liveBook · Manning

Fine-tuning

As explained in Build AI Drug Discovery Pipelines

Fine-tuning is the continued training of a pretrained model on task-specific data, usually with its parameters initialized from pretraining.

Fine-tuning continues training a pretrained model on labeled data for a specific task. Instead of learning every feature from scratch, the model adapts representations learned from millions of unlabeled protein sequences. section 12.3.4

For antibody classification, start with a protein language model such as ESM-2, attach a classification head, and teach the combined system patterns distinguishing HIV-1 from SARS-CoV-2 antibodies. Pretraining may encode motifs, secondary-structure propensities, and biophysical constraints before task training begins. section 12.3.4

A practical fine-tuning workflow includes:

  • Select a pretrained protein language model and add a task-specific classification head. section 12.3.4
  • Train on labeled antibody sequences rather than rebuilding sequence representations from random initialization. section 12.3.4
  • Compare validation and test accuracy, AUC, precision, recall, and F1, then inspect confusion matrices and performance by sequence length. section 12.3.4

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Defines the transfer-learning strategy and model components, but defers fine-tuning implementation details.
Examples
Uses ESM-2, labeled HIV-1 and SARS-CoV-2 antibody sequences, and classification metrics as its concrete examples.
What it assumes
Assumes labeled task data and contrasts pretrained adaptation with training a classifier from scratch.
What you can do after
Evaluate/understand how pretrained protein knowledge can be adapted for antibody classification.
How it connects
Connects transfer learning with protein language models, classification heads, antibody classification, and sequence representation learning.

Also explained in

Compare how 52 books explain fine-tuning →

Related concepts

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.