Aug 2026· Proceedings of the National Academy of Sciences of the United States of America· Vol 123 32, pp.
e2535979123
· 0 citations· 25 references
Medicine
TL;DR
The AI-guided development of a first-in-class proteolysis-targeting chimera (PROTAC) designed to selectively degrade the CLIP1-LTK fusion protein is reported, providing a promising therapeutic strategy for overcoming acquired resistance in kinase-driven cancers.
Abstract
The discovery of CAP-Gly domain-containing linker protein 1(CLIP1)-Leukocyte tyrosine kinase (LTK) as an oncogenic fusion reveals a unique dependency not only on LTK kinase activity but also on CLIP1-mediated multimerization, a noncatalytic function that drives oncogenic signaling. While this fusion is currently targeted with anaplastic lymphoma kinase inhibitors, their exclusive focus on kinase inhibition leaves the scaffolding function intact, necessitating a complete protein clearance strategy. Here, we report the AI-guided development of a first-in-class proteolysis-targeting chimera (PROTAC) designed to selectively degrade the CLIP1-LTK fusion protein. By integrating deep learning models for ternary complex prediction with structure-based molecular optimization, we designed DCL05, an orally bioavailable degrader of CLIP1-LTK fusion protein, achieving picomolar degradation potency (DC50 = 40 pM) and robust antitumor activity. DCL05 consistently outperformed existing kinase inhibitors across a broad spectrum of LTK resistance-associated mutations, both in vitro and in vivo. Collectively, our study explores resistance-associated contexts of LTK and establishes a structure-guided PROTAC development pipeline, providing a promising therapeutic strategy for overcoming acquired resistance in kinase-driven cancers.
KLHL12 is identified as a potentially tumor-selective E3 ligase and the development of the first-in-class KLHL12-recruiting PROTACs are reported, which established KLHL12 as a promising tumor‑selective E3 ligase and provided a KLHL12-recruiting PROTAC platform for cancer therapy.
Shicheng Xu, Xian Zhang, Shun-Bo Hu et al.· Angewandte Chemie· 0 citations
Nuclear receptor-binding SET domain protein 3 (NSD3) is a histone H3K36 methyltransferase implicated in lung squamous cell carcinoma, yet chemical targeting is challenging due to the shallow PWWP reader pocket. Here, we report XSY12, a hydrophobic-tag degrader of the NSD3 PWWP domain that enables cellular NSD3 depletion (DC50 = 2.21 μM; Dmax = 80.2%). AI-guided discovery using a 3D fingerprinting platform (TF3P) identified a new NSD3-PWWP chemotype, which was optimized via deep learning-based molecular generation to the high-affinity ligand SYC2 (KD = 0.07 μM) and subsequently converted into XSY12. XSY12 promotes proteasome-dependent NSD3 depletion accompanied by HSP90-associated signatures, reduces H3K36 methylation, and induces apoptosis and G2/M arrest in NSD3-dependent models. In vivo, XSY12 achieved measurable exposure and significant tumor growth inhibition in an LUSC xenograft model at 100 mg/kg with acceptable tolerability. Collectively, these results provide a practical workflow linking AI-guided ligand discovery to functional degrader development.
Si-Yu Xiu, Zhenyu Jia, Qi Li et al.· Journal of Medicinal Chemist...· 0 citations
This work developed panKRAS degraders using a structure-guided strategy combining reversible KRAS binders with VHL-recruiting PROTACs and enables potent pan-allelic degradation, including ON-biased mutants, establishing KRAS degradation as a viable therapeutic modality and positioning ACBI4 as a pioneering panKRAS ON/OFF chemical probe.
A. Mantoulidis· Clinical Cancer Research· 0 citations
This review systematically explores AI applications in TPD development, covering the prediction and design of stable ternary complexes, rational optimization of linkers, high‐throughput screening for E3 ligase ligands, and accurate predictions of degradation efficiency and ADMET properties.
Proteolysis-targeting chimeras (PROTACs) are heterobifunctional small molecules that induce targeted protein degradation by recruiting an E3 ligase to a protein of interest. Since 2019, publication volume has accelerated, and computational methods have expanded from isolated demonstrations into practical tools for modeling PROTAC-induced ternary complexes, designing linkers, and forecasting degradation-related outcomes. Here, we present a Perspective on computational PROTAC methodologies published from 2019 to the present, organizing the field into two complementary streams: (i) constraint-driven, physics-based workflows that assemble and refine ternary complex models by enforcing geometric feasibility and evaluating pose stability using docking and molecular simulation; and (ii) data-driven workflows, including deep learning predictors and generative models that predict ternary complex structure, degradation end points, or linker chemistry from structural and assay data. We highlight representative approaches spanning restrained/tethered docking, MD-based refinement and dynamic stability scoring, coarse-grained free-energy modeling, SE(3)/E(3)-equivariant structure prediction, supervised degradation efficacy prediction, and generative linker design. We close by emphasizing persistent gaps, fragmented benchmarking, score robustness across targets and E3 ligases, and nonstandard molecular representations that currently limit generalization and reproducible, pipeline-ready deployment.
Joseph M. Schulz, R. Reynolds, Stephan C. Schürer· Journal of Chemical Informat...· 0 citations
Proteolysis-targeting chimeras (PROTACs) are heterobifunctional small molecules that induce selective degradation of disease-associated proteins through the ubiquitin-proteasome system. Rather than transiently inhibiting protein function, PROTACs induce selective elimination of the target protein. This event-driven pharmacological strategy offers significant advantages for targeting proteins that are difficult to modulate using conventional occupancy-driven inhibitors. Since the initial proof-of-concept studies and the entry of the first PROTAC candidates into clinical trials, targeted protein degradation has evolved into a clinically relevant therapeutic platform, particularly in oncology. In this review, we examine how these degraders work and the chemistry involved in their design—from linker optimization to selecting E3 ligases. We also explain how they form the molecular connections needed to function. Representative clinical programs targeting the androgen receptor, estrogen receptor, bromodomain-containing proteins, and Bruton tyrosine kinase are discussed to illustrate current therapeutic progress, remaining challenges, and lessons learned during clinical development. We also explore the hurdles in bringing these to patients, such as large molecular size, solubility, limited cell permeability, pharmacokinetics, tumor resistance, and the complexity of manufacturing. Emerging approaches, including reversible degraders, photoactivatable PROTACs, antibody-directed delivery systems, and artificial intelligence-assisted molecular design, are also highlighted as promising strategies to improve selectivity and drug-like properties. Collectively, these advances establish PROTAC technology as a transformative platform in modern drug discovery while emphasizing the scientific and translational challenges that must be addressed to enable broader clinical application.
Sandip Badadhe, Vikas B. Gawali, Mahesh D. Bhalsing et al.· Discover Chemistry· 0 citations
What does it take to trust AI-driven HVAC optimization? Our AI Model Factory combines agents, machine learning, reinforcement learning and deterministic checks in a governed workflow designed for messy, real-world building data. The post We built an AI factory for HVAC control appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduAug 18, 2026
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
MIT News · Artificial Intelligence· news.mit.eduMay 20, 2026
