{"meta":{"title":"TabBench Bio","tagline":"A living benchmark for tabular learning in biomedical HDLSS regimes.","snapshot_utc":"2026-10-21T11:25:39.324658+00:00","reference_cell":"cap_10000_n100","paper_url":"https://arxiv.org/abs/2609.07441","github_url":"https://github.com/not-a-feature/TabBench-Bio","domain":"tabbench-bio.eu","contact_url":"https://github.com/not-a-feature/TabBench-Bio/issues","affiliation":"Methods in Medical Informatics, University of T\u00fcbingen","plot_excluded_models":["DUMMY","KNN","CAT","GBM","TABPFN-V3","TABPFN-WIDE","TABICL"],"primary_analysis_view":"strict_nominal_cell","adaptive_analysis_role":"sensitivity_only","paper_analysis_view":"strict","configured_model_count":29,"evaluation_points_per_model":6440,"bootstrap_rounds":2000},"models":{"AUTOGLUON":{"id":"AUTOGLUON","display":"AutoGluon","tuned_from":null,"tuning":null,"category":"AutoML","color":"#111827","regular_max_features":null,"training_data_overlap":false},"CAT":{"id":"CAT","display":"CatBoost","tuned_from":null,"tuning":null,"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"CAUSILO":{"id":"CAUSILO","display":"Causilo","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"DUMMY":{"id":"DUMMY","display":"Constant","tuned_from":null,"tuning":null,"category":"Baseline","color":"#9ca3af","regular_max_features":null,"training_data_overlap":false},"GBM":{"id":"GBM","display":"LightGBM","tuned_from":null,"tuning":null,"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"GENEICL":{"id":"GENEICL","display":"GeneICL","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"KNN":{"id":"KNN","display":"KNN","tuned_from":null,"tuning":null,"category":"Traditional ML","color":"#2563eb","regular_max_features":null,"training_data_overlap":false},"KUMO-TABULAR-MEDIUM":{"id":"KUMO-TABULAR-MEDIUM","display":"Kumo Tabular (M)","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"LIMIX-2":{"id":"LIMIX-2","display":"LimiX2","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"LR":{"id":"LR","display":"Logistic Regression","tuned_from":null,"tuning":null,"category":"Traditional ML","color":"#2563eb","regular_max_features":null,"training_data_overlap":false},"LR-TUNED":{"id":"LR-TUNED","display":"Logistic Regression (tuned)","tuned_from":"LR","tuning":{"grid":[{"C":[0.01,0.1,10,100,0.001,0.0001]}],"protocol":"holdout-grid-v1","search_fraction":0.8,"seed":42,"selection":"inner_holdout","validation_fraction":0.2,"budget_seconds":3600},"category":"Traditional ML","color":"#2563eb","regular_max_features":null,"training_data_overlap":false},"MITRA":{"id":"MITRA","display":"MITRA","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":500,"training_data_overlap":false},"NN_TORCH":{"id":"NN_TORCH","display":"MLP","tuned_from":null,"tuning":null,"category":"Deep Learning","color":"#dc2626","regular_max_features":null,"training_data_overlap":false},"NN_TORCH-TUNED":{"id":"NN_TORCH-TUNED","display":"MLP (tuned)","tuned_from":"NN_TORCH","tuning":{"grid":[{"dropout_prob":[0.0,0.2],"hidden_size":[64,128],"learning_rate":[0.0003,0.001],"num_layers":[2,4]}],"protocol":"holdout-grid-v1","search_fraction":0.8,"seed":42,"selection":"inner_holdout","validation_fraction":0.2,"budget_seconds":3600},"category":"Deep Learning","color":"#dc2626","regular_max_features":null,"training_data_overlap":false},"REALMLP":{"id":"REALMLP","display":"RealMLP","tuned_from":null,"tuning":null,"category":"Deep Learning","color":"#dc2626","regular_max_features":null,"training_data_overlap":false},"REALTABPFN-V2":{"id":"REALTABPFN-V2","display":"RealTabPFN v2","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":500,"training_data_overlap":false},"REALTABPFN-V2.5":{"id":"REALTABPFN-V2.5","display":"RealTabPFN 2.5","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2000,"training_data_overlap":false},"RF":{"id":"RF","display":"Random Forest","tuned_from":null,"tuning":null,"category":"Tree-based","color":"#059669","regular_max_features":null,"training_data_overlap":false},"RF-TUNED":{"id":"RF-TUNED","display":"Random Forest (tuned)","tuned_from":"RF","tuning":{"grid":[{"max_features":["log2",0.1,"sqrt",0.5],"min_samples_leaf":[1,5]}],"protocol":"holdout-grid-v1","search_fraction":0.8,"seed":42,"selection":"inner_holdout","validation_fraction":0.2,"budget_seconds":3600},"category":"Tree-based","color":"#059669","regular_max_features":null,"training_data_overlap":false},"TABDPT":{"id":"TABDPT","display":"TabDPT","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2500,"training_data_overlap":true},"TABFM":{"id":"TABFM","display":"TabFM","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2000,"training_data_overlap":false},"TABICL":{"id":"TABICL","display":"TabICL v2","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2000,"training_data_overlap":false},"TABM":{"id":"TABM","display":"TabM","tuned_from":null,"tuning":null,"category":"Deep Learning","color":"#dc2626","regular_max_features":null,"training_data_overlap":false},"TABPFN-V3":{"id":"TABPFN-V3","display":"TabPFN 3","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":10000,"training_data_overlap":false},"TABPFN-V3.5":{"id":"TABPFN-V3.5","display":"TabPFN 3.5","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":20000,"training_data_overlap":false},"TABPFN-WIDE":{"id":"TABPFN-WIDE","display":"TabPFN Wide (8k)","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"TABPFN-WIDE-5K-NE3":{"id":"TABPFN-WIDE-5K-NE3","display":"TabPFN Wide 5k (ne3)","tuned_from":null,"tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"XGB":{"id":"XGB","display":"XGBoost","tuned_from":null,"tuning":null,"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"XGB-TUNED":{"id":"XGB-TUNED","display":"XGBoost (tuned)","tuned_from":"XGB","tuning":{"grid":[{"learning_rate":[0.03,0.1],"max_depth":[3,6],"n_estimators":[500]},{"colsample_bytree":[0.1,0.5],"learning_rate":[0.1],"max_depth":[3,6],"n_estimators":[500]},{"learning_rate":[0.03,0.1],"max_depth":[1,2],"n_estimators":[500]},{"learning_rate":[0.1],"max_depth":[3,6],"min_child_weight":[5,20],"n_estimators":[500]},{"learning_rate":[0.1],"max_depth":[3,6],"n_estimators":[500],"reg_lambda":[10,100]}],"protocol":"holdout-grid-v1","search_fraction":0.8,"seed":42,"selection":"inner_holdout","validation_fraction":0.2,"budget_seconds":3600},"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"XT":{"id":"XT","display":"Extra Trees","tuned_from":null,"tuning":null,"category":"Tree-based","color":"#059669","regular_max_features":null,"training_data_overlap":false},"XT-TUNED":{"id":"XT-TUNED","display":"Extra Trees (tuned)","tuned_from":"XT","tuning":{"grid":[{"max_features":["log2",0.1],"min_samples_leaf":[1,5]},{"bootstrap":[false]},{"bootstrap":[false],"max_features":["log2",0.1,"sqrt",0.5],"min_samples_leaf":[1,5]}],"protocol":"holdout-grid-v1","search_fraction":0.8,"seed":42,"selection":"inner_holdout","validation_fraction":0.2,"budget_seconds":3600},"category":"Tree-based","color":"#059669","regular_max_features":null,"training_data_overlap":false}},"cell_options":[{"id":"cap_2000_n20","label":"p=2,000, n=20","feature_cap":2000,"n_train":20},{"id":"cap_2000_n50","label":"p=2,000, n=50","feature_cap":2000,"n_train":50},{"id":"cap_2000_n100","label":"p=2,000, n=100","feature_cap":2000,"n_train":100},{"id":"cap_2000_n200","label":"p=2,000, n=200","feature_cap":2000,"n_train":200},{"id":"cap_2000_n500","label":"p=2,000, n=500","feature_cap":2000,"n_train":500},{"id":"cap_2000_n1000","label":"p=2,000, n=1,000","feature_cap":2000,"n_train":1000},{"id":"cap_2000","label":"p=2,000, n=all","feature_cap":2000,"n_train":null},{"id":"cap_10000_n20","label":"p=10,000, n=20","feature_cap":10000,"n_train":20},{"id":"cap_10000_n50","label":"p=10,000, n=50","feature_cap":10000,"n_train":50},{"id":"cap_10000_n100","label":"p=10,000, n=100","feature_cap":10000,"n_train":100},{"id":"cap_10000_n200","label":"p=10,000, n=200","feature_cap":10000,"n_train":200},{"id":"cap_10000_n500","label":"p=10,000, n=500","feature_cap":10000,"n_train":500},{"id":"cap_10000_n1000","label":"p=10,000, n=1,000","feature_cap":10000,"n_train":1000},{"id":"cap_10000","label":"p=10,000, n=all","feature_cap":10000,"n_train":null},{"id":"cap_25000_n20","label":"p=25,000, n=20","feature_cap":25000,"n_train":20},{"id":"cap_25000_n50","label":"p=25,000, n=50","feature_cap":25000,"n_train":50},{"id":"cap_25000_n100","label":"p=25,000, n=100","feature_cap":25000,"n_train":100},{"id":"cap_25000_n200","label":"p=25,000, n=200","feature_cap":25000,"n_train":200},{"id":"cap_25000_n500","label":"p=25,000, n=500","feature_cap":25000,"n_train":500},{"id":"cap_25000_n1000","label":"p=25,000, n=1,000","feature_cap":25000,"n_train":1000},{"id":"cap_25000","label":"p=25,000, n=all","feature_cap":25000,"n_train":null},{"id":"cap_full_n20","label":"p=all, n=20","feature_cap":null,"n_train":20},{"id":"cap_full_n50","label":"p=all, n=50","feature_cap":null,"n_train":50},{"id":"cap_full_n100","label":"p=all, n=100","feature_cap":null,"n_train":100},{"id":"cap_full_n200","label":"p=all, n=200","feature_cap":null,"n_train":200},{"id":"cap_full_n500","label":"p=all, n=500","feature_cap":null,"n_train":500},{"id":"cap_full_n1000","label":"p=all, n=1,000","feature_cap":null,"n_train":1000},{"id":"cap_full","label":"p=all, n=all","feature_cap":null,"n_train":null}],"datasets":[{"dataset_id":"CHEMBL2034","display_name":"Glucocorticoid Receptor Bioactivity","source":"chembl","source_url":"https://www.ebi.ac.uk/chembl/explore/target/CHEMBL2034","citation":null,"data_type":"Molecular Fingerprint","target":"pchembl_value","problem_type":"regression","license":"CC BY-SA 3.0","modality":"Molecular properties","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"b462526224d942ba.json"},{"dataset_id":"CHEMBL206","display_name":"Estrogen Receptor Bioactivity","source":"chembl","source_url":"https://www.ebi.ac.uk/chembl/explore/target/CHEMBL206","citation":null,"data_type":"Molecular Fingerprint","target":"pchembl_value","problem_type":"regression","license":"CC BY-SA 3.0","modality":"Molecular properties","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"9f78dfe38b59c401.json"},{"dataset_id":"FusionAI-NTv2-GeneFusion","display_name":"Gene Fusion Breakpoints (NT-v2)","source":"fusionai","source_url":null,"citation":null,"data_type":"DNA Embedding","target":"fusion","problem_type":"binary","license":"CC BY 4.0","modality":"GLM/PLM Embeddings","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"d99ea1752d3317f2.json"},{"dataset_id":"GEO-GSE10893","display_name":"Breast Cancer Subtypes (GSE10893)","source":"geo","source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE10893","citation":null,"data_type":"Gene Expression","target":"subtype","problem_type":"multiclass","license":"Not specified","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"b656730266026961.json"},{"dataset_id":"GEO-GSE147221-Methylation-Schizophrenia","display_name":"Schizophrenia DNA Methylation (GSE147221)","source":"geo_matrix","source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE147221","citation":null,"data_type":"DNA Methylation","target":"status","problem_type":"binary","license":"NCBI GEO public data; study-specific terms require verification before re-hosting","modality":"DNA methylation","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"a52c766d4850bf4f.json"},{"dataset_id":"GEO-GSE40279-Methylation-Age","display_name":"Blood DNA Methylation Age (GSE40279)","source":"geo_matrix","source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE40279","citation":null,"data_type":"DNA Methylation","target":"age (y)","problem_type":"regression","license":"NCBI GEO public data; study-specific terms require verification before re-hosting","modality":"DNA methylation","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"13329fddc636d01b.json"},{"dataset_id":"GEO-GSE42861-Methylation-RA","display_name":"Rheumatoid Arthritis DNA Methylation (GSE42861)","source":"geo_matrix","source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE42861","citation":null,"data_type":"DNA Methylation","target":"disease state","problem_type":"binary","license":"NCBI GEO public data; study-specific terms require verification before re-hosting","modality":"DNA methylation","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"609dc8ebd48fdba8.json"},{"dataset_id":"GEO-GSE50660-Methylation-Smoking","display_name":"Smoking Status DNA Methylation (GSE50660)","source":"geo_matrix","source_url":"https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50660","citation":null,"data_type":"DNA Methylation","target":"smoking (0, 1 and 2, which represent never, former and current smokers)","problem_type":"multiclass","license":"NCBI GEO public data; study-specific terms require verification before re-hosting","modality":"DNA methylation","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"bbfbf5bfa2bce59b.json"},{"dataset_id":"MGYS00001056","display_name":"Human Microbiome Environment Metagenome","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00001056","citation":null,"data_type":"Metagenomic Functional Profile","target":"isolation source","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"3c6fb64375350931.json"},{"dataset_id":"MGYS00001255","display_name":"Human feces metagenome 16s rDNA sequencing","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00001255","citation":null,"data_type":"Metagenomic Functional Profile","target":"host sex","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"4913eab3105772ee.json"},{"dataset_id":"MGYS00002425","display_name":"EMG produced TPA metagenomics assembly of the Metagenomic sequencing of preterm infant gut microbiota raw sequence reads () data set.","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00002425","citation":null,"data_type":"Metagenomic Functional Profile","target":"host sex","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"7ba4f2c11393723e.json"},{"dataset_id":"MGYS00005285","display_name":"EMG produced TPA metagenomics assembly of the A metagenome-wide association study of gut microbiota in type 2 diabetes. (gut metagenome) data set.","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00005285","citation":null,"data_type":"Metagenomic Functional Profile","target":"host sex","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"39520c5d59930a23.json"},{"dataset_id":"MGYS00005379","display_name":"EMG produced TPA metagenomics assembly of the PRJNA46333 data set (Gene-Environment Interactions at the Skin Surface).","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00005379","citation":null,"data_type":"Metagenomic Functional Profile","target":"environment (material)","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"cec756643ce5a4f8.json"},{"dataset_id":"MGYS00005380","display_name":"EMG produced TPA metagenomics assembly of the PRJNA275349 data set (Human Microbiome Environment Metagenome).","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00005380","citation":null,"data_type":"Metagenomic Functional Profile","target":"isolation source","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"a2014db27a0697ee.json"},{"dataset_id":"MGYS00005381","display_name":"EMG produced TPA metagenomics assembly of the PRJNA300541 data set (Antibiotic resistance exchange between microbiota in resource-poor settings in Latin America).","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00005381","citation":null,"data_type":"Metagenomic Functional Profile","target":"environment (biome)","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"2626068e09cce0e1.json"},{"dataset_id":"MGYS00005384","display_name":"Human skin bacterial metagenome and Virome Metagenome","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00005384","citation":null,"data_type":"Metagenomic Functional Profile","target":"host sex","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"b9fd0942b8420ac7.json"},{"dataset_id":"MGYS00006282","display_name":"EMG produced TPA metagenomics assembly of PRJNA728374 data set (Gut microbiome responses to dietary intervention with hypocholesterolemic vegetable oils.).","source":"mgnify","source_url":"https://www.ebi.ac.uk/metagenomics/studies/MGYS00006282","citation":null,"data_type":"Metagenomic Functional Profile","target":"host sex","problem_type":"binary","license":"Public","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"57c2d8c9c7d06699.json"},{"dataset_id":"MW-ST001000-CD-UC","display_name":"PRISM Stool Metabolomics CD vs UC","source":"metabolomics","source_url":"https://www.metabolomicsworkbench.org/data/DRCCMetadata.php?StudyID=ST001000","citation":"Franzosa EA et al. (2019), Gut microbiome structure and metabolic activity in inflammatory bowel disease. doi:10.1038/s41564-018-0306-4; ST001000 / AN001880.","data_type":"Metabolomics","target":"diagnosis","problem_type":"binary","license":"CC BY 4.0","modality":"Other","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n50","scores_file":"5a631ee669953db2.json"},{"dataset_id":"MoleculeNet-Tox21-NR-AhR","display_name":"Tox21 Aryl Hydrocarbon Receptor Activity","source":"moleculenet","source_url":"https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/tox21.csv.gz","citation":"Wu Z et al. (2018), MoleculeNet: a benchmark for molecular machine learning. doi:10.1039/C7SC02664A; Tox21 NR-AhR assay.","data_type":"Molecular Fingerprint","target":"NR-AhR","problem_type":"binary","license":"Tox21 / MoleculeNet distribution; underlying source terms apply","modality":"Molecular properties","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"18dbdb29547df14e.json"},{"dataset_id":"MoleculeNet-Tox21-SR-MMP","display_name":"Tox21 Mitochondrial Membrane Potential","source":"moleculenet","source_url":"https://deepchemdata.s3-us-west-1.amazonaws.com/datasets/tox21.csv.gz","citation":"Wu Z et al. (2018), MoleculeNet: a benchmark for molecular machine learning. doi:10.1039/C7SC02664A; Tox21 SR-MMP assay.","data_type":"Molecular Fingerprint","target":"SR-MMP","problem_type":"binary","license":"Tox21 / MoleculeNet distribution; underlying source terms apply","modality":"Molecular properties","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"249d654f7e594ef8.json"},{"dataset_id":"OpenML-1083","display_name":"mouseType","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1083&status=active","citation":null,"data_type":"Gene Expression","target":"Decision","problem_type":"multiclass","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"f3cdbeedad25eb02.json"},{"dataset_id":"OpenML-1084","display_name":"BurkittLymphoma","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1084&status=active","citation":null,"data_type":"Gene Expression","target":"Decision","problem_type":"multiclass","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"348d69458cec3012.json"},{"dataset_id":"OpenML-1088","display_name":"variousCancers_final","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1088&status=active","citation":null,"data_type":"Gene Expression","target":"Decision","problem_type":"multiclass","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"35f253c372514fd5.json"},{"dataset_id":"OpenML-1106","display_name":"GCM","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1106&status=active","citation":null,"data_type":"Gene Expression","target":"class","problem_type":"multiclass","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"f850ae11d695ed26.json"},{"dataset_id":"OpenML-1137","display_name":"AP_Colon_Kidney","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1137&status=active","citation":null,"data_type":"Gene Expression","target":"Tissue","problem_type":"binary","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"b53cf98f235cd061.json"},{"dataset_id":"OpenML-1138","display_name":"Uterus vs. Other Tissue","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1138&status=active","citation":null,"data_type":"Gene Expression","target":"Tissue","problem_type":"binary","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"0d0dfa8ccfa2c86c.json"},{"dataset_id":"OpenML-1140","display_name":"AP_Ovary_Lung","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1140&status=active","citation":null,"data_type":"Gene Expression","target":"Tissue","problem_type":"binary","license":"Public","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"950b78acd10e178d.json"},{"dataset_id":"OpenML-1458","display_name":"ARCENE Serum Cancer","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1458&status=active","citation":null,"data_type":"Mass Spectrometry","target":"Class","problem_type":"binary","license":"CC BY 4.0","modality":"Other","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"d1bcbedd902665e6.json"},{"dataset_id":"OpenML-430","display_name":"mtp2","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=430&status=active","citation":null,"data_type":"Misc","target":"oz1143","problem_type":"regression","license":"Public","modality":"Other","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"7010cdfe48046340.json"},{"dataset_id":"OpenML-46983","display_name":"Riboflavin Production","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=46983&status=active","citation":null,"data_type":"Gene Expression","target":"x","problem_type":"regression","license":"Public","modality":"Gene expression","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n50","scores_file":"8d380491f57500cc.json"},{"dataset_id":"TCGA-TCGA-BRCA_Gene-Expression-Quantification","display_name":"TCGA Breast (BRCA, RNA-seq)","source":"tcga","source_url":"https://portal.gdc.cancer.gov/projects/TCGA-BRCA","citation":null,"data_type":"Gene Expression","target":"sample_type","problem_type":"binary","license":"NIH Genomic Data Sharing Policy (GDC open-access)","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"566a4e2e85219930.json"},{"dataset_id":"TCGA-TCGA-HNSC_Gene-Expression-Quantification","display_name":"TCGA Head & Neck (HNSC, RNA-seq)","source":"tcga","source_url":"https://portal.gdc.cancer.gov/projects/TCGA-HNSC","citation":null,"data_type":"Gene Expression","target":"sample_type","problem_type":"binary","license":"Not specified","modality":"Gene expression","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"05a5065279ed7dfc.json"},{"dataset_id":"TDC-AMES","display_name":"Ames Mutagenicity","source":"tdc","source_url":"https://dataverse.harvard.edu/api/access/datafile/4259564","citation":"Hansen K et al. (2009), Benchmark data set for in silico prediction of Ames mutagenicity.","data_type":"Molecular Fingerprint","target":"Y","problem_type":"binary","license":"CC BY 4.0 via TDC; underlying source terms require verification before re-hosting","modality":"Molecular properties","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"76e4ae9a252d190a.json"},{"dataset_id":"TDC-AqSolDB","display_name":"Aqueous Solubility (AqSolDB)","source":"tdc","source_url":"https://dataverse.harvard.edu/api/access/datafile/4259610","citation":"Sorkun MC et al. (2019), AqSolDB, a curated reference set of aqueous solubility.","data_type":"Molecular Fingerprint","target":"Y","problem_type":"regression","license":"CC BY 4.0 via TDC; underlying source terms require verification before re-hosting","modality":"Molecular properties","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"b6d8b408861f50ae.json"},{"dataset_id":"TDC-BBB-Martins","display_name":"Blood-Brain Barrier Penetration (Martins)","source":"tdc","source_url":"https://dataverse.harvard.edu/api/access/datafile/4259566","citation":"Martins IF et al. (2012), A Bayesian approach to in silico blood-brain barrier penetration modeling.","data_type":"Molecular Fingerprint","target":"Y","problem_type":"binary","license":"CC BY 4.0 via TDC; underlying source terms require verification before re-hosting","modality":"Molecular properties","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"55a85ec44f41c943.json"},{"dataset_id":"TDC-CYP3A4-Veith","display_name":"CYP3A4 Inhibition (Veith)","source":"tdc","source_url":"https://dataverse.harvard.edu/api/access/datafile/4259582","citation":"Veith H et al. (2009), Comprehensive characterization of cytochrome P450 isozyme selectivity.","data_type":"Molecular Fingerprint","target":"Y","problem_type":"binary","license":"CC BY 4.0 via TDC; underlying source terms require verification before re-hosting","modality":"Molecular properties","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"857dd1ae3152a477.json"},{"dataset_id":"TDC-LD50-Zhu","display_name":"Acute Toxicity LD50 (Zhu)","source":"tdc","source_url":"https://dataverse.harvard.edu/api/access/datafile/4267146","citation":"Zhu H et al. (2009), Quantitative structure-activity relationship modeling of rat acute toxicity.","data_type":"Molecular Fingerprint","target":"Y","problem_type":"regression","license":"CC BY 4.0 via TDC; underlying source terms require verification before re-hosting","modality":"Molecular properties","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"e4302cb01c6447fe.json"},{"dataset_id":"TDC-Lipophilicity-AstraZeneca","display_name":"Lipophilicity (AstraZeneca)","source":"tdc","source_url":"https://dataverse.harvard.edu/api/access/datafile/4259595","citation":"AstraZeneca / MoleculeNet lipophilicity benchmark, distributed by Therapeutics Data Commons.","data_type":"Molecular Fingerprint","target":"Y","problem_type":"regression","license":"CC BY 4.0 via TDC; underlying source terms require verification before re-hosting","modality":"Molecular properties","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"5acd231bb7ce025c.json"},{"dataset_id":"gp-maize-FT","display_name":"Maize Flowering Time Genomic Prediction","source":"gp","source_url":"https://doi.org/10.5061/dryad.xksn02vb9","citation":"Azodi CB et al. (2019), Benchmarking Parametric and Machine Learning Models for Genomic Prediction of Complex Traits, G3: Genes|Genomes|Genetics, doi:10.1534/g3.119.400498.","data_type":"SNP Genotype","target":"FT","problem_type":"regression","license":"CC0-1.0","modality":"Genomic prediction","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"b68086cfcb8e17ec.json"},{"dataset_id":"gp-rice-FT","display_name":"Rice Flowering Time Genomic Prediction","source":"gp","source_url":"https://doi.org/10.5061/dryad.xksn02vb9","citation":"Azodi CB et al. (2019), Benchmarking Parametric and Machine Learning Models for Genomic Prediction of Complex Traits, G3: Genes|Genomes|Genetics, doi:10.1534/g3.119.400498.","data_type":"SNP Genotype","target":"FT","problem_type":"regression","license":"CC0-1.0","modality":"Genomic prediction","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"de49ab7ef40eeb38.json"},{"dataset_id":"gp-soy-YLD","display_name":"Soybean Yield Genomic Prediction","source":"gp","source_url":"https://doi.org/10.5061/dryad.xksn02vb9","citation":"Azodi CB et al. (2019), Benchmarking Parametric and Machine Learning Models for Genomic Prediction of Complex Traits, G3: Genes|Genomes|Genetics, doi:10.1534/g3.119.400498.","data_type":"SNP Genotype","target":"YLD","problem_type":"regression","license":"CC0-1.0","modality":"Genomic prediction","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"989125282150c1a5.json"},{"dataset_id":"gp-switchgrass-HT","display_name":"Switchgrass Height Genomic Prediction","source":"gp","source_url":"https://doi.org/10.5061/dryad.xksn02vb9","citation":"Azodi CB et al. (2019), Benchmarking Parametric and Machine Learning Models for Genomic Prediction of Complex Traits, G3: Genes|Genomes|Genetics, doi:10.1534/g3.119.400498.","data_type":"SNP Genotype","target":"HT","problem_type":"regression","license":"CC0-1.0","modality":"Genomic prediction","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"aaff603eff52a66a.json"},{"dataset_id":"gut-cirrhosis","display_name":"Gut microbiome markers (healthy vs cirrhosis)","source":"metagenomics","source_url":"https://github.com/segatalab/metaml","citation":null,"data_type":"Metagenomic Marker Presence","target":"disease","problem_type":"binary","license":"CC-BY-4.0","modality":"Metagenomics","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"475a31a9b9b50e3b.json"},{"dataset_id":"local-BRCA_Evo2-VEP","display_name":"BRCA VEP (Evo2)","source":"local","source_url":null,"citation":null,"data_type":"DNA Embedding","target":"y","problem_type":"multiclass","license":"Source terms apply; redistribution authorized by dataset curator","modality":"GLM/PLM Embeddings","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"8f63867a6951733e.json"},{"dataset_id":"local-DeepLoc2-Fungi-ESM2","display_name":"DeepLoc2 Fungi (ESM-2)","source":"local","source_url":null,"citation":null,"data_type":"Protein Embedding","target":"membrane","problem_type":"binary","license":"DeepLoc 2.0 source terms; ESM-2 model MIT; redistribution authorized by dataset curator","modality":"GLM/PLM Embeddings","task":"Classification","metrics":[{"key":"f1_macro","label":"Macro-F1","better":"high"},{"key":"matthews_corrcoef","label":"MCC","better":"high"},{"key":"balanced_accuracy","label":"Balanced accuracy","better":"high"},{"key":"roc_auc","label":"ROC-AUC","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"e90d5f92434f68c3.json"},{"dataset_id":"local-PEER-BetaLactamase-ESM2","display_name":"TEM-1 Activity (ESM-2)","source":"local","source_url":null,"citation":null,"data_type":"Protein Embedding","target":"activity","problem_type":"regression","license":"PEER/TorchDrug source terms; ESM-2 model MIT; redistribution authorized by dataset curator","modality":"GLM/PLM Embeddings","task":"Regression","metrics":[{"key":"rmse","label":"RMSE","better":"low"},{"key":"mae","label":"MAE","better":"low"},{"key":"r2","label":"R\u00b2","better":"high"}],"default_cell":"cap_10000_n100","scores_file":"99ea9b56c515a48e.json"}]}