BEND
Human-genome tasks with biologically aligned splits; inspect each track for leakage controls.
7 个 benchmark 数值协议 · 105 条 benchmark 全局结果(非 task 小计)D4 · 变异效应与进化
Predict effects of non-coding variants on regulatory activity.
Regulatory variant-effect prediction
Benchmark coverage
Human-genome tasks with biologically aligned splits; inspect each track for leakage controls.
7 个 benchmark 数值协议 · 105 条 benchmark 全局结果(非 task 小计)Regulatory DNA evaluation across zero-shot, probing and fine-tuning regimes.
0 个 benchmark 数值协议 · 0 条 benchmark 全局结果(非 task 小计)One-time benchmark study rather than a maintained benchmark suite.
6 个 benchmark 数值协议 · 8 条 benchmark 全局结果(非 task 小计)Only molecular and functional variant challenges are in scope; phenotype-from-exome and patient-level tasks are excluded.
0 个 benchmark 数值协议 · 0 条 benchmark 全局结果(非 task 小计)评测协议
| Protocol | Track | Split / subset | 可比状态 |
|---|---|---|---|
P-B08-SQTL | Benchmarking DNA foundation models for genomic and genetic tasks — Regulatory variant-effect prediction B08-TR05 | nested chromosome-based held-out test groups putative causal sQTL | same_table_comparable cross-work compute/hardware equivalence |
P-B08-IPAQTL | Benchmarking DNA foundation models for genomic and genetic tasks — Regulatory variant-effect prediction B08-TR05 | nested chromosome-based held-out test groups putative causal ipaQTL | same_table_comparable cross-work compute/hardware equivalence |
P-B08-EQTL | Benchmarking DNA foundation models for genomic and genetic tasks — Regulatory variant-effect prediction B08-TR05 | nested chromosome-based held-out test groups putative causal eQTL | same_table_comparable cross-work compute/hardware equivalence |