InstaNovo 1.0.0

Improved code utility and data validation

• Check labels match precursor
• Check for data leakage
• Verify residue vocabulary
• Added better residue support
  • Fine-tuning trainer automatically updates model weights with new sizes
• Added Flash attention, torch.compile(), AMP (fp16)
• Added improved fast greedy search
• Improved test coverage

Added Spectrum Data Handler

• Supports lazy loading with asynchronous prefetching
• Filtering and sampling performed non-destructively (by updating the row filter)
• Two-fold shuffling strategy for training ensures optimal load times

Extended model checkpoint released. Trained on 32M spectra with additional PTMs:

• AC-PT
• Additional PRIDE dataset
• Additional phosphorylation dataset

0.1.7

What's Changed

• feat: generalise mgf to all metadata by @KevinEloff in #19
• Add GitHub action to purge GitHub cache of badge image on new release by @BioGeek in #18
• fix: dataloader using old schema by @KevinEloff in #24
• refactor: linting by @BioGeek in #21
• Add integration test by @BioGeek in #27
• fix: update benchmark URL to InstaDeepAI/ms_ninespecies_benchmark by @BioGeek in #28
• Fix version conflict for docs build by @BioGeek in #29
• docs: add link to Tran et al 2017 + fix ploars link by @BioGeek in #30
• ci: add dependabot to update github actions and packages by @BioGeek in #31
• Release 0.1.7 by @BioGeek in #33

Full Changelog: 0.1.6...0.1.7

0.1.6 Data conversion scripts

• Add data conversion scripts
• Add InstaNovo+ to starter notebook
• Add functionality to return all beams (return_all_beams=True argument in decoder.decode) #12

0.1.5 Diffusion Model and Checkpoints

• Add code for diffusion model
• Add checkpoint for diffusion model pre-trained on HC-PT fine-tuned on Nine Species excluding yeast.

Full Changelog: 0.1.4...0.1.5

0.1.4 InstaNovo model checkpoints

What's Changed

• feat: bundle config files with checkpoints
• add checkpoints instanovo.pt trained on HC-PT, and instanovo_yeast.pt fine-tuned on nine-species excluding yeast.

Full Changelog: 0.1.2...0.1.4

0.1.3

What's Changed

• docs: add hyperlinks by @BioGeek in #6
• fix: update URLs by @BioGeek in #7

Full Changelog: 0.1.2...0.1.3

0.1.2

Merge pull request #5 from instadeepai/pypi

Pypi

0.1.1

Initial code release

0.1.0

Initial code release