v0.6.1

• Fixed issue with predictor train due to traingraph being null when starting train
• Added shortcuts for DesignConstraints

v0.6.0

• release session.predictor module
  • allows training gaussian process models on different types of embeddings
  • can also use fitted svds for high fidelity custom sized embeddings to fit GPs
  • predictors can then be used for design
  • deprecated session.train into session.deprecated.train
• release newer session.design interface
  • allows using the newly trained predictor
  • supports syntactic sugar for quickly creating criteria
  • deprecated old session.design interface which requires awkward construction using pydantic into session.deprecated.design
    • might still be needed to support older train models
• migration is planned for all old models and design into the new interface so that they can be listed, fetched and used for prediction.

v0.5.5

• fixed wait on old predict jobs returning job_id = None

v0.5.4

Release v0.5.4

v0.5.3

• fixed issues with load_job
• fixed issues listing jobs with alignment type of jobs

v0.5.2

• fixed workflow predict handling of None job_id when the job is cached
• fixed handling of single site too

v0.5.1

• Relaxed python version constraint to >=3.10

v0.5.0 Release

• support new predictor train API
• updated notebooks
• more consistent usage of futures
  • fixed svd fit future
• handle fetching svd embed directly
• consistent usage of prompt and msa and assay data as objects to apis
• new PoET interface with embeddings api
  • old PoET still available under session.embedding.poet.deprecated.

v0.5.0 Development Release Fix 1

Fixes

• Prevents unnecessary reload

v0.5.0 Development Release

Public release of the python client for OpenProtein. Read more

Release notes:

• Refactor
  • More reliable and consistent Future implementation and usage
  • Polymorphic Jobs and properties persist through refresh and wait
• New PoET interface with Embeddings API
• Added predictor capability with access to all foundational models
  • Train and predict with GPs using PoET, ESM and more
• Some model aliases esm1[bv] and esm2