Generative Modeling in Protein Design: Neural Representations, Conditional Generation, and Evaluation Standards

TL;DR

This survey systematically reviews generative AI methods in protein research, focusing on representations, architectures, task settings, evaluation standards, and future challenges for reliable protein engineering.

Contribution

It provides a comprehensive synthesis of generative models in protein design, comparing assumptions, conditioning, and evaluation practices to guide future research.

Findings

Catalogs foundational representations and architectures used in protein generative models.

Synthesizes evaluation standards emphasizing physical validity and function-oriented benchmarks.

Identifies open challenges like modeling dynamics, scaling, and biosecurity for future work.

Abstract

Generative modeling has become a central paradigm in protein research, extending machine learning beyond structure prediction toward sequence design, backbone generation, inverse folding, and biomolecular interaction modeling. However, the literature remains fragmented across representations, model classes, and task formulations, making it difficult to compare methods or identify appropriate evaluation standards. This survey provides a systematic synthesis of generative AI in protein research, organized around (i) foundational representations spanning sequence, geometric, and multimodal encodings; (ii) generative architectures including $\mathrm{SE}(3)$-equivariant diffusion, flow matching, and hybrid predictor-generator systems; and (iii) task settings from structure prediction and de novo design to protein-ligand and protein-protein interactions. Beyond cataloging methods, we compare assumptions, conditioning mechanisms, and controllability, and we synthesize evaluation best practices that emphasize leakage-aware splits, physical validity checks, and function-oriented benchmarks. We conclude with critical open challenges: modeling conformational dynamics and intrinsically disordered regions, scaling to large assemblies while maintaining efficiency, and developing robust safety frameworks for dual-use biosecurity risks. By unifying architectural advances with practical evaluation standards and responsible development considerations, this survey aims to accelerate the transition from predictive modeling to reliable, function-driven protein engineering.