v0.6.1 Various Fixes

Various fixes of deprecation warnings, data conversion warnings, notebook sync workflow and some notebooks.

What's Changed

• Restore docs/notebooks/05_smiles_sanitization.py by @mieczyslaw in #75
• fix deprecation warning for DataFrame.swapaxes by @kbarbary in #74
• Fix notebooks generation flow by @asiomchen in #76
• Jaccard fix by @EBjerrum in #77

New Contributors

• @kbarbary made their first contribution in #74

Full Changelog: v0.6.0...v0.6.1

v0.6.0

What's Changed

• AD estimators by @EBjerrum in #65
• Updated Logo files by @Productivista in #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/13_applicability_domain/

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: v0.5.5...v0.6.0

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 #68
• Correct various typos in the code and docs by @mieczyslaw in #71

New Contributors

• @mieczyslaw made their first contribution in #71

Full Changelog: v0.5.3...v0.5.5

v0.5.4

What's Changed

• Improving the custom fingerprint creation by @asiomchen in #68
• Subclass fix by @EBjerrum in #69
• Now it was forced to be there by @EBjerrum in #70

Full Changelog: v0.5.3...v0.5.4

v0.5.3

MkDocs documentation for ReadTheDocs by @asiomchen in #61

Add links to RTD by @asiomchen in #62

Updates to Readme and Documentation @EBjerrum

Full Changelog: v0.4.6...v0.5.3

v0.5.0

What's Changed

• MkDocs documentation for ReadTheDocs by @asiomchen in #61
• Add links to RTD by @asiomchen in #62

Full Changelog: v0.4.6...v0.5.0

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 n_jobs to align with scikit-learn’s API.
If you previously used parallel=True, update your code to n_jobs=-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 #58

Full Changelog: v0.4.5...v0.4.6

+AvalonFP

New transformer class, AvalonFingerprintTransformer.

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

Parallel transformations

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