ME-pKa: Un método de aprendizaje profundo con aprendizaje multimodal para la predicción de pKa de proteínas

Área de la Ciencia:

• Biochemistry and Molecular Biology; Computational Biology and Cheminformatics

Sus antecedentes:

• Protein pKa values dictate amino acid protonation states, crucial for protein structure, function, and drug interactions.

Objetivo del estudio:

• To develop a novel, accurate, and efficient multimodal protein pKa prediction model.

Principales métodos:

• Developed ME-pKa (Multimodal ESM pKa), a model integrating local amino acid environmental attributes with FASTA sequence characteristics.

Principales resultados:

• ME-pKa achieved superior prediction accuracy, outperforming existing models with low RMSE (0.845 ± 0.09) and MAE (0.641 ± 0.07) on the PE-pKa dataset.
• Demonstrated robust performance across major ionizable residues (Asp, Glu, His, Lys).
• Showcased exceptional accuracy for buried residues (RSA < 0.2), achieving low MAE values on multiple datasets.
• Confirmed the pH-dependent binding of PD-L1 antibodies, highlighting the model's practical implications in drug design.

Conclusiones:

• ME-pKa offers a significant advancement in predicting protein pKa values, particularly for challenging buried residues.