v1.1.7

What's Changed

• feat: allow protein tokenizer to be pickled by @jannisborn in #166
  -> Support for pytorch lightning ~ > 1.5

Full Changelog: v1.1.6...v1.1.7

v1.1.6

What's Changed

• Crawlers by @jannisborn in #165

• Fix a bug in the PubChem crawler that occurs when the database has multiple SMILES for a molecule
• Removing zinc crawler because it is not functional
• Restructure installation to support recent versions of numpy (2), torch (2), pip (20-24) and python (3.9-3.12)

Full Changelog: v1.1.5...v1.1.6

v1.1.5

What's Changed

• higher python compatibility by @jannisborn in #164

Full Changelog: v1.1.4...v1.1.5

v1.1.4

Full Changelog: v1.1.3...v1.1.4

Improved PubChem error handling

What's Changed

• Update PubChem crawler by @jannisborn in #163

Full Changelog: v1.1.2...v1.1.3

v1.1.2

What's Changed

• feat: bump selfies version (close #150) by @jannisborn in #162

Full Changelog: v1.1.1...v1.1.2

v1.1.1

Kinase sequence alignment data now available as pytoda.proteins.kinase_as_alignment: (245c9b5)

Full Changelog: v1.1.0...v1.1.1

v1.1.0

What's Changed

• Deprecate device handling by @YoelShoshan in #156
  NOTE: This DOES impact backwards compatibility because now, whenever a device is passed, an exception will be raised saying that GPU support is not longer maintained. The reason for this is that having pytoda handling sending data to the GPU is significantly slower compared to sending the full batch (for details see: #155)
• Novel protein augmentation by @jannisborn and @YoelShoshan in #160

Full Changelog: v1.0.2...v1.1.0

v1.0.2

What's Changed

• Save language restoration by @jannisborn in #154

Full Changelog: v1.0.1...v1.0.2

v1.0.1

What's Changed

• Compatibility by @jannisborn in #153

Full Changelog: 1.0.0...v1.0.1