TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction
This method addresses the challenge of scarce data in drug discovery by enabling prediction for unseen assays and molecules, potentially accelerating therapeutic identification.
The study tackled the problem of predicting molecular properties with limited data by integrating a fine-tuned large language model with Barlow Twins and gradient boosting, achieving state-of-the-art zero-shot learning performance on the FS-Mol benchmark.
The success of drug discovery and development relies on the precise prediction of molecular activities and properties. While in silico molecular property prediction has shown remarkable potential, its use has been limited so far to assays for which large amounts of data are available. In this study, we use a fine-tuned large language model to integrate biological assays based on their textual information, coupled with Barlow Twins, a Siamese neural network using a novel self-supervised learning approach. This architecture uses both assay information and molecular fingerprints to extract the true molecular information. TwinBooster enables the prediction of properties of unseen bioassays and molecules by providing state-of-the-art zero-shot learning tasks. Remarkably, our artificial intelligence pipeline shows excellent performance on the FS-Mol benchmark. This breakthrough demonstrates the application of deep learning to critical property prediction tasks where data is typically scarce. By accelerating the early identification of active molecules in drug discovery and development, this method has the potential to help streamline the identification of novel therapeutics.