Target context boosts performance in scarce-data regimes when fused properly via FiLM but degrades results under distribution shift, while standard molecular benchmarks suffer from severe leakage and trivial baselines.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.
Pre-training improves CLMs' encoding of molecular substructures especially in upper layers while fine-tuning selectively modifies task-relevant substructures more than others.
FlexMS is a new flexible benchmarking framework that lets researchers dynamically combine deep learning architectures and evaluate their mass spectrum prediction performance on public metabolomics datasets using multiple metrics and retrieval tasks.
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.
Adding Bertz index regression and MMFF94 strain penalty as auxiliary losses to a GINE GNN yields small but statistically significant OOD AUC improvements (up to +0.0066) on natural products when trained on drug-like molecules.
citing papers explorer
-
When Does Context Help? A Systematic Study of Target-Conditional Molecular Property Prediction
Target context boosts performance in scarce-data regimes when fused properly via FiLM but degrades results under distribution shift, while standard molecular benchmarks suffer from severe leakage and trivial baselines.
-
Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction
Chem-GMNet uses sphere-native embeddings, DualSKA attention, and SH-FFN layers to match or beat ChemBERTa-2 on MoleculeNet tasks with fewer parameters and sometimes no pretraining.
-
Probing Chemical Language Models: Effects of Pre-training and Fine-tuning
Pre-training improves CLMs' encoding of molecular substructures especially in upper layers while fine-tuning selectively modifies task-relevant substructures more than others.
-
FlexMS is a flexible framework for benchmarking deep learning-based mass spectrum prediction tools in metabolomics
FlexMS is a new flexible benchmarking framework that lets researchers dynamically combine deep learning architectures and evaluate their mass spectrum prediction performance on public metabolomics datasets using multiple metrics and retrieval tasks.
-
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.
-
Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter
Adding Bertz index regression and MMFF94 strain penalty as auxiliary losses to a GINE GNN yields small but statistically significant OOD AUC improvements (up to +0.0066) on natural products when trained on drug-like molecules.