Skip to content

InDyVAE: An interaction and dependency-aware variational autoencoder for single-cell perturbation response generation.

Oct 2026 · Computational biology and chemistry · Vol 126 Pt 2, pp. 109514 · 0 citations · 33 references
Medicine

TL;DR

InDyVAE, an interaction- and dependency-aware variational autoencoder that models response generation as a connected sequence of transformations, is evaluated on four Perturb-seq datasets using treatment-effect agreement, top-gene overlap, and quality-control compliance under three thresholds.

Abstract

Single-cell perturbation profiling provides a powerful means of studying how genetic interventions reshape cellular transcription, but only a small portion of the possible perturbation space can be measured experimentally. Predicting the remaining conditions requires more than transferring an average treatment effect: jointly applied perturbations may alter one another, cellular and technical states modulate the observed response, and the resulting latent variation must be faithfully expressed at the gene level. We address these coupled requirements with InDyVAE, an interaction- and dependency-aware variational autoencoder that models response generation as a connected sequence of transformations. Perturbation Interaction Learning (PIL) represents the effects of active interventions in a shared context, allowing each treatment's contribution to reflect its co-occurring perturbations while preserving its individual signal. Latent State Dependency Modeling (LSDM) then conditions the perturbation response on basal cellular and quality-associated states, retaining the distinct roles of these sources of variation. Nonlinear Expression Mapping (NEM) translates the integrated state into gene expression through a direct pathway complemented by localized functional responses in latent space. We evaluate InDyVAE on four Perturb-seq datasets using treatment-effect agreement, top-gene overlap, and quality-control compliance under three thresholds. Comparisons with recent reference models, including CRADLE-VAE and AttentionPert, show strong response recovery on Norman and metric-dependent trade-offs between response accuracy and rule-based QC pass rates on Dixit. For single-gene interventions, it achieves higher quality-control pass rates on Replogle and stronger treatment-effect estimates on Adamson, while the remaining comparisons are dataset- and metric-dependent. Ablation experiments further show that the three components contribute complementary capabilities, supporting the proposed organization of interaction, context, and expression modeling. Source code is available at https://github.com/yuqi0373-rgb/InDyVAE.

View source

Similar papers

Preprint Oct 2026

Synergy-Aware Residual Flow Matching for Single-Cell Perturbation Prediction

Predicting single-cell responses to genetic and chemical perturbations is important for understanding regulatory mechanisms and prioritizing therapeutic interventions. Existing methods have made progress by modeling perturbation-conditioned expression shifts with neural networks, graph priors, foundation-model represen...

Jing-Rui Wu, Wang-Yun Dan · 0 citations

DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction

Across several benchmarks, this method outperforms the strongest published method in settings involving combinatorial and unseen perturbation prediction, and is the strongest published method in settings involving combinatorial and unseen perturbation prediction.

Mustapha Bounoua, G. Franzese, P. Michiardi · 0 citations
#artificial intelligence Preprint Oct 2026

VCLMU: Mechanism-Centric Virtual Cell World Modeling for Perturbation Response

A mechanism-centric virtual cell world model that represents cellular state as a set of Latent Mechanism Units (LMUs) and treats genetic perturbations as actions on these latent states supports mechanism-level latent state transition as a useful formulation for virtual cell models that aim to predict and interpret cell...

Yu-Wei Miao, Azim Dehghani Amirabad, S. Oloff et al. · 0 citations
#diffusion models Open access Sep 2026

scLDM: a conditional diffusion framework for single-cell perturbation prediction

Overall, scLDM provides a robust and biologically consistent strategy for in silico perturbation screening, and exhibits strong interpretability, as the learned perturbation embeddings show high functional alignment with known biological mechanisms.

Bo-Yang Wu, Yu-Hang Liu, Yue Cheng et al. · 0 citations

P2P: Cross-View Population Denoising for Unpaired Single-Cell Perturbation Response Prediction

AIVC (AI Virtual Cell) is a learned simulator of cellular behavior across conditions, and P2P (Perturbation-to-Perturbation) takes a stochastic cell-set view as its supervision unit, which attains the lowest expression RMSE and the highest Effect Pearson, DEG F1, and DEG average precision.

Hao-Jie Yang, Ran Su · 1 citation
Open access Sep 2026

PerturbBridge: Conditional Latent Schrödinger Bridge for Single-Cell Perturbation Response Prediction

PerturbBridge is proposed, a conditional latent Schrödinger Bridge framework that reformulates stochastic population transport over high-dimensional, sparse geneexpression profiles as bridge learning in a compact cell latent space, and achieves state-of-the-art performance in differential-expression recovery on both be...

Zhi-Hao Liu, Chang-Zhi Jiang, Can Yang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.