Reproduce “CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Chen Zhao, Anqi Liu, Xiao Zhang, Xuewei Cao, Zhengming Ding, Qiuying Sha, Hui Shen, Hong-Wen Deng and 1 more
CLCLSA classifies subjects with incomplete multi-omics data by predicting missing omics representations from observed ones. It uses complete subjects to learn cross-omics mappings, alongside contrastive learning and attention over features and omics types. On KIPAN kidney-cancer classification, accuracy remains above 88% at a missing rate of 0.8, under imposed missingness; this does not establish biological recovery or clinical benefit.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.