deep learning

Frequency-Dependent Structural Responses of Amyloid-β Fibrils to Terahertz Pulses: A Nonequilibrium Molecular Dynamics Study

This study uses nonequilibrium molecular dynamics to show frequency-dependent structural changes in amyloid fibrils under terahertz pulses, identifying two electric-field thresholds for disruption.

A Dynamic Stem Cell State Links Environmental Cues to Skeletal and Regenerative Fates

The paper identifies a dynamic stem cell state marked by Panx3 that responds to environmental cues and enables regeneration in aged and osteoarthritic joints.

Agentic AI enables cell segmentation-free cell-type inference and cell-type-guided cell segmentation in spatial transcriptomics

This paper introduces SSAF-T, a segmentation-free framework for cell-type inference in spatial transcriptomics that avoids cell segmentation and enables accurate cell-type-guided segmentation.

Label-free flow operators and stability operators from single-cell time courses: what local dynamical operators can and cannot identify

This paper introduces scJDO2, a method to separate score and flow operators from single-cell time courses, evaluating their ability to identify unstable cells and bifurcations in hematopoiesis.

DisCell: Separating Spillover from Niche Response in Spatial Transcriptomics

DisCell identifies and separates spillover from niche responses in spatial transcriptomics data, confirming a previously reported finding about esophageal cancer cells.

Maximum Likelihood Localization Maps

This paper introduces a non-iterative method to create molecular probability maps from single-molecule localization data, preserving positional likelihood without coordinate-based rendering.

Human organoid screen links transient translational modulation to progenitor progression in corticogenesis

The paper screens human cortical organoids with small molecules to identify translational modulators affecting progenitor progression in corticogenesis, finding Emetine promotes neuronal differentiation.

Single-cell multi-omics identify OTP and NOVA1 as regulators of leptin action in hypothalamic feeding circuits

This study uses single-cell multi-omics to identify OTP and NOVA1 as key regulators of leptin action in hypothalamic feeding circuits, revealing cell-type-specific transcriptional and regulatory changes.

Epigenome-informed Polymer Modeling Reveals Chromosome Folding Landscapes across Distinct Genetic and Epigenetic Contexts

This study uses epigenome-informed polymer modeling to generate chromosomal conformational ensembles from epigenomic data, revealing how genetic and epigenetic contexts shape chromosome folding landscapes.

TailEnrich enables discovery of dysregulated genes through disease sample enrichment testing

TailEnrich identifies dysregulated genes in patient subsets by testing expression distribution tails, outperforming DESeq2 and edgeR in simulated data and uncovering novel genes in Alzheimer's disease.

Residual barcode-like sequences and barcode-associated artifacts after Dorado and Barbell preprocessing of metagenomic reads

The paper evaluates Dorado and Barbell preprocessing tools for metagenomic reads, finding Barbell reduces barcode-like sequences more effectively while retaining most reads.

Hybrid RY-mers increase aDNA alignment sensitivity

This paper introduces hybrid RY-mers to improve aDNA alignment sensitivity and efficiency, showing higher accuracy and reduced runtime compared to existing methods.

Visual surfaceomics reveals the substrate-scavenging cell surface of Asgard archaea

This study identifies surface proteins in Asgard archaea using visual surfaceomics, revealing a peptidophilic cell surface involved in peptide capture and symbiotic interactions.

CauloBrowser 2.0: an AI powered update

CauloBrowser 2.0 updates the systems-biology database for Caulobacter crescentus with AI-powered tools for querying and visualizing experimental data.

LinearRaccess: linear-time approximation of RNA accessibility without base-pair span limits

LinearRaccess computes RNA accessibility for long windows in linear time without base-pair span limits, achieving high accuracy and efficiency.

Development of a Pan-Proteome Multi-Epitope Vaccine Candidate Against Nipah Virus Using Reverse Vaccinology and Immunoinformatics Approaches

This paper designs a multi-epitope vaccine candidate against Nipah virus using immunoinformatics and reverse vaccinology, identifying VC033_V6_BD_L03 as a lead candidate with high global and regional population coverage.

Individual differences reveal shared computational structure in perceptual decision-making

The paper uses population-level individual differences to discover shared computational components in perceptual decision-making, revealing a six-dimensional structure across datasets.

Multimodal cellular context enables molecular phenotyping from single-molecule trajectories

The paper introduces MIST, a framework that integrates single-molecule trajectory data with cellular context to improve molecular phenotyping in E. coli.

Real-time detection of N2 and N3 sleep from scalp and intracranial EEG

This paper develops a real-time sleep stage classifier for N2 and N3 sleep using scalp and intracranial EEG, showing high accuracy and informing stimulation timing.

QRAFT: Scaling coalescent-based species tree inference to one million taxa

QRAFT efficiently infers species trees for up to a million taxa using coalescent-based methods, outperforming existing tools in speed and memory usage.

Probing EEG Foundation Model Attention Maps for Lightweight Interpretable Emotion Recognition

This paper proposes a lightweight, interpretable method for emotion recognition using EEG foundation models by analyzing attention maps, achieving competitive performance with fewer computations.

Hierarchical Temporal Transformer for Cancer Grade Prediction and Cross-Cancer Transfer Learning from Pathology Reports

This paper introduces a hierarchical temporal transformer for cancer grade prediction from pathology reports, showing improved performance across cancer types and using visit timing when identifiable.

Learning Strand-Equivariant Tokenizations of DNA with MirrorDNA

This paper introduces MirrorDNA, a DNA language model with a strand-equivariant tokenizer that improves prediction consistency across DNA strands.

MOCHI enables systematic identification of candidate independent intronic transcriptional signals from short-read RNA-seq data

MOCHI identifies candidate independent intronic transcripts from short-read RNA-seq data, revealing novel transcripts associated with cancer survival.

Hub labeling makes exact distance calculation practical for large human pangenome graphs

The paper introduces a hub labeling method to reduce the space required for distance indexing in large pangenome graphs, improving query support and reducing storage needs.

A biomimetic deep encoder for auditory restoration by cortical stimulation

This paper introduces Braincodec, a deep encoder that improves sound transmission via cortical stimulation, achieving high-fidelity sound reconstruction and matching non-implanted mice in sound discrimination.

Coarse-graining genome-scale metabolic models for dynamic, multi-scale simulations of Pseudomonas aeruginosa in gel environments

This paper introduces GEM-CM, a computational framework that couples reaction-diffusion models with genome-scale metabolic models to simulate Pseudomonas aeruginosa growth and pyocyanin production in agar gels.

MitoDecode: quantitative phenotypic decoding of mitochondrial stress states from fluorescence images

MitoDecode assesses mitochondrial stress types and severity from fluorescence images without segmentation, showing adaptability across cell types and stress conditions.

Generative Models for Novel Enzymatic Reactions: How Far Do They Go?

This paper evaluates generative models for predicting novel enzymatic reactions, finding they can generate correct reactions for 25% of test cases and improve over existing methods.

Phase-locked dual-band vibration bursts strengthen anti-kindling by vibrotactile coordinated reset stimulation in a spiking network model

The paper shows that a dual-band vibration burst improves anti-kindling in a spiking network model compared to single-frequency stimulation.