New scAnyOmics framework integrates multi-omics data for virtual cell models

Researchers have developed scAnyOmics, a new generative framework designed to integrate and predict missing molecular information from incomplete single-cell multi-omics data. This framework distills knowledge from a pre-trained foundation model into a multimodal student model, enabling cross-modal prediction and reconstruction of data like transcriptomics, proteomics, and chromatin accessibility. Evaluated on a large dataset of 690,880 cells, scAnyOmics demonstrated superior performance over baseline methods in reconstructing missing modalities and showed promise in applications such as cell-type annotation and biological age estimation. AI

IMPACT Enables more comprehensive analysis of biological data by integrating disparate molecular measurements.

RANK_REASON The cluster contains an academic paper detailing a new computational framework for biological data analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXivLabs
• CatalyzeX Code Finder for Papers
• chromatin accessibility
• Connected Papers
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Litmaps
• protein-marker
• Proteomics
• scAnyOmics
• scATAC-seq
• ScienceCast
• scite Smart Citations
• single-cell RNA-seq
• transcriptomics

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →