← Back to all news
arXiv AI By Zhaoqi Song, Ye Du, Yusuke Iwasawa, Yutaka Matsuo, Qian Niu

scAnyOmics: Foundation-Model Distillation for Any-to-Any Completion of Multi-omics Virtual Cells

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 2

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

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.

By Shuizhou Chen, Lang Yu, Xueqin Lin, Xinjie Mao, Songming Zhang, Xinyu Gu, Hao Wu, Sheng Xu, Kedu Jin, Lei Bai, Quan Qian, Qin Chen, Qiang Gao, Siqi Sun, Zhangyang Gao
More like this →
arXiv Machine Learning
1d ago

One Method Does Not Fit All: A Large-Scale Benchmark of Imputation Methods for Single-Cell RNA Sequencing Data

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.

By Yuichiro Iwashita, Ahtisham Fazeel Abbasi, Koichi Kise, Andreas Dengel, Muhammad Nabeel Asim
efficiencybenchmarkssafety
More like this →
Hugging Face Trending Papers
Aug 6

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

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.

ragfine-tuningefficiency
More like this →