Saved in:
Bibliographic Details
Main Authors: Liang, Langzhang, Yang, Ming, Feng, Yi, Li, Junfan, Pan, Shirui, Xu, Yinghui, Ying, Tianlei, Zheng, Yizhen, Xu, Zenglin
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.22252
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911706792329216
author Liang, Langzhang
Yang, Ming
Feng, Yi
Li, Junfan
Pan, Shirui
Xu, Yinghui
Ying, Tianlei
Zheng, Yizhen
Xu, Zenglin
author_facet Liang, Langzhang
Yang, Ming
Feng, Yi
Li, Junfan
Pan, Shirui
Xu, Yinghui
Ying, Tianlei
Zheng, Yizhen
Xu, Zenglin
contents Protein sequence generation for engineering requires samples that are biophysically plausible and, when targeting a family/domain, remain recognizable members while exploring within-family diversity. Current discrete generative models typically start from uniform or masked-token noise, which discards strong position-specific constraints induced by evolution and forces the model to reconstruct conserved residues from scratch, leading to weak family control and low plausibility. We propose \emph{LineageFlow}, a Dirichlet flow-matching model that initializes generation from lineage priors derived from ancestral sequence reconstruction, turning generation into structured mutation from an evolved scaffold. Across diverse protein families, LineageFlow achieves family validity close to held-out natural sequences and improves predicted structural confidence over uniform-/mask-initialized baselines while maintaining substantial novelty and diversity. Finally, we introduce \emph{rerouting}, a single intermediate-time mutate--select--amplify intervention that enables objective-guided sampling without per-step predictor guidance and yields further gains in plausibility, including a zero-shot enzyme generation case study. Code is available at https://github.com/Jinx-byebye/LineageFlow.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22252
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence Generation
Liang, Langzhang
Yang, Ming
Feng, Yi
Li, Junfan
Pan, Shirui
Xu, Yinghui
Ying, Tianlei
Zheng, Yizhen
Xu, Zenglin
Computational Engineering, Finance, and Science
Protein sequence generation for engineering requires samples that are biophysically plausible and, when targeting a family/domain, remain recognizable members while exploring within-family diversity. Current discrete generative models typically start from uniform or masked-token noise, which discards strong position-specific constraints induced by evolution and forces the model to reconstruct conserved residues from scratch, leading to weak family control and low plausibility. We propose \emph{LineageFlow}, a Dirichlet flow-matching model that initializes generation from lineage priors derived from ancestral sequence reconstruction, turning generation into structured mutation from an evolved scaffold. Across diverse protein families, LineageFlow achieves family validity close to held-out natural sequences and improves predicted structural confidence over uniform-/mask-initialized baselines while maintaining substantial novelty and diversity. Finally, we introduce \emph{rerouting}, a single intermediate-time mutate--select--amplify intervention that enables objective-guided sampling without per-step predictor guidance and yields further gains in plausibility, including a zero-shot enzyme generation case study. Code is available at https://github.com/Jinx-byebye/LineageFlow.
title LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence Generation
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2605.22252