Archive of Jupyter Notebook scripts and adsorption free energy data used in
the paper
"Biomolecular Adsorption on Nanomaterials: Combining Molecular Simulations
with Machine Learning"
by Marzieh Saeedimasine, Roja Rahmani and Alexander Lyubartsev
Stockholm University, 2023.

Data file:
top_Gads_updated.dat : a full set of numerical data on adsorption free energies of small biomolecules to various nanomaterials.
top_Gads_updated.xlsx : the same data in the excel format


Scripts:

Workflow of computations and results, to be accessed or run in Jupyter Notebook

PCA.ipynb: Principal Component Analysis for Linear Dimensionality
Reduction and Eigenvectors analysis along the original features.

Clustering.ipynb: Biomolecules Agglomerative Clustering and K-meansClustering;
Nanomaterials AgglomerativeClustering using both full data set and predicted
data set

LR-ML.ipynb: LinearRegression modelling of Nanomaterial-Biomolecule
adsorption free energy

AdaBoostRegressor-ML.ipynb: AdaBoostRegressor modelling using
DecisionTreeRegressor as week learner for Nanomaterial-Biomolecule
adsorption free energy

ANN-ML.ipynb: Neural network modelling of Nanomaterial-Biomolecule
adsorption free energy