schemist 0.0.1__tar.gz

schemist-0.0.1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) [year] [fullname]
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

schemist-0.0.1/PKG-INFO

@@ -0,0 +1,140 @@
+Metadata-Version: 2.1
+Name: schemist
+Version: 0.0.1
+Summary: Organizing and processing tables of chemical structures.
+Author-email: Eachan Johnson <eachan.johnson@crick.ac.uk>
+License: MIT License
+        
+        Copyright (c) [year] [fullname]
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+Project-URL: Homepage, https://github.com/scbirlab/schemist
+Project-URL: Repository, https://github.com/scbirlab/schemist.git
+Project-URL: Bug Tracker, https://github.com/scbirlab/schemist/issues
+Project-URL: Documentation, https://readthedocs.org/schemist
+Keywords: science,chemistry,SMILES,SELFIES,cheminformatics
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Chemistry
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: carabiner-tools[pd]>=0.0.3.post1
+Requires-Dist: datamol
+Requires-Dist: descriptastorus==2.6.1
+Requires-Dist: nemony
+Requires-Dist: openpyxl==3.1.0
+Requires-Dist: pandas
+Requires-Dist: rdkit
+Requires-Dist: requests
+Requires-Dist: selfies
+
+# ⬢⬢⬢ schemist
+
+![GitHub Workflow Status (with branch)](https://img.shields.io/github/actions/workflow/status/scbirlab/schemist/python-publish.yml)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/schemist)
+![PyPI](https://img.shields.io/pypi/v/schemist)
+[![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg)](https://huggingface.co/spaces/scbirlab/chem-converter)
+
+Cleaning, collating, and augmenting chemical datasets.
+
+- [Installation](#installation)
+- [Command-line usage](#command-line-usage)
+- [Python API](#python-api)
+- [Documentation](#documentation)
+
+## Installation
+
+### The easy way
+
+Install the pre-compiled version from PyPI:
+
+```bash
+pip install schemist
+```
+
+### From source
+
+Clone the repository, then `cd` into it. Then run:
+
+```bash
+pip install -e .
+```
+
+## Command-line usage
+
+**schemist**  provides command-line utlities. The list of commands can be checked like so:
+
+```bash
+$ schemist --help
+usage: schemist [-h] [--version] {clean,convert,featurize,collate,dedup,enumerate,react,split} ...
+
+Tools for cleaning, collating, and augmenting chemical datasets.
+
+options:
+  -h, --help            show this help message and exit
+  --version, -v         show program's version number and exit
+
+Sub-commands:
+  {clean,convert,featurize,collate,dedup,enumerate,react,split}
+                        Use these commands to specify the tool you want to use.
+    clean               Clean and normalize SMILES column of a table.
+    convert             Convert between string representations of chemical structures.
+    featurize           Convert between string representations of chemical structures.
+    collate             Collect disparate tables or SDF files of libraries into a single table.
+    dedup               Deduplicate chemical structures and retain references.
+    enumerate           Enumerate bio-chemical structures within length and sequence constraints.
+    react               React compounds in silico in indicated columns using a named reaction.
+    split               Split table based on chosen algorithm, optionally taking account of chemical structure during splits.
+```
+
+Each command is designed to work on large data files in a streaming fashion, so that the entire file is not held in memory at once. One caveat is that the scaffold-based splits are very slow with tables of millions of rows.
+
+All commands (except `collate`) take from the input table a named column with a SMILES, SELFIES, amino-acid sequence, HELM, or InChI representation of compounds.
+
+The tools complete specific tasks which 
+can be easily composed into analysis pipelines, because the TSV table output goes to
+`stdout` by default so they can be piped from one tool to another.
+
+To get help for a specific command, do
+
+```bash
+schemist <command> --help
+```
+
+For the Python API, [see below](#python-api).
+
+
+## Python API
+
+**schemist** can be imported into Python to help make custom analyses.
+
+```python
+>>> import schemist as sch
+```
+
+## Documentation
+
+Full API documentation is at [ReadTheDocs](https://schemist.readthedocs.org).

schemist-0.0.1/README.md

@@ -0,0 +1,87 @@
+# ⬢⬢⬢ schemist
+
+![GitHub Workflow Status (with branch)](https://img.shields.io/github/actions/workflow/status/scbirlab/schemist/python-publish.yml)
+![PyPI - Python Version](https://img.shields.io/pypi/pyversions/schemist)
+![PyPI](https://img.shields.io/pypi/v/schemist)
+[![Open in Spaces](https://huggingface.co/datasets/huggingface/badges/resolve/main/open-in-hf-spaces-md-dark.svg)](https://huggingface.co/spaces/scbirlab/chem-converter)
+
+Cleaning, collating, and augmenting chemical datasets.
+
+- [Installation](#installation)
+- [Command-line usage](#command-line-usage)
+- [Python API](#python-api)
+- [Documentation](#documentation)
+
+## Installation
+
+### The easy way
+
+Install the pre-compiled version from PyPI:
+
+```bash
+pip install schemist
+```
+
+### From source
+
+Clone the repository, then `cd` into it. Then run:
+
+```bash
+pip install -e .
+```
+
+## Command-line usage
+
+**schemist**  provides command-line utlities. The list of commands can be checked like so:
+
+```bash
+$ schemist --help
+usage: schemist [-h] [--version] {clean,convert,featurize,collate,dedup,enumerate,react,split} ...
+
+Tools for cleaning, collating, and augmenting chemical datasets.
+
+options:
+  -h, --help            show this help message and exit
+  --version, -v         show program's version number and exit
+
+Sub-commands:
+  {clean,convert,featurize,collate,dedup,enumerate,react,split}
+                        Use these commands to specify the tool you want to use.
+    clean               Clean and normalize SMILES column of a table.
+    convert             Convert between string representations of chemical structures.
+    featurize           Convert between string representations of chemical structures.
+    collate             Collect disparate tables or SDF files of libraries into a single table.
+    dedup               Deduplicate chemical structures and retain references.
+    enumerate           Enumerate bio-chemical structures within length and sequence constraints.
+    react               React compounds in silico in indicated columns using a named reaction.
+    split               Split table based on chosen algorithm, optionally taking account of chemical structure during splits.
+```
+
+Each command is designed to work on large data files in a streaming fashion, so that the entire file is not held in memory at once. One caveat is that the scaffold-based splits are very slow with tables of millions of rows.
+
+All commands (except `collate`) take from the input table a named column with a SMILES, SELFIES, amino-acid sequence, HELM, or InChI representation of compounds.
+
+The tools complete specific tasks which 
+can be easily composed into analysis pipelines, because the TSV table output goes to
+`stdout` by default so they can be piped from one tool to another.
+
+To get help for a specific command, do
+
+```bash
+schemist <command> --help
+```
+
+For the Python API, [see below](#python-api).
+
+
+## Python API
+
+**schemist** can be imported into Python to help make custom analyses.
+
+```python
+>>> import schemist as sch
+```
+
+## Documentation
+
+Full API documentation is at [ReadTheDocs](https://schemist.readthedocs.org).

schemist-0.0.1/pyproject.toml

@@ -0,0 +1,61 @@
+[project]
+name = "schemist"
+version = "0.0.1"
+authors = [
+  { name="Eachan Johnson", email="eachan.johnson@crick.ac.uk" },
+]
+description = "Organizing and processing tables of chemical structures."
+readme = "README.md"
+requires-python = ">=3.8"
+license = {file = "LICENSE"}
+keywords = ["science", "chemistry", "SMILES", "SELFIES", "cheminformatics"]
+
+classifiers = [  
+  
+  "Development Status :: 3 - Alpha",
+
+  # Indicate who your project is intended for
+  "Intended Audience :: Science/Research",
+  "Topic :: Scientific/Engineering :: Chemistry",
+
+  "License :: OSI Approved :: MIT License",
+
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3 :: Only",
+]
+
+dependencies = [ 
+  "carabiner-tools[pd]>=0.0.3.post1",
+  "datamol",
+  "descriptastorus==2.6.1",
+  "nemony",
+  "openpyxl==3.1.0", 
+  "pandas",
+  "rdkit",
+  "requests",
+  "selfies",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/scbirlab/schemist"
+"Repository" = "https://github.com/scbirlab/schemist.git"
+"Bug Tracker" = "https://github.com/scbirlab/schemist/issues"
+"Documentation" = "https://readthedocs.org/schemist"
+
+[project.scripts]  # Optional
+schemist = "schemist.cli:main"
+
+[tool.setuptools]
+packages = ["schemist"]
+# If there are data files included in your packages that need to be
+# installed, specify them here.
+# package-data = {"" = ["*.yml"]}
+
+[build-system]
+# These are the assumed default build requirements from pip:
+# https://pip.pypa.io/en/stable/reference/pip/#pep-517-and-518-support
+requires = ["setuptools>=43.0.0", "wheel"]
+build-backend = "setuptools.build_meta"

schemist-0.0.1/schemist/__init__.py

@@ -0,0 +1,3 @@
+from importlib.metadata import version
+
+__version__ = version("schemist")

schemist-0.0.1/schemist/cleaning.py

@@ -0,0 +1,27 @@
+"""Chemical structure cleaning routines."""
+
+from carabiner.decorators import vectorize
+
+from datamol import sanitize_smiles
+import selfies as sf
+
+@vectorize
+def clean_smiles(smiles: str, 
+                 *args, **kwargs) -> str:
+
+    """Sanitize a SMILES string or list of SMILES strings.
+    
+    """
+
+    return sanitize_smiles(smiles, *args, **kwargs) 
+
+
+@vectorize
+def clean_selfies(selfies: str, 
+                  *args, **kwargs) -> str:
+
+    """Sanitize a SELFIES string or list of SELFIES strings.
+    
+    """
+
+    return sf.encode(sanitize_smiles(sf.decode(selfies), *args, **kwargs))