RetFold is proposed, a zero-training baseline that constructs backbones by retrieving CATH domains and refining inter-domain connections through geometry-based helix-linker optimization, at two orders of magnitude lower cost on CPU alone.
Abstract
Protein backbone generation models are often credited with exploring novel fold space based solely on low full-chain similarity to known proteins, yet this cannot distinguish a genuinely new fold from a novel assembly of known structural units. We first ask whether this granularity mismatch alone explains the reported rates, and introduce the Domain Retrieval Rate (DRR), the fraction of generated backbones for which any constituent domain matches a known domain in CATH S40. Applied to eight backbone generation models spanning diffusion and flow-matching paradigms, DRR finds locally alignable known structure in most outputs, while the fraction containing a substantially covered complete domain is considerably smaller and depends on the scoring convention. To calibrate what retrieval alone can achieve, we propose RetFold, a zero-training baseline that constructs backbones by retrieving CATH domains and refining inter-domain connections through geometry-based helix-linker optimization, at two orders of magnitude lower cost on CPU alone.
Structure-based drug design (SBDD) models are central to modern pharmaceutical research, enabling the rational exploration of protein-ligand interactions at atomic resolution. However, most existing approaches frame molecular generation as an isolated optimization or a one-to-one matching task, overlooking the shared binding patterns and intrinsic similarities among protein-ligand complexes. This fragmented perspective constrains their ability to capture the fundamental principles governing molecular recognition and binding specificity. Moreover, the limited availability of high-quality experimental data further hampers model generalization and real-world applicability. To address these challenges, we present READ, a retrieval-alignment molecular generation framework that conditions the generative process on small molecules targeting homologous proteins. Retrieved ligands are aligned with a diffusion model across multiple representational spaces and integrated as conditional guidance throughout successive stages of generation. Under a standardized docking-based evaluation protocol, READ achieves consistently strong performance against state-of-the-art SBDD methods. More importantly, it introduces a retrieval-alignment paradigm for structure-based molecular generation, offering a practical framework for early-stage computational hit generation while leaving prospective experimental validation as future work.
Dong Xu, Zhangfan Yang, Junchuang Cai et al.· IEEE transactions on computa...· 1 citation
UniStab is introduced, an end-to-end framework for predicting stability changes across all mutation types by leveraging the implicit geometric reasoning of a pre-trained folding model and demonstrates state-of-the-art performance, particularly in the challenging scenarios of multi-point mutations and indels.
Hong Tan, Shenggeng Lin, Yi Xiong· Chemical Science· 0 citations
Molecular docking and co-folding engines are widely used to prioritize compounds for wet-lab validation, yet their accuracy is known to vary substantially across protein targets for reasons that remain only qualitatively understood. Here we benchmark six docking and co-folding engines (RevDock, DiffDock, Boltz2, AutoDock-GPU, rDock, and PandaDock) across 14 protein families, evaluating scoring power, ranking power, docking power, and physical validity. Rather than treating engine performance as protein-family-specific, we classify all 14 families into six mechanistic groups according to which of four scoring-function simplifications, rigid receptor, pairwise additivity, fixed point charges, and implicit solvent, is most severely stressed by that family’s binding site. This framework helps explain, rather than simply describe, where each engine succeeds or fails: RevDock’s CNN rescoring layer mitigates the pairwise additivity and fixed-charge limitations relative to physics-only scoring, achieving the highest overall pose accuracy (73.3% of poses ≤ 2.0 Å RMSD), while Boltz2’s sequence-based co-folding bypasses the rigid-receptor assumption and achieves comparable affinity correlation (mean Pearson r ≈ 0.60 for both engines). PandaDock, run with expanded conformational sampling, matches RevDock on pose accuracy (72.1% of poses ≤ 2.0 Å, lowest median RMSD at 0.96 Å) and exceeds AutoDock-GPU on affinity correlation (mean r = 0.460), indicating that the performance of a physics-based scoring function is limited as much by search adequacy as by the scoring function itself. These results suggest that engine selection for a docking or co-folding campaign should be guided less by an engine’s aggregate benchmark ranking and more by which of these four structural and physical characteristics dominate the target of interest.
Kristoffer Alejo, Sarah Fisher, Tejaswan Kalluri et al.· bioRxiv· 0 citations
Performance estimates in protein function prediction depend not only on model choice but also on upstream decisions that define the learning problem. Using antioxidant protein classification as a controlled case study, we evaluated how dataset harmonisation, protein representation, redundancy control, and partitioning strategy affect protein machine learning pipelines. We integrated 18,804 records from 12 publicly available dataset entries into a curated consensus dataset of 4,193 protein sequences. One-hot encoding and six pretrained protein language model representations were evaluated as model inputs and as similarity spaces for redundancy reduction and distance-aware splitting. Representation choice substantially altered dataset geometry, retained dataset size, class balance, and downstream evaluation. At representation-specific p90 thresholds, one-hot encoding retained the complete dataset, whereas pretrained embeddings retained between 5% and 25% of sequences. Distance-aware partitioning reduced apparent performance relative to random splitting by up to 0.15 MCC before redundancy control, while this difference narrowed after similarity filtering. Selected configurations nevertheless maintained high performance under stricter evaluation, reaching an MCC of 0.84. These findings show that performance estimates should be interpreted as outcomes of complete data-centric workflows rather than isolated properties of predictive models.
Understanding and generation are often treated as two separate paradigms in training deep neural networks, despite the fact that both are trained with closely related objectives such as denoising and masked prediction. While prior studies have shown that generative models often learn suboptimal representations for understanding tasks in vision, it is less understood whether a similar gap exists in the protein domain. In this work, we systematically investigate this question by benchmarking state-of-the-art protein generative models on widely-used protein understanding tasks, and observe that these models exhibit consistently poor performance compared to existing protein encoders. Furthermore, inspired by the Representation Alignment (REPA) framework, we propose to explicitly align generative protein diffusion models with pretrained protein understanding models during training. Experiments on the MotifBench demonstrate that representation alignment significantly improves functional protein generation, boosting the MotifBench score of Protpardelle-1c from 39.2 to 47.1, corresponding to a 20% relative improvement. Our results suggest that representation alignment provides a general and effective mechanism for bridging understanding and generation in protein structure modeling.
Junde Xu, Yuansheng Huang, Zijun Gao et al.· 0 citations
TEDlm variants also substantially improve zero-shot Molecular Function prediction over ESM2, while matching it on various biophysical property tasks, indicating that signals are largely domain-intrinsic.
Tiejun Wei, S. Kandathil, Daniel W. A. Buchan et al.· bioRxiv· 0 citations