rewire.it
Paper-reported evidence

Prediction of Gene Regulatory Connections with Joint Single-Cell Foundation Models and Graph-Based Learning

2025 · Preprint · PMC11838224.2

Paper-reported results. The values below come from this source, not an independent rewire.it run.

Open primary paper →DOI: 10.1101/2024.12.16.628715

Primary full text via Europe PMC XML; venue: bioRxiv; PMC ID: PMC11838224.

2 verified numerical rows · source checked 2026-09-15

Paper-reportedAuthor's model

scRegNet (Geneformer backbone)

Gene-regulatory link prediction

Reported score
0.89± 0.00 as printed
Metric
AUROC
Dataset / split
hESC cell-type-specific GRN

TFs plus 500 variable genes; mean from 50 independent evaluations.

Table 2, scRegNet (w/ Geneformer) row, hESC AUROC entryVerify at source →
Paper-reportedAuthor's model

scRegNet (scBERT backbone)

Gene-regulatory link prediction

Reported score
0.88± 0.00 as printed
Metric
AUROC
Dataset / split
hESC cell-type-specific GRN

TFs plus 500 variable genes; mean from 50 independent evaluations.

Table 2, scRegNet (w/ scBERT) row, hESC AUROC entryVerify at source →