question · intermediate · partly written
Does any RNA plus protein integration method beat RNA-only and concatenated-PCA baselines in an independent test?
No independent head-to-head of WNN, MOFA+ and totalVI with RNA-only and concatenated baselines on RNA plus protein, with labels not derived from them, was found.
What was found more
Independent tests rank methods against each other or test RNA plus ATAC; the three methods' own authors compared them on one dataset. 123
Reported, not yet replicated
Observation
What is missing
An RNA plus protein benchmark with a zero point 2026-11-18
Add RNA-only, concatenated-PCA and random rows to a published per-dataset score table. 1
Reported, not yet replicated
What is known
Concatenated PCs scored 0.93 against 0.87 for MOFA+ on RNA plus ATAC; a linear model beat three joint methods at protein imputation. 2
Reported, not yet replicated
What is not
Whether WNN, MOFA+ or totalVI beat a trivial baseline on RNA plus protein. 1
Reported, not yet replicated
What would settle it
A run of the three methods and the baselines on the same paired RNA plus protein sets, with labels from an independent source. 1
Our inference
Still open here
- Would a reviewer count Liu's per-dataset score tables as enough to add baselines?
Not yet written: Hypotheses, Who works on it.
Linked from
Sources
- Liu C, Ding S, Kim HJ, Long S, et al.. Multitask benchmarking of single-cell multimodal omics integration methods. Nat Methods (2025). paper; opened 2026-11-18 all records citing this
- Makrodimitris S, Pronk B, Abdelaal T, Reinders M. An in-depth comparison of linear and non-linear joint embedding methods for bulk and single-cell multi-omics. Brief Bioinform (2023). paper; opened 2026-11-18 all records citing this
- Hao Y, Hao S, Andersen-Nissen E, Mauck WM, et al.. Integrated analysis of multimodal single-cell data. Cell (2021). paper; opened 2026-11-18 all records citing this
Where it sits on the map
History of this record (1)
This record has been changed 1 time, on the dates below. The note kept against each change is written for the people who maintain the atlas, in their own shorthand, so it is not shown here; it is in the record itself.
- Kind
- big-open
- Register
- open-question
- Triage
- needs-research
- Status
- partly written
- Last updated
- 2026-11-18
- Record
- content/questions/which-rna-and-protein-integration-method-beats-concatenated-pca.json