An AI-enabled structural atlas decodes kinase specificity across the human proteome.

David Vanderwall Edward L. Huttlin J. Mintseris Tomer M. Yaron-Barir Jared L. Johnson Kevin Dong Alex J. Bott Yuchen He Christina B. Schroeter Geordon A. Frere Mohamed Uduman Harin Lee Sean D. Landry S. Beausoleil João A. Paulo Lewis C. Cantley S. Gygi

Jul 2026 · Nature Biotechnology · 0 citations · 57 references

Medicine

TL;DR

KinoPlex, a computational framework that integrates predicted protein structures and kinase recognition motifs to assign phosphorylation potential and kinase specificity to all serine/threonine/tyrosine residues, is presented.

DOI PubMed Semantic Scholar

View source

Similar papers

Review Open access Jul 2026

Energetic and structural classification of the activation segment in typical protein kinases

An integrated energetic and structural classification of the activation segment across the human and murine kinome is provided, complementing existing conformational catalogues and offering a quantitative comparative basis for understanding kinase activation mechanisms relevant to drug design.

A. Ahiri, A. Aboulmouhajir · The European Chemistry and B... · 0 citations

Jul 2026

Unveiling Large-Scale Kinase-Centric Protein-Protein Interactions through a Knowledge-Informed Workflow.

A pipeline reformulating kinase-substrate modeling as a Bayesian inference problem is presented and it is revealed that the interaction types and distances to the catalytic pocket significantly influence pathogenicity scores.

Jinyuan Hu, Shimian Li, Yue Xue et al. · Journal of Chemical Informat... · 0 citations

Jul 2026

Abstract B052: The Kinase Library: A global atlas of the human protein kinome and its applications in drug discovery

Mass-spectrometry-based phosphoproteomics now profiles phosphorylation at proteome scale, yet converting site-level measurements into coherent, kinase-centered biology — and into actionable drug discovery decisions — remains a persistent barrier to target nomination, mechanism-of-action confirmation, and resistance m...

Tomer M. Yaron-Barir, Jared L. Johnson, Lewis C. Cantley · Clinical Cancer Research · 0 citations

#protein folding Open access Sep 2026

A curated benchmark for cofolding models on kinase conformational states

KinConfBench is introduced, a curated benchmark of 2225 high-quality human kinase chains to evaluate the ability of four state-of-the-art cofolding models—Boltz-2, Chai-1, Protenix, and RoseTTAFold-All-Atom—to recover both canonical and rare conformational states.

Kun-Yang Sun, T. Head-Gordon · npj Drug Discovery · 0 citations

Open access Jul 2026

A machine learning model predicts protein stability of annotated and alternate protein isoforms

The regulation of protein stability is essential for cellular homeostasis and is determined by a combination of intrinsic sequence motifs and extrinsic recognition enzymes. Despite growing knowledge of the protein degradation machinery, the ability to predict a protein’s stability from its amino acid sequence remains c...

Océane Marescal, Iain M. Cheeseman · bioRxiv · 0 citations

Open access Aug 2026

Structure-conditioned self-supervised learning of residue interaction constraints in protein kinases for variant interpretation

A structure-based method using SE(3)-transformers to learn residue compatibility with the local structural environment from experimentally resolved kinase 3D structures that captures biologically meaningful relationships between residue identity and 3D structural context is presented.

Shakiba Fadaei, F. Krebs, V. Zoete · Bioinformatics · 0 citations