On The Use Of Large Language Model For Virtual Screening

Date

2023-9-11

Author

Sığırcı, Ali İlker

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

94
views

39
downloads

Cite This

Due to the abundance of drug candidates, conducting in-lab experiments to find an effective compound for a given target is a costly and time-consuming task in drug discovery. This thesis aims to reduce the number of drug candidates during early drug discovery by clustering the compounds. ChemBERTa, a Bidirectional Encoder Representation from Transformers (BERT) model, is employed to extract the descriptors for a compound. The compounds are clustered with respect to the learned features, and several clustering algorithms, including the k-means clustering algorithm and the Butina algorithm, are used. Finally, obtained clusters are evaluated by measures such as the Silhouette Score and Homogeneity Score. Our empirical findings show that using learned descriptors of ChemBERTa produces results that are comparable with traditional and graph-based models, as shown by metrics of cluster accuracy and computing runtime.

Subject Keywords

Drug-target interaction, Compound descriptors, Representation learning, Natural language processing, Clustering

URI

https://hdl.handle.net/11511/105319

Collections

Graduate School of Natural and Applied Sciences, Thesis