Skip to main content

AbGPT: De Novo B-Cell Receptor Design via Generative Language Modeling

Project description

AbGPT

Official repository for AbGPT: De Novo B-Cell Receptor Design via Generative Language Modeling.

Setup

To use AbGPT, install via pip:

pip install abgpt

Alternatively, you can clone this repository and install the package locally:

$ git clone git@github.com:BaratiLab/AbGPT.git 
$ pip install AbGPT

Command line usage

Full sequence generation

To generate 1000 light chain sequences starting with "QLQL":

abgpt_generate --chain_type light --starting_residue QLQL --num_seqs 1000

To generate a BCR library with 1000 sequences for a number of starting residue (e.g., "QVQL", "EVQL", "VQLV") in the heavy chain:

abgpt_generate --chain_type heavy --starting_residue QVQL,EVQL,VQLV --num_seqs_per_residue 1000

To generate a BCR library with 1000 sequences for a number of starting residue (e.g., "QVQL", "EVQL", "VQLV") in the light chain:

abgpt_generate --chain_type light --starting_residue EIVL,EIVM,DIQM --num_seqs_per_residue 1000

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

abgpt-0.1.0.tar.gz (3.8 kB view details)

Uploaded Source

Built Distribution

abgpt-0.1.0-py3-none-any.whl (4.2 kB view details)

Uploaded Python 3

File details

Details for the file abgpt-0.1.0.tar.gz.

File metadata

  • Download URL: abgpt-0.1.0.tar.gz
  • Upload date:
  • Size: 3.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.14

File hashes

Hashes for abgpt-0.1.0.tar.gz
Algorithm Hash digest
SHA256 32dba27afbf4bc2919ffdb32889c2a737bb8cf527b8b3b21e270df8889148f0e
MD5 99fa821c5207f193c6accc7bb2be6ba7
BLAKE2b-256 2bc598a9e8f62b6b5bb74b492edcde4e6e217cde4adbb355a3d78d7b27a591f0

See more details on using hashes here.

File details

Details for the file abgpt-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: abgpt-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 4.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.14

File hashes

Hashes for abgpt-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 96ffef33e23642a50502449c34ec9e9b3c63574c72e7a30817d24ca19a19a455
MD5 6fd3ece9dbaed56972388469a92ff2d4
BLAKE2b-256 404a03f66d162083496a69cd54ee0587f4840a37944a3c8685de36c4d715b12f

See more details on using hashes here.

Supported by

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