embedder_lib.py

from sklearn.base import BaseEstimator, TransformerMixin
from bio_embeddings.embed.seqvec_embedder import SeqVecEmbedder
import pandas as pd
from sklearn.feature_selection import SelectKBest

class Embedder(BaseEstimator, TransformerMixin):
    def __init__(self) -> None:
        self.embedder = SeqVecEmbedder()
        super().__init__()

    def fit(self, X, y=None):
        return self
    
    def transform(self, X: pd.DataFrame):
        return X.apply(self.embeddings, axis='columns')
        
    def embeddings(self, row):
        sequence = row[0]
        per_residue = self.embedder.embed(sequence)
        per_protein = self.embedder.reduce_per_protein(per_residue)
        return pd.Series(per_protein)
    
class FeaturesSelector(BaseEstimator, TransformerMixin):
    def fit(self, X, y=None):
        return self
    
    def transform(self, X: pd.DataFrame):
        return self.features_selector.transform(X)