multiome

MINT Block: multivariate integration across independent studies to identify multi-omics signatures

MINT Block integrates multi-omics data across studies to identify generalisable signatures while accounting for study-specific variation, improving prediction accuracy.

Engineered regulatory states resolve context-dependent genetics in macular degeneration

The paper uses CRISPR activation to engineer regulatory states in RPE-1 cells, revealing hidden genetic effects in AMD by analyzing chromatin accessibility and transcriptional interactions.

Automated Segmentation and Tractography of Brainstem and Subcortical White Matter

The paper develops an automated pipeline for segmenting and parcellating brainstem and subcortical white matter pathways using diffusion MRI data.

An Open Test--Retest Dataset of Rapid Myelin Mapping Acquisitions

The paper introduces a multimodal MRI dataset to evaluate myelin-sensitive imaging methods across test-retest acquisitions and metrics.

BiomiX 3.0: A user-friendly platform for democratized multi-omics integration with graph-based learning.

BiomiX 3.0 is a multi-omics integration platform that introduces PRAMIGO, a supervised heterogeneous graph transformer, and benchmarks five methods on CLL and PTB datasets, showing that no single method captures all biologically relevant signals.

A spectral framework for measuring diversity in multiple sequence alignments

This paper introduces Leff, a spectral measure to quantify effective information in multiple sequence alignments, showing evolutionary constraints reduce sequence diversity in RNA and proteins.

Dual-targeted nanoparticles enable the ex vivo generation of cytotoxic and phagocytic CAR effector cells

This study develops dual-targeted lipid nanoparticles to enhance the ex vivo generation of CAR-T cells and CAR-monocytes, showing improved cytotoxic and phagocytic activity.

DeepSCENIC: transfer learning from sequence-to-function models enables causal gene regulatory network inference

DeepSCENIC uses transfer learning from sequence-to-function models to infer causal gene regulatory networks from single-cell multiome data.

Accelerated discovery of thermostable vaccines using data-efficient AI

This study uses AI to rapidly develop thermostable mRNA vaccines that maintain bioactivity at high temperatures and can be delivered via microneedle patches.

The Virtual Biotech: A Multi-Agent AI Framework for Therapeutic Discovery and Development

The Virtual Biotech uses AI agents to integrate multi-omic and clinical data for drug discovery, identifying genomic features linked to trial success and proposing therapeutic strategies.

Quantifying Uncertainty in Brain Age Predictions via Conformal Prediction

This paper introduces brain age intervals (BAIs) as a method to quantify uncertainty in brain age predictions using conformal prediction, showing stable coverage and highlighting the need for larger samples.

scPyviewer: a Python-native interactive viewer from AnnData single-cell data

scPyviewer provides a Python-native interactive viewer for AnnData single-cell data, matching R Shiny tools' features and outperforming them in speed and memory efficiency.

SCALE: Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction

A set-aware latent transport model predicts treated cell populations from unpaired controls, keeps perturbation-specific signal in CRISPR, drug and cytokine data, and guided a cytokine choice tested in three donors.

MIND the gap: methodological considerations and guidance for structural MRI similarity network analysis with MIND

The paper provides methodological guidance for using MIND, a structural MRI similarity metric, and demonstrates how input properties affect its accuracy using simulated and observational data.

A geometric anthropomorphic phantom for quantitative susceptibility mapping: accuracy and repeatability

This paper evaluates the accuracy and repeatability of quantitative susceptibility mapping using an anthropomorphic phantom, finding better performance at 3T than 7T.

A multi-b-value test-retest diffusion MRI brain dataset for model validation and reproducibility assessment

The paper introduces a densely sampled longitudinal diffusion MRI dataset for validating dMRI techniques and assessing reproducibility.

dioscRi enables transferable prediction of clinical outcomes in multi-parameter cytometry data

dioscRi improves transferability of deep learning models for cytometry data by integrating normalization, cell type hierarchies, and clinical outcome prediction.

CodonMamba: a foundation model for programmable mRNA coding sequence design

CodonMamba is a foundation model for mRNA coding sequence design that achieves state-of-the-art performance and enables programmable codon optimization through inference-time steering.

Testing the reliability of novel Voxel Placement approaches for Magnetic Resonance Spectroscopy

This study evaluates three voxel placement methods for MRS, finding that SSVR significantly improves reliability and reduces metabolite variability in challenging regions.

SpatialMOC: Accurate reconstruction of spatial multi-omics landscapes through cross-modality prediction

SpatialMOC reconstructs missing spatial multi-omics data by integrating spatial context and cross-modality learning, outperforming existing methods across multiple tissues and modalities.

From gHBfix to NBfix: Reweighting-Driven Refinement of Hydrogen-Bond Interactions in RNA Force Fields

This paper reparameterizes RNA force fields by replacing hydrogen-bond corrections with Lennard-Jones modifications, improving simulation accuracy without external potentials.

Identifying multi-omics biomarkers for ovarian cancer survival estimation

This paper develops a multi-omics machine learning framework to estimate ovarian cancer survival, identifying a 20-biomarker signature that improves prognostic accuracy.

DIVAS: an R package for identifying shared and individual variations of multiomics data

DIVAS identifies shared and individual variations in multiomics data, revealing partially shared patterns missed by existing methods.

Exploring the sensitivity limits of neuronal current imaging with MRI and MEG in the human brain

This paper evaluates the sensitivity of spin-lock fMRI for detecting neuronal magnetic fields in vivo, finding it insufficient compared to MEG and BOLD-fMRI.

Optimizing Network-Level TMS-fMRI: Benchmarking the TMS-Compatible Sushi MR Setup

The paper benchmarks a TMS-compatible Sushi MR setup for whole-brain fMRI, showing it matches a 64-channel reference in resting-state networks and improves task-fMRI with multi-echo combination.

Study design and rationale of Boxed-Breathing-Heart: a translational ex vivo study evaluating virus-mediated gene delivery for gene therapy in normothermic machine-perfused human hearts

The paper describes an ex vivo study using normothermic machine-perfused human hearts to evaluate AAV-mediated gene delivery for cardiac gene therapy.

Calcium-binding protein expression alone is insufficient to identify and classify GABAergic neurons in macaque cortex

The paper evaluates the use of calcium-binding proteins for classifying GABAergic neurons in macaque cortex and finds that this scheme is invalid due to high non-GABAergic expression and inability to distinguish subpopulations.

Automated Ventricle Assessment via Three-dimensional Anatomical Reconstruction (AVA-TAR): a computational toolkit for autonomous lateral ventricle assessment in preclinical hydrocephalus models

This paper develops a deep learning tool for automated segmentation and morphological analysis of lateral ventricles in rodent MRIs, achieving high accuracy and correlation with manual measurements.

PACMOS: an R package for Projection And Classification of Multi-Omic Samples

PACMOS projects query cancer samples into pretrained MOFA latent factor spaces for classification.

OMIDIENT: Multiomics Integration for Cancer by Dirichlet Auto-Encoder Networks

OMIDIENT is a multi-omics integration method that uses Dirichlet auto-encoders to improve clustering, classification, and data reconstruction across cancer types.