# Olab solution

Introduction
Before anything else, our team would like to say thank you to the competition organizers, EU-OPENSCREEN ERIC and SLAS, for hosting this interesting and challenging competition. Also, We would also like to thank all of the researchers who were involved in collecting and curating this high-quality compound solubility dataset. In this article, we would like to provide and explain in detail the solution that we employed to tackle this problem.
Overview
In short, our solution is LM/GNN ensemble. To reach the point of the final solution, we have done various experiments and discovered many interesting outcomes. The key contribution to the performance of our solution is the utilization of the Pre-train Language Model for molecule representation. Attached, we will describe the detail and some stories behind the development of our solution.
[assets/a50659a56a04fc5371649c46.pdf](assets/a50659a56a04fc5371649c46.pdf)