Skip to main content

Unoffical wrapper around UnipKa

Project description

Unofficial inference wrapper around DPTech's UnipKa model

This repo provides a simple wrapper around Zheng and co's fantastic UnipKa model. It refactors their example notebook into a small python package.

This repo provides:

  • A macro and micro pKa calculator, including pH-adjusted free energies for each microstate
  • A logD calculator following the methodology of Rowan Sci, calculating the weighted average of logP values for each microstate.
  • A state penalty function, useful for calculating permeability of neutral species, also following the methodology of Rowan Sci and Lawrenz and co.
  • An aqueous solvation energy calculator that uses xTB and the ALPB implicit solvent model.
  • A Kp,uu classifier built using Gsolv, logD and the state penalty as features.
  • A Jupyter widget to visualise the microstate distributions across a range of pH values.

Please cite the corresponding authors if you use this wrapper in your work!

Install using pip install unipka

Please see examples.ipynb Open In Colab or the unit tests for example usage.

Performance on the SAMPL benchmarks (pKa prediction):

Performance on logD benchmark:

Performance on Kpuu benchmark:

Performance on FreeSolv benchmark (solvation prediction):

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

unipka-0.0.6.tar.gz (41.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

unipka-0.0.6-py3-none-any.whl (43.5 kB view details)

Uploaded Python 3

File details

Details for the file unipka-0.0.6.tar.gz.

File metadata

  • Download URL: unipka-0.0.6.tar.gz
  • Upload date:
  • Size: 41.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for unipka-0.0.6.tar.gz
Algorithm Hash digest
SHA256 a5eb5b82c56706cb95b71dee6cf985c10eb51f6d25e3024b6095ea7a459ed560
MD5 a66771cbdd477814094bdd19f6658708
BLAKE2b-256 eca40d3e686d5e33eb957213b6d16d7c0fe047403f4c97e448c5d30b6abc6fbb

See more details on using hashes here.

File details

Details for the file unipka-0.0.6-py3-none-any.whl.

File metadata

  • Download URL: unipka-0.0.6-py3-none-any.whl
  • Upload date:
  • Size: 43.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.12

File hashes

Hashes for unipka-0.0.6-py3-none-any.whl
Algorithm Hash digest
SHA256 8ced841ec815ffa6312ccdbf1580a515cb028d450ca29bab711229dbee3e8d08
MD5 1a9a4b164d9999abb8c7867a2610004b
BLAKE2b-256 90e4dc793624fdd6be9c3c77250fc1d683beef7e94f9bcf7217041f93b9e4a68

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page