rewire.it
Paper-reported evidence

Benchmarking DNA large language models on quadruplexes

2025 · Peer-reviewed · version of record

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

Open primary paper →DOI: 10.1016/j.csbj.2025.03.007

Primary full text via Europe PMC XML; venue: Computational and Structural Biotechnology Journal; PMC ID: PMC11953744.

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

Paper-reportedIndependent paper evaluation

Caduceus (8M)

G-quadruplex classification

Reported score
95.0%± 0.5
Metric
Accuracy
Dataset / split
KEx

Pretrained model evaluated on KEx as reported in Table 5.

Table 5, Caduceus (8 M) row, Accuracy columnVerify at source →
Paper-reportedIndependent paper evaluation

DNABERT-2 (117M)

G-quadruplex classification

Reported score
97.0%± 0.5
Metric
Accuracy
Dataset / split
KEx

Pretrained model evaluated on KEx as reported in Table 5.

Table 5, DNABERT-2 (117 M) row, Accuracy columnVerify at source →