{
  "id": 7248990,
  "title": "Machine Learning-Guided Classification of Druggable Pockets and Phylogenetic Druggability Transfer Across the Human Kinome",
  "url": "https://urgent.news/2026/09/13/machine-learning-guided-classification-of-druggable-pockets-and",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-13T00:00:00.000Z",
  "source": {
    "name": "bioRxiv",
    "slug": "biorxiv",
    "url": "https://www.biorxiv.org/content/10.64898/2026.09.06.749698v1?rss=1"
  },
  "original_language": "en",
  "account": "Machine learning techniques have been employed to create a comprehensive structural atlas of 11,945 kinase inhibitor complexes, enabling the classification of the seven canonical binding modes of protein kinases. This research highlights that around 303 Manning kinase domains have been targeted by known inhibitors, accounting for roughly 56.5% of the total Manning kinase domains. Notably, only 26% (78 kinases) among these targeted kinases are inhibited using allosteric pharmacological agents, suggesting a vast untapped pharmacological potential. By examining the kinome's evolutionary relationships, researchers discovered that evolutionary closeness to another kinase often suggests shared allosteric pocket accessibility. Consequently, this study establishes that phylogenetic druggability transfer can serve as a valuable indicator for predicting whether a specific kinase can be effectively targeted with allosteric inhibitors. Furthermore, this work reframes the kinome phylogeny as a valuable tool for identifying pharmacological opportunities and offers a robust predictive framework for various types of inhibitors, such as orthosteric, allosteric, covalent, bifunctional inhibitors, and chemical degraders, across the less explored regions of the kinome.",
  "summary": "Protein kinases are among the most intensively pursued therapeutic targets in oncology and beyond, yet selectivity remains largely unsolved; around 536 Manning kinase domains share a conserved ATP-binding pocket, making it difficult to target one without hitting others. Allosteric binding modes which exploit conformational states unique to individual kinases or narrow kinase subfamilies offer a…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}