Cancer survival analysis aims to predict survival outcomes to evaluate the efficacy and prognosis of treatment. Although current approaches have designed diverse cross-modal learning methods to integrate genetic data and pathology images, they are frequently hindered by data redundancy. Pattern representation in high-dimensional genetic data remains a significant hurdle. Pathology data analysis is computationally intensive because of the giga-pixel resolution. Moreover, the heterogeneity of data types poses a barrier to extending multimodal fusion methods. To address the aforementioned issues, we propose a novel LLM-driven Cross-Modality MoE-feature Fusion Network (LCM-Net) with three innovative modules for boosting cancer survival prediction. Specifically, the Genomic Language Alignment (GLA) module integrates genomic features with learnable prompts. Utilizing large language models, it encodes genomic information into concise and semantically relevant representations. Then, we devise the Pathological Feature Refinement (PFR) module to serve as a plug-and-play component that filters out irrelevant regions in pathology images. Finally, we propose a Multimodal Expert Integration (MEI) module to effectively leverage the capabilities of different experts, integrating the processed features from both the genomic and pathological domains. Extensive experiments on five public datasets demonstrate that our approach outperforms state-of-the-art methods, and the ablation study confirms the effectiveness of the proposed modules. Our code is publicly available at https://github.com/script-Yang/LCM-Net.

Articles containing geographic information are widely distributed and commonly used in daily life, frequently incorporating geographic visualizations as illustrations. However, the creation of such articles remains cumbersome, necessitating authors to switch between authoring text and illustrations, thereby disrupting immersive writing. Our interviews corroborated this observation and revealed the primary challenge in the traditional process stems from the low synchronization frequency between text and geographic visualizations during creation, coupled with weak visual links, forcing users to mentally maintain this synchronization and thereby increasing their cognitive burden. In response, we developed GeoAuthor, which facilitates the interactive creation of geographic articles by automatically synchronizing text creation with geographic visualizations with rich visual links. This bidirectional approach ensures that the written content and visual representations remain consistent and mutually informative throughout the creation process. Our evaluation demonstrated the efficacy of GeoAuthor, indicating its capacity to streamline the process of creating geographic articles.

In geo-related fields such as urban informatics, atmospheric science, and geography, large-scale spatial time (ST) series (i.e., geo-referred time series) are collected for monitoring and understanding important spatiotemporal phenomena. ST series visualization is an effective means of understanding the data and reviewing spatiotemporal phenomena, which is a prerequisite for in-depth data analysis. However, visualizing these series is challenging due to their large scales, inherent dynamics, and spatiotemporal nature. In this study, we introduce the notion of patterns of evolution in ST series. Each evolution pattern is characterized by 1) a set of ST series that are close in space and 2) a time period when the trends of these ST series are correlated. We then leverage Storyline techniques by considering an analogy between evolution patterns and sessions, and finally design a novel visualization called GeoChron, which is capable of visualizing large-scale ST series in an evolution pattern-aware and narrative-preserving manner. GeoChron includes a mining framework to extract evolution patterns and two-level visualizations to enhance its visual scalability. We evaluate GeoChron with two case studies, an informal user study, an ablation study, parameter analysis, and running time analysis.

Numerous patterns found in urban phenomena, such as air pollution and human mobility, can be characterized as many directed geospatial networks (geo-networks) that represent spreading processes in urban space. These geo-networks can be analyzed from multiple levels, ranging from the macro-level of summarizing all geo-networks, meso-level of comparing or summarizing parts of geo-networks, and micro-level of inspecting individual geo-networks. Most of the existing visualizations cannot support multilevel analysis well. These techniques work by: 1) showing geo-networks separately with multiple maps leads to heavy context switching costs between different maps; 2) summarizing all geo-networks into a single network can lead to the loss of individual information; 3) drawing all geo-networks onto one map might suffer from the visual scalability issue in distinguishing individual geo-networks. In this study, we propose GeoNetverse, a novel visualization technique for analyzing aggregate geo-networks from multiple levels. Inspired by metro maps, GeoNetverse balances the overview and details of the geo-networks by placing the edges shared between geo-networks in a stacked manner. To enhance the visual scalability, GeoNetverse incorporates a level-of-detail rendering, a progressive crossing minimization, and a coloring technique. A set of evaluations was conducted to evaluate GeoNetverse from multiple perspectives.

In this paper, we present a toolset and related resources for rapid identification of viruses and microorganisms from short-read or long-read sequencing data. We present fastv as an ultra-fast tool to detect microbial sequences present in sequencing data, identify target microorganisms and visualize coverage of microbial genomes. This tool is based on the k-mer mapping and extension method. K-mer sets are generated by UniqueKMER, another tool provided in this toolset. UniqueKMER can generate complete sets of unique k-mers for each genome within a large set of viral or microbial genomes. For convenience, unique k-mers for microorganisms and common viruses that afflict humans have been generated and are provided with the tools. As a lightweight tool, fastv accepts FASTQ data as input and directly outputs the results in both HTML and JSON formats. Prior to the k-mer analysis, fastv automatically performs adapter trimming, quality pruning, base correction and other preprocessing to ensure the accuracy of k-mer analysis. Specifically, fastv provides built-in support for rapid severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) identification and typing. Experimental results showed that fastv achieved 100% sensitivity and 100% specificity for detecting SARS-CoV-2 from sequencing data; and can distinguish SARS-CoV-2 from SARS, Middle East respiratory syndrome and other coronaviruses. This toolset is available at: https://github.com/OpenGene/fastv.

BACKGROUND: Removing duplicates might be considered as a well-resolved problem in next-generation sequencing (NGS) data processing domain. However, as NGS technology gains more recognition in clinical application, researchers start to pay more attention to its sequencing errors, and prefer to remove these errors while performing deduplication operations. Recently, a new technology called unique molecular identifier (UMI) has been developed to better identify sequencing reads derived from different DNA fragments. Most existing duplicate removing tools cannot handle the UMI-integrated data. Some modern tools can work with UMIs, but are usually slow and use too much memory. Furthermore, existing tools rarely report rich statistical results, which are very important for quality control and downstream analysis. These unmet requirements drove us to develop an ultra-fast, simple, little-weighted but powerful tool for duplicate removing and sequence error suppressing, with features of handling UMIs and reporting informative results. RESULTS: This paper presents an efficient tool gencore for duplicate removing and sequence error suppressing of NGS data. This tool clusters the mapped sequencing reads and merges reads in each cluster to generate one single consensus read. While the consensus read is generated, the random errors introduced by library construction and sequencing can be removed. This error-suppressing feature makes gencore very suitable for the application of detecting ultra-low frequency mutations from deep sequencing data. When unique molecular identifier (UMI) technology is applied, gencore can use them to identify the reads derived from same original DNA fragment. Gencore reports statistical results in both HTML and JSON formats. The HTML format report contains many interactive figures plotting statistical coverage and duplication information. The JSON format report contains all the statistical results, and is interpretable for downstream programs. CONCLUSIONS: Comparing to the conventional tools like Picard and SAMtools, gencore greatly reduces the output data's mapping mismatches, which are mostly caused by errors. Comparing to some new tools like UMI-Reducer and UMI-tools, gencore runs much faster, uses less memory, generates better consensus reads and provides simpler interfaces. To our best knowledge, gencore is the only duplicate removing tool that generates both informative HTML and JSON reports. This tool is available at: https://github.com/OpenGene/gencore.

Motivation: Quality control and preprocessing of FASTQ files are essential to providing clean data for downstream analysis. Traditionally, a different tool is used for each operation, such as quality control, adapter trimming and quality filtering. These tools are often insufficiently fast as most are developed using high-level programming languages (e.g. Python and Java) and provide limited multi-threading support. Reading and loading data multiple times also renders preprocessing slow and I/O inefficient. Results: We developed fastp as an ultra-fast FASTQ preprocessor with useful quality control and data-filtering features. It can perform quality control, adapter trimming, quality filtering, per-read quality pruning and many other operations with a single scan of the FASTQ data. This tool is developed in C++ and has multi-threading support. Based on our evaluation, fastp is 2-5 times faster than other FASTQ preprocessing tools such as Trimmomatic or Cutadapt despite performing far more operations than similar tools. Availability and implementation: The open-source code and corresponding instructions are available at https://github.com/OpenGene/fastp.

BACKGROUND: Some types of clinical genetic tests, such as cancer testing using circulating tumor DNA (ctDNA), require sensitive detection of known target mutations. However, conventional next-generation sequencing (NGS) data analysis pipelines typically involve different steps of filtering, which may cause miss-detection of key mutations with low frequencies. Variant validation is also indicated for key mutations detected by bioinformatics pipelines. Typically, this process can be executed using alignment visualization tools such as IGV or GenomeBrowse. However, these tools are too heavy and therefore unsuitable for validating mutations in ultra-deep sequencing data. RESULT: We developed MutScan to address problems of sensitive detection and efficient validation for target mutations. MutScan involves highly optimized string-searching algorithms, which can scan input FASTQ files to grab all reads that support target mutations. The collected supporting reads for each target mutation will be piled up and visualized using web technologies such as HTML and JavaScript. Algorithms such as rolling hash and bloom filter are applied to accelerate scanning and make MutScan applicable to detect or visualize target mutations in a very fast way. CONCLUSION: MutScan is a tool for the detection and visualization of target mutations by only scanning FASTQ raw data directly. Compared to conventional pipelines, this offers a very high performance, executing about 20 times faster, and offering maximal sensitivity since it can grab mutations with even one single supporting read. MutScan visualizes detected mutations by generating interactive pile-ups using web technologies. These can serve to validate target mutations, thus avoiding false positives. Furthermore, MutScan can visualize all mutation records in a VCF file to HTML pages for cloud-friendly VCF validation. MutScan is an open source tool available at GitHub: https://github.com/OpenGene/MutScan.

Freehand three-dimensional (3D) ultrasound imaging is an attractive research area because it is capable of providing large field of view and high in-plane resolution image to allow better illustration of complex anatomy structures. However, reconstructed image is corrupted with speckle noise and artifacts in the conventional reconstructed volume data. In this paper, we propose a simple but effective adaptive kernel regression method for volume reconstruction from freehand swept B-scan images. By creating a linear model for estimating the homogeneous region of the B-scan image and learning the parameters of the model with a supervised learning method, the statistical characteristic of speckle can be well recovered. With the learned linear model of speckle, we can easily estimate the homogenous region and reconstruct image with speckle reduction and edge preservation via the adaptive turning of the smoothing parameters of the kernel regression. Our algorithm lends itself to parallel processing, and yields a 288× speedup on a graphics processing unit (GPU). Experiments on the simulated data, ultrasonic abdominal phantom and in-vivo liver of human subject and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both volume reconstruction accuracy and efficiency.

Plasma cell-free DNA (cfDNA) has certain fragmentation patterns, which can bring non-random base content curves of the sequencing data's beginning cycles. We studied the patterns and found that we could determine whether a sample is cfDNA or not by just looking into the first 10 cycles of its base content curves. We analysed 3189 FastQ files, including 1442 cfDNA, 1234 genomic DNA, 507 FFPE tumour DNA and 6 urinary cfDNA. By deep analysing these data, we find the patterns are stable enough to distinguish cfDNA from other kinds of DNA samples. Based on this finding, we build classification models to recognise cfDNA samples by their sequencing data. Pattern recognition models are then trained with different classification algorithms like k-nearest neighbours (KNN), random forest and support vector machine (SVM). The result of 1000 iteration .632+ bootstrapping shows that all these classifiers can give an average accuracy higher than 98%, indicating that the cfDNA patterns are unique and can make the dataset highly separable. The best result is obtained using random forest classifier with a 99.89% average accuracy (σ = 0.00068). A tool called CfdnaPattern (http://github.com/OpenGene/CfdnaPattern) has been developed to train the model and to predict whether a sample is cfDNA or not.

BACKGROUND: Some applications, especially those clinical applications requiring high accuracy of sequencing data, usually have to face the troubles caused by unavoidable sequencing errors. Several tools have been proposed to profile the sequencing quality, but few of them can quantify or correct the sequencing errors. This unmet requirement motivated us to develop AfterQC, a tool with functions to profile sequencing errors and correct most of them, plus highly automated quality control and data filtering features. Different from most tools, AfterQC analyses the overlapping of paired sequences for pair-end sequencing data. Based on overlapping analysis, AfterQC can detect and cut adapters, and furthermore it gives a novel function to correct wrong bases in the overlapping regions. Another new feature is to detect and visualise sequencing bubbles, which can be commonly found on the flowcell lanes and may raise sequencing errors. Besides normal per cycle quality and base content plotting, AfterQC also provides features like polyX (a long sub-sequence of a same base X) filtering, automatic trimming and K-MER based strand bias profiling. RESULTS: For each single or pair of FastQ files, AfterQC filters out bad reads, detects and eliminates sequencer's bubble effects, trims reads at front and tail, detects the sequencing errors and corrects part of them, and finally outputs clean data and generates HTML reports with interactive figures. AfterQC can run in batch mode with multiprocess support, it can run with a single FastQ file, a single pair of FastQ files (for pair-end sequencing), or a folder for all included FastQ files to be processed automatically. Based on overlapping analysis, AfterQC can estimate the sequencing error rate and profile the error transform distribution. The results of our error profiling tests show that the error distribution is highly platform dependent. CONCLUSION: Much more than just another new quality control (QC) tool, AfterQC is able to perform quality control, data filtering, error profiling and base correction automatically. Experimental results show that AfterQC can help to eliminate the sequencing errors for pair-end sequencing data to provide much cleaner outputs, and consequently help to reduce the false-positive variants, especially for the low-frequency somatic mutations. While providing rich configurable options, AfterQC can detect and set all the options automatically and require no argument in most cases.

Tuning bioinformatics pipelines and training software parameters require sequencing data with known ground truth, which are actually difficult to get from real sequencing data. Particularly, for those applications of detecting low frequency variations (like ctDNA sequencing), it is hard to tell whether a called variation is a true positive, or a false positive caused by errors from sequencing or other processes. In these cases, simulated data with configured variations can be used to troubleshoot and validate bioinformatics programs. Although lots of next generation sequencing simulators have already been developed, most of them lack of capability to simulate lots of practical features, such like target capturing sequencing, copy number variations, gene fusions, amplification bias and sequencing errors. In this paper, we will present SeqMaker, a modern NGS simulator with capability to simulate different kinds of variations, with amplification bias and sequencing errors integrated. Target capturing sequencing is simply supported by using a capturing panel description file, other characteristics like sequencing error rate, average duplication level, DNA template length distribution and quality distribution can be easily configured with a simple JSON format profile file. With the integration sequencing errors and amplification bias, SeqMaker is able to simulate more real next generation sequencing data. The configurable variants and capturing regions make SeqMaker very useful to generate data for training bioinformatics pipelines for applications like somatic mutation calling.

Point-based algorithms are a class of approximate methods for Partially Observable Markov Decision Processes (POMDPs). They do backup operators on a belief set only. This paper will propose a preprocessing method for point-based algorithms (PPBA). This method preprocesses each sampled belief point, and before generating alpha-vectors it estimates which action and alpha-vectors to be selected first, in so doing repeated computing is eliminated. Base-alpha is also defined in this paper, which cancels meaningless computing with sparseness of problem.

The imbalance of dataset will directly affect the precision of classifier. PC4.5, an improved C4.5 algorithm is proposed. The experiments in MIT dataset indicate that PC4.5 is effective on imbalanced dataset and the scale of the decision tree could be reduced.

This paper focuses on how to automatically determine the suitable clustering number in image segmentation and designs an algorithm of CANA using spectral clustering. Experiment results indicate that ACNA can provide superior performance. An application sample in image punching is introduced

An illumination invariant face recognition method based on neural network ensemble architecture is proposed. Given a face image with an arbitrary illumination direction, it can complete recognition in a uniform way with high performance without knowing or estimating the illumination direction. Experimental result shows that the recognition ratio of the ensemble architecture is higher than the conventional approach that uses a single neural network to recognize faces of a specific illumination direction.

This work presents a texture based image retrieval method, called RAH, in the frequency domain. In RAH, texture features are represented as power spectral histograms of images. RAH mainly consists of two parts: the extraction of texture features based on the histogram of image power spectral in the frequency domain and the similarity measurement function based on the texture features. The experimental results indicate that RAH outperforms the traditional cooccurrence matrix texture representation.

Aiming at the incipient fault detection of power transformer, the paper proposes a novel fuzzy classification by evolutionary neural network. The method models the membership fuctions of all fuzzy sets by utilizing a three-layer feedforward neural network, and trains a group of neural networks by combining the modified Evolutionary Strategy with Levenberg-Marquardt optimization method in order to accelerate convergence and avoid falling into local minima. Thus each trained neural network denotes an "expert" model. The classification results obtained from all "expert" models are integrated according to the absolute-majority-voting rule. A lot of samples are tested, and the testing results demonstrate that the novel method is much better in neural network structure, classification accuracy, generalization capability, fault-tolerance ability and robustness that then other traditional methods.

Abstract This paper introduces valuation structures associated with preferential models. Based on KLM valuation structures, we present a canonical approach to obtain injective preferential models for any preferential relation satisfying the property INJ, and give uniform proofs of representation theorems for injective preferential relations appeared in the literature. In particular, we show that, in any propositional language (finite or infinite), a preferential inference relation satisfies INJ if and only if it can be represented by a standard preferential model. This conclusion generalizes the result obtained by Freund. In addition, we prove that, when the language is finite, our framework is sufficient to establish a representation theorem for any injective relation.

A universal fault instance model, which aims to solve problems existing in the present technology of fault diagnosis, such as the lack of universality, the difficulty in the use of real time systems and the dilemma of stability and plasticity, is proposed. An experiment demonstrates that the FANNC used can successfully settle the problems mentioned above by its effective incremental ability and processing new input patterns via one round learning.

In this paper, a statistics based approach named STARE (statistics-based rule extraction) that is designed to extract symbolic rules from trained neural networks is proposed. STARE deals with continuous attributes in a unique way so that not only different attributes could be discretized to different number of clusters but also unnecessary discretization could be avoided. STARE introduces statistics to the generation and evaluation of priority rules that have concise appearance. Since it is independent of the network architectures and training algorithms, STARE could be applied to diversified neural classifiers. Experimental results show that rules extracted via STARE are comprehensible, compact and accurate.

Neural network technology has not been fully utilised in data mining. There are two reasons for this. Firstly, most neural algorithms need long-term training, and cannot perform incremental learning. Secondly, the knowledge learned by neural networks is concealed within a large quantity of connections. We have develop a neural network method to mine typhoon knowledge which overcomes those two obstacles. Experimental results show that our method shows considerable promise.

NeedlePaint-a new generation of intelligent punching environment for computerized embroidery is introduced in the paper. Its systems organization, data structure and implementation techniques are described in great detail. Computer software techniques such as image processing, computer-aided design and artificial intelligence etc., rich embroidery knowledge and rules, and highly efficient inference mechanism are adopted in NeedlePaint. Various input methods for original designs are available and stitches are organized automatically. Both integrity and automaticity of embroidery punching ranging from original designs inputting to image processing, stitch organizing, stitch optimizing and data transforming are covered in NeedlePaint. As a result, the quality and efficiency of embroidery punching are improved greatly.>

This paper presents a knowledge based model description language KBMDL. It is taken as the basis of NUIDSS, an intelligent decision support system. Due to the flexible connection with a knowledge base, the language not only enhances the construction and the management of the model base, but also has the capability of both quantitative and qualitative analysis. The other features include graphic description and interface to model, data file and database. Based on KBMDL, semi-structured and non-structured problems are decomposed as various cooperative models where the relationships are contained in the domain knowledge base. This provides efficient support for decision making.>