PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction

• URL: http://arxiv.org/abs/2606.27752v1
• Date: Fri, 26 Jun 2026 06:15:04 GMT
• Title: PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction
• Abstract summary: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond to interventions.<n>We introduce PerturbCellRL, a reinforcement learning framework that post-trains a pretrained single-cell transcriptomic generator.<n>We evaluate PerturbCellRL on multiple genetic and chemical perturbation benchmarks.
• Score: 28.013973806760976
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single-cell perturbation models can reduce costly wet-lab screening by predicting how cells respond transcriptionally to interventions. While recent generative models improve population-level prediction, individual generated cells are not explicitly checked for biological consistency. We introduce PerturbCellRL, a reinforcement learning (RL) framework that post-trains a pretrained single-cell transcriptomic generator using a suite of cell-level verifiers as rewards. These verifiers define four rewards: Pearson top-k similarity, RMSE top-k proximity, DE Spearman, and Pathway activity. The Pathway activity verifier rewards cells whose pathway responses match known perturbation biology. We evaluate PerturbCellRL on multiple genetic and chemical perturbation benchmarks. Across these benchmarks, PerturbCellRL improves over the pretrained flow-matching generator on reward-aligned evaluation metrics and a held-out evaluation metric. Moreover, PerturbCellRL remains competitive with state-of-the-art methods on population-level metrics. Together, these results frame trustworthy single-cell prediction as verifier-guided generative alignment, moving beyond matching expression distributions toward predictions whose single-cell perturbation effects are explicitly checked for biological consistency.

Related papers

• PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction [17.491072730946158]
  We propose PopPert, a framework that explicitly parameterizes population-level joint gene expression distributions.<n>Given a control population distribution and a perturbation condition, PopPert predicts perturbation-induced changes in distribution parameters.<n>PopPert achieves superior overall performance in differential expression recovery, perturbation effect estimation, and population-level distribution matching.
  arXiv  Detail & Related papers  (2026-09-01T14:59:03Z)
• BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells [64.21963170814706]
  BioM-JEPA predicts aggregate representations of graph-connected gene blocks.<n>A student network infers each target-block representation from the remaining genes in a cell.<n>Across CellBench tasks, BioM-JEPA embeddings retained expression, pathway and neighbourhood information.
  arXiv  Detail & Related papers  (2026-08-06T11:58:29Z)
• Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning [27.902219493068824]
  Perturbation experiments are central to understanding cellular mechanisms.<n>They remain costly and sparse, motivating prediction of gene expression responses for unobserved conditions.<n>We introduce CORE, which reframes prediction as a comparison task by organizing evidence into positive and negative outcomes from related perturbations.
  arXiv  Detail & Related papers  (2026-05-31T06:13:26Z)
• CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment [46.660621971318996]
  Inferring dynamics from population snapshots is a fundamental challenge in machine learning and biology.<n>We introduce CellBRIDGE, which augments feature-based OT with a directed, typed interaction cost derived from ligand-receptor activity.<n>By explicitly modeling cell-cell communication, CellBRIDGE improves cross-snapshot couplings and downstream trajectory estimates.
  arXiv  Detail & Related papers  (2026-05-28T22:37:54Z)
• Prototype Guided Post-pretraining for Single-Cell Representation Learning [0.0]
  Single-cell representation learning from gene expression data offers a way to uncover the complex regulatory logic underlying cellular function.<n>Several single-cell pretrained models have recently been proposed that treat genes as tokens and cells as sentences.<n>We introduce CellRefine, a post-pretraining method that operates between the pretraining and fine-tuning stages of a single-cell foundation model.
  arXiv  Detail & Related papers  (2026-05-08T16:08:10Z)
• MAT-Cell: A Multi-Agent Tree-Structured Reasoning Framework for Batch-Level Single-Cell Annotation [81.82645086402366]
  We propose MAT-Cell, a neuro-symbolic reasoning framework that reframes single-cell analysis into constructive, verifiable proof generation.<n> MAT-Cell injects symbolic constraints through adaptive Retrieval-Augmented Generation (RAG) to ground neural reasoning in biological axioms and reduce transcriptomic noise.<n>It significantly outperforms state-of-the-art (SOTA) models and maintains robust per-formance in challenging scenarios.
  arXiv  Detail & Related papers  (2026-04-07T04:56:06Z)
• Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells [48.885716676667776]
  Lingshu-Cell is a discrete diffusion model that learns transcriptomic state distributions and supports conditional simulation under perturbations.<n>It captures complex transcriptome-wide expression dependencies across approximately 18,000 genes without relying on prior gene selection.<n>It achieves leading performance on the Virtual Cell Challenge H1 genetic perturbation benchmark and in predicting cytokine-induced responses in human PBMCs.
  arXiv  Detail & Related papers  (2026-03-26T09:46:27Z)
• Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation [11.439588896862155]
  PT-RAG (Perturbation-aware Two-stage Retrieval-Augmented Generation) is a novel framework that extends Retrieval-Augmented Generation beyond traditional language-model applications to cellular biology.<n>Our results establish retrieval-augmented generation as a promising paradigm for modelling cellular responses to gene perturbation.
  arXiv  Detail & Related papers  (2026-03-07T14:31:27Z)
• Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schrödinger Bridges [51.83259180910313]
  A major bottleneck in gene function analysis is the unpaired nature of single-cell data.<n>We approximate Schrdinger Bridge (SB) to tackle unpaired single-cell perturbation data.<n>Our model effectively captures heterogeneous single-cell responses and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-17T08:27:13Z)
• Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges [68.98973318553983]
  We propose a framework based on Dual Diffusion Implicit Bridges (DDIB) to learn the mapping between different data distributions.<n>We integrate gene regulatory network (GRN) information to propagate perturbation signals in a biologically meaningful way.<n>We also incorporate a masking mechanism to predict silent genes, improving the quality of generated profiles.
  arXiv  Detail & Related papers  (2025-06-26T09:05:38Z)
• CausalBench: A Large-scale Benchmark for Network Inference from Single-cell Perturbation Data [61.088705993848606]
  We introduce CausalBench, a benchmark suite for evaluating causal inference methods on real-world interventional data. CaulBench incorporates biologically-motivated performance metrics, including new distribution-based interventional metrics.
  arXiv  Detail & Related papers  (2022-10-31T13:04:07Z)

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.