Variable-Length Generative Protein Design via Generalized Poisson Flow

• URL: http://arxiv.org/abs/2607.09039v1
• Date: Fri, 10 Jul 2026 02:11:43 GMT
• Title: Variable-Length Generative Protein Design via Generalized Poisson Flow
• Abstract summary: Generalized Poisson Flow (GPFlow) is a variable-length generative framework that learns the rate function of an inhomogeneous generalized Poisson process.<n>We evaluate GPFlow across structure and sequence design, motif scaffolding, and peptide co-design.
• Score: 26.832992997199238
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The ability to generate variable-length proteins is crucial in protein design, where the optimal length is often unknown and tightly coupled to designability. Current diffusion- and flow-based generative models typically require the protein length to be specified before sampling, limiting their flexibility in exploring the feasible design space. To address this limitation, we introduce Generalized Poisson Flow (GPFlow), a variable-length generative framework that learns the rate function of an inhomogeneous generalized Poisson process by minimizing its negative log-likelihood. We establish population-level guarantees for recovering the joint multimodal distribution and derive an upper bound on the KL divergence between the data and generated distributions. We comprehensively evaluate GPFlow across structure and sequence design, motif scaffolding, and peptide co-design, spanning Euclidean, categorical, and Riemannian modalities to fully validate its variable-length generation quality. In unconditional design, GPFlow improves structural designability and achieves the best distributional fitness for sequence design compared to their corresponding fixed-length baselines, while perfectly recovering the length distribution. In conditional motif scaffolding, GPFlow ranks first on 10 of 16 structure-based design tasks with significantly more unique successes and also achieves more passed tasks in sequence-based design. In peptide co-design, GPFlow remains competitive even without access to a native-length oracle.

Related papers

• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Surface-based Molecular Design with Multi-modal Flow Matching [64.00572241268597]
  SurfFlow is a novel surface-based generative algorithm that enables comprehensive co-design of sequence, structure, and surface for peptides.<n> evaluated on the comprehensive PepMerge benchmark, SurfFlow consistently outperforms full-atom baselines across all metrics.
  arXiv  Detail & Related papers  (2026-01-08T02:19:29Z)
• ProtFlow: Fast Protein Sequence Design via Flow Matching on Compressed Protein Language Model Embeddings [8.068149785650649]
  ProtFlow is a fast flow matching-based protein sequence design framework.<n>By compressing and smoothing the latent space, ProtFlow enhances performance while training on limited computational resources.<n>We evaluate ProtFlow across diverse protein design tasks, including general peptides and long-chain proteins, antimicrobial peptides, and antibodies.
  arXiv  Detail & Related papers  (2025-04-15T08:46:53Z)
• Sampling-based Continuous Optimization with Coupled Variables for RNA Design [4.226911519009711]
  We develop continuous optimization methods for RNA design problems.<n>Our work consistently outperforms state-of-the-art methods in key metrics such as Boltzmann probability, ensemble defect, and energy gap.
  arXiv  Detail & Related papers  (2024-12-11T19:46:54Z)
• Pan-protein Design Learning Enables Task-adaptive Generalization for Low-resource Enzyme Design [44.258193520999484]
  We present CrossDesign, a domain-adaptive framework that leverages pretrained protein language models (PPLMs)<n>By aligning protein structures with sequences, CrossDesign transfers pretrained knowledge to structure models, overcoming the limitations of limited structural data.<n> Experimental results highlight CrossDesign's superior performance and robustness, especially with out-of-domain enzymes.
  arXiv  Detail & Related papers  (2024-11-26T17:51:33Z)
• On Generalization for Generative Flow Networks [54.20924253330039]
  Generative Flow Networks (GFlowNets) have emerged as an innovative learning paradigm designed to address the challenge of sampling from an unnormalized probability distribution. This paper attempts to formalize generalization in the context of GFlowNets, to link generalization with stability, and also to design experiments that assess the capacity of these models to uncover unseen parts of the reward function.
  arXiv  Detail & Related papers  (2024-07-03T13:42:21Z)
• Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation [55.93511121486321]
  We introduce FoldFlow-2, a novel sequence-conditioned flow matching model for protein structure generation.<n>We train FoldFlow-2 at scale on a new dataset that is an order of magnitude larger than PDB datasets of prior works.<n>We empirically observe that FoldFlow-2 outperforms previous state-of-the-art protein structure-based generative models.
  arXiv  Detail & Related papers  (2024-05-30T17:53:50Z)
• PPFlow: Target-aware Peptide Design with Torsional Flow Matching [52.567714059931646]
  We propose a target-aware peptide design method called textscPPFlow to model the internal geometries of torsion angles for the peptide structure design.<n>Besides, we establish a protein-peptide binding dataset named PPBench2024 to fill the void of massive data for the task of structure-based peptide drug design.
  arXiv  Detail & Related papers  (2024-03-05T13:26:42Z)
• OT-Flow: Fast and Accurate Continuous Normalizing Flows via Optimal Transport [8.468007443062751]
  A normalizing flow is an invertible mapping between an arbitrary probability distribution and a standard normal distribution. OT-Flow tackles two critical computational challenges that limit a more widespread use of CNFs. On five high-dimensional density estimation and generative modeling tasks, OT-Flow performs competitively to state-of-the-art CNFs.
  arXiv  Detail & Related papers  (2020-05-29T22:31:10Z)
• Learning Likelihoods with Conditional Normalizing Flows [54.60456010771409]
  Conditional normalizing flows (CNFs) are efficient in sampling and inference. We present a study of CNFs where the base density to output space mapping is conditioned on an input x, to model conditional densities p(y|x)
  arXiv  Detail & Related papers  (2019-11-29T19:17:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.