Releases: OpenProteinAI/openprotein-python
Releases · OpenProteinAI/openprotein-python
v0.6.1
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
intosession.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 intosession.deprecated.design
- might still be needed to support older
train
models
- might still be needed to support older
- allows using the newly trained
- 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
v0.5.4
v0.5.3
v0.5.2
v0.5.1
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
andwait
- 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]
andesm2