Manod: A multi-modal anomaly detection framework for distributed system.

Distributed infrastructure has been widely deployed in large-scale software systems in recent years to meet the growing demand for applications, due to its scalability and resource-sharing characteristics. Accurately predicting and identifying anomalies is critical to ensure the stable and reliable running of complex distributed systems. System abnormalities can often be reflected through key performance indicators and logs.

CSFformer: Redefining multi-channel time series analysis with cross-scale fusion Transformer.

Current Transformer models with channel independence (CI) have made tremendous achievements in time series data analysis. However, the CI methods suffer from short-term fluctuations with intra-channel noise and long-term trend extraction. The fixed receptive field of CI models struggles with capturing multi-scale temporal features within each channel.

Integrating genomic and pathological characteristics to enhance prognostic precision in advanced NSCLC.

Although immunotherapy combined with chemotherapy (ICT) is the standard treatment for advanced non-small cell lung cancer (NSCLC), identification of reliable prognostic biomarkers remains challenging. In this multicenter study, we performed next-generation sequencing of tumor samples from 162 patients receiving first-line ICT at the Chinese PLA General Hospital and collected their pathological image information. First, we established a model to predict the risk of tumor progression based on genomic characteristics.

Soft graph clustering for single-cell RNA sequencing data.

Background: Clustering analysis is fundamental in single-cell RNA sequencing (scRNA-seq) data analysis for elucidating cellular heterogeneity and diversity. Recent graph-based scRNA-seq clustering methods, particularly graph neural networks (GNNs), have significantly improved in tackling the challenges of high-dimension, high-sparsity, and frequent dropout events that lead to ambiguous cell population boundaries. However, one major challenge for GNN-based methods is their reliance on hard graph constructions derived from similarity matrices.

In-depth review of colloidal and interfacial fundamentals in fracturing development of deep coal seam methane.

Deep coal seam methane represents a significant global energy resource, but its efficient extraction requires specialized fracturing technologies that address the unique characteristics of coal formations. This review provides a comprehensive examination of the fundamental colloidal and interfacial phenomena governing fracturing processes in deep coal seam methane development, with particular emphasis on the behavior of methane-water interfaces, the colloidal science of fracturing fluids, and transport mechanisms at the pore scale. The distinct properties of methane-water interfaces under confinement in coal micropores are analyzed, revealing how surface heterogeneity, temperature, pressure, and salinity influence interfacial tension, wettability, and fluid distribution.

PhyloScape: interactive and scalable visualization platform for phylogenetic trees.

Background: With the accumulation of phylogenomic data and the growing demand for bioinformatics analyses, it has become increasingly important and complex to construct evolutionary relationships for different research purposes. Therefore, the ability to support multiple scenarios has become an essential need for phylogenetic visualization.

Results: In this study, we present PhyloScape, a web-based application for interactive visualization of phylogenetic trees that can be used stand-alone or as a toolkit deployed on the users' website.

A Generalizable Machine Learning Framework for Identifying Sustainable Multi-Ion Garnet Electrolytes.

Lithium-ion (Li-ion) solid-state batteries (SSBs) are highly regarded for their exceptional energy density and prolonged operational lifespan. However, concerns regarding their sustainability have arisen due to the uneven global distribution of Li resources and Li's relatively low abundance in the Earth's crust. Consequently, significant interest has shifted toward developing alternative SSBs, such as sodium (Na), magnesium (Mg) and Aluminum (Al)-ion batteries.

FemXpress: Systematic Analysis of X Chromosome Inactivation Heterogeneity in Female Single-Cell RNA-Seq Samples.

X chromosome inactivation (XCI) is crucial for balancing X-linked gene dosage in female cells by randomly silencing one X chromosome during early embryogenesis. However, accurately classifying cells based on the parental origin of the inactivated X chromosome in single-cell samples remains challenging. Here we present FemXpress, a computational tool leveraging X-linked single nucleotide polymorphisms (SNPs) to group cells based on the origin of the inactivated X chromosome in female single-cell RNA sequencing (scRNA-Seq) data.

Breast cancer homologous recombination deficiency prediction from pathological images with a sufficient and representative Transformer.

Homologous recombination deficiency (HRD) has been recognized as a key biomarker for poly-ADP ribose polymerase inhibitors (PARPi) and platinum-based chemotherapy in breast cancer (BC). HRD prediction typically relies on molecular biology assays, which have a high turnaround time, and cost. In contrast, tissue sections stained with hematoxylin and eosin (H&E) are ubiquitously available.

CODC-S: A quality-controlled global ocean salinity profiles dataset.

Changes in the global ocean salinity reflect the evolution of the global hydrological cycle. These secular changes are assessed using seawater salinity profiles obtained during the past ~80 years. Here, we introduce a new global ocean salinity profiles database named CODC-S (the Chinese Academy of Science (CAS) Oceanography Data Center - Salinity component), which encompasses over 11 million in-situ salinity profiles from 1940 to 2023 obtained by means of several instrument types.

Folding Transition of Single Semiflexible Polymers Controlled by the Range of Intermonomer Attractions.

Semiflexible polymer folding has been employed by nature for protein folding and by researchers for designing smart materials and nanomachines. Hence, it is of great importance to understand and control semiflexible polymer folding. Here, we find that the range of intermonomer attraction, or the width of attraction (), can significantly control the structural phase diagram of a semiflexible polymer through entropic effects.

Association of electrolytes and complete blood count in adolescent depression with and without psychotic symptoms.

Background: The aim of this study was to investigate physiological differences in electrolytes and complete blood counts in adolescent patients with depression with and without psychotic symptoms. By comparing baseline data in adolescent patients, it will provide more comprehensive information for individualised diagnosis and treatment of depression.

Methods: Clinical baseline data of adolescent patients were collected, including information on gender, age, smoking history, and alcohol consumption history.

CPDP: Contrastive Protein-Drug Pre-Training for Novel Drug Discovery.

Novel drug discovery and repositioning remain critical challenges in biomedical research, requiring accurate prediction of drug-target interactions (DTIs). We propose the CPDP framework, which builds upon existing biomedical representation models and integrates contrastive learning with multi-dimensional representations of proteins and drugs to predict DTIs. By aligning the representation space, CPDP enables GNN-based methods to achieve zero-shot learning capabilities, allowing for accurate predictions of unseen drug data.

scCompass: An Integrated Multi-Species scRNA-seq Database for AI-Ready.

Emerging single-cell sequencing technology has generated large amounts of data, allowing analysis of cellular dynamics and gene regulation at the single-cell resolution. Advances in artificial intelligence enhance life sciences research by delivering critical insights and optimizing data analysis processes. However, inconsistent data processing quality and standards remain to be a major challenge.

Scalable intermediate-term earthquake forecasting with multimodal fusion neural networks.

Seismology is witnessing rapid growth in both the volume and variety of earthquake observational data, but current tools for effectively integrating these heterogeneous data remain limited. Here, we propose SafeNet, a scalable deep learning framework designed to address these challenges through the use of multimodal fusion neural networks. SafeNet integrates 282-dimensional seismic indicators from earthquake catalogs, capturing long-, medium-, and short-term seismic patterns, and associates seismic activity with geological information using integrated maps.

A secure visualization platform for pathogenic genome analysis with an accurate reference database.

Investigating the genetic and developmental characteristics, infection transmission attributes, and epidemiological trends of pathogens using genomic data represents the foundation for pathogen surveillance and is a crucial prerequisite for guaranteeing global health security. To meet the analytical demands of research relating to pathogen prevention and control, we designed a secure visualization system capable of pathogen genome assembly, annotation, species identification, sequence typing, antibiotic resistance and virulence analysis, genomic mobile element and transferable resistance gene annotation, and phylogenetic tree reconstruction. For highly pathogenic organisms requiring complete data protection, we have developed a secure computing tool that utilizes a trusted execution environment, is combined with blockchain and privacy computing technologies, and is specifically designed for nucleotide basic local alignment search tool (BLASTn) comparison analysis.

Sex disparities in the association between rare earth elements exposure and genetic mutation frequencies in lung cancer patients.

The ubiquitous use of rare earth elements (REEs) in modern living environments raised concern about their impact on human health. With the detrimental and beneficial effects of REEs reported by different studies, the genuine role of REEs in the human body remains a mystery. This study explored the association between REEs and genetic mutations in patients with lung adenocarcinoma (LUAD).

Carboxyl hybrid monolithic column in-tube solid-phase microextraction coupled with UPLC-QTRAP MS/MS for the determination of amphetamine-type stimulants.

A carboxyl functionalized organic-inorganic hybrid monolithic column (TMOS-co-CES) was applied as in-tube solid-phase microextraction (SPME) sorbent combining with ultra-performance liquid chromatography-triple quadrupole/linear ion trap mass spectrometer for separation and analyzation of seven typical amphetamine-type stimulants (ATSs), including amphetamine (AM), methamphetamine (MAM), cathinone, methcathinone, 3,4-methylenedioxyamphetamine, 3,4-methylenedioxymethamphetamine and 3,4-methylenedioxyethylamphetamine. The application potential of TMOS-co-CES material to ATSs was preliminarily confirmed by computational simulation by using cathinone as a representative. The influences of various SPME parameters and analytical performance were investigated systematically.

Tripartite interaction representation algorithm for crystal graph neural networks.

Driven by emerging research paradigms, the application of artificial intelligence models presents innovative tools for designing materials and optimizing their performance. In the field of materials science, there is a current research emphasis on exploring techniques for characterizing material structures to achieve precise descriptions. This paper proposes a crystal graph convolution neural network model that incorporates a tripartite interaction approach.

Scaling Laws for Protein Folding under Confinement.

Spatial confinement significantly affects protein folding. Without the confinement provided by chaperones, many proteins cannot fold correctly. However, the quantitative effect of confinement on protein folding remains elusive.

IIFS2.0: An Improved Incremental Feature Selection Method for Protein Sequence Processing Based on a Caching Strategy.

The purpose of feature selection in protein sequence recognition problems is to select the optimal feature set and use it as training input for classifiers and discover key sequence features of specific proteins. In the feature selection process, relevant features associated with the target task will be retained, and irrelevant and redundant features will be removed. Therefore, in an ideal state, a feature combination with smaller feature dimensions and higher performance indicators is desired.