diffusion model

Impact of gene selection criteria on transcriptomic ontology-based point of departure estimates

The paper evaluates how gene selection criteria affect transcriptomic-based point of departure estimates in toxicology using rat kidney and liver data.

A General Single-Cell Analysis Framework via Conditional Diffusion Generative Models

This paper introduces a general single-cell analysis framework using conditional diffusion models, showing competitive performance across tasks with added flexibility via prior information.

Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom

This paper introduces RFAA and RFdiffusionAA, models that can predict and design complex biomolecular assemblies including proteins, nucleic acids, small molecules, and covalent modifications.

Glycolytic oscillations under periodic drivings

This study examines how periodic glucose injection affects glycolytic oscillations using a dynamical systems approach, revealing entrainment and chaotic behavior under specific driving conditions.

Reviving collapsed networks from a single species: the importance of trait variation and network architecture

The paper shows that perturbing a single species can revive collapsed mutualistic networks, even under unfavorable conditions, by leveraging network architecture and trait variation.

Generative Diffusion Models for Antibody Design, Docking, and Optimization

This paper introduces a diffusion model-based pipeline for antibody design and optimization, achieving high performance in structure and sequence design and docking, validated by improved binding to flaviviruses.

Protein generation with evolutionary diffusion: sequence is all you need

This paper introduces EvoDiff, a diffusion model that generates diverse, high-fidelity proteins in sequence space, overcoming limitations of structure-based models.

The floral development of the allotetraploid Coffea arabica L. correlates with a small RNA dynamic reprogramming.

The paper analyzes small RNA dynamics during floral development in Coffea arabica to identify stage-specific regulatory mechanisms affecting flower development and ripening.

PRO-LDM: Protein Sequence Generation with a Conditional Latent Diffusion Model

PRO-LDM generates protein sequences with tailored properties using a conditional latent diffusion model, enhancing diversity and design fidelity.

Advanced image generation for cancer using diffusion models

This study uses diffusion models to generate medical images, including brain MRI and X-rays, demonstrating their ability to capture oncology-specific features while preserving patient anonymity.

A conditional protein diffusion model generates artificial programmable endonuclease sequences with enhanced activity

This paper introduces CPDiffusion, a conditional protein diffusion model that generates artificial endonuclease sequences with enhanced activity without labeled data.

In vivo Mapping of Cellular Resolution Neuropathology in Brain Ischemia by Diffusion MRI

This paper introduces tDKI to map cellular pathology in brain ischemia, showing it detects changes in cell morphology and membrane permeability in vivo.

Adaptation of the Spalax galili transcriptome to life under hypoxia may hold a key to a complex phenotype including longevity and cancer resistance

This study compares transcriptomic responses to hypoxia in Spalax and rat, identifying gene expression patterns linked to longevity and cancer resistance.

EMDiffuse: a diffusion-based deep learning method augmenting ultrastructural imaging and volume electron microscopy

EMDiffuse enhances volume electron microscopy by using diffusion models to improve resolution and enable isotropic reconstruction of large biological volumes.

Broadly applicable and accurate protein design by integrating structure prediction networks and diffusion generative models

Fine-tuning RoseTTAFold as a diffusion denoiser gives RFdiffusion, a general protein backbone generator; a designed influenza haemagglutinin binder matched its model by cryo-EM.

Travelling waves due to negative plant-soil feedbacks in a model including tree life-stages

This paper develops a reaction-diffusion-ODE model to show that strong negative plant-soil feedback can produce travelling wave solutions consistent with the Janzen-Connell hypothesis.

High-resolution image reconstruction with latent diffusion models from human brain activity

This paper reconstructs high-resolution images from human brain activity using a latent diffusion model, showing high fidelity without additional training.

An all-atom protein generative model

This paper introduces an all-atom diffusion model for protein structure generation that co-designs structure and sequence, producing high-quality proteins with accurate sidechain behavior.

Fluctuations in auxin levels depend upon synchronicity of cell divisions in a one-dimensional model of auxin transport

This paper shows that auxin fluctuations in plant roots arise from asynchronous cell divisions, not periodic signals, and that synchronized divisions can lead to stable oscillations.

Joint Generation of Protein Sequence and Structure with RoseTTAFold Sequence Space Diffusion

ProteinGenerator uses a diffusion model based on RoseTTAFold to generate protein sequences and structures simultaneously, validated for functional properties and structural accuracy.

ProteinSGM: Score-based generative modeling for de novo protein design

This paper introduces ProteinSGM, a score-based diffusion model for de novo protein design, showing it can generate native-like structures and perform conditional design.

Chronic alcohol consumption dysregulates innate immune response to SARS-CoV-2 in the lung

This study shows chronic alcohol consumption reduces antiviral cytokine induction and disrupts TLR signaling in lung cells from humans and rhesus macaques infected with SARS-CoV-2.

The Power of Two: integrating deep diffusion models and variational autoencoders for single-cell transcriptomics analysis

This paper introduces scVAEDer, a deep-learning model combining variational autoencoders and diffusion models to generate meaningful embeddings for single-cell transcriptomics data, enabling data generation, perturbation prediction, and regulator detection.

Dynamical modeling reveals RNA decay mediates the effect of matrix stiffness on aged muscle stem cell fate

This study shows that matrix stiffness affects aged muscle stem cell self-renewal through RNA decay dynamics, which can be modulated by young matrix environments.

Phyllotaxis as a dynamical system

The paper explains the prevalence of Fibonacci spirals in phyllotaxis by showing they are a form of symmetry, while other spirals like Lucas are developmental errors.

A dual diffusion model enables 3D binding bioactive molecule generation and lead optimization given target pockets

This paper introduces PMDM, a dual diffusion model for generating 3D bioactive molecules and optimizing leads for specific protein targets.

FedDP: Secure Federated Learning for Disease Prediction with Imbalanced Genetic Data

FedDP improves disease prediction from imbalanced genetic data by combining federated learning with differential privacy and a weighted minmax loss.

RNA-to-image multi-cancer synthesis using cascaded diffusion models

This paper introduces RNA-Cascaded-Diffusion-Model to generate synthetic whole-slide image tiles from RNA-Seq data, improving machine learning model performance in low-data settings.

Knowledge "installed" diffusion model predicts the geometry of actin cytoskeleton from cell morphology

The paper introduces a diffusion model that predicts stress fiber distribution from cell morphology, achieving 79.3% overlap with experimental data and revealing geometric relationships.

Structure-based discovery of inhibitors of the SARS-CoV-2 Nsp14 N7-methyltransferase

The paper identifies multiple inhibitors of SARS-CoV-2 Nsp14 N7-methyltransferase using docking strategies, with some showing sub-10 M potency and selectivity.