MolecularDiffusion.cli.data¶
Data CLI module for MolCraft. Exposes data preparation, augmentation, and ASE operations via CLI commands.
Attributes¶
Classes¶
A Click Option that consumes all remaining arguments until the next flag. |
Functions¶
|
Annotate an ASE database with a tag. |
ASE database operations. |
|
|
Data augmentation commands. |
|
Augment data by random charge modification. |
|
Compile molecular data into an ASE database. |
|
Data processing utilities. |
|
Augment data by random coordinate distortion. |
|
Featurize 3D molecules into vectors. |
|
Generate Mol Blocks, SMILES, and properties (SA, SC). |
|
Inspect an ASE database and optionally plot statistics. |
|
Merge multiple ASE databases. |
|
Data preparation commands. |
|
Sample entries from an ASE database. |
|
Augment data to balance molecule sizes. |
|
Split an ASE database. |
Module Contents¶
- class MolecularDiffusion.cli.data.VariadicOption(*args, **kwargs)¶
Bases:
click.OptionA Click Option that consumes all remaining arguments until the next flag.
- add_to_parser(parser, ctx)¶
- MolecularDiffusion.cli.data.annotate_cmd(db, tag, value)¶
Annotate an ASE database with a tag.
- MolecularDiffusion.cli.data.ase_ops_group()¶
ASE database operations.
- MolecularDiffusion.cli.data.augment()¶
Data augmentation commands.
- MolecularDiffusion.cli.data.charge_cmd(input, output, max_h, fraction, db)¶
Augment data by random charge modification.
- MolecularDiffusion.cli.data.compile_cmd(source, db, natoms, csv, sdf, fraction, seed)¶
Compile molecular data into an ASE database.
- MolecularDiffusion.cli.data.data()¶
Data processing utilities.
- MolecularDiffusion.cli.data.distortion_cmd(input, output, sigma, fraction, freeze)¶
Augment data by random coordinate distortion.
- MolecularDiffusion.cli.data.featurize_cmd(method, input, output, format, readout, smilify_method, radius, nbits, rcut, nmax, lmax)¶
Featurize 3D molecules into vectors.
- MolecularDiffusion.cli.data.generate_blocks_cmd(source, sdf, natoms, csv, fraction, indices, method)¶
Generate Mol Blocks, SMILES, and properties (SA, SC).
- MolecularDiffusion.cli.data.inspect_cmd(db, output, keys, limit)¶
Inspect an ASE database and optionally plot statistics.
- MolecularDiffusion.cli.data.merge_cmd(input, output, recursive)¶
Merge multiple ASE databases.
- MolecularDiffusion.cli.data.prepare()¶
Data preparation commands.
- MolecularDiffusion.cli.data.sample_cmd(input, output, fraction, number, seed, verify)¶
Sample entries from an ASE database.
- MolecularDiffusion.cli.data.size_cmd(input, output, s_start, t_start, s_end, t_end, strength, decay, invert, plot_prefix)¶
Augment data to balance molecule sizes.
- MolecularDiffusion.cli.data.split_cmd(db, output, n)¶
Split an ASE database.
- MolecularDiffusion.cli.data.logger¶