scikit-mol - v0.5.4

What's Changed

• Improving the custom fingerprint creation by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/68
• Subclass fix by @EBjerrum in https://github.com/EBjerrum/scikit-mol/pull/69
• Now it was forced to be there by @EBjerrum in https://github.com/EBjerrum/scikit-mol/pull/70

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.5.3...v0.5.4

- Python
Published by github-actions[bot] 11 months ago

scikit-mol - v0.6.0

What's Changed

• AD estimators by @EBjerrum in https://github.com/EBjerrum/scikit-mol/pull/65
• Updated Logo files by @Productivista in https://github.com/EBjerrum/scikit-mol/pull/72

New Capabilities

A new set of feature-based Applicability Domain (AD) estimators has been introduced. These include kNN and Leverage-based approaches, offering expanded model introspection capabilities.

See the usage and examples in the updated notebook: https://scikit-mol.readthedocs.io/en/latest/notebooks/13applicabilitydomain/

Enhancements

• Improved consistency across AD estimator implementations via a shared base class
• Added test coverage for new estimators
• Automatic NumPy seed setting in tests for consistent results
• Various docstring and markdown improvements in README and docs

Logo and Documentation

• New hybrid logo optimized for both dark and light backgrounds
• Updated GitHub README.md now synchronized with the documentation landing page

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.5.5...v0.6.0

- Python
Published by github-actions[bot] 11 months ago

scikit-mol - v0.5.5

Bug Fixes and Cleanup of Typos and Misspellings

This release enables the use of local subclasses of abstract classes in both single and parallel execution. The documentation and spelling have been overhauled.

Breaking Change

The spelling of a class name has been corrected. Scripts using the CheckSmilesSanitazion class must update the class name to CheckSmilesSanitization.

What's Changed

• Improving the custom fingerprint creation by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/68
• Correct various typos in the code and docs by @mieczyslaw in https://github.com/EBjerrum/scikit-mol/pull/71

New Contributors

• @mieczyslaw made their first contribution in https://github.com/EBjerrum/scikit-mol/pull/71

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.5.3...v0.5.5

- Python
Published by github-actions[bot] 11 months ago

scikit-mol - v0.5.3

MkDocs documentation for ReadTheDocs by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/61

Add links to RTD by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/62

Updates to Readme and Documentation @EBjerrum

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.4.6...v0.5.3

- Python
Published by github-actions[bot] 12 months ago

scikit-mol - v0.5.0

What's Changed

• MkDocs documentation for ReadTheDocs by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/61
• Add links to RTD by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/62

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.4.6...v0.5.0

- Python
Published by github-actions[bot] 12 months ago

scikit-mol - v0.4.6

Improved Parallelism via joblib and software development flow improvements

Parallel Execution Improvements & API Changes

The codebase has been updated to improve parallel execution, now handled via joblib. This migration simplifies the underlying implementation, enhances robustness, and significantly improves performance, especially on Windows, reducing test run times from approximately 7 minutes to 1.5 minutes.

API Change: The parallel argument has been replaced with njobs to align with scikit-learn’s API. If you previously used parallel=True, update your code to njobs=-1 to utilize all available cores. Note: n_jobs now only accepts integer values—boolean values are no longer supported.

Bug Fix: Resolved a potential issue with safe_inference during parallel executions.

Other Updates: Python 3.8 is deprecated as it is no longer supported. Migrated to uv and hatchling for build and dependency management. See CONTRIBUTING.md for details. Added plotting.py for parallel benchmark visualization and updated Notebook 7 with new benchmarks.

What's Changed

• Migration to joblib + new build system + separate reusable publish workflow by @asiomchen in https://github.com/EBjerrum/scikit-mol/pull/58

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.4.5...v0.4.6

- Python
Published by github-actions[bot] about 1 year ago

scikit-mol - +AvalonFP

New transformer class, AvalonFingerprintTransformer.

- Python
Published by EBjerrum almost 3 years ago

scikit-mol - v0.2.0

Renaming of modules and classes for consistency

Module and Class renaming for better consistency. This will break imports in existing scripts, but better now than later.

Fingerprints are now in the fingerprints module rather than in the transformers module (all are transformers, so this is more descriptive)

Fingerprint consistently spelled out in the class names, e.g. not FP, but Fingerprint

Descriptors in the descriptors module

Smiles2Mol is now in a new module called conversions

Also: New transformer available: MHFingerprintTransformer

- Python
Published by EBjerrum almost 3 years ago

scikit-mol - Parallel transformations

Parallel transformations, see https://github.com/EBjerrum/scikit-mol/blob/main/notebooks/07paralleltransforms.ipynb for example and guidelines for use.

- Python
Published by EBjerrum almost 3 years ago

scikit-mol - Documentation

Merged the documentation branch to the main, and re-releasing tagged version.

What's Changed

• Documentation by @EBjerrum in https://github.com/EBjerrum/scikit-mol/pull/23

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.0.4...v0.1.1

- Python
Published by EBjerrum about 3 years ago

scikit-mol - Updated documentation notebooks

Updated notebooks and Readme's, as well as various bug fixes.

What's Changed

• Fixed a bug in Standardize script by @son-ha-264 in https://github.com/EBjerrum/scikit-mol/pull/21
• minor fixes, test script and adding toy data to run test by @adrienchaton in https://github.com/EBjerrum/scikit-mol/pull/12
• Integration test by @EBjerrum in https://github.com/EBjerrum/scikit-mol/pull/22

New Contributors

• @adrienchaton made their first contribution in https://github.com/EBjerrum/scikit-mol/pull/12

Full Changelog: https://github.com/EBjerrum/scikit-mol/compare/v0.0.3...v0.1.0

- Python
Published by EBjerrum about 3 years ago

scikit-mol - Integration testing

Integration testing and minor bug fixes. There is now a test dataset available for basic testing available for pytest via the fixture SLC6A4_subset. The samples are selected to give a higher validation/test performance despite the small size, and are thus artificially inflated and should not be used for regular QSAR work.

- Python
Published by EBjerrum over 3 years ago

scikit-mol - bugfixes and tests

More complete coverage of tests and some bugfixes in the transformers

- Python
Published by EBjerrum over 3 years ago

scikit-mol - Tested and updated classes

Unittests coverage is now decent, and the dynamics around decslist is now implemented correctly, so that parameters can be set after instantiation of the object and the desciptorcalculator function list be updates

- Python
Published by EBjerrum over 3 years ago

scikit-mol -

First release of the draft code. Not all transformers fully tested.

- Python
Published by EBjerrum over 3 years ago