DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baselines in novelty and on-target performance.
3d equivariant diffusion for target-aware molecule generation and affinity prediction
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 10representative citing papers
Multigrid training accelerates convergence and improves generalization for receptor-conditioned 3D ligand generation by transferring parameters from coarse to fine graph and voxel resolutions.
GeoCoupling optimizes temporal couplings between modalities in biomolecular generative models and outperforms synchronous baselines on drug design and protein design tasks.
EDMolGPT generates molecules from low-resolution electron density for de novo structure-based drug design, claiming better performance than pocket-based methods on 101 targets.
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
Flow-Direct constructs a reusable non-parametric guidance field from the log-density ratio of base and target distributions using all accumulated reward samples for feedback-efficient guidance in flow models.
An SE(3)-equivariant transformer encodes 3D protein-ligand interactions via contrastive learning for zero-shot virtual screening, and these embeddings condition a multimodal chemical language model to autoregressively generate target-specific molecules with favorable predicted binding properties.
D-Flow applies multi-modality flow matching and a mirror-image data augmentation to generate D-peptides with 10.2% higher sequence identity and 24.31% top affinity on the PepMerge benchmark.
Hyformer jointly models molecule generation and property prediction via alternating attention and joint pre-training, showing synergistic gains in conditional sampling, OOD prediction, and a drug design case for antimicrobial peptides.
FTDiff applies GRPO-style RL fine-tuning and fast sampling to a time-free pretrained diffusion model to generate valid diverse high-quality molecules balancing multiple drug design objectives in SBDD.
citing papers explorer
-
DGLD: Domain-Gated Latent Diffusion for the Discovery of Novel Energetic Materials
DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baselines in novelty and on-target performance.
-
Multigrid Training for Molecular Generation using Graph Neural Networks
Multigrid training accelerates convergence and improves generalization for receptor-conditioned 3D ligand generation by transferring parameters from coarse to fine graph and voxel resolutions.
-
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
GeoCoupling optimizes temporal couplings between modalities in biomolecular generative models and outperforms synchronous baselines on drug design and protein design tasks.
-
From Holo Pockets to Electron Density: GPT-style Drug Design with Density
EDMolGPT generates molecules from low-resolution electron density for de novo structure-based drug design, claiming better performance than pocket-based methods on 101 targets.
-
Toward Better Geometric Representations for Molecule Generative Models
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
-
Flow-Direct: Feedback-Efficient and Reusable Guidance for Flow Models via Non-Parametric Guidance Field
Flow-Direct constructs a reusable non-parametric guidance field from the log-density ratio of base and target distributions using all accumulated reward samples for feedback-efficient guidance in flow models.
-
Structure-guided molecular design with contrastive 3D protein-ligand learning
An SE(3)-equivariant transformer encodes 3D protein-ligand interactions via contrastive learning for zero-shot virtual screening, and these embeddings condition a multimodal chemical language model to autoregressively generate target-specific molecules with favorable predicted binding properties.
-
D-Flow: Multi-modality Flow Matching for D-peptide Design
D-Flow applies multi-modality flow matching and a mirror-image data augmentation to generate D-peptides with 10.2% higher sequence identity and 24.31% top affinity on the PepMerge benchmark.
-
Synergistic Benefits of Joint Molecule Generation and Property Prediction
Hyformer jointly models molecule generation and property prediction via alternating attention and joint pre-training, showing synergistic gains in conditional sampling, OOD prediction, and a drug design case for antimicrobial peptides.
-
Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Sampling
FTDiff applies GRPO-style RL fine-tuning and fast sampling to a time-free pretrained diffusion model to generate valid diverse high-quality molecules balancing multiple drug design objectives in SBDD.