Collection of data sets of molecules for a validation of properties inference

MoleculeNet benchmark dataset & MolMapNet dataset

Extract Molecular SMILES embeddings from language models pre-trained with various objectives architectures.

Training pre-trained BERT language model on molecular SMILES from the Molecule Net benchmark by leveraging mixup and enumeration augmentations.

MSc Dissertation: Estimating Uncertainty in Machine Learning Models for Drug Discovery

Semi-supervised learning techniques (pseudo-label, mixmatch, and co-training) for pre-trained BERT language model amidst low-data regime based on molecular SMILES from the Molecule Net benchmark.

Molecule Transformers is a collection of recipes for pre-training and fine-tuning molecular transformer language models, including BART, BERT, etc. Full thesis available at https://moleculetransformers.github.io/thesis_cs_msc_Khan_Shahrukh.pdf.

Collection of Machine Learning and GNN methods for Molecular Property Prediction Task