scAnyOmics is a generative framework that distills knowledge from a frozen single-cell foundation model into a multimodal student model, integrating scRNA‑seq, protein‑marker measurements, and scATAC‑seq into a shared representation. It enables cross‑modal prediction and reconstruction of missing modalities, and was evaluated on 690,880 cells from six studies, outperforming baseline methods on held‑out donor data. The framework also supports applications such as cell‑type annotation, perturbation‑response prediction, and biological age estimation, providing a unified approach for integrating incomplete single‑cell multi‑omics data and transferring pretrained biological knowledge.
arXiv:2606. 03906v1 Announce Type: new Abstract: Simultaneous measurement of multiple omics modalities in single cells enables researchers to gain a more comprehensive understanding of cellular states and regulatory mechanisms.
arXiv:2608. 05928v1 Announce Type: new Abstract: Single-cell transcriptomes are sparse observations of coordinated biological programmes, yet most self-supervised models learn by reconstructing individual genes.
arXiv:2606. 07676v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) is a powerful tool for exploring biological properties dependent on structure, proximity, and interaction in tissue.
SCALE is a conditional transport model that treats cells as unordered sets to predict treated cell populations without requiring cell-level matching. It uses a shared set-aware encoder and a conditional DiT backbone to learn latent transport, enabling endpoint supervision that is directly delta-aligned. Across diverse perturbation types—including genetic, chemical, developmental, and immune—SCALE accurately recovers gene‑expression changes, response directions, and population structure, outperforming competing methods on CRISPR data and successfully prioritizing cytokines that elicit distinct immune responses.
The study evaluates 16 imputation methods for single‑cell RNA sequencing across 10 protocols, 6 downstream tasks, and 30 datasets. It finds that traditional methods generally perform better across many tasks, while deep learning approaches show more variability. No single method consistently outperforms others, and strong numerical recovery does not always improve biological interpretation.
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.
The paper introduces scEGFlow, an energy‑guided flow matching framework that predicts how single cells respond to perturbations by modeling continuous transitions from control to perturbed states. It uses conditional flow matching and condition‑specific energy gradients to dynamically adjust predictions without retraining, achieving superior performance on imaging and transcriptomic benchmarks, even for unseen perturbations or limited data. The method preserves cellular manifold geometry, heterogeneity, and accurately recapitulates gene‑expression regulatory patterns.
arXiv:2606. 29949v1 Announce Type: cross Abstract: H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides transcriptome-wide resolution at high cost with limited archival availability.
arXiv:2602. 15253v2 Announce Type: replace Abstract: Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and vision transformers, yet their existence in single-cell genomics remains largely unexplored.
The paper introduces CellForge, a team of autonomous agents that can autonomously generate, train, and validate predictive models for single‑cell perturbation data across transcriptomic, epigenomic, and proteomic contexts. By surveying literature, parsing data, and engaging in critic‑mediated discussions among specialized agents, CellForge produces end‑to‑end model architectures and code without human specification, achieving performance competitive with state‑of‑the‑art hand‑crafted methods. Human evaluators found CellForge’s research plans to be more scientifically sound and innovative than those produced by single large language models or deep‑research systems.
arXiv:2607. 22712v1 Announce Type: cross Abstract: Single-cell light microscopy images have become an important data source for characterizing cell phenotypes, but their complexity and heterogeneity pose challenges to high-throughput automated analysis.
CellMSA introduces a novel single‑cell representation learning framework that leverages a multiple‑sequence‑alignment‑inspired context model. For each target cell, it retrieves relevant cells across batches and related cell types, summarizing cross‑cell patterns into a context‑dependent gene‑pair representation that is fed into a pair‑aware encoder. Pretraining on a massive human single‑cell corpus (≈109 million cells) and subsequent benchmarks demonstrate consistent performance gains over existing methods.