dimensionality reduction

Exploring Healthy Neurocognitive Ageing with Deep Learning Interpretability Methods

This study uses deep learning interpretability methods on resting-state fMRI data to show how functional brain networks reorganize with age and relate to cognitive performance.

Sparse Linear Algebra Accelerates Genotype Representation Graph Computation at Biobank Scale

This paper introduces Mikado, a method using sparse linear algebra to accelerate genotype representation graph computations, significantly improving speed over existing tools on large biobank datasets.

Machine learning on subcortical brain features: A study of sample size efficiency for neurodegenerative disease classification

This study evaluates how sample size affects machine learning performance in classifying dementia stages using subcortical brain features from 2,511 ADNI samples.

Gravlax: an annotation-independent molecular evidence archive for single-cell RNA-seq

Gravlax archives single-cell RNA-seq data in a compact format that preserves molecular evidence, enabling reanalysis under new annotations and discovery of unannotated features.

Code-Multiplexed Multi-Frequency Impedance Cytometry with a Unified Deep-Unfolding Network

This paper develops a deep-unfolding network for code-multiplexed, multi-frequency impedance cytometry to resolve signal overlaps and enable label-free single-cell analysis.

CUBE: Multimodal Representation Learning Reveals Biological Structure Across Histomorphology, Spatial Protein Phenotypes, and Transcriptome-Associated Signals

CUBE integrates spatial protein and transcriptomic data via histology, creating a multimodal representation that captures biological structure from incompletely paired data.

Neural Architectures of Slow and Fast Dynamics in the Human Brain

The paper identifies distinct fast and slow temporal components in human brain activity using SPLIT on intracranial EEG data, showing they follow different organizational principles.

Mapping Gene Expression to an Interpretable Semantic Space

The paper introduces MESIC, a method that maps gene expression data into an interpretable semantic space using gene annotations, enabling biological interpretation of clusters and outliers.

Time-Series Foundation Models for Cognitive Workload Classification using Eye-Tracking Data

This study evaluates two time-series foundation models for cognitive workload classification from eye-tracking data, showing better generalization to unseen individuals than task-specific models.

Spatially resolved multimodal hallmarks of response to neoadjuvant immunotherapies in the melanoma ecosystem in 2D and 3D

The paper analyzes the spatial molecular architecture of melanoma tumors under different immunotherapy regimens and identifies biomarkers predicting response to treatment.

A Hybrid Residual-Swin Transformer Design with Attention for Prostate Cancer Segmentation

The paper introduces RSAUNet, a deep learning model for prostate cancer segmentation in MRI scans, achieving high Dice and Jaccard scores.

Independent noise realizations enable morphologically agnostic image reconstruction in single-photon-sensitive microscopy

This paper introduces a morphology-agnostic regularization framework for image deconvolution in single-photon-sensitive microscopy, eliminating semi-convergence and improving reconstruction quality.

Interrogating contrastive learning embeddings for structure-based virtual screening: a case study on DrugCLIP

This paper evaluates DrugCLIP's contrastive learning embeddings for virtual screening, showing strong performance but limitations under realistic conditions.

An open field phenomics resource for multimodal maize yield prediction across divergent environments

Drone imagery from 356 flights in 19 Genomes to Fields maize environments; vegetation-index functional principal components complement genomic kernels, predicting yield of held-out hybrids at r up to 0.501.

Setting the SCENE for Interpretable Cell-Gene Embeddings in Single-Cell RNA-seq

This paper introduces SCENE, a probabilistic model for embedding cells and genes in scRNA-seq data, achieving state-of-the-art performance and interpretable visualization.

The core microbiome as a reproducible, data-driven abstraction, not a biological entity

The paper defines a core microbiome as a data-driven abstraction that preserves ecological information under dimensional reduction, showing it retains key patterns and functions despite low taxonomic diversity.

A Gene-Program Architecture of Mouse T cells

The paper introduces immgenT-GP, a gene-program framework that identifies 200 reproducible gene programs in mouse T cells, capturing lineage identity, activation states, and tissue location.

Division-Specific Organization of a Shared Functional Scaffold in the Early-Life Human Brain

This paper develops a fine-grained whole-brain functional parcellation framework for early human development and identifies a shared functional scaffold with division-specific organization.

Broadband backscattering confocal microscopy enables label-free 3D live cell nanoscale sensitive imaging

This paper introduces broadband backscattering confocal microscopy (BBCM) for label-free 3D live cell imaging with improved contrast and size sensitivity.

Divergent specializations for motion-driven representations in higher lateral and dorsal visual areas

The paper investigates how artificial neural networks trained on motion-related tasks develop representations that align with brain activity and support object categorization using motion cues.

Microglia modulate concussion biomarkers and cognitive recovery in male mice

This study shows microglia influence concussion recovery and identifies EV miRNA biomarkers affected by microglial presence.

Physics-aware resolution enhancement of soft X-ray tomography with measurement-supervised learning

This paper enhances the spatial resolution of soft X-ray tomography using physics-aware learning, improving structural fidelity and reducing radiation exposure.

Multiphoton tomographic fluorescence lifetime imaging microscopy -TomoFLIM

This paper introduces TomoFLIM, a high-speed multiphoton FLIM technique that enables rapid, accurate imaging of dynamic biological processes with compression ratios over 90%.

Towards foundation models that learn across biological scales

The paper introduces Xpressor, a framework for cross-scale learning in biology, improving cell-type prediction and embedding quality.

NOTE ON RHEIFORMES (AVES: PALAEOGNATHAE) FROM A QUATERNARY CAVE IN THE LAGOA SANTA KARST, EASTERN BRAZIL

The paper describes two Quaternary rheiform bones from a cave in the Lagoa Santa karst region, attributed to Rhea americana, extending the fossil record of the group in Brazil.

How to Catch a Blank Mind? Brain Similarities and Differences between Self- and Probe-Caught Mind Blanking

The paper compares brain activity during self-caught and probe-caught mind blanking events using fMRI, finding behavioral convergence but neural divergence in the dorsal anterior cingulate cortex.

White-matter-microstructure-informed whole-brain models reveal localized excitation-inhibition imbalance in schizophrenia

The paper develops white-matter-microstructure-informed whole-brain models to identify excitation-inhibition imbalance in schizophrenia, improving model performance and diagnostic prediction.

Stability-driven multi-omics integration for reproducible latent structure

This paper introduces a Stability-driven framework for multi-omics integration to identify reproducible latent structures in thyroid cancer data.

SVD-SN2N: Self-Inspired Noise2Noise Learning for Denoising Log-Compressed SVD-Filtered Ultrasound Imaging

SVD-SN2N improves denoising of SVD-filtered ultrasound images by converting multiplicative speckle to additive noise, enhancing SNR and vessel resolution without requiring clean references or raw data.

Brain deviation scores derived from normative modelling identify dimensions of psychopathology in children and adolescents

The paper uses normative modeling to derive brain deviation scores and identifies an emotion-dysregulation dimension in children and adolescents linked to psychiatric symptoms.