Journal Article

Charting γ-secretase substrates by explainable AI

Basset, Gabriele, Breimann, Stephan, Langosch, Dieter, Kamp, Frits, Abou-Ajram, Claudia, Steiner, Harald, Okochi, Masayasu, Frishman, Dmitrij, Müller, Stephan A., Lichtenthaler, Stefan F., Yanagida, Kanta, Güner, Gökhan

2025

Overview

Proteases recognize substrates by decoding sequence information—an essential cellular process elusive when recognition motifs are absent. Here, we unravel this problem for γ-secretase, an intramembrane-cleaving protease associated with Alzheimer’s disease and cancer, by developing Comparative Physicochemical Profiling (CPP), a sequence-based algorithm for identifying interpretable physicochemical features. We show that CPP deciphers a γ-secretase substrate signature with single-residue resolution, which can explain the conformational transitions observed in substrates upon γ-secretase binding. Using machine learning, we predict the entire human γ-secretase substrate scope, revealing numerous previously unknown substrates. Our approach outperforms state-of-the-art protein language models, improving prediction accuracy from 60% to 90%, and achieves an 88% success rate in experimental validation. Building on these advancements, we identify pathways and diseases not linked before to γ-secretase. Generally, CPP decodes physicochemical signatures—a concept that extends beyond sequence motifs. We anticipate that our approach will be broadly applicable to diverse molecular recognition processes. Comparative Physicochemical Profiling (CPP), an interpretable machine learning algorithm, identifies physicochemical signatures of γ-secretase substrates, capturing features hidden in sequences and enabling proteome-wide prediction of substrate recognition.

• Publisher: Nature Publishing Group UK,Nature Publishing Group,Nature Portfolio
• Subject: 631/114/1305 / 631/114/2410 / 631/45/468 / 82/80 / Accuracy / Algorithms / Alzheimer Disease - metabolism / Alzheimer's disease / Amino acids / Amyloid Precursor Protein Secretases - chemistry / Amyloid Precursor Protein Secretases - genetics / Amyloid Precursor Protein Secretases - metabolism / Artificial intelligence / Datasets / Decoding / Explainable artificial intelligence / Humanities and Social Sciences / Humans / Learning algorithms / Machine Learning / multidisciplinary / Neurodegenerative diseases / Physicochemical properties / Proteases / Protein Binding / Proteins / Proteomes / Science / Science (multidisciplinary) / Secretase / Signatures / Substrate Specificity / Substrates