ImmunoMatch 0.1.10

ImmunoMatch predicts the pairing between heavy and light chains in antibody.

ImmunoMatch is a machine learning framework for deciphering the molecular rules governing the pairing of antibody chains. Fine-tuned on an antibody-specific language model (AntiBERTa2), ImmunoMatch learns from paired H and L sequences from single human B cells to distinguish cognate H-L pairs and randomly paired sequences.

A total of three variants of ImmunoMatch, trained on different subsets of the data, are made available on huggingface:

Checkpoint name	Trained on
ImmunoMatch	A mixture of antibodies with both κ and λ light chains
ImmunoMatch-κ	Antibodies with κ light chains
ImmunoMatch-λ	Antibodies with λ light chains

Please note that the ImmunoMatch models are provided under a CC-BY-NC-4.0 license.

This package provides functions that can easily run immunomatch on batches of sequences stored in dataframe on your local computer, and attach the calculated pairing scores as a separate column for further analysis.

Use

Import the package: from ImmunoMatch import *

run_immunomatch_batches(data,hseq_col,lseq_col,ltype_col): where data is a dataframe, hseq_col is the name of the column holding the VH sequences, lseq_col is the name of the column holding the VL sequences, ltype_col is the name of the column indicating whether it's IGK or IGL.