liveBook · Manning

Antibody heavy chain

As explained in Build AI Drug Discovery Pipelines

A heavy chain is one of the larger polypeptide chains forming an antibody and contributing to its antigen-binding and effector properties.

An antibody heavy chain is one of two identical protein chains in an antibody. Its variable region helps determine which antigen the antibody binds, making its amino-acid sequence useful for target prediction. section 12.3.4

A heavy-chain sequence can serve as:

  • The input to a supervised classifier labeled for virus target, such as HIV-1 or SARS-CoV-2. section 12.3.4
  • A tokenized representation processed with embeddings, positional encodings, a Transformer encoder, and mean pooling. section 12.3.4
  • A screening aid for triaging candidate binders before experimental follow-up. section 12.3.4

Classifying antibody targets

A Transformer classifier receives a heavy-chain sequence and returns scores for HIV-1 and SARS-CoV-2. Test evaluation reports 0.7609 accuracy, 0.8053 AUC, and 0.7580 F1. section 12.3.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains variable-region binding and a complete sequence-classification workflow, but does not detail antibody structural biology beyond this role.
Examples
Uses HIV-1 and SARS-CoV-2 target labels, amino-acid sequences, mean pooling, and reported classifier metrics.
What it assumes
Assumes amino-acid sequences and labeled targets, while defining antibodies, heavy chains, variable regions, and antigen binding.
What you can do after
Apply it via a PyTorch Transformer classifier to rank antibody sequences by predicted HIV-1 or SARS-CoV-2 target.
How it connects
Connects antibody heavy chains with antibodies, antigens, protein language models, Transformers, and supervised classification.

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.