STL_LDMO_project

Getting Started

Python implementation of the main results for the paper entitled: Conformal prediction of molecule-induced cancer cell growth inhibition challenged by strong distribution shifts

Data split

Utilizing the UMAP-based clustering method, 7 clusters were derived for non-outlier molecules, with the outlier set forming its distinct cluster.

Prerequisites

• Python 3.9.7

Usage

1. Download and store the from the NCI-60 Growth Inhibition Data.
   1. The required files contain the endpoints calculated from concentration curves ("CANCER60GI50_Oct2020.LST", for instance) and SMILES ("Chem2D_Jun2016.smi", for instance). Other releases of both files are also available for download.

To run:

jupyter notebook code_Figure5.ipynb
jupyter notebook code_Figure6.ipynb

Output: Figures 5 and 6.

License

MIT

Contact

1. Saiveth Hernández-Hernández, email: [email protected]
2. Pedro J.Ballester, email: [email protected]