Biology-Instructions
A multi-omics sequence-instruction suite with 21 formal predictive tasks across DNA, RNA, protein, and multi-molecule inputs; the final paper reports task-specific held-out evaluations rather than a single aggregate score.
Scientific task · Sequence and regulation
Predict or design RNA structure
RNA功能与设计
rna-function-designCoverage
A multi-omics sequence-instruction suite with 21 formal predictive tasks across DNA, RNA, protein, and multi-molecule inputs; the final paper reports task-specific held-out evaluations rather than a single aggregate score.
Three-output regression of ON, OFF, and ON/OFF programmable RNA-switch values, aggregated as their mean squared Pearson correlation.
A 13-task RNA representation benchmark covering structure, function, processing, modification, translation, degradation, programmable switches, and CRISPR activity.
Thirteen-class functional classification of a non-coding RNA sequence, evaluated with exact extracted-label accuracy.
Multi-label prediction of RNA chemical modifications, evaluated with macro area under the ROC curve.
Regression of alternative-polyadenylation isoform usage from an RNA sequence, reported as squared Pearson correlation under the paper's R2 label.
Regression of mean ribosome loading from an RNA sequence, reported as squared Pearson correlation under the paper's R2 label.
Sequence-comprehension and manipulation category spanning 15 formal tasks involving PCR, restriction digestion, ORFs, translation, GC content, and DNA–protein relationships.
Finds the amino acid encoded at a specified position in the longest ORF of a DNA sequence.
Translates the longest ORF in a DNA sequence to its amino-acid sequence.
Counts open reading frames encoding proteins above a specified amino-acid length.
Selects an RNA sequence whose ORF context is most likely to yield high translation efficiency.
A living collection of eight curated 3D molecular-learning tasks spanning small molecules, protein interactions and mutations, ligand binding, and protein/RNA structure ranking.
Regression of siRNA efficiency from paired sequence context, evaluated with the SAIS-inspired mixed score.
Each row keeps its original unit and basis. Rows with different units or overlapping mappings are never added.
| Benchmark | Mapped task | Coverage | Count | Version | Evidence |
|---|---|---|---|---|---|
| Biology-Instructions root: bioinstruction | RNA design official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (Programmable RNA Switches). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions Programmable RNA Switches root: bioinstruction | RNA design official-track · high | explicitly-in-scope | 93399 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-prs-evidence-paper |
| BEACON root: beacon-rna | RNA function classification official-taxonomy · high | explicitly-in-scope | 1 tasks Formal RNA benchmark tasks. | neurips-2024 | beacon-paper-definition-evidence |
| Biology-Instructions root: bioinstruction | RNA function classification official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (Non-coding RNA Function Classification). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions Non-coding RNA Function Classification root: bioinstruction | RNA function classification official-track · high | explicitly-in-scope | 11160 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-ncrna-evidence-paper |
| BEACON root: beacon-rna | RNA modification prediction official-taxonomy · high | explicitly-in-scope | 1 tasks Formal RNA benchmark tasks. | neurips-2024 | beacon-paper-definition-evidence |
| Biology-Instructions root: bioinstruction | RNA modification prediction official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (RNA Modification Prediction). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions RNA Modification Prediction root: bioinstruction | RNA modification prediction official-track · high | explicitly-in-scope | 309460 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-modification-evidence-paper |
| BEACON root: beacon-rna | RNA processing and translation prediction official-taxonomy · high | explicitly-in-scope | 3 tasks Formal RNA benchmark tasks. | neurips-2024 | beacon-paper-definition-evidence |
| Biology-Instructions root: bioinstruction | RNA processing and translation prediction official-track · high | explicitly-in-scope | 2 tracks Formal evaluation tracks (APA Isoform Prediction and Mean Ribosome Loading). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions APA Isoform Prediction root: bioinstruction | RNA processing and translation prediction official-track · high | explicitly-in-scope | 1658482 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-apa-evidence-paper |
| Biology-Instructions Mean Ribosome Loading Prediction root: bioinstruction | RNA processing and translation prediction official-track · high | explicitly-in-scope | 91519 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-mrl-evidence-paper |
| LAB-Bench SeqQA root: lab-bench | RNA processing and translation prediction official-track · high | explicitly-in-scope | 200 questions Four 50-question ORF and translation formal child tracks. | repository-998a8e0 | lab-bench-seqqa-evidence-paper |
| LAB-Bench SeqQA — ORF amino-acid position root: lab-bench | RNA processing and translation prediction official-track · high | explicitly-in-scope | 50 questions questions across public and private splits | repository-998a8e0 | lab-bench-seqqa-orf-seq-aaid-evidence-paper |
| LAB-Bench SeqQA — ORF amino-acid sequence root: lab-bench | RNA processing and translation prediction official-track · high | explicitly-in-scope | 50 questions questions across public and private splits | repository-998a8e0 | lab-bench-seqqa-orf-seq-aaseq-evidence-paper |
| LAB-Bench SeqQA — ORF count above length root: lab-bench | RNA processing and translation prediction official-track · high | explicitly-in-scope | 50 questions questions across public and private splits | repository-998a8e0 | lab-bench-seqqa-orf-seq-numlen-evidence-paper |
| LAB-Bench SeqQA — Translation efficiency root: lab-bench | RNA processing and translation prediction official-track · high | explicitly-in-scope | 50 questions questions across public and private splits | repository-998a8e0 | lab-bench-seqqa-orf-transeff-evidence-paper |
| BEACON root: beacon-rna | RNA stability and degradation prediction official-taxonomy · high | explicitly-in-scope | 1 tasks Formal RNA benchmark tasks. | neurips-2024 | beacon-paper-definition-evidence |
| BEACON root: beacon-rna | RNA structure prediction official-taxonomy · high | explicitly-in-scope | 4 tasks Formal RNA benchmark tasks. | neurips-2024 | beacon-paper-definition-evidence |
| ATOM3D root: atom3d | RNA structure quality assessment official-track · high | explicitly-in-scope | 1 tasks Curated 3D benchmark datasets. | v0.2.6 as of 2026-07-22 | atom3d-paper-definition-evidence |
| BEACON root: beacon-rna | Programmable RNA-switch activity prediction official-taxonomy · high | explicitly-in-scope | 1 tasks Formal RNA benchmark tasks. | neurips-2024 | beacon-paper-definition-evidence |
| Biology-Instructions root: bioinstruction | siRNA efficacy prediction official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (siRNA Efficiency Prediction). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions siRNA Efficiency Prediction root: bioinstruction | siRNA efficacy prediction official-track · high | explicitly-in-scope | 66987 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-sirna-evidence-paper |
Runs are included only for benchmark records mapped here (and formal child tracks when a mapped suite is the root). A task mapping does not imply that every run isolates this task.