deepchem-circular-featurization

Name: deepchem-circular-featurization
Author: ma-compbio-lab

36stars5forks

How to install deepchem-circular-featurization?

ma-compbio-lab/skillfoundry/deepchem-circular-featurization

$npx -y skills add ma-compbio-lab/SkillFoundry --skill deepchem-circular-featurization

Installs into the current project.

Summary

Use this skill to compute compact DeepChem circular fingerprints from a small set of SMILES strings with the repo-managed DeepChem prefix. Do not use it for model training, docking, or large library screening.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Turn one or more SMILES strings into deterministic DeepChem `CircularFingerprint` summaries without requiring TensorFlow or PyTorch.
3
4	## When to use
5	- You need a lightweight DeepChem-backed fingerprinting step before downstream molecular ML work.
6	- You want a compact JSON payload with canonical SMILES, dense bit vectors, and active bit indices.
7
8	## When not to use
9	- You need graph featurizers, model training, or dataset download workflows.
10	- You need batch-scale featurization for very large libraries.
11
12	## Inputs
13	- Repeated `--smiles` arguments, or no arguments to use the bundled aspirin/caffeine example
14	- Optional `--size`, `--radius`, and `--out`
15
16	## Outputs
17	- JSON summary with `canonical_smiles`, `bit_vector`, `on_bits`, and `on_bit_count` for each molecule
18
19	## Requirements
20	- `slurm/envs/deepchem`
21	- DeepChem 2.8.0 and RDKit installed in that prefix
22
23	## Procedure
24	1. Run `slurm/envs/deepchem/bin/python skills/drug-discovery-and-cheminformatics/deepchem-circular-featurization/scripts/compute_circular_fingerprints.py --out skills/drug-discovery-and-cheminformatics/deepchem-circular-featurization/assets/aspirin_caffeine_fingerprints.json`.
25	2. Inspect `size`, `radius`, and each molecule's `canonical_smiles`, `bit_vector`, and `on_bits`.
26	3. Reuse the compact JSON as a deterministic preprocessing artifact for later experiments.
27
28	## Validation
29	- The command exits successfully under `slurm/envs/deepchem/bin/python`.
30	- Each molecule gets a non-empty canonical SMILES and a bit vector of the requested length.
31	- Repeated runs with the same inputs produce the same fingerprint payload.
32
33	## Failure modes and fixes
34	- Missing DeepChem runtime: run the script with `slurm/envs/deepchem/bin/python`.
35	- Invalid SMILES: correct the input string before featurization.
36	- Optional backend warnings: TensorFlow and PyTorch are not required for this fingerprint-only skill.
37
38	## Safety and limits
39	- Local featurization only.
40	- No activity prediction, medicinal-chemistry recommendation, or safety interpretation is implied.
41
42	## Provenance
43	- DeepChem documentation: https://deepchem.readthedocs.io/en/latest/
44	- RDKit documentation: https://www.rdkit.org/docs/index.html
45
46	## Related skills
47	- `rdkit-molecular-descriptors`

People who liked this also viewed

6 picks

Type

deepchem-circular-featurization

36stars5forks

View on GitHub

How to install deepchem-circular-featurization?

ma-compbio-lab/skillfoundry/deepchem-circular-featurization

$npx -y skills add ma-compbio-lab/SkillFoundry --skill deepchem-circular-featurization

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Turn one or more SMILES strings into deterministic DeepChem `CircularFingerprint` summaries without requiring TensorFlow or PyTorch.
3
4	## When to use
5	- You need a lightweight DeepChem-backed fingerprinting step before downstream molecular ML work.
6	- You want a compact JSON payload with canonical SMILES, dense bit vectors, and active bit indices.
7
8	## When not to use
9	- You need graph featurizers, model training, or dataset download workflows.
10	- You need batch-scale featurization for very large libraries.
11
12	## Inputs
13	- Repeated `--smiles` arguments, or no arguments to use the bundled aspirin/caffeine example
14	- Optional `--size`, `--radius`, and `--out`
15
16	## Outputs
17	- JSON summary with `canonical_smiles`, `bit_vector`, `on_bits`, and `on_bit_count` for each molecule
18
19	## Requirements
20	- `slurm/envs/deepchem`
21	- DeepChem 2.8.0 and RDKit installed in that prefix
22
23	## Procedure
24	1. Run `slurm/envs/deepchem/bin/python skills/drug-discovery-and-cheminformatics/deepchem-circular-featurization/scripts/compute_circular_fingerprints.py --out skills/drug-discovery-and-cheminformatics/deepchem-circular-featurization/assets/aspirin_caffeine_fingerprints.json`.
25	2. Inspect `size`, `radius`, and each molecule's `canonical_smiles`, `bit_vector`, and `on_bits`.
26	3. Reuse the compact JSON as a deterministic preprocessing artifact for later experiments.
27
28	## Validation
29	- The command exits successfully under `slurm/envs/deepchem/bin/python`.
30	- Each molecule gets a non-empty canonical SMILES and a bit vector of the requested length.
31	- Repeated runs with the same inputs produce the same fingerprint payload.
32
33	## Failure modes and fixes
34	- Missing DeepChem runtime: run the script with `slurm/envs/deepchem/bin/python`.
35	- Invalid SMILES: correct the input string before featurization.
36	- Optional backend warnings: TensorFlow and PyTorch are not required for this fingerprint-only skill.
37
38	## Safety and limits
39	- Local featurization only.
40	- No activity prediction, medicinal-chemistry recommendation, or safety interpretation is implied.
41
42	## Provenance
43	- DeepChem documentation: https://deepchem.readthedocs.io/en/latest/
44	- RDKit documentation: https://www.rdkit.org/docs/index.html
45
46	## Related skills
47	- `rdkit-molecular-descriptors`

People who liked this also viewed

6 picks

Type