What question did this study set out to answer?

January 25, 2026Kinases and Phosphatases0 citationsOpen Access

SPINET-KSP: A Multi-Modal LLM-Graph Foundation Model for Contextual Prediction of Kinase-Substrate-Phosphatase Triads

MAMichael Olaolu ArowoloXavier University of Louisiana MOMarian Emmanuel OkonXavier University of Louisiana DADavis AustriaXavier University of Louisiana

Key Points

The research aims to develop a model for the contextual prediction of kinase-substrate-phosphatase triads and enhance interaction predictions.
Developed a multi-modal LLM-Graph foundation model named SPINET-KSP.
Integrated multiple data sources including interactomes and structural contacts.
Utilized a cross-attention Graphormer to model kinase–phosphatase interactions.
Pre-trained on a large dataset of validated phospho-sites to improve prediction accuracy.
Achieved an AUROC of 0.852 for kinase-family classification with high sensitivity and specificity.
Identified 72% of known cancer-resistance triads within the top 10 rankings in mass spectrometry datasets.
Uncovered 247 additional triads validated using orthogonal proteomics.

Abstract

Reversible protein phosphorylation is an important regulatory mechanism in cellular signalling and disease, regulated by the opposing actions of kinases and phosphatases. Modern computer methods predict kinase–substrate or phosphatase–substrate interactions in isolation and lack specificity for biological conditions, neglecting triadic regulation. We present SPINET-KSP, a multi-modal LLM–Graph foundation model engineered for the prediction of kinase–substrate–phosphatase (KSP) triads with contextual awareness. SPINET-KSP integrates high-confidence interactomes (SIGNOR, BioGRID, STRING), structural contacts obtained from AlphaFold3, ESM-3 sequence embeddings, and a 512-dimensional cell-state manifold with 1612 quantitative phosphoproteomic conditions. A heterogeneous KSP graph is examined utilising a cross-attention Graphormer with Reversible Triad Attention to mimic kinase–phosphatase antagonism. SPINET-KSP, pre-trained on 3.41 million validated phospho-sites utilising masked phosphorylation modelling and contrastive cell-state learning, achieves an AUROC of 0.852 for kinase-family classification (sensitivity 0.821, specificity 0.834, MCC 0.655) and a Pearson correlation coefficient of 0.712 for phospho-occupancy prediction. In distinct 2025 mass spectrometry datasets, it identifies 72% of acknowledged cancer-resistance triads within the top 10 rankings and uncovers 247 supplementary triads validated using orthogonal proteomics. SPINET-KSP is the first foundational model for simulating context-dependent reversible phosphorylation, enabling the targeting of dysregulated kinase-phosphatase pathways in diseases.

Ask AI

Helpful

Bookmark

View Full Paper