Flexible Flows for Biological Sequence Design

• URL: http://arxiv.org/abs/2606.10543v1
• Date: Tue, 09 Jun 2026 08:11:14 GMT
• Title: Flexible Flows for Biological Sequence Design
• Abstract summary: We propose a structured coupling that encodes domain-specific preferences among sequence elements, biasing the source distribution toward plausible regions without modifying the flow objective or training procedure.<n>We introduce a latent classifier-free guidance mechanism that steers generation coherently in continuous latent space, along with Dirichlet-prior temperature scaling for test-time control over edit operations.<n>Our method achieves state-of-the-art performance across diverse biological sequence tasks, including density estimation, unconditional and conditional DNA sequence generation, and peptide sequence generation.
• Score: 32.53604513116057
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing functional biological sequences requires navigating vast discrete spaces under strict evolutionary and biophysical constraints. Discrete Flow Matching (DFM) offers a generative framework over such spaces, but existing approaches rely on biologically uninformative couplings and offer limited flexibility for variable-length sequence generation and fine-grained control. We propose a structured coupling that encodes domain-specific preferences among sequence elements, biasing the source distribution toward plausible regions without modifying the flow objective or training procedure. Building on this, we introduce a latent edit-based rate parameterization that models variable-length generation via edit operations conditioned on a shared global latent, akin to a latent variable model, while remaining tractable. We further introduce a latent classifier-free guidance mechanism that steers generation coherently in continuous latent space, along with Dirichlet-prior temperature scaling for test-time control over edit operations. Our method achieves state-of-the-art performance across diverse biological sequence tasks, including density estimation, unconditional and conditional DNA sequence generation, and peptide sequence generation.

Related papers

• Residual-Space Evolutionary Optimization via Flow-based Generative Models [42.567799767855035]
  We introduce residual-space evolutionary optimization, a model-agnostic framework that combines flow-based generative editing with evolutionary algorithms.<n>As a proof of concept, we validate on MorphoMNIST, a benchmark dataset for counterfactual generation.
  arXiv  Detail & Related papers  (2026-06-18T11:02:11Z)
• Towards A Generative Protein Evolution Machine with DPLM-Evo [73.57855006698269]
  We present DPLM-Evo, an evolutionary discrete diffusion framework that explicitly predicts substitution, insertion, and deletion operations during denoising.<n> DPLM-Evo improves sequence understanding and state-of-the-art mutation effect prediction performance on ProteinGym in the single-sequence setting.
  arXiv  Detail & Related papers  (2026-04-30T19:59:07Z)
• Minimal-Action Discrete Schrödinger Bridge Matching for Peptide Sequence Design [1.063850381314547]
  We introduce Minimal-action discrete Schrdinger Bridge Matching (MadSBM) as a rate-based generative framework for peptide design.<n>MadSBM formulates generation as a controlled continuous-time Markov process on the amino-acid edit graph.<n>We introduce guidance to the MadSBM sampling procedure towards a specific functional objective, expanding the design space of therapeutic peptides.
  arXiv  Detail & Related papers  (2026-01-29T23:38:36Z)
• Simulating Distribution Dynamics: Liquid Temporal Feature Evolution for Single-Domain Generalized Object Detection [58.25418970608328]
  Single-Domain Generalized Object Detection (Single-DGOD) aims to transfer a detector trained on one source domain to multiple unknown domains.<n>Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity.<n>We propose a new method, which simulates the progressive evolution of features from the source domain to simulated latent distributions.
  arXiv  Detail & Related papers  (2025-11-13T03:10:39Z)
• SURGIN: SURrogate-guided Generative INversion for subsurface multiphase flow with quantified uncertainty [9.423344821042933]
  We present a SURrogate-guided Generative INversion framework tailed for assimilation multiphase flow data.<n>SurGIN features a zero-shot conditional generation capability, enabling real-time assimilation of unseen monitoring data without task-specific retraining.<n>By unifying generative learning with surrogate-guided Bayesian inference, SURGIN establishes a new paradigm for inverse flow modeling and uncertainty quantification in parametric functional spaces.
  arXiv  Detail & Related papers  (2025-09-16T15:42:22Z)
• Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design [5.64033072458324]
  We present Multi-Objective-Guided Discrete Flow Matching (MOG-DFM), a general framework to steer any pretrained discrete flow matching generator.<n>At each sampling step, MOG-DFM computes a hybrid rank-directional score for candidate transitions.<n>We also trained two unconditional discrete flow matching models, PepDFM for diverse peptide generation and EnhancerDFM for functional enhancer DNA generation.
  arXiv  Detail & Related papers  (2025-05-11T18:17:44Z)
• Constrained Discrete Diffusion [61.81569616239755]
  This paper introduces Constrained Discrete Diffusion (CDD), a novel integration of differentiable constraint optimization within the diffusion process.<n>CDD directly imposes constraints into the discrete diffusion sampling process, resulting in a training-free and effective approach.
  arXiv  Detail & Related papers  (2025-03-12T19:48:12Z)
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials [62.72989417755985]
  We present UniGenX, a unified generative model for function in natural systems.<n>UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens.<n>It achieves state-of-the-art or competitive performance for the function-aware generation across domains.
  arXiv  Detail & Related papers  (2025-03-09T16:43:07Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
  This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
  arXiv  Detail & Related papers  (2024-07-16T14:05:03Z)
• Conditional Hybrid GAN for Sequence Generation [56.67961004064029]
  We propose a novel conditional hybrid GAN (C-Hybrid-GAN) to solve this issue. We exploit the Gumbel-Softmax technique to approximate the distribution of discrete-valued sequences. We demonstrate that the proposed C-Hybrid-GAN outperforms the existing methods in context-conditioned discrete-valued sequence generation.
  arXiv  Detail & Related papers  (2020-09-18T03:52:55Z)

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.