G. thurberi genes in upland cotton demonstrated how wild cottons can be exploited for crop improvement. Conclusions Our study substantially deepens understanding about how centromeres have developed and evolutionarily impacted the divergence among closely related cotton species and reveals genes and 3D genome structures which can guide basic investigations and applied efforts to improve crops.

Abstract Background VISPR is an interactive visualization and analysis framework for CRISPR screening experiments. However, it only supports the output of MAGeCK, and requires installation and manual configuration. Furthermore, VISPR is designed to run on a single computer, and data sharing between collaborators is challenging. Results To make the tool easily accessible to the community, we present VISPR-online, a web-based general application allowing users to visualize, explore, and share CRISPR screening data online with a few simple steps. VISPR-online provides an exploration of screening results and visualization of read count changes. Apart from MAGeCK, VISPR-online supports two more popular CRISPR screening analysis tools: BAGEL and JACKS. It provides an interactive environment for exploring gene essentiality, viewing guide RNA (gRNA) locations, and allowing users to resume and share screening results. Conclusions VISPR-online allows users to visualize, explore and share CRISPR screening data online. It is freely available at http://vispr-online.weililab.org , while the source code is available at https://github.com/lemoncyb/VISPR-online .

With the rapid development of internet of things technology,in order to better develop modern medicine,avoid the “isolated” crisis of information,and meet the requirements of timeliness and computing performance of massive data generated by edge devices,it is a new trend of the times to combine edge computing with smart healthcare treatment.However,edge computing has a certain degree of openness,and it is prone to potential safety hazards.Therefore,people pay more and more attention to the security and privacy protection of edge computing system for smart healthcare treatment.The edge computing system and its architecture for smart healthcare were introduced,and the security risks encountered by smart healthcare in edge computing was explained,and some scholars’ solutions to the security risks were introduced.Finally,a security framework,and specific solutions for security and privacy protection under the framework were put forward,which providing some help for the trusted research of smart healthcare edge computing.

Abstract Background The Type II clustered regularly interspaced short palindromic repeats (CRISPR) and CRISPR-associated proteins (Cas) is a powerful genome editing technology, which is more and more popular in gene function analysis. In CRISPR/Cas, RNA guides Cas nuclease to the target site to perform DNA modification. Results The performance of CRISPR/Cas depends on well-designed single guide RNA (sgRNA). However, the off-target effect of sgRNA leads to undesired mutations in genome and limits the use of CRISPR/Cas. Here, we present OffScan, a universal and fast CRISPR off-target detection tool. Conclusions OffScan is not limited by the number of mismatches and allows custom protospacer-adjacent motif (PAM), which is the target site by Cas protein. Besides, OffScan adopts the FM-index, which efficiently improves query speed and reduce memory consumption.

Medical data contains multiple records of patient data that are important for subsequent treatment and future research. However, it needs to be stored and shared securely to protect the privacy of the data. Blockchain is widely used in the management of healthcare data because of its decentralized and tamper-proof features. In order to study the development of blockchain in healthcare, this paper evaluates it from various perspectives. We analyze blockchain-based approaches from different application scenarios. These are blockchain-based electronic medical record sharing, blockchain and the Internet of Medical Things and blockchain-based federal learning. The results show that blockchain and smart contracts have a natural advantage in the field of medical data since they are tamper-proof and traceable. Finally, the challenges and future directions of blockchain in healthcare are discussed, which can help drive the field forward.

Abstract Background Novel sequence motifs detection is becoming increasingly essential in computational biology. However, the high computational cost greatly constrains the efficiency of most motif discovery algorithms. Results In this paper, we accelerate MEME algorithm targeted on Intel Many Integrated Core (MIC) Architecture and present a parallel implementation of MEME called MIC-MEME base on hybrid CPU/MIC computing framework. Our method focuses on parallelizing the starting point searching method and improving iteration updating strategy of the algorithm. MIC-MEME has achieved significant speedups of 26.6 for ZOOPS model and 30.2 for OOPS model on average for the overall runtime when benchmarked on the experimental platform with two Xeon Phi 3120 coprocessors. Conclusions Furthermore, MIC-MEME has been compared with state-of-arts methods and it shows good scalability with respect to dataset size and the number of MICs. Source code: https://github.com/hkwkevin28/MIC-MEME.

Abstract Background Frequent subgraphs mining is a significant problem in many practical domains. The solution of this kind of problem can particularly used in some large-scale drug molecular or biological libraries to help us find drugs or core biological structures rapidly and predict toxicity of some unknown compounds. The main challenge is its efficiency, as (i) it is computationally intensive to test for graph isomorphisms, and (ii) the graph collection to be mined and mining results can be very large. Existing solutions often require days to derive mining results from biological networks even with relative low support threshold. Also, the whole mining results always cannot be stored in single node memory. Results In this paper, we implement a parallel acceleration tool for classical frequent subgraph mining algorithm called cmFSM. The core idea is to employ parallel techniques to parallelize extension tasks, so as to reduce computation time. On the other hand, we employ multi-node strategy to solve the problem of memory constraints. The parallel optimization of cmFSM is carried out on three different levels, including the fine-grained OpenMP parallelization on single node, multi-node multi-process parallel acceleration and CPU-MIC collaborated parallel optimization. Conclusions Evaluation results show that cmFSM clearly outperforms the existing state-of-the-art miners even if we only hold a few parallel computing resources. It means that cmFSM provides a practical solution to frequent subgraph mining problem with huge number of mining results. Specifically, our solution is up to one order of magnitude faster than the best CPU-based approach on single node and presents a promising scalability of massive mining tasks in multi-node scenario. More source code are available at:Source Code: https://github.com/ysycloud/cmFSM.

Through consulting lots of domestic and international literatures about sensor-cloud security,a series of security problems are found,such as reputation problem of service provider,the coupling problem of physical nodes,the leak of authority management,et al,which seriously hinders the further development of sensor-cloud.The secure problems occurring in sensor-cloud were analyzed,the current secure technologies were contrasted ,similarities and differences of various types solutions were discussed and summarized.After that,several future challenges of sensor-cloud security were concluded.Finally,a fog-based structure was proposed to solve the security problems,which would bring new ideas to the sensor-cloud security research.

The genome of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) encodes 16 non-structural (Nsp) and 4 structural proteins. Among the Nsps, Nsp1 inhibits host gene expression and also evades the immune system. This protein has been proposed as a target for vaccine development and also for drug design. Owing to its important role, the current study aimed to identify mutations in Nsp1 and their effect on protein stability and flexibility. This is the first comprehensive study in which 295,000 complete genomes have been screened for mutations after alignment with the Wuhan-Hu-1 reference genome (Accession NC_045512), using the CoVsurver app. The sequences harbored 933 mutations in the entire coding region of Nsp1. The most frequently occurring mutation in the 180-amino-acid Nsp1 protein was R24C (n = 1122), followed by D75E (n = 890), D48G (n = 881), H110Y (n = 860), and D144A (n = 648). Among the 933 non-synonymous mutations, 529 exhibited a destabilizing effect. Similarly, a gain in flexibility was observed in 542 mutations. The majority of the most frequent mutations were detected in the loop regions. These findings imply that Nsp1 mutations might be useful to exploit SARS-CoV-2′s pathogenicity. Genomic sequencing of SARS-CoV-2 on a regular basis will further assist in analyzing variations among the drug targets and to test the diagnostic accuracy. This wide range of mutations and their effect on Nsp1’s stability may have some consequences for the host’s innate immune response to SARS-CoV-2 infection and also for the vaccines’ efficacy. Based on this mutational information, geographically strain-specific drugs, vaccines, and antibody combinations could be a useful strategy against SARS-CoV-2 infection.

Atmospheric continuous-variable quantum key distribution (ACVQKD) has been proven to be secure theoretically with the assumption that the signal source is well protected by the sender so that it cannot be compromised. However, this assumption is quite unpractical in realistic quantum communication system. In this work, we investigate a practical situation in which the signal source is no longer protected by the legitimate parts, but is exposed to the untrusted atmospheric channel. We show that the performance of ACVQKD is reduced by removing the assumption, especially when putting the untrusted source at the middle of the channel. To improve the performance of the ACVQKD with the untrusted source, a non-Gaussian operation, called photon subtraction, is subsequently introduced. Numerical analysis shows that the performance of ACVQKD with an untrusted source can be improved by properly adopting the photon subtraction operation. Moreover, a special situation where the untrusted source is located in the middle of the atmospheric channel is also considered. Under direct reconciliation, we find that its performance can be significantly improved when the photon subtraction operation is manipulated by the sender.

Sequence alignment and mutation detection are the basic steps of genomic data analysis.They are the premise of subsequent functional analysis,and the most time-consuming steps.In order to effectively deal with the massive genomic big data brought by high-throughput sequencing technology,MPI,OpenMP and other technologies to perform multi-level parallel optimization of sequence alignment algorithm and SNP detection algorithm were used.By testing on different data sets and parallel scales,the core algorithm reached more than 9x speedup,and the parallel efficiency remained above 60% in large-scale test.The improved algorithms obtain good parallel performance and scalability,that effectively improves the ability of genomic big data mutation detection.

The severity of an epidemic has a significant impact on individual vaccinating decisions under voluntary vaccination. During the epidemic of a vaccine-preventable disease, individuals in a social network can perceive the infection risks based on global information announced by public health authorities, or local information obtained from their social neighbors. After that, they can rationally decide whether or not to take the vaccine through weighing the relative cost of vaccination and infection (i.e., relative vaccine cost). In this case, both social network structure and individuals’ risk perception strategies will affect the final vaccine coverage. In this paper, we focus on the problem of how individuals’ perceptions on epidemic severity affect their vaccinating behaviors in the face of flu-like seasonal diseases in social networks, and vice versa. Specifically, we first present three types of static decision-making mechanisms, each of which simulates human vaccinating behaviors based on different local/global information. On this basis, we further present a reinforcement-learning-based mechanism, where individuals can use their historical vaccination experiences to determine what information is more suitable to estimate the severity of the epidemic. Finally, we carry out simulations on three types of social networks to investigate the effects of network structure, source of information, relative vaccine cost, and individual social connections on the final vaccine coverage and epidemic size. The results and findings can provide a new insight for designing incentive-based vaccination policies and intervention strategies for flu-like seasonal diseases.

Frequent subgraph mining is an important issue to be solved in many practical fields.Due to the computational intensiveness,the mining of the atlas and the large capacity of the results,the existing solutions can not meet the time requirements,and its efficiency is currently the main challenge.The frequent subgraph mining tool cmFSM for parallel acceleration was originally proposed.cmFSM performs parallel optimization on three levels:fine-grained OpenMP parallelization on a single node,multi-node multi-process parallelization and CPU-MIC collaborative parallelization.cmFSM is twice as fast as the best CPU-based algorithm on a single node and provides scalability in a multi-node approach.In the future,we will continue to improve the scalability of multiple solutions.The results show that even with only a few parallel computing resources,cmFSM is significantly better than the most advanced algorithms available.This fully demonstrates the effectiveness of the proposed tool in the field of bioinformatics.

The biological assessment,including matching algorithm,is realized by measuring and analyzing the human cells’ transcription reaction after stimulated by biological agents,to quickly determine the relevant detection markers and treatment targets.Similarly,the big data strategy was used to estimate the sudden biological effect model.MPI,OpenMP two-level parallel acceleration was considered,transplantation and optimization of the GSEA alignment algorithm and clustering algorithm were used.The potential scalability and the ability of dealing with massive data by testing different scales of data and parallelisms were improved.

With advances in next-generation sequencing(NGS) technologies, a large number of multiple types of high-throughput genomics data are available. A great challenge in exploring cancer progression is to identify the driver genes from the variant genes by analyzing and integrating multi-types genomics data. Breast cancer is known as a heterogeneous disease. The identification of subtype-specific driver genes is critical to guide the diagnosis, assessment of prognosis and treatment of breast cancer. We developed an integrated frame based on gene expression profiles and copy number variation (CNV) data to identify breast cancer subtype-specific driver genes. In this frame, we employed statistical machine-learning method to select gene subsets and utilized an module-network analysis method to identify potential candidate driver genes. The final subtype-specific driver genes were acquired by paired-wise comparison in subtypes. To validate specificity of the driver genes, the gene expression data of these genes were applied to classify the patient samples with 10-fold cross validation and the enrichment analysis were also conducted on the identified driver genes. The experimental results show that the proposed integrative method can identify the potential driver genes and the classifier with these genes acquired better performance than with genes identified by other methods.

To tackle the exponentially increasing throughput of Next-Generation Sequencing (NGS), most of the existing short-read aligners can be configured to favor speed in trade of accuracy and sensitivity. SOAP3-dp, through leveraging the computational power of both CPU and GPU with optimized algorithms, delivers high speed and sensitivity simultaneously. Compared with widely adopted aligners including BWA, Bowtie2, SeqAlto, CUSHAW2, GEM and GPU-based aligners BarraCUDA and CUSHAW, SOAP3-dp was found to be two to tens of times faster, while maintaining the highest sensitivity and lowest false discovery rate (FDR) on Illumina reads with different lengths. Transcending its predecessor SOAP3, which does not allow gapped alignment, SOAP3-dp by default tolerates alignment similarity as low as 60%. Real data evaluation using human genome demonstrates SOAP3-dp's power to enable more authentic variants and longer Indels to be discovered. Fosmid sequencing shows a 9.1% FDR on newly discovered deletions. SOAP3-dp natively supports BAM file format and provides the same scoring scheme as BWA, which enables it to be integrated into existing analysis pipelines. SOAP3-dp has been deployed on Amazon-EC2, NIH-Biowulf and Tianhe-1A.