Molecular machine learning has been maturing rapidly over the last few years. Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are...

In this study, we introduce semi-supervised machine learning models designed to predict molecular properties. Our model employs a two-stage approach, involving pre-training and fine-tuning. Particularly, our leverages substantial amount of labeled unlabeled data consisting SMILES strings, text representation system for molecules. During the stage, capitalizes on Masked Language Model, which is ...

Predicating macroscopic influences of drugs on human body, like efficacy and toxicity, is a central problem of smallmolecule based drug discovery. Molecules can be represented as an undirected graph, and we can utilize graph convolution networks to predication molecular properties. However, graph convolutional networks and other graph neural networks all focus on learning node-level representat...

1 Model Training and Hyperparameter Optimization All models were trained on Stanford’s GPU clusters via DeepChem. No model was allowed to train for more than 10 hours(time profile in Table S1. Users can reproduce benchmarks locally by following directions from DeepChem. Hyperparameters were determined using Gaussian Process Optimization via pyGPGO(https://github.com/hawk31/pyGPGO), with max num...