SCONE: a subset-contrastive method for multi-omics network embedding
Pedro Henrique da Costa Avelar, Jonathan Cardoso-Silva, Min Wu, Sophia Tsoka · 2026
Read SCONE: a subset-contrastive method for multi-omics network embedding by Pedro Henrique da Costa Avelar, Jonathan Cardoso-Silva, Min Wu, Sophia Tsoka (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13631930.txt.
Description
Pedro Avelar and co-authors present a method that maps combined omics data into network form without heavy memory demands, in work published in 2026. Standard network methods choke on large single cell data sets. Their approach learns from small subgraphs at a time, using contrast between subsets as the training signal.
The pairwise similarity base of omics networks, usually a weakness, becomes the method's raw material. On single cell data it grouped cell types well by joining several omics layers. On bulk data it matched leading methods while seeing only limited views of the full data. The authors expect subset contrast ideas to spread in omics analysis.
Catalog record
| CREATOR | Pedro Henrique da Costa Avelar, Jonathan Cardoso-Silva, Min Wu, Sophia Tsoka |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 55 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |