LAB-Bench DbQA — Protein variant from sequence
Uses a protein sequence and ClinVar lookup to identify benign or pathogenic variants.
Scientific task · Property and function prediction
Predict protein function
蛋白质性质与功能预测
protein-property-functionCoverage
Uses a protein sequence and ClinVar lookup to identify benign or pathogenic variants.
Identifies ClinVar variant pathogenicity while reasoning across multiple protein sequences.
Versioned deep-mutational-scanning and clinical-variant benchmarks for protein fitness prediction and design in zero-shot and supervised regimes.
ProteinGym track for classifying short human clinical insertion and deletion variants against ClinVar and gnomAD-derived labels.
ProteinGym track for classifying expert-annotated human clinical substitution variants on a per-protein basis.
A supervised protein sequence-to-fitness benchmark that turns three experimental landscapes into 15 biologically motivated dataset splits for testing generalization in protein engineering.
Seven supervised splits over sampled and machine-designed AAV2 VP-1 capsid variants, measuring generalization across mutation depth, fitness, and sampled-versus-designed pools.
Five supervised splits over a downsampled, highly epistatic four-site GB1 immunoglobulin-binding landscape, designed to test mutation-depth and low-to-high-fitness generalization.
ProteinGym track for predicting experimental fitness measurements of insertion and deletion mutants across deep-mutational-scanning assays.
ProteinGym track for predicting experimental fitness measurements of substitution mutants across deep-mutational-scanning assays.
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.
Regression of protein fluorescence from an amino-acid sequence, evaluated with Spearman rank correlation.
A five-task benchmark for protein representation learning spanning secondary structure, residue contacts, remote homology, fluorescence, and stability.
Multi-label Enzyme Commission number prediction from a protein sequence, evaluated with the creator's Fmax implementation.
A living collection of eight curated 3D molecular-learning tasks spanning small molecules, protein interactions and mutations, ligand binding, and protein/RNA structure ranking.
Binary protein-solubility prediction from an amino-acid sequence, evaluated with accuracy.
Regression of protein stability from an amino-acid sequence, evaluated with Spearman rank correlation.
Regression of protein thermostability from an amino-acid sequence, evaluated with Spearman rank correlation.
Three supervised sequence-to-melting-temperature splits spanning all species, human proteins, and a single human cell line, with sequence-cluster-aware train/test separation.
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 |
|---|---|---|---|---|---|
| LAB-Bench DbQA — Protein variant from sequence root: lab-bench | Protein clinical variant interpretation official-track · high | explicitly-in-scope | 100 questions questions across public and private splits | repository-998a8e0 | lab-bench-dbqa-variant-from-sequence-evidence-paper |
| LAB-Bench DbQA — Protein variant with multiple sequences root: lab-bench | Protein clinical variant interpretation official-track · high | explicitly-in-scope | 100 questions questions across public and private splits | repository-998a8e0 | lab-bench-dbqa-variant-multi-sequence-evidence-paper |
| ProteinGym root: proteingym | Protein clinical variant interpretation official-track · high | explicitly-in-scope | Not reported Clinical substitution and indel tracks. | 1.3 | proteingym-evidence-taxonomy |
| ProteinGym Clinical Indels root: proteingym | Protein clinical variant interpretation official-track · high | explicitly-in-scope | 1555 records Clinical proteins. | 1.3 | proteingym-clinical-indel-evidence-v13 |
| ProteinGym Clinical Substitutions root: proteingym | Protein clinical variant interpretation official-track · high | explicitly-in-scope | 2525 records Clinical proteins. | 1.3 | proteingym-clinical-sub-evidence-v13 |
| FLIP root: flip | Protein fitness prediction official-taxonomy · high | explicitly-in-scope | 15 tasks Dataset-and-split benchmark tasks. | original-2021 | flip-evidence-paper-definition |
| FLIP AAV root: flip | Protein fitness prediction official-track · high | explicitly-in-scope | 284009 examples Distinct sequence-fitness examples across the sampled and designed AAV pools. | original-2021 | flip-aav-evidence-paper |
| FLIP GB1 root: flip | Protein fitness prediction official-track · high | explicitly-in-scope | 8733 examples Downsampled sequence-fitness examples retained for FLIP. | original-2021 | flip-gb1-evidence-paper |
| ProteinGym root: proteingym | Protein fitness prediction official-taxonomy · high | explicitly-in-scope | Not reported ProteinGym DMS assays. | 1.3 | proteingym-evidence-taxonomy |
| ProteinGym DMS Indels root: proteingym | Protein fitness prediction official-track · high | explicitly-in-scope | 66 assays DMS assays. | 1.3 | proteingym-dms-indel-evidence-v13 |
| ProteinGym DMS Substitutions root: proteingym | Protein fitness prediction official-track · high | explicitly-in-scope | 217 assays DMS assays. | 1.3 | proteingym-dms-sub-evidence-v13 |
| Biology-Instructions root: bioinstruction | Protein fluorescence prediction official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (Protein Fluorescence Prediction). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions Protein Fluorescence Prediction root: bioinstruction | Protein fluorescence prediction official-track · high | explicitly-in-scope | 54025 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-fluorescence-evidence-paper |
| TAPE root: tape | Protein fluorescence prediction official-taxonomy · high | explicitly-in-scope | 1 tasks Supervised downstream benchmark tasks. | original-2019 | tape-paper-definition-evidence |
| Biology-Instructions root: bioinstruction | Protein function annotation official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (Enzyme Commission Number Prediction). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions Enzyme Commission Number Prediction root: bioinstruction | Protein function annotation official-track · high | explicitly-in-scope | 19199 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-ec-evidence-paper |
| FLIP root: flip | Protein mutation-effect prediction official-taxonomy · high | explicitly-in-scope | 15 tasks Dataset-and-split benchmark tasks. | original-2021 | flip-evidence-paper-definition |
| ProteinGym root: proteingym | Protein mutation-effect prediction official-track · high | explicitly-in-scope | Not reported DMS assays and mutant measurements across version 1.3 tracks. | 1.3 | proteingym-evidence-taxonomy |
| ProteinGym DMS Indels root: proteingym | Protein mutation-effect prediction official-track · high | explicitly-in-scope | 66 assays DMS assays. | 1.3 | proteingym-dms-indel-evidence-v13 |
| ProteinGym DMS Substitutions root: proteingym | Protein mutation-effect prediction official-track · high | explicitly-in-scope | 217 assays DMS assays. | 1.3 | proteingym-dms-sub-evidence-v13 |
| TAPE root: tape | Protein remote-homology detection official-taxonomy · high | explicitly-in-scope | 1 tasks Supervised downstream benchmark tasks. | original-2019 | tape-paper-definition-evidence |
| ATOM3D root: atom3d | Protein residue-identity prediction official-track · high | explicitly-in-scope | 1 tasks Curated 3D benchmark datasets. | v0.2.6 as of 2026-07-22 | atom3d-paper-definition-evidence |
| Biology-Instructions root: bioinstruction | Protein solubility prediction official-track · high | explicitly-in-scope | 1 tracks Formal evaluation tracks (Protein Solubility Prediction). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions Protein Solubility Prediction root: bioinstruction | Protein solubility prediction official-track · high | explicitly-in-scope | 71421 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-solubility-evidence-paper |
| Biology-Instructions root: bioinstruction | Protein stability prediction official-track · high | explicitly-in-scope | 2 tracks Formal evaluation tracks (Protein Stability and Protein Thermostability). | emnlp-2025 | bioinstruction-evidence-paper |
| Biology-Instructions Protein Stability Prediction root: bioinstruction | Protein stability prediction official-track · high | explicitly-in-scope | 68977 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-stability-evidence-paper |
| Biology-Instructions Protein Thermostability Prediction root: bioinstruction | Protein stability prediction official-track · high | explicitly-in-scope | 7031 examples distinct examples across the published train, validation, and test splits | emnlp-2025 | bioinstruction-thermostability-evidence-paper |
| FLIP Meltome Thermostability root: flip | Protein stability prediction official-track · high | explicitly-in-scope | 27951 examples Sequence-temperature examples in the Mixed split universe. | original-2021 | flip-meltome-evidence-paper |
| TAPE root: tape | Protein stability prediction official-taxonomy · high | explicitly-in-scope | 1 tasks Supervised downstream benchmark tasks. | original-2019 | tape-paper-definition-evidence |
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.