SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction

• URL: http://arxiv.org/abs/2603.17380v2
• Date: Thu, 19 Mar 2026 07:12:41 GMT
• Title: SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction
• Abstract summary: We present a specialized large-scale foundation model for virtual cell perturbation prediction.<n>First, we build a BioNeMo-based training and inference framework that substantially improves data throughput.<n>Second, we formulate perturbation prediction as conditional transport and implement it with a set-aware flow architecture.<n>Third, we evaluate the model on Tahoe-100M using a rigorous cell-level protocol centered on biologically meaningful metrics.
• Score: 46.645872209565574
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations from single-cell measurements. In practice, however, large-scale perturbation prediction remains constrained by three coupled bottlenecks: inefficient training and inference pipelines, unstable modeling in high-dimensional sparse expression space, and evaluation protocols that overemphasize reconstruction-like accuracy while underestimating biological fidelity. In this work we present a specialized large-scale foundation model SCALE for virtual cell perturbation prediction that addresses the above limitations jointly. First, we build a BioNeMo-based training and inference framework that substantially improves data throughput, distributed scalability, and deployment efficiency, yielding 12.51* speedup on pretrain and 1.29* on inference over the prior SOTA pipeline under matched system settings. Second, we formulate perturbation prediction as conditional transport and implement it with a set-aware flow architecture that couples LLaMA-based cellular encoding with endpoint-oriented supervision. This design yields more stable training and stronger recovery of perturbation effects. Third, we evaluate the model on Tahoe-100M using a rigorous cell-level protocol centered on biologically meaningful metrics rather than reconstruction alone. On this benchmark, our model improves PDCorr by 12.02% and DE Overlap by 10.66% over STATE. Together, these results suggest that advancing virtual cells requires not only better generative objectives, but also the co-design of scalable infrastructure, stable transport modeling, and biologically faithful evaluation.

Related papers

• Large-Small Model Collaboration for Zero-Shot Surgical Phase Recognition [45.191945465591374]
  Task-specific lightweight models for surgical phase recognition excel at capturing temporal dynamics but generalize poorly under domain shift.<n>We propose textbfLarge-textbfSmall textbfTemporal adaptation (textbfLaST), a novel large-small collaborative framework that enables zero-shot adaptation to unseen clinical domains.
  arXiv  Detail & Related papers  (2026-08-24T07:06:52Z)
• Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations [14.561544063927228]
  We propose a comprehensive methodology to adapt a deterministic physics foundation model into a highly efficient and accurate generative surrogate.<n>First, we introduce a two-stage inference scheme that combines a large-stride causal auto-regressive model with a non-causal temporal super-resolution network.<n>Second, we present Mean prediction regularization (MPR), a novel training objective that constrains the generative model to predict the deterministic distribution mean under null noise conditioning.
  arXiv  Detail & Related papers  (2026-08-06T14:41:11Z)
• Structure-Aware Prediction of PROTAC-Mediated Protein Degradability via Graph Neural Networks [0.0]
  We present DegradoMap, a graph neural network that predicts PROTAC-mediated degradability from protein structure and E3 ligase identity alone.<n>The model encodes biophysical priors through lysine-weighted graph pooling with per-protein normalization.<n>It achieves 0.646+-0.124 AUROC on target-unseen evaluation and 0.811 AUROC on CRBN->VHL E3-unseen transfer.
  arXiv  Detail & Related papers  (2026-06-01T09:39:22Z)
• MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data [47.97758608694957]
  We introduce Interpolating Manifold-Transport Flow (MIOFlow) 2.0.<n>This framework learns biologically informed cellular trajectories by integrating manifold learning, optimal transport, and neural differential equations.<n>It is validated on synthetic datasets, embryoid body differentiation, and spatially resolved axolotl brain regeneration.
  arXiv  Detail & Related papers  (2026-03-23T20:49:45Z)
• FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller [13.961569964076451]
  We present FEMBA, a bidirectional Mamba architecture pre-trained on over 21,000 hours of EEG.<n>We introduce a novel Physiologically-Aware pre-training objective, consisting of a reconstruction with low-pass filtering.<n>We employ Quantization-Aware Training (QAT) to compress the model to 2-bit weights.
  arXiv  Detail & Related papers  (2026-03-18T13:23:13Z)
• Anisotropic Permeability Tensor Prediction from Porous Media Microstructure via Physics-Informed Progressive Transfer Learning with Hybrid CNN-Transformer [0.0]
  Prediction of permeability tensors from pore-scale microstructure images is essential for subsurface flow modeling, yet direct numerical simulation requires hours per sample.<n>A physics-informed deep learning framework is presented that resolves this bottleneck by combining a MaxViT hybrid CNN-Transformer architecture with progressive transfer learning and differentiable physical constraints.
  arXiv  Detail & Related papers  (2026-03-18T09:41:01Z)
• Adaptive Uncertainty-Guided Surrogates for Efficient phase field Modeling of Dendritic Solidification [0.24629531282150874]
  This work presents a surrogate model for dendritic solidification that employs uncertainty-driven adaptive sampling with micro XG and CNNs.<n>The framework systematically investigates how temporal selection, adaptive sampling, and the choice between domain-informed data-driven surrogates affect Xtemporal- model performance.
  arXiv  Detail & Related papers  (2026-02-17T10:43:24Z)
• From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures [12.68400434984463]
  MLIPs fail to reproduce the physical smoothness of the quantum potential energy surface.<n>Existing evaluations, such as microcanonical molecular dynamics, are computationally expensive and primarily probe near-equilibrium states.<n>We introduce the Bond Smoothness Characterization Test (BSCT) to improve evaluation metrics for MLIPs.
  arXiv  Detail & Related papers  (2026-02-04T18:50:10Z)
• Universal Battery Degradation Forecasting Driven by Foundation Model Across Diverse Chemistries and Conditions [15.502149500162227]
  This work proposes a unified capacity forecasting framework that maintains robust performance across diverse chemistries and usage scenarios.<n>We curate 20 public aging datasets into a large-scale corpus covering 1,704 cells and 3,961,195 charge-discharge cycle segments.<n>Experiments on both seen and deliberately held-out unseen datasets show that a single unified model achieves competitive or superior accuracy compared with strong per-dataset baselines.
  arXiv  Detail & Related papers  (2025-12-30T10:14:37Z)
• 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)
• Linearized Optimal Transport for Analysis of High-Dimensional Point-Cloud and Single-Cell Data [45.87606039212519]
  Single-cell technologies generate high-dimensional point clouds of cells.<n>Each patient is represented by an irregular point cloud rather than a simple vector.<n>We adapt the Linear Optimal Transport framework to embed irregular point clouds into a fixed-dimensional Euclidean space.
  arXiv  Detail & Related papers  (2025-10-24T21:33:12Z)
• TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion [18.028061388104963]
  We propose textbfTGLF-SINN (Spectra-Informed Neural Network) with three key innovations.<n>Our approach achieves superior performance with significantly less training data.<n>In downstream flux matching applications, our NN surrogate provides 45x speedup over TGLF while maintaining comparable accuracy.
  arXiv  Detail & Related papers  (2025-09-07T09:36:51Z)
• STONet: A neural operator for modeling solute transport in micro-cracked reservoirs [0.49998148477760973]
  We introduce a novel neural operator, the Solute Transport Operator Network (STONet), to efficiently model contaminant transport in micro-cracked porous media.<n>Our numerical experiments demonstrate that, once trained, STONet achieves accurate predictions, with relative errors typically below 1% compared with FEM simulations.
  arXiv  Detail & Related papers  (2024-12-07T07:53:47Z)
• CRTRE: Causal Rule Generation with Target Trial Emulation Framework [47.2836994469923]
  We introduce a novel method called causal rule generation with target trial emulation framework (CRTRE) CRTRE applies randomize trial design principles to estimate the causal effect of association rules. We then incorporate such association rules for the downstream applications such as prediction of disease onsets.
  arXiv  Detail & Related papers  (2024-11-10T02:40:06Z)
• Learning Large-scale Subsurface Simulations with a Hybrid Graph Network Simulator [57.57321628587564]
  We introduce Hybrid Graph Network Simulator (HGNS) for learning reservoir simulations of 3D subsurface fluid flows. HGNS consists of a subsurface graph neural network (SGNN) to model the evolution of fluid flows, and a 3D-U-Net to model the evolution of pressure. Using an industry-standard subsurface flow dataset (SPE-10) with 1.1 million cells, we demonstrate that HGNS is able to reduce the inference time up to 18 times compared to standard subsurface simulators.
  arXiv  Detail & Related papers  (2022-06-15T17:29:57Z)

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.