Loading
Life sciences · Preprint
arXiv · September 9, 2026
Posted before peer review. The findings may change or fail to hold.
ProMeta is a prototype-based graph neural network trained on episodic meta-learning to predict PROTAC degradation activity across E3 ligases using minimal labeled data. In silico benchmarks show improved AUROC over supervised baselines (19.9% improvement on CRBN-to-VHL transfer under K=2, Q=3), but the work is computationally validated only and has not undergone peer review; practical utility for PROTAC discovery remains undemonstrated experimentally.
Computational method development with episodic meta-learning validation. Computational framework trained and evaluated on PROTAC-E3 ligase degradation datasets; focus on CRBN and VHL ligases with underexplored ligase generalization goal.. Intervention: ProMeta: prototype-based graph neural network with episodic meta-learning training. Compared with: Supervised graph neural network baseline.
ProMeta achieves AUROC 0.796 (K=2, Q=3) and 0.883 (K=2, Q=5) on CRBN-to-VHL transfer benchmark Improvement of 19.9% and 6.8% over supervised GNN baseline respectively Reverse VHL-to-CRBN transfer yields AUROC 0.702 (K=2, Q=3) and 0.821 (K=2, Q=5)
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is a computational method development study published on arXiv without peer-review status stated; it demonstrates algorithmic performance on benchmark datasets but lacks experimental validation in wet-lab or clinical contexts.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Proteolysis-targeting chimeras (PROTACs) have emerged as a transformative therapeutic strategy that selectively degrades historically ''undruggable'' targets via the ubiquitin-proteasome system. Despite growing efforts to develop computational predictors of PROTAC degradation activity, existing supervised approaches remain severely challenged by data scarcity and imbalance across E3 ligases, limiting their ability to generalize beyond well-studied ligase contexts. In practice, labeled data are heavily concentrated on a few ligases (e.g., CRBN and VHL), while the majority of E3 ligases remain underexplored yet are critical for expanding the design space of targeted degraders. Developing methods that enable robust cross-ligase generalization with minimal labeled data is therefore essential for improving the practical utility of computational PROTAC discovery. We reformulate PROTAC degradation activity prediction across E3 ligases as a few-shot meta-learning problem and present ProMeta, a prototype-based graph neural network trained through episodic meta-learning on source-E3 tasks and evaluated on held-out target-E3 tasks through support-conditioned inference. ProMeta performs inference without updating the encoder by dynamically estimating class prototypes from minimal target-ligase support samples. On the CRBN-to-VHL benchmark, ProMeta achieves AUROC values of 0.796 under K=2, Q=3 and 0.883 under K=2, Q=5, improving by 19.9% and 6.8%, respectively, over the corresponding supervised GNN baseline. Reverse VHL-to-CRBN transfer under the same protocol yielded AUROC values of 0.702 (K=2, Q=3) and 0.821 (K=2, Q=5), confirming bidirectional applicability while revealing direction and data-regime dependence. Together, these results support ProMeta as a practical framework for cross-ligase few-shot prediction under the evaluated support/query protocols.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.