diffusion model

A Diffusion-Based Autoencoder for Learning Patient-Level Representations from Single-Cell Data

This paper introduces scSet, a diffusion-based autoencoder that learns patient-level representations from single-cell data, outperforming existing methods in clinical prediction with limited labeled data.

Temperature-Induced Bifurcations and Timescale Warping in the Hodgkin-Huxley Model: Dynamical Systems Insights into Temperature Modulation of Neuronal Excitability and Action Potential Morphology

This study uses the Hodgkin-Huxley model to analyze how temperature changes affect neuronal firing patterns and excitability through bifurcation analysis.

Structure-based Generation of a Secondary Nucleation Inhibitor in alpha-Synuclein Aggregation Using a Conditional Diffusion Model

The paper uses a conditional diffusion model to design a small molecule inhibitor of secondary nucleation in alpha-synuclein aggregation, showing it effectively inhibits fibril proliferation.

Deep learning-based joint sequence-structure de novo membrane protein design

This paper introduces TMDiffusion, a deep learning model for designing membrane proteins, achieving high experimental success and accurate structural predictions.

PXDesign: Fast, Modular, and Accurate De Novo Design of Protein Binders

PXDesign achieves high hit rates for protein binder design by combining generative models and filtering strategies, validated experimentally and made publicly available.

Accelerating Biomolecular Modeling with AtomWorks andRF3

AtomWorks, a modular atom-level data framework, trains structure prediction and design models; the resulting RF3 improves chirality handling and performs between AF3 and Boltz.

Geometric Characterization of Pediatric Multiple Sclerosis Lesion Morphology: A Cross-Sectional and Temporal Analysis using Differential Geometry

This study uses differential geometry to analyze lesion shapes in pediatric MS patients, identifying reproducible morphotypes and tracking their progression over time.

Deep Generative Models for Discrete Genotype Simulation

This study evaluates deep generative models for simulating discrete genotype data, showing their ability to capture genetic patterns and preserve genotype-phenotype associations.

Learning from B Cell Evolution: Adaptive Multi-Expert Diffusion for AntibodyDesign via Online Optimization

This paper introduces an adaptive diffusion model for antibody design inspired by B cell evolution, showing improved optimization across diverse targets.

De novo design and structure of a peptide-centric TCR mimic binding module

A de novo four-helix bundle designed with RFdiffusion and ProteinMPNN binds NY-ESO-1/HLA-A*02 at Kd 9.5 nM, with a 2.05 Å crystal structure and peptide-focused docking.

Spatial Needleman-Wunsch: A Deterministic Dynamic Programming Framework for Molecular Docking

This paper introduces a deterministic dynamic programming framework for molecular docking that improves reproducibility and interpretability compared to stochastic methods.

Causal disentanglement for single-cell representations and controllable counterfactual generation

CausCell improves explainability and controllability of single-cell data through causal disentanglement learning and counterfactual generation.

Expression of LTR and LINE1 transposable elements defines atypical teratoid/rhabdoid tumor subtypes

This study identifies distinct TE transcription profiles in ATRT subtypes, revealing unique patterns in ATRT-MYC that may inform new therapeutic strategies.

Equations describing semi-confluent cell growth (II) Colony formation on a flat surface

The paper develops a model for non-symmetrical multilayer cell growth on a solid plate, using ordinary differential equations to describe variable contact inhibition and colony formation kinetics.

De novo design of functionally diverse and druggable antimicrobial peptides by diffusion and multimodal deep learning

This paper introduces AMP-D3, a framework for designing diverse and druggable antimicrobial peptides using diffusion and multimodal deep learning, achieving high accuracy in prediction and validation.

On the design and stability of cancer adaptive therapy cycles: deterministic and stochastic models

This paper develops deterministic and stochastic models to analyze the design and stability of adaptive therapy cycles for cancer treatment.

TabSyM: A Generative Pipeline for Small Multi-Cohort Omics Tabular Data

TabSyM improves predictive modeling of small, high-dimensional biomedical datasets by generating synthetic data and aligning cross-cohort distributions.

AntiDIF: Accurate and Diverse Antibody Specific Inverse Folding with Discrete Diffusion

AntiDIF improves antibody inverse folding by increasing sequence diversity while maintaining high sequence recovery rates and structural accuracy.

Scalable emulation of protein equilibrium ensembles with generative deep learning

BioEmu, a diffusion model trained on structures, molecular dynamics trajectories, and stability assays, samples protein equilibrium ensembles and folding free energies within ~1 kcal/mol in GPU-hours.

Metalorian: De Novo Generation of Heavy Metal-Binding Peptides with Classifier-Guided Diffusion Sampling

Metalorian generates heavy metal-binding peptides using a diffusion model guided by a classifier, producing peptides with controlled specificity and reduced length compared to known proteins.

Ambient Proteins: Training Diffusion Models on Low Quality Structures

Treating low-confidence AlphaFold structures as noisy data at pLDDT-dependent diffusion times lets a 16.7M-parameter model generate long proteins with higher diversity, designability and novelty than Proteína.

Denoising 7T Structural MRI with Conditional Generative Diffusion Models

This paper introduces a conditional diffusion model to denoise 7T MRI scans, improving image quality and outperforming existing methods.

Visual-like 2D Geometric Template Diffusion for Boosting Single-Sequence Protein Structure Prediction

TDFold improves single-sequence protein structure prediction using a 2D geometric template diffusion method, outperforming existing models on homology-insufficient datasets and offering lower resource consumption and faster inference.

STRAND: Structure Refinement of RNA-Protein Complexes via Diffusion

STRAND improves RNA-protein complex backbone predictions using a diffusion model, building on existing tools like AlphaFold 3 and ProRNA3D-single.

Uncertainty-Aware Discrete Diffusion Improves Protein Design

This paper introduces an uncertainty-aware discrete diffusion model for protein design, improving sequence generation from 3D structures by incorporating position-specific uncertainty and pretrained models.

De Novo Structure-Based Design of TEM-171 β-Lactamase Protein Inhibitors Using Integrated Deep Learning and Multi-Scale Simulations to Combat Bacterial Resistance

This paper designs a protein inhibitor for TEM-171 β-lactamase using deep learning and simulations, showing high stability and binding affinity.

Improving diffusion-based protein backbone generation with global-geometry-aware latent encoding

This paper introduces TopoDiff, a diffusion-based framework for protein backbone generation that improves global geometry control and fold diversity through a structure encoder and latent sampler.

Frequency-Blended Diffusion Models for Synthetic Generation of Biologically Realistic Splice Site Sequences

This paper introduces a frequency-blended diffusion model to generate biologically realistic splice site sequences, showing improved motif conservation and model transferability.

ProtoBind-Diff: A Structure-Free Diffusion Language Model for Protein Sequence-Conditioned Ligand Design

ProtoBind-Diff generates novel, chemically valid ligands based on protein sequences without structural data, performing well in docking and binding affinity evaluations.

A Hyperbolic Discrete Diffusion 3D RNA Inverse Folding Model for functional RNA design

This paper introduces RIdiffusion, a hyperbolic diffusion model for 3D RNA inverse folding, which outperforms baselines in generating RNA sequences for target structures.