TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction. (arXiv:2401.04478v2 [q-bio.BM] UPDATED)

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 …

arxiv bio boosting development discovery drug discovery drug discovery and development gradient language language models large language large language models prediction property q-bio.bm success twins