SupSiam: Non-contrastive Auxiliary Loss for Learning from Molecular Conformers
We investigate Siamese networks for learning related embeddings for augmented samples of molecular conformers. We find that a non-contrastive (positive-pair only) auxiliary task aids in supervised training of Euclidean neural networks (E3NNs) and increases manifold smoothness (MS) around point-cloud geometries. We demonstrate this property for multiple drug-activity prediction tasks while maintaining relevant performance metrics, and propose an extension of MS to probabilistic and regression settings. We provide an analysis of representation collapse, finding substantial effects of task-weighting, latent dimension, and regularization. We expect the presented protocol to aid in the development of reliable E3NNs from molecular conformers, even for small-data drug discovery programs.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity PredictionDrug DiscoveryregressionSimilar Papers 제목 키워드 기반
Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on molecular graphs has shown promise, many e…
Representation LearningGraph Neural NetworkLearning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
Molecular chirality, a form of stereochemistry most often describing relative spatial arrangements of bonded neighbors around tetrahedral carbon centers, influences the set of 3D conformers accessible to the molecule wit…
Contrastive LearningData AugmentationMolecular Property PredictionProperty Prediction+1GEOM: Energy-annotated molecular conformations for property prediction and molecular generation
Machine learning (ML) outperforms traditional approaches in many molecular design tasks. ML models usually predict molecular properties from a 2D chemical graph or a single 3D structure, but neither of these representati…
Property PredictionTransfer LearningMolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning
In this work, we propose a simple transformer-based baseline for multimodal molecular representation learning, integrating three distinct modalities: SMILES strings, 2D graph representations, and 3D conformers of molecul…
molecular representationRepresentation LearningMolecular Property Prediction by Semantic-invariant Contrastive Learning
Contrastive learning have been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, exiting methods that generate molecular…
Contrastive LearningDrug DesignMolecular Property Predictionmolecular representation+3