PLMA

This repository contains the analysis code for the manuscript "

Protein Language Modeling and Evolutionary Analysis Reveal an N-terminal Determinant of Functional Divergence in Cytochrome P450s from Sophora. tonkinensis

". It includes four core Python scripts that implement the complete workflow: 1) Feature generation from ESM-2 embeddings and evolutionary rates (Method 2.6), 2) Classifier evaluation (Method 2.7.1), 3) Sequence length optimization (Method 2.7.2), and 4) Amino acid position importance analysis (Method 2.8). The code is fully reproducible and accompanies the preprint on bioRxiv.