Figure - PMC

Skip to main content

View full-text article in PMC

. Author manuscript; available in PMC: 2023 Dec 1.

Published in final edited form as: Artif Intell Life Sci. 2022 Jan 24;2:100031. doi: 10.1016/j.ailsci.2022.100031

Figure 2. — A case study of generative peptide design for GLP-1. A. An RNN-LSTM was trained on a dataset of 1554 antimicrobial peptides and generated peptides were scored with a GLP-1 agonist model generated from data in ChEMBL. B. dimensionality reduction using a t-SNE plot and nearest neighbor distance of generated proposed GLP-1 agonists. C. visualizing de novo generated GLP-1 agonists alongside commercial GLP-1 drugs to illustrate they are close in chemical property space.

Figure 2. — A case study of generative peptide design for GLP-1. A. An RNN-LSTM was trained on a dataset of 1554 antimicrobial peptides and generated peptides were scored with a GLP-1 agonist model generated from data in ChEMBL. B. dimensionality reduction using a t-SNE plot and nearest neighbor distance of generated proposed GLP-1 agonists. C. visualizing de novo generated GLP-1 agonists alongside commercial GLP-1 drugs to illustrate they are close in chemical property space.