datamol

Name: datamol
Author: K-Dense-AI

31kstars3.1kforks

How to install datamol?

k-dense-ai/scientific-agent-skills/datamol

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill datamol

Installs into the current project.

Summary

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For ad

Files · 1

View on GitHub

SKILL.md

1	# Datamol Cheminformatics Skill
2
3	## Overview
4
5	Datamol is a Python library that provides a lightweight, Pythonic abstraction layer over RDKit for molecular cheminformatics. Simplify complex molecular operations with sensible defaults, efficient parallelization, and modern I/O capabilities. All molecular objects are native `rdkit.Chem.Mol` instances, ensuring full compatibility with the RDKit ecosystem.
6
7	Version note: Examples target datamol 0.12.x (PyPI stable: 0.12.5, June 2024). Since 0.10.0, modules are lazy-loaded by default (set `DATAMOL_DISABLE_LAZY_LOADING=1` to disable). Since 0.12.2, RDKit is a direct PyPI dependency of datamol. Fingerprints use RDKit's `rdFingerprintGenerator` API (0.12.5+).
8
9	Key capabilities:
10	- Molecular format conversion (SMILES, SELFIES, InChI)
11	- Structure standardization and sanitization
12	- Molecular descriptors and fingerprints
13	- 3D conformer generation and analysis
14	- Clustering and diversity selection
15	- Scaffold and fragment analysis
16	- Chemical reaction application
17	- Visualization and alignment
18	- Batch processing with parallelization
19	- Cloud storage support via fsspec
20
21	## Installation and Setup
22
23	Guide users to install datamol:
24
25	```bash
26	uv pip install datamol
27	```
28
29	RDKit is installed automatically with datamol. For remote file paths (S3, GCS, HTTP), install the matching fsspec backend:
30
31	```bash
32	uv pip install s3fs # AWS S3
33	uv pip install gcsfs # Google Cloud Storage
34	```
35
36	Import convention:
37	```python
38	import datamol as dm
39	```
40
41	## Core Workflows
42
43	### 1. Basic Molecule Handling
44
45	Creating molecules from SMILES:
46	```python
47	import datamol as dm
48
49	# Single molecule
50	mol = dm.to_mol("CCO") # Ethanol
51
52	# From list of SMILES
53	smiles_list = ["CCO", "c1ccccc1", "CC(=O)O"]
54	mols = [dm.to_mol(smi) for smi in smiles_list]
55
56	# Error handling
57	mol = dm.to_mol("invalid_smiles") # Returns None
58	if mol is None:
59	print("Failed to parse SMILES")
60	```
61
62	Converting molecules to SMILES:
63	```python
64	# Canonical SMILES
65	smiles = dm.to_smiles(mol)
66
67	# Isomeric SMILES (includes stereochemistry)
68	smiles = dm.to_smiles(mol, isomeric=True)
69
70	# Other formats
71	inchi = dm.to_inchi(mol)
72	inchikey = dm.to_inchikey(mol)
73	selfies = dm.to_selfies(mol)
74	```
75
76	Standardization and sanitization (always recommend for user-provided molecules):
77	```python
78	# Sanitize molecule
79	mol = dm.sanitize_mol(mol)
80
81	# Full standardization (recommended for datasets)
82	mol = dm.standardize_mol(
83	mol,
84	disconnect_metals=True,
85	normalize=True,
86	reionize=True
87	)
88
89	# For SMILES strings directly
90	clean_smiles = dm.standardize_smiles(smiles)
91	```
92
93	### 2. Reading and Writing Molecular Files
94
95	Refer to `references/io_module.md` for comprehensive I/O documentation.
96
97	Reading files:
98	```python
99	# SDF files (most common in chemistry)
100	df = dm.read_sdf("compounds.sdf", mol_column='mol')
101
102	# SMILES files
103	df = dm.read_smi("molecules.smi", smiles_column='smiles', mol_column='mol')
104
105	# CSV with SMILES column
106	df = dm.read_csv("data.csv", smiles_column="SMILES", mol_column="mol")
107
108	# Excel files
109	df = dm.read_excel("compounds.xlsx", sheet_name=0, mol_column="mol")
110
111	# Universal reader/writer (auto-detects format; supports compression)
112	df = dm.open_df("file.sdf") # .sdf, .csv, .xlsx, .parquet, .json, .gz, etc.
113	dm.save_df(df, "output.parquet")
114	```
115
116	Writing files:
117	```python
118	# Save as SDF
119	dm.to_sdf(mols, "output.sdf")
120	# Or from DataFrame
121	dm.to_sdf(df, "output.sdf", mol_column="mol")
122
123	# Save as SMILES file
124	dm.to_smi(mols, "output.smi")
125
126	# Excel with rendered molecule images
127	dm.to_xlsx(df, "output.xlsx", mol_columns=["mol"])
128	```
129
130	Remote file support (S3, GCS, HTTP via fsspec):
131
132	Only use cloud paths when the user explicitly requests them. Confirm the destination before writing.
133
134	```python
135	# Read from cloud storage or HTTPS (user-provided URLs only)
136	df = dm.read_sdf("s3://bucket/compounds.sdf")
137	df = dm.read_csv("https://example.com/data.csv")
138
139	# Write to cloud storage — confirm path with user first
140	dm.to_sdf(mols, "s3://bucket/output.sdf")
141	```
142
143	Cloud backends read credentials from the standard provider environment (for example `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`, or `GOOGLE_APPLICATION_CREDENTIALS`). Datamol passes these to fsspec locally; it does not collect or transmit environment variables to third-party endpoints. Scope credential access

People who liked this also viewed

6 picks

Type

datamol

31kstars3.1kforks

View on GitHub

How to install datamol?

k-dense-ai/scientific-agent-skills/datamol

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill datamol

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Datamol Cheminformatics Skill
2
3	## Overview
4
5	Datamol is a Python library that provides a lightweight, Pythonic abstraction layer over RDKit for molecular cheminformatics. Simplify complex molecular operations with sensible defaults, efficient parallelization, and modern I/O capabilities. All molecular objects are native `rdkit.Chem.Mol` instances, ensuring full compatibility with the RDKit ecosystem.
6
7	Version note: Examples target datamol 0.12.x (PyPI stable: 0.12.5, June 2024). Since 0.10.0, modules are lazy-loaded by default (set `DATAMOL_DISABLE_LAZY_LOADING=1` to disable). Since 0.12.2, RDKit is a direct PyPI dependency of datamol. Fingerprints use RDKit's `rdFingerprintGenerator` API (0.12.5+).
8
9	Key capabilities:
10	- Molecular format conversion (SMILES, SELFIES, InChI)
11	- Structure standardization and sanitization
12	- Molecular descriptors and fingerprints
13	- 3D conformer generation and analysis
14	- Clustering and diversity selection
15	- Scaffold and fragment analysis
16	- Chemical reaction application
17	- Visualization and alignment
18	- Batch processing with parallelization
19	- Cloud storage support via fsspec
20
21	## Installation and Setup
22
23	Guide users to install datamol:
24
25	```bash
26	uv pip install datamol
27	```
28
29	RDKit is installed automatically with datamol. For remote file paths (S3, GCS, HTTP), install the matching fsspec backend:
30
31	```bash
32	uv pip install s3fs # AWS S3
33	uv pip install gcsfs # Google Cloud Storage
34	```
35
36	Import convention:
37	```python
38	import datamol as dm
39	```
40
41	## Core Workflows
42
43	### 1. Basic Molecule Handling
44
45	Creating molecules from SMILES:
46	```python
47	import datamol as dm
48
49	# Single molecule
50	mol = dm.to_mol("CCO") # Ethanol
51
52	# From list of SMILES
53	smiles_list = ["CCO", "c1ccccc1", "CC(=O)O"]
54	mols = [dm.to_mol(smi) for smi in smiles_list]
55
56	# Error handling
57	mol = dm.to_mol("invalid_smiles") # Returns None
58	if mol is None:
59	print("Failed to parse SMILES")
60	```
61
62	Converting molecules to SMILES:
63	```python
64	# Canonical SMILES
65	smiles = dm.to_smiles(mol)
66
67	# Isomeric SMILES (includes stereochemistry)
68	smiles = dm.to_smiles(mol, isomeric=True)
69
70	# Other formats
71	inchi = dm.to_inchi(mol)
72	inchikey = dm.to_inchikey(mol)
73	selfies = dm.to_selfies(mol)
74	```
75
76	Standardization and sanitization (always recommend for user-provided molecules):
77	```python
78	# Sanitize molecule
79	mol = dm.sanitize_mol(mol)
80
81	# Full standardization (recommended for datasets)
82	mol = dm.standardize_mol(
83	mol,
84	disconnect_metals=True,
85	normalize=True,
86	reionize=True
87	)
88
89	# For SMILES strings directly
90	clean_smiles = dm.standardize_smiles(smiles)
91	```
92
93	### 2. Reading and Writing Molecular Files
94
95	Refer to `references/io_module.md` for comprehensive I/O documentation.
96
97	Reading files:
98	```python
99	# SDF files (most common in chemistry)
100	df = dm.read_sdf("compounds.sdf", mol_column='mol')
101
102	# SMILES files
103	df = dm.read_smi("molecules.smi", smiles_column='smiles', mol_column='mol')
104
105	# CSV with SMILES column
106	df = dm.read_csv("data.csv", smiles_column="SMILES", mol_column="mol")
107
108	# Excel files
109	df = dm.read_excel("compounds.xlsx", sheet_name=0, mol_column="mol")
110
111	# Universal reader/writer (auto-detects format; supports compression)
112	df = dm.open_df("file.sdf") # .sdf, .csv, .xlsx, .parquet, .json, .gz, etc.
113	dm.save_df(df, "output.parquet")
114	```
115
116	Writing files:
117	```python
118	# Save as SDF
119	dm.to_sdf(mols, "output.sdf")
120	# Or from DataFrame
121	dm.to_sdf(df, "output.sdf", mol_column="mol")
122
123	# Save as SMILES file
124	dm.to_smi(mols, "output.smi")
125
126	# Excel with rendered molecule images
127	dm.to_xlsx(df, "output.xlsx", mol_columns=["mol"])
128	```
129
130	Remote file support (S3, GCS, HTTP via fsspec):
131
132	Only use cloud paths when the user explicitly requests them. Confirm the destination before writing.
133
134	```python
135	# Read from cloud storage or HTTPS (user-provided URLs only)
136	df = dm.read_sdf("s3://bucket/compounds.sdf")
137	df = dm.read_csv("https://example.com/data.csv")
138
139	# Write to cloud storage — confirm path with user first
140	dm.to_sdf(mols, "s3://bucket/output.sdf")
141	```
142
143	Cloud backends read credentials from the standard provider environment (for example `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_DEFAULT_REGION`, or `GOOGLE_APPLICATION_CREDENTIALS`). Datamol passes these to fsspec locally; it does not collect or transmit environment variables to third-party endpoints. Scope credential access

People who liked this also viewed

6 picks

Type