Automatic Selection And Prediction tools for materials and molecules

Basic usage of the command line tool

Type asap and use the sub-commands for various tasks.

• asap gen_desc: generate global or atomic descriptors based on the input [ASE](https://wiki.fysik.dtu.dk/ase/ase/atoms.html)) xyze file.

• asap map: make 2D plots using the specified design matrix. Currently PCA pca, sparsified kernel PCA skpca, UMAP umap, and t-SNE tsne are implemented.

• asap cluster: perform density based clustering. Currently supports DBSCAN dbscan and [Fast search of density peaks](https://science.sciencemag.org/content/344/6191/1492) fdb.

• asap fit: fast fit ridge regression ridge or sparsified kernel ridge regression model kernelridge based on the input design matrix and labels.

• asap kde: quick kernel density estimation on the design matrix. Several versions of kde available.

• asap select: select a subset of frames using sparsification algorithms.

Note

To get help string: asap --help .or. asap subcommand --help .or. asap subcommand subcommand --help depending which level of help you are interested in.

Using the PYTHON library

In python3, one can import asap as a libaray using

import asaplib

Please refer to the documentation of each module for available functionalities.

Contents:

• Installation
  • Direct installation
  • Install in a conda environment
  • List of requirements
• Quick & basic example
  • Step 1: generate a design matrix
  • Step 2: generate a low-dimensional map
  • Step 2+: interactive visualization
• How-to: asap gen_desc
  • Input
  • Output
  • Overview of sub-commands
    • asap gen_desc
• How-to: asap map
  • Overview of sub-commands
    • asap map
• How-to: asap fit
  • Overview of sub-commands
    • asap fit
• How-to: asap kde
  • Overview of sub-commands
    • asap kde
• How-to: asap cluster
  • Overview of sub-commands
    • asap cluster
• How-to: asap select
  • asap select
• How-to: use the asaplib library
  • Example on quick analyisis of atomic coordinates using a SOAP based metric
    • load structures
    • compute SOAP descriptors
    • Build a kernel Matrix
    • kernal PCA on environmental similarity
    • Plot the result
• Tutorials
• Advanced topics
  • How to add your own atomic or global descriptors
• modules of asaplib
  • asaplib package
    • Subpackages
    • Module contents

Indices and tables

• Index

• Module Index