# PETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening

arXiv: https://arxiv.org/abs/2608.19906 · HTML: https://mlsanity.com/paper/2608.19906/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 20 Aug 2026.

## Builds on (most cited first, 4 of 4)

- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [DeepDTA: Deep Drug-Target Binding Affinity Prediction](https://mlsanity.com/paper/1801.10193/) (2018)
- [AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation](https://mlsanity.com/paper/2506.05768/) (2025)
- [BindCLIP: A Unified Contrastive-Generative Representation Learning Framework for Virtual Screening](https://mlsanity.com/paper/2602.15236/) (2026)

## Abstract (arXiv)

Accurately ranking active ligands for a target protein pocket from massive chemical libraries remains a central challenge in virtual screening. DrugCLIP and its recent extensions substantially accelerate this process by encoding protein pockets and molecules into a shared embedding space. Despite this progress, further performance improvements typically require retraining the entire model, incurring substantial computational overhead and making target-specific customization inefficient. In this work, we formulate the specialization of pretrained virtual screening models to individual pockets as a test-time adaptation problem and propose PETA, a parameter-efficient framework that directly adapts pretrained model at test time. Given a target pocket, PETA constructs pocket-specific negatives through molecular diffusion and chemical validity filtering, and further moves them toward the reference ligand retrieved from structural databases via embedding-space mixup to create more challenging ranking tasks. A ranking objective then places greater emphasis on suppressing high-scoring invalid candidates that could contaminate the top-ranked screening results, providing structured supervision for lightweight adaptation. Experiments across diverse benchmarks demonstrate that this lightweight, pocket-specific adaptation outperforms both pretrained and fully retrained baselines while updating only the LayerNorm parameters, which account for approximately 0.03% of the full model.