Splice-site prediction

Predict splice donor and acceptor positions.

Task definition

Input granularity: long sequence/base
Biological target: donor/acceptor sites
Output representation: per-base class probabilities
ML formulation: segmentation
Counting notes: NR

Benchmark coverage

8 benchmarks cover this task

B03Numeric results available

BEND

Human-genome tasks with biologically aligned splits; inspect each track for leakage controls.

7 benchmark-wide protocols · 105 benchmark-wide rows (not a task subtotal)

B05No public numeric result

GenBench

Framework and dataset suite; native task count follows current release documentation.

0 benchmark-wide protocols · 0 benchmark-wide rows (not a task subtotal)

B08Numeric results available

Benchmarking DNA foundation models for genomic and genetic tasks

One-time benchmark study rather than a maintained benchmark suite.

6 benchmark-wide protocols · 8 benchmark-wide rows (not a task subtotal)

B09Numeric results available

BEACON

Thirteen native tasks; some reuse OpenVaccine, Optimus and CRISPR datasets.

13 benchmark-wide protocols · 221 benchmark-wide rows (not a task subtotal)

B12No public numeric result

Benchmarking pre-trained gLMs for RNA sequence applications

Four native study processes; the GTEx tissue-specific splicing evaluation is additionally mapped to the alternative-splicing task family without changing the native-task count.

0 benchmark-wide protocols · 0 benchmark-wide rows (not a task subtotal)

B33No public numeric result

OmniGenBench

Meta-suite packaging RGB, BEACON, GUE, Genomic Benchmarks and PGB; native_task_count=5 suites, not the sum of their downstream tasks.

0 benchmark-wide protocols · 0 benchmark-wide rows (not a task subtotal)

B34Numeric results available

ERNIE-RNA downstream evaluation study

One-time model study spanning 15 named data packages; PrismNet is additionally stratified into 17 HeLa RBP assays.

12 benchmark-wide protocols · 231 benchmark-wide rows (not a task subtotal)

B02Numeric results available

Nucleotide Transformer benchmark

Eighteen downstream tasks are benchmark instances, not eighteen unique task families.

67 benchmark-wide protocols · 821 benchmark-wide rows (not a task subtotal)

Evaluation protocols

18 protocol units

Protocol	Track	Split / subset	Comparability
`PROT-B09-SPL-OFFICIAL-TRAIN-VALIDATION-TEST-SPLIT-SPL-1E33A2FA`	SPL B09-TR04	official train/validation/test split SPL	same_table_comparable external_data_policy;inference_budget
`PROT-B10-SPLICING-SITE-DONOR-HUMAN-ACCURACY-8B32E325`	Splicing Site NR	Donor_human Accuracy	official_board_comparable external_data_policy;inference_budget
`PROT-B10-SPLICING-SITE-DONOR-ARA-ACCURACY-6D33607C`	Splicing Site NR	Donor_ara Accuracy	official_board_comparable external_data_policy;inference_budget
`PROT-B10-SPLICING-SITE-DONOR-RICE-ACCURACY-70CE499C`	Splicing Site NR	Donor_rice Accuracy	official_board_comparable external_data_policy;inference_budget
`PROT-B10-SPLICING-SITE-ACCEPTOR-HUMAN-ACCURACY-74CC9BB8`	Splicing Site NR	Acceptor_human Accuracy	official_board_comparable external_data_policy;inference_budget
`PROT-B10-SPLICING-SITE-ACCEPTOR-ARA-ACCURACY-3E29C2A1`	Splicing Site NR	Acceptor_ara Accuracy	official_board_comparable external_data_policy;inference_budget
`PROT-B10-SPLICING-SITE-ACCEPTOR-RICE-ACCURACY-6E46F01E`	Splicing Site NR	Acceptor_rice Accuracy	official_board_comparable external_data_policy;inference_budget
`P-B08-SPLICE-DONOR`	Benchmarking DNA foundation models for genomic and genetic tasks — Splice-site prediction B08-TR04	paper-defined held-out test split splice donor identification	same_table_comparable cross-work compute/hardware equivalence
`P-B08-SPLICE-ACCEPTOR`	Benchmarking DNA foundation models for genomic and genetic tasks — Splice-site prediction B08-TR04	paper-defined held-out test split splice acceptor identification	same_table_comparable cross-work compute/hardware equivalence
`PROT-B02-NT-HF-BB57C4E1F7BBB374`	splice_sites_all B02-TR01	official tenfold cross-validation test folds splice_sites_all	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-901698F283EB4B59`	splice_sites_all B02-TR01	official tenfold cross-validation test folds splice_sites_all	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-E236852A1DAC5F27`	splice_sites_all B02-TR01	official tenfold cross-validation test folds splice_sites_all	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-8AD4FBFBA5A0CE1F`	splice_sites_acceptors B02-TR01	official tenfold cross-validation test folds splice_sites_acceptors	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-B3C58F8117ED8865`	splice_sites_acceptors B02-TR01	official tenfold cross-validation test folds splice_sites_acceptors	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-2355B1D9018EF94B`	splice_sites_acceptors B02-TR01	official tenfold cross-validation test folds splice_sites_acceptors	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-1DEE6FF253392D3A`	splice_sites_donors B02-TR01	official tenfold cross-validation test folds splice_sites_donors	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-DCA2FDDAC160D004`	splice_sites_donors B02-TR01	official tenfold cross-validation test folds splice_sites_donors	official_board_comparable external_data_policy;inference_budget
`PROT-B02-NT-HF-F34E5925B01C43FF`	splice_sites_donors B02-TR01	official tenfold cross-validation test folds splice_sites_donors	official_board_comparable external_data_policy;inference_budget