Genetics

Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation

Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported due to the omission of subtle findings. For example, prior studies show that cardiomegaly may be omitted from ICU chest X-ray reports when the imaging request is focused on monitoring support device ...

scMaize: A Single-Cell Foundation Model and Integrated Atlas for Maize

Single-cell transcriptomics has resolved cell type-specific gene expression in plants, yet maize still lacks an integrated reference and species-specific foundation models. We present scMaize, which combines scMaizeAtlas, an integrated atlas of 385,675 cells from 20 projects and 66 samples across seven tissues with hierarchical annotation, with two Transformer-based foundation models pretrained on...

In vitro and in silico characterization of competitive inhibition and repression of DUX4 target gene activation as a therapeutic approach for facioscapulohumeral muscular dystrophy (FSHD)

Facioscapulohumeral muscular dystrophy (FSHD) is a rare neuromuscular disease caused by aberrant re-expression of the embryonic transcription factor D...

Contrastive Regulatory Embeddings Attention Model for Differential Expression Prediction with Personalized Genomes: Insights and Challenges

Deep learning models applied to DNA sequences have achieved success in predicting gene expression, chromatin profiles, and variant pathogenicity. Howe...

iStructTab: Structured Feature Sequencing for Multimodal Learning of Image and Tabular Data

Multimodal learning of images and tabular data is often impaired by ineffective representations, resulting in redundancy, dispersion, and generalizati...

OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing

Instruction-based video editing (IVE) is an emerging field with broad applications, yet evaluating editing models remains challenging. Existing benchm...

Pervasive Backdoor Vulnerabilities in Genomic Foundation Models

Genomic foundation models are increasingly used to interpret and design DNA sequences, yet their susceptibility to training-data manipulation remains ...

AI-enabled simultaneous phenotyping of leaf vein and stomatal traits uncovers independent genetic control in maize

Leaves maintain hydraulic homeostasis during photosynthesis through the coordinated action of stomata, which regulate gas exchange and transpiration, ...

GoT-CD: Graph-of-Thoughts Causal Discovery and the Fragility of Post-hoc Path-Specific Fairness Audits

Causal discovery recovers directed structure from observational data and is increasingly used in clinical settings to support mechanism reasoning and ...

Machine Learning-based Prediction of the Long-term Stability of Chinese Hamster Ovary Cells due to Epigenetic Changes

Background: Chinese hamster ovary (CHO) cells are the main system for producing recombinant protein biopharmaceuticals, but are inherently unstable, a...

DNA-binding domain-aware classification enables systematic annotation of the regulatory genome

Defining the cis-regulatory code remains one of the central challenges of modern genomics, requiring the reliable association of transcription factor ...

Interpretable Machine Learning Model of Receptor Dynamics Reveals AT1R Allostery and a Negative Allosteric Modulator

Allosteric modulation of G protein-coupled receptors (GPCRs) offers major advantages in receptor selectivity and signaling control; yet systematic app...

Genome-scale prediction of context-specific synthetic lethality beyond protein interaction networks

Identifying synthetic lethal (SL) interactions offers a principled framework for discovering disease-specific therapeutic targets. However, current ma...

A sequence-to-function model to predict T7 transcription rates and redesign T7 expression systems with lowered production of immunogenic RNA byproducts

T7 RNA polymerase is widely used to produce RNA using a canonical T7 promoter; however, it will also bind to low-affinity sites to generate cryptic tr...

Two Sides of the Same Coin: Co-Evolving Search for Cross-Task Attacks on Vision-Language Models

Vision-language models (VLMs) exhibit strong generalization across multimodal tasks but remain vulnerable to adversarial perturbations. Existing attac...

Harnessing Adversarial Distillation to Customise Debiased, Disease-Specific Pathology Foundation Models for Breast Cancer

Pathology foundation models (PFMs) provide strong tissue representations and have become central to digital pathology. However, deployment in disease-...

Detailed curation of biological samples and experimental designs for genomics using LLM-supported agentic workflows

We describe an automated software tool to accomplish data curation tasks previously performed by humans for the Gemma genomics data re-analysis resour...

Benchmarking Deep Learning Predictions of Mutation-Induced Fold Switching

Many proteins are known to adopt multiple distinct folded states which are often associated with key functional behavior. A predictive understanding o...

SPINDLE: Unlocking protein dynamics from single-field NMR relaxation data using a deep learning ensemble.

A protein's function is derived from its three-dimensional structure and the motions of the atoms about that structure. The detailed characterization ...

CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation

LiDAR scene flow estimation has settled into a monoculture: nearly all recent methods share the same feed-forward architecture and the same family of ...