Reproduce “SynLeaF: A Dual-Stage Multimodal Fusion Framework for Synthetic Lethality Prediction Across Pan- and Single-Cancer Contexts” 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

Zheming Xing, Siyuan Zhou, Ruinan Wang, Rui Han, Shiming Zhang, Shiqu Chen, Yurui Huang, Jiahao Ma and 4 more

SynLeaF predicts synthetic-lethal gene pairs by combining omics measurements with a biomedical knowledge graph. It separately pretrains both modalities, then applies feature-distilled joint training or averages predictions, choosing by validation AUC. Across 19 settings it leads in 17; pan-cancer CV3 zero-shot AUC is 0.7407 versus SLGNN’s 0.5757, but predictions are not experimental confirmation.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.