Intervention-Aware Multiscale Representation Learning from Imaging Phenomics and Perturbation Transcriptomics

• URL: http://arxiv.org/abs/2604.22832v1
• Date: Sun, 19 Apr 2026 19:14:21 GMT
• Title: Intervention-Aware Multiscale Representation Learning from Imaging Phenomics and Perturbation Transcriptomics
• Abstract summary: We introduce an intervention-aware distillation framework that leverages perturbational transcriptomics to guide image representation learning.<n>A transcriptome-conditioned teacher integrates gene expression and intervention metadata to produce soft distributions over a chemistry-aware codebook.<n>An image-only student learns to predict these distributions from microscopy alone, distilling mechanistic knowledge while operating independently at test time.
• Score: 8.652528896724666
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Microscopy-based phenotypic profiling is scalable for drug discovery but lacks the mechanistic depth of transcriptomics, which remains costly and scarce. Existing multimodal approaches either use images to support other modalities or naively align representations by sample identity, ignoring cell-type and dose variations in weakly paired data-limiting generalization to unseen interventions. In this paper, we introduce an intervention-aware distillation framework that leverages perturbational transcriptomics to guide image representation learning. A transcriptome-conditioned teacher integrates gene expression and intervention metadata to produce soft distributions over a chemistry-aware codebook organized by drug similarity. The teacher employs a fine-tuned single-cell foundation model to encode cell-type context and disentangle dose effects. An image-only student learns to predict these distributions from microscopy alone, distilling mechanistic knowledge while operating independently at test time. This design emphasizes intervention semantics rather than identity alignment and explicitly handles dose and cell-type mismatches. We provide theoretical guarantees showing that transcriptomic guidance tightens the risk bound for image-based prediction. On Cell Painting and RxRx datasets paired with L1000, our method significantly improves one-shot transfer to unseen interventions and drug-target gene discovery compared to self-supervised and alignment baselines.

Related papers

• Predicting Therapeutic Outcome via Aligning Patient-Specific Knowledge Graph and Gene-Level Perturbation Representations [8.993049322779862]
  PREDIKTOR aligns a personalized network view with a transferable transcriptomic perturbation view to predict clinical drug response.<n>On TCGA, PREDIKTOR consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-07-06T00:10:31Z)
• Integrating Biological Knowledge for Robust Microscopy Image Profiling on De Novo Cell Lines [6.8917447861745735]
  We propose a framework that integrates external biological knowledge into existing pretraining strategies to enhance microscopy image profiling models.<n>Our approach explicitly disentangles perturbation-specific and cell line-specific representations using external biological information.<n> Experimental results demonstrate that our method enhances microscopy image profiling for textitde novo cell lines.
  arXiv  Detail & Related papers  (2025-07-14T19:01:06Z)
• 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)
• Self-supervised Representation Learning with Local Aggregation for Image-based Profiling [84.52554180480037]
  Image-based cell profiling aims to create informative representations of cell images.<n>Recent developments in non-contrastive Self-Supervised Learning have inspired this paper.<n>We introduce specialized data augmentation and representation post-processing methods tailored to cell images.
  arXiv  Detail & Related papers  (2025-06-17T07:25:57Z)
• A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features [2.240470404069435]
  We propose a framework to enhance transcriptomics by distilling knowledge from microscopy images.<n>Using weakly paired data, our method aligns and binds modalities, enriching gene expression representations with morphological information.<n>These strategies improve the predictive power and retain the interpretability of transcriptomics, enabling rich unimodal representations for complex biological tasks.
  arXiv  Detail & Related papers  (2025-05-27T15:15:34Z)
• Meta-Entity Driven Triplet Mining for Aligning Medical Vision-Language Models [9.76070837929117]
  Existing alignment methods prioritize separation between disease classes over segregation of fine-grained pathology attributes.<n>Here, we propose MedTrim, a novel method that enhances image-text alignment through multimodal triplet learning.<n>Our demonstrations indicate that MedTrim improves performance in downstream retrieval and classification tasks compared to state-of-the-art alignment methods.
  arXiv  Detail & Related papers  (2025-04-22T14:17:51Z)
• Causal integration of chemical structures improves representations of microscopy images for morphological profiling [25.027684911103897]
  We introduce a representation learning framework, MICON, that models chemical compounds as treatments that induce counterfactual transformations of cell phenotypes.<n>We demonstrate that incorporating chemical compound information into the learning process provides consistent improvements in our evaluation setting.<n>Our findings point to a new direction for representation learning in morphological profiling, suggesting that methods should explicitly account for the multimodal nature of microscopy screening data.
  arXiv  Detail & Related papers  (2025-04-13T12:27:21Z)
• DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images [105.46086313858062]
  We introduce DiffKillR, a novel framework that reframes cell annotation as the combination of archetype matching and image registration tasks.<n>DiffKillR efficiently propagates annotations across large microscopy images, reducing the need for extensive manual labeling.<n>We will discuss the theoretical properties of DiffKillR and validate it on three microscopy tasks, demonstrating its advantages over existing supervised, semi-supervised, and unsupervised methods.
  arXiv  Detail & Related papers  (2024-10-04T00:38:29Z)
• Seeing Unseen: Discover Novel Biomedical Concepts via Geometry-Constrained Probabilistic Modeling [53.7117640028211]
  We present a geometry-constrained probabilistic modeling treatment to resolve the identified issues. We incorporate a suite of critical geometric properties to impose proper constraints on the layout of constructed embedding space. A spectral graph-theoretic method is devised to estimate the number of potential novel classes.
  arXiv  Detail & Related papers  (2024-03-02T00:56:05Z)
• BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys [99.7082441544384]
  We present BiomedJourney, a novel method for counterfactual biomedical image generation by instruction-learning. We use GPT-4 to process the corresponding imaging reports and generate a natural language description of disease progression. The resulting triples are then used to train a latent diffusion model for counterfactual biomedical image generation.
  arXiv  Detail & Related papers  (2023-10-16T18:59:31Z)
• Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing [53.89917396428747]
  Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. We explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model.
  arXiv  Detail & Related papers  (2023-01-11T16:35:33Z)
• Towards Unsupervised Learning for Instrument Segmentation in Robotic Surgery with Cycle-Consistent Adversarial Networks [54.00217496410142]
  We propose an unpaired image-to-image translation where the goal is to learn the mapping between an input endoscopic image and a corresponding annotation. Our approach allows to train image segmentation models without the need to acquire expensive annotations. We test our proposed method on Endovis 2017 challenge dataset and show that it is competitive with supervised segmentation methods.
  arXiv  Detail & Related papers  (2020-07-09T01:39:39Z)

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.