MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from Histology

• URL: http://arxiv.org/abs/2602.02282v1
• Date: Mon, 02 Feb 2026 16:23:31 GMT
• Title: MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from Histology
• Authors: Susu Hu, Stefanie Speidel,
• Abstract summary: We introduce MoLF, a generative model for pan-cancer histogenomic prediction.<n>By dynamically routing inputs to specialized sub-networks, MoLF effectively decouples the optimization of diverse tissue patterns.<n>MoLF exhibits zero-shot generalization to cross-species data, suggesting it captures fundamental, conserved histo-molecular mechanisms.
• Score: 2.4068264948068276
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Inferring spatial transcriptomics (ST) from histology enables scalable histogenomic profiling, yet current methods are largely restricted to single-tissue models. This fragmentation fails to leverage biological principles shared across cancer types and hinders application to data-scarce scenarios. While pan-cancer training offers a solution, the resulting heterogeneity challenges monolithic architectures. To bridge this gap, we introduce MoLF (Mixture-of-Latent-Flow), a generative model for pan-cancer histogenomic prediction. MoLF leverages a conditional Flow Matching objective to map noise to the gene latent manifold, parameterized by a Mixture-of-Experts (MoE) velocity field. By dynamically routing inputs to specialized sub-networks, this architecture effectively decouples the optimization of diverse tissue patterns. Our experiments demonstrate that MoLF establishes a new state-of-the-art, consistently outperforming both specialized and foundation model baselines on pan-cancer benchmarks. Furthermore, MoLF exhibits zero-shot generalization to cross-species data, suggesting it captures fundamental, conserved histo-molecular mechanisms.

Related papers

• Towards Spatial Transcriptomics-driven Pathology Foundation Models [32.70436266943553]
  We introduce a vision-omics self-supervised learning framework that infuses localized molecular information into pathology vision encoders.<n>We instantiate SEAL by training on over 700,000 paired gene expression spot-tissue region examples spanning tumor and normal samples from 14 organs.<n> SEAL encoders exhibit robust domain generalization on out-of-distribution and enable new cross-modal capabilities such as gene-to-image retrieval.
  arXiv  Detail & Related papers  (2026-02-15T15:06:45Z)
• Mixture-of-experts Wishart model for covariance matrices with an application to Cancer drug screening [0.8594140167290097]
  We introduce a comprehensive Bayesian framework for analyzing heterogeneous covariance data through both classical mixture models and a novel mixture-of-experts Wishart model.<n>We develop an efficient Gibbs-within-Metropolis-Hastings sampling algorithm tailored to the geometry of the Wishart likelihood and the gating network.<n>We present an innovative application of our methodology to a challenging dataset: cancer drug sensitivity profiles.
  arXiv  Detail & Related papers  (2026-02-14T21:07:14Z)
• SAGE-FM: A lightweight and interpretable spatial transcriptomics foundation model [2.060288975192133]
  We introduce SAGE-FM, a lightweight spatial transcriptomics foundation model based on graph convolutional networks (GCNs)<n>Trained on 416 human Visium samples spanning 15 organs, SAGE-FM learns spatially coherent embeddings that robustly recover masked genes.<n>Results demonstrate that simple, parameter-efficient GCNs can serve as biologically interpretable and spatially aware foundation models for large-scale spatial transcriptomics.
  arXiv  Detail & Related papers  (2026-01-21T22:22:38Z)
• AdaFusion: Prompt-Guided Inference with Adaptive Fusion of Pathology Foundation Models [49.550545038402184]
  We propose AdaFusion, a novel prompt-guided inference framework.<n>Our method compresses and aligns tile-level features from diverse models.<n>AdaFusion consistently surpasses individual PFMs across both classification and regression tasks.
  arXiv  Detail & Related papers  (2025-08-07T07:09:31Z)
• Masked Omics Modeling for Multimodal Representation Learning across Histopathology and Molecular Profiles [0.0]
  Self-supervised learning has driven major advances in computational pathology.<n>However, histopathology alone often falls short for molecular characterization and understanding clinical outcomes.<n>We introduce MORPHEUS, a unified transformer-based pre-training framework that encodes both histopathology and multi-omics data into a shared latent space.
  arXiv  Detail & Related papers  (2025-08-01T15:29:26Z)
• A Phylogenetic Approach to Genomic Language Modeling [0.2912705470788796]
  We introduce a novel framework for training gLMs that explicitly models nucleotide evolution on phylogenetic trees.<n>Our approach integrates an alignment into the loss function during training but does not require it for making predictions.<n>We applied this framework to train PhyloGPN, a model that excels at predicting functionally disruptive variants from a single sequence alone.
  arXiv  Detail & Related papers  (2025-03-04T06:53:03Z)
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention [57.044719143401664]
  Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease.<n>We present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention.<n>Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance.
  arXiv  Detail & Related papers  (2025-03-01T07:02:30Z)
• TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model [32.670806339139034]
  We propose a novel approach that integrates topological constraints into a diffusion model to improve the generation of realistic, contextually accurate cell topologies.<n>Our method refines the simulation of cell distributions and interactions, increasing the precision and interpretability of results in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-08T18:02:22Z)
• LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models [55.5427001668863]
  We present a novel latent diffusion model dubbed LDMol for text-conditioned molecule generation.<n> Experiments show that LDMol outperforms the existing autoregressive baselines on the text-to-molecule generation benchmark.<n>We show that LDMol can be applied to downstream tasks such as molecule-to-text retrieval and text-guided molecule editing.
  arXiv  Detail & Related papers  (2024-05-28T04:59:13Z)
• Adaptive Fuzzy C-Means with Graph Embedding [84.47075244116782]
  Fuzzy clustering algorithms can be roughly categorized into two main groups: Fuzzy C-Means (FCM) based methods and mixture model based methods. We propose a novel FCM based clustering model that is capable of automatically learning an appropriate membership degree hyper- parameter value.
  arXiv  Detail & Related papers  (2024-05-22T08:15:50Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)
• A Twin Neural Model for Uplift [59.38563723706796]
  Uplift is a particular case of conditional treatment effect modeling. We propose a new loss function defined by leveraging a connection with the Bayesian interpretation of the relative risk. We show our proposed method is competitive with the state-of-the-art in simulation setting and on real data from large scale randomized experiments.
  arXiv  Detail & Related papers  (2021-05-11T16:02:39Z)
• PANTHER: Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning [7.7415390727490445]
  We introduce Augmented Pathway Nonnegative factorization for HighER-order feature learning (PANTHER) PANTHER selects genetic pathways that directly encode molecular mechanisms. We train a softmax classifier for disease types using the identified pathway groups.
  arXiv  Detail & Related papers  (2020-12-15T19:39:55Z)

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.