Efficient Molecular Property Prediction using Recurrent Neural Networks
A heuristic approach using recurrent neural networks, specifically the gated recurrent unit (GRU), can achieve close to state-of-the-art results in molecular property prediction with 99+% fewer parameters than large graph-based or language models.
Leveraging Transformer Models for Efficient Molecular Property Prediction: Insights and Challenges
Transformer models have shown promising results for molecular property prediction tasks, but their effective implementation requires careful consideration of various architectural and training decisions.
Generalizable, Fast, and Accurate Deep Learning Framework for Quantitative Structure-Property Relationship (DeepQSPR) with fastprop
fastprop is a deep learning framework that achieves state-of-the-art accuracy on molecular property prediction datasets of all sizes without sacrificing speed or interpretability.
Automated Uncertainty Quantification for Accurate Molecular Property Predictions using Graph Neural Architecture Search
AutoGNNUQ, an automated uncertainty quantification approach, leverages neural architecture search to generate an ensemble of high-performing graph neural networks, enabling accurate estimation of both aleatoric and epistemic uncertainties in molecular property predictions.
© 2024 by Linnk AI