depthcharge v0.2.3

[v0.2.3] - 2023-08-18

Fixed

• Applied hotfix from v0.3.1

depthcharge v0.3.0

[v0.3.0] - 2023-06-06

Added

• Providing a proper tokenization class (also resolves #24 and #18)
• First-class support for ProForma peptide annotations, thanks to spectrum_utils and pyteomics.
• Adding primitive dataclasses for peptides, peptide ions, mass spectra ... and even small molecules 🚀
• Adding type hints to everything and stricter linting with Ruff.
• Adding a ton of tests.
• Tight integration with spectrum_utils 💪

Changed

• Moving preprocessing onto parsing instead of data loading (similar to @bittremieux's proposal in #31)
• Combining the SpectrumIndex and SpectrumDataset classes into one.
• Changing peak encodings. Instead of encoding the intensity using a linear projection and summing with the sinusoidal m/z encodings, now the intensity is also sinusoidally encoded and is combined with the sinusoidal m/z encodings using a linear layer.

depthcharge v0.2.2

[v0.2.2] - 2023-05-15

Fixed

• Fixed retrieving version information.

depthcharge v0.2.1

[v0.2.1] - 2023-05-13

Changed

• Change target mask from float to boolean.
• Log the number spectra that are skipped due to an invalid precursor charge.

depthcharge v0.2.0

[0.2.0] - 2023-03-06

Breaking Changes

• Dropped pytorch-lightning as a dependency.
• Removed SpectrumDataModule
• Removed full-blown models (depthcharge.models)
• Fixed sinusoidal encoders (Issue #27)
• MassEncoder is now FloatEncoder, because its generally useful for encoding floating-point numbers.

Added

• pre-commit hooks and linting with Ruff.

Changed

• Tensorboard is now an optional dependency.

Removed

• The example de novo peptide sequencing model.

depthcharge v0.1.0

[0.1.0] - 2022-11-15

Changed

• The detokenize() method now returns a list instead of a string.

depthcharge v0.0.1

[0.0.1] - 2022-09-29

Added

• This is the first release! All changes from this point forward will be recorded in this changelog.