# Pepti-drift: Scalable Safe-Active Peptide Generation Without Inference-Time Guidance

arXiv: https://arxiv.org/abs/2606.27824 · HTML: https://mlsanity.com/paper/2606.27824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 56 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation](https://mlsanity.com/paper/1806.02473/) (2018)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [SE(3) diffusion model with application to protein backbone generation](https://mlsanity.com/paper/2302.02277/) (2023)
- [ProGen2: Exploring the Boundaries of Protein Language Models](https://mlsanity.com/paper/2206.13517/) (2022)
- [Sample Efficiency Matters: A Benchmark for Practical Molecular Optimization](https://mlsanity.com/paper/2206.12411/) (2022)
- [Generative Modeling via Drifting](https://mlsanity.com/paper/2602.04770/) (2026)
- [Multi-Objective GFlowNets](https://mlsanity.com/paper/2210.12765/) (2022)
- [Diffusion Language Models Are Versatile Protein Learners](https://mlsanity.com/paper/2402.18567/) (2024)
- [PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion](https://mlsanity.com/paper/2412.17780/) (2024)
- [Full-Atom Peptide Design based on Multi-modal Flow Matching](https://mlsanity.com/paper/2406.00735/) (2024)
- [PPFlow: Target-aware Peptide Design with Torsional Flow Matching](https://mlsanity.com/paper/2405.06642/) (2024)
- [ProteinBench: A Holistic Evaluation of Protein Foundation Models](https://mlsanity.com/paper/2409.06744/) (2024)
- [Training Free Guided Flow Matching with Optimal Control](https://mlsanity.com/paper/2410.18070/) (2024)
- [CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph](https://mlsanity.com/paper/2406.10840/) (2024)
- [Multi-Objective-Guided Discrete Flow Matching for Controllable Biological Sequence Design](https://mlsanity.com/paper/2505.07086/) (2025)
- [Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension](https://mlsanity.com/paper/2411.18463/) (2024)
- [PepBenchmark: A Standardized Benchmark for Peptide Machine Learning](https://mlsanity.com/paper/2604.10531/) (2026)
- [DriftingMol: Decoder-Coupled Drift for One-Pass Property-Conditional Molecular Generation](https://mlsanity.com/paper/2605.24841/) (2026)

## Abstract (arXiv)

Therapeutic peptides are a promising drug modality, but their generation must satisfy multiple therapeutic constraints. We introduce BindSafe-PepBench, a fixed-budget benchmark that jointly evaluates target binding and four major safety metrics on the same generated candidates. We reveal that peptide length is a major confounder of joint binding-safety evaluation: longer peptides tend toward stronger predicted binding but less favorable predicted safety. This creates an apparent trade-off and can bias comparisons among models with different output-length distributions. We report absolute Safe-Active yield and exact-length-matched gains to distinguish generative improvements from output-length effects. High Safe-Active yield remains challenging, while the strongest multi-property methods rely on costly inference-time guidance. We therefore introduce Pepti-drift, a one-step generation framework that incorporates attraction toward target-specific binders and repulsion from liability-associated regions, requiring a single latent refinement followed by parallel decoding without inference-time guidance. Across 88 held-out targets, Pepti-drift achieves an 18.37% predicted Safe-Active yield while retaining positive exact-length-matched gains. The resulting gains are competitive with multi-property-guided baselines while requiring 468 times lower generation cost, enabling scalable and fair high-throughput peptide design.