BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells

• URL: http://arxiv.org/abs/2608.05928v1
• Date: Thu, 06 Aug 2026 11:58:29 GMT
• Title: BioM-JEPA: joint-embedding prediction of graph-connected gene blocks in single cells
• Abstract summary: 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.
• Score: 64.21963170814706
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes. Here we present BioM-JEPA, a joint-embedding predictive architecture that instead predicts aggregate representations of graph-connected gene blocks defined by protein-association and corpus-derived coexpression evidence. A student network infers each target-block representation from the remaining genes in a cell, while a slowly updated teacher supplies the corresponding target from the full observed gene set. Under the reported extraction procedure, block-level prediction produced embeddings with higher effective rank and weaker association with detected-gene depth in the tested diagnostics than token-prediction, random-block and reconstruction controls. Across CellBench tasks, frozen BioM-JEPA embeddings retained expression, pathway and neighbourhood information and achieved the lowest aggregate perturbation-response error among the evaluated models. Representation diagnostics were also consistent with canonical pancreatic programmes and compositional relationships between genetic perturbations. Linear attention avoids constructing a quadratic gene-by-gene attention matrix; in a matched one-epoch hPancreas experiment at batch size 8, BioM-JEPA provided 5.75-fold higher fine-tuning throughput and 3.76-fold higher held-out embedding throughput than scFoundation. Together, these results support graph-connected gene blocks as useful prediction units for JEPA-style representation learning in single-cell biology.

Related papers

• Beyond Gene Reconstruction: Learning Cell Representations through Complementary Transcriptomic Views [8.738986684868424]
  We propose a contrastive pretraining framework that learns cell representations through complementary transcriptomic views.<n>We introduce specific adaptations along three dimensions --- co-expression-guided gene partitioning, expression-aware contrast-set construction, and competence-gated contrastive onset.
  arXiv  Detail & Related papers  (2026-08-02T04:35:45Z)
• BRIDGE: Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks [25.29216866424431]
  We propose an innovative framework named Biological Evidence Refinement and Heterogeneous Dynamic Gating for Gene Regulatory Networks (BRIDGE)<n>BRIDGE extracts gene and cell representations from the expression matrix and its matrix dual, and performs contrastive learning in the gene space and cell space between self and neighbors.<n>It then applies heterogeneous gated encoding to adaptively regulate information transfer between genes and cells, enabling robust transcription factor-to-target gene prediction.
  arXiv  Detail & Related papers  (2026-06-02T11:54:36Z)
• Graph Transformer-Based Pathway Embedding for Cancer Prognosis [12.185038682072213]
  We introduce PATH, a modulation-based, patient-conditioned gene embedding strategy.<n> PATH represents a paradigm shift by starting from a shared base embedding for each gene.<n> PATH achieves an F1 score of 0.8766, representing an 8.8 percent improvement over the current SOTA multi-omics benchmarks.
  arXiv  Detail & Related papers  (2026-04-17T20:41:58Z)
• Progressive Multi-Agent Reasoning for Biological Perturbation Prediction [32.71169480836875]
  We present LINCSQA, a novel benchmark for predicting target gene regulation under complex chemical perturbations.<n>We also propose PBio-Agent, a multi-agent framework that integrates difficulty-aware task sequencing with iterative knowledge refinement.<n>Our key insight is that genes affected by the same perturbation share causal structure, allowing confidently predicted genes to contextualize more challenging cases.
  arXiv  Detail & Related papers  (2026-02-07T06:59:44Z)
• Beyond Independent Genes: Learning Module-Inductive Representations for Gene Perturbation Prediction [48.80217316452559]
  scBIG is a module-inductive prediction framework that explicitly models coordinated gene programs.<n> scBIG consistently outperforms state-of-the-art methods, particularly on unseen and perturbation settings.
  arXiv  Detail & Related papers  (2026-02-03T16:43:40Z)
• Interpretable Perturbation Modeling Through Biomedical Knowledge Graphs [2.9275990558029075]
  multimodal embeddings are integrated into biomedical knowledge graphs.<n>We train a graph attention network to learn the delta expression profile of landmark genes for a given drug-cell pair.<n>Our framework provides a path toward mechanistic drug modeling.
  arXiv  Detail & Related papers  (2025-12-24T04:42:25Z)
• 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)
• CSGDN: Contrastive Signed Graph Diffusion Network for Predicting Crop Gene-phenotype Associations [6.5678927417916455]
  We propose a Contrastive Signed Graph Diffusion Network, CSGDN, to learn robust node representations with fewer training samples to achieve higher link prediction accuracy. We conduct experiments to validate the performance of CSGDN on three crop datasets: Gossypium hirsutum, Brassica napus, and Triticum turgidum.
  arXiv  Detail & Related papers  (2024-10-10T01:01:10Z)
• Predicting Genetic Mutation from Whole Slide Images via Biomedical-Linguistic Knowledge Enhanced Multi-label Classification [119.13058298388101]
  We develop a Biological-knowledge enhanced PathGenomic multi-label Transformer to improve genetic mutation prediction performances. BPGT first establishes a novel gene encoder that constructs gene priors by two carefully designed modules. BPGT then designs a label decoder that finally performs genetic mutation prediction by two tailored modules.
  arXiv  Detail & Related papers  (2024-06-05T06:42:27Z)
• Single-Cell Deep Clustering Method Assisted by Exogenous Gene Information: A Novel Approach to Identifying Cell Types [50.55583697209676]
  We develop an attention-enhanced graph autoencoder, which is designed to efficiently capture the topological features between cells. During the clustering process, we integrated both sets of information and reconstructed the features of both cells and genes to generate a discriminative representation. This research offers enhanced insights into the characteristics and distribution of cells, thereby laying the groundwork for early diagnosis and treatment of diseases.
  arXiv  Detail & Related papers  (2023-11-28T09:14:55Z)
• Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology [57.25098075813054]
  We propose a new framework for gene discovery entitled Un Phenotype Ensembles. It builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations.
  arXiv  Detail & Related papers  (2023-01-07T18:36:44Z)

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.