{"meta":{"title":"TabBench-Bio paper snapshot","tagline":"A living benchmark for tabular learning in biomedical HDLSS regimes.","snapshot_utc":"2026-11-12T12:42:56.402836+00:00","reference_cell":"cap_10000_n100","paper_url":"REMOVED","github_url":"REMOVED","domain":"anonymous_iclr.codeberg.page/TabBench-Bio-Anonymous/paper-snapshot","contact_url":"REMOVED","affiliation":"REMOVED","plot_excluded_models":["DUMMY"],"primary_analysis_view":"strict_nominal_cell","adaptive_analysis_role":"sensitivity_only","paper_analysis_view":"strict","configured_model_count":19,"evaluation_points_per_model":6020,"bootstrap_rounds":2000,"snapshot_scope":"Original paper roster, using the latest stored results restricted to that roster."},"models":{"AUTOGLUON":{"id":"AUTOGLUON","display":"AutoGluon","tuned_from":null,"classification_only":false,"source_url":"https://github.com/autogluon/autogluon","description":"AutoGluon automates tabular learning by training multiple models and combining their predictions in ensembles. Here it runs its native extreme preset within a one-hour budget as a separate AutoML reference.","tuning":null,"category":"AutoML","color":"#111827","regular_max_features":null,"training_data_overlap":false},"CAT":{"id":"CAT","display":"CatBoost","tuned_from":null,"classification_only":false,"source_url":"https://github.com/catboost/catboost","description":"CatBoost builds an ensemble of decision trees through gradient boosting, adding trees that improve the current predictions. It supports numerical and categorical features for classification and regression.","tuning":null,"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"DUMMY":{"id":"DUMMY","display":"Constant","tuned_from":null,"classification_only":false,"source_url":"https://github.com/scikit-learn/scikit-learn","description":"The constant baseline ignores the input features. It returns the training set's class proportions for classification or its mean target value for regression, showing what can be predicted without using the measurements.","tuning":null,"category":"Baseline","color":"#9ca3af","regular_max_features":null,"training_data_overlap":false},"GBM":{"id":"GBM","display":"LightGBM","tuned_from":null,"classification_only":false,"source_url":"https://github.com/lightgbm-org/LightGBM","description":"LightGBM is a gradient boosting method that builds decision trees using binned feature values. It grows each tree by splitting the leaf with the largest reduction in the training objective.","tuning":null,"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"KNN":{"id":"KNN","display":"KNN","tuned_from":null,"classification_only":false,"source_url":"https://github.com/scikit-learn/scikit-learn","description":"KNN predicts from the training examples closest to a new sample in feature space. The benchmark uses equally weighted neighbors, taking their class votes for classification or averaging their target values for regression.","tuning":null,"category":"Traditional ML","color":"#2563eb","regular_max_features":null,"training_data_overlap":false},"LR":{"id":"LR","display":"Logistic Regression","tuned_from":null,"classification_only":false,"source_url":"https://github.com/scikit-learn/scikit-learn","description":"Logistic regression learns a weighted combination of the input features and turns it into class probabilities. For continuous targets, this entry uses ridge regression, a linear model with a penalty that keeps its coefficients from becoming too large.","tuning":null,"category":"Traditional ML","color":"#2563eb","regular_max_features":null,"training_data_overlap":false},"MITRA":{"id":"MITRA","display":"MITRA","tuned_from":null,"classification_only":false,"source_url":"https://github.com/autogluon/autogluon","description":"MITRA is a pretrained model for tabular classification and regression that learns from a mixture of synthetic datasets generated by different rules. It uses labelled examples as context for new predictions, and AutoGluon's implementation also adapts its pretrained weights to the target dataset through fine-tuning.","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,"classification_only":false,"source_url":"https://github.com/autogluon/autogluon","description":"This multilayer perceptron uses AutoGluon's PyTorch implementation for tabular classification and regression. It passes the input features through fully connected hidden layers with nonlinear activations to learn the prediction function.","tuning":null,"category":"Deep Learning","color":"#dc2626","regular_max_features":null,"training_data_overlap":false},"REALMLP":{"id":"REALMLP","display":"RealMLP","tuned_from":null,"classification_only":false,"source_url":"https://github.com/dholzmueller/pytabkit","description":"RealMLP is a multilayer perceptron trained on each dataset for classification or regression. It combines numerical preprocessing with a carefully chosen network and training setup, using defaults selected across a broad collection of tabular tasks.","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,"classification_only":false,"source_url":"https://github.com/PriorLabs/TabPFN","description":"TabPFN v2, by Prior Labs, is a pretrained transformer for classification and regression on tables. It takes labelled training rows as context and predicts new rows without training a separate neural network from scratch for each dataset.","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,"classification_only":false,"source_url":"https://github.com/PriorLabs/TabPFN","description":"TabPFN 2.5, by Prior Labs, uses a pretrained transformer to make predictions from labelled examples, extending the v2 family to wider tables. Its default classifier includes pretraining on real datasets, while its default regressor is pretrained on synthetic data only.","tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2000,"training_data_overlap":false},"RF":{"id":"RF","display":"Random Forest","tuned_from":null,"classification_only":false,"source_url":"https://github.com/scikit-learn/scikit-learn","description":"Random Forest grows decision trees on bootstrap samples of the training data, considering a random subset of features at each split. It averages their class probabilities for classification or their numerical predictions for regression.","tuning":null,"category":"Tree-based","color":"#059669","regular_max_features":null,"training_data_overlap":false},"TABDPT":{"id":"TABDPT","display":"TabDPT","tuned_from":null,"classification_only":false,"source_url":"https://github.com/layer6ai-labs/TabDPT-inference","description":"TabDPT is a tabular foundation model by Layer6 AI pretrained on real datasets using self-supervised prediction tasks. For a new classification or regression problem, it retrieves relevant labelled rows and uses them as context to predict new rows without updating its weights on that dataset.","tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2500,"training_data_overlap":true},"TABFM":{"id":"TABFM","display":"TabFM","tuned_from":null,"classification_only":false,"source_url":"https://github.com/google-research/tabfm","description":"TabFM is Google's pretrained model for classification and regression on tables containing numerical and categorical columns. It predicts from labelled training rows supplied as context, using sampled groups of rows and features when needed, rather than updating its model weights for each new dataset.","tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2000,"training_data_overlap":false},"TABICL":{"id":"TABICL","display":"TabICL v2","tuned_from":null,"classification_only":false,"source_url":"https://github.com/soda-inria/tabicl","description":"TabICL v2 is a transformer pretrained on varied synthetic tables for classification and regression. It uses labelled training rows as context when predicting new rows, with attention designed to handle larger tables without requiring equally long tables throughout pretraining.","tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":2000,"training_data_overlap":false},"TABM":{"id":"TABM","display":"TabM","tuned_from":null,"classification_only":false,"source_url":"https://github.com/yandex-research/tabm","description":"TabM, by Yandex Research, trains a group of multilayer perceptrons together for tabular classification or regression, with most of their weights shared. Each input produces several predictions that are combined, giving the model an ensemble structure without storing and training a full set of separate networks.","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,"classification_only":false,"source_url":"https://github.com/PriorLabs/TabPFN","description":"TabPFN 3, by Prior Labs, is a transformer pretrained on synthetic prediction tasks. For classification or regression on a new table, it uses the labelled training rows as examples to guide its predictions rather than learning the task from scratch.","tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":10000,"training_data_overlap":false},"TABPFN-WIDE":{"id":"TABPFN-WIDE","display":"TabPFN Wide (8k)","tuned_from":null,"classification_only":true,"source_url":"REMOVED","description":"TabPFN-Wide continues pre-training TabPFN 2 on synthetic tables with many features and few samples, a setting common in omics. This classification model uses the wide-v2-8k checkpoint to work with wider inputs than the original model.","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,"classification_only":true,"source_url":"REMOVED","description":"TabPFN-Wide continues pre-training TabPFN 2 on synthetic tables with many features and few samples, a setting common in omics. This TabPFN-Wide configuration uses the wide-v2-5k checkpoint, pretrained for classification with many features and few samples. It averages three inference variants while keeping the checkpoint's original feature grouping.","tuning":null,"category":"Tabular Foundation","color":"#7c3aed","regular_max_features":null,"training_data_overlap":false},"XGB":{"id":"XGB","display":"XGBoost","tuned_from":null,"classification_only":false,"source_url":"https://github.com/dmlc/xgboost","description":"XGBoost combines decision trees through gradient boosting, adding trees to improve the ensemble's predictions. Its training objective includes penalties on tree complexity, alongside the loss for classification or regression.","tuning":null,"category":"Gradient Boosting","color":"#d97706","regular_max_features":null,"training_data_overlap":false},"XT":{"id":"XT","display":"Extra Trees","tuned_from":null,"classification_only":false,"source_url":"https://github.com/scikit-learn/scikit-learn","description":"Extra Trees averages the predictions of many decision trees. Each tree considers randomly chosen features and split thresholds, adding more randomness than a conventional random forest when learning a classification or regression task.","tuning":null,"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,"description":"This dataset pairs chemical structures with measured bioactivity against the human glucocorticoid receptor. The benchmark represents each molecule as a fingerprint and predicts its median pChEMBL value, which summarizes potency or affinity on a logarithmic scale.","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,"description":"This dataset collects measured bioactivity of compounds tested against the human estrogen receptor. The benchmark uses molecular fingerprints to predict each compound's median pChEMBL value, a logarithmic measure of reported potency or affinity.","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":"https://doi.org/10.5281/zenodo.18713246","citation":null,"description":"Each row pairs DNA sequences around two candidate gene-fusion breakpoints, represented by concatenated Nucleotide Transformer v2 embeddings. The task distinguishes fusion-positive pairs from constructed pseudo-fusions, whose partner genes were not known to participate in fusions.","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,"description":"Microarray measurements record gene expression in human breast tissue samples from a study of breast cancer subtypes. The benchmark uses the GPL8864 subset to predict the intrinsic subtype recorded for each sample.","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,"description":"Blood DNA methylation profiles from the Dublin schizophrenia study, measured at CpG sites with Illumina HumanMethylation450 arrays. The task is to distinguish participants with schizophrenia from control participants using their methylation measurements.","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,"description":"DNA methylation measurements from human whole blood, collected with Illumina HumanMethylation450 arrays across people of different ages. The regression task is to predict a participant's chronological age from methylation levels at CpG sites.","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,"description":"DNA methylation profiles from peripheral blood leukocytes of people with rheumatoid arthritis and control participants, measured with Illumina HumanMethylation450 arrays. The task is to classify rheumatoid arthritis case status from methylation levels at CpG sites.","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,"description":"Peripheral blood DNA methylation profiles measured with Illumina HumanMethylation450 arrays in a study of cigarette smoking. The task is to classify each participant as a never, former, or current smoker using methylation levels at CpG sites.","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,"description":"Microbial functional profiles from Human Microbiome Project samples collected across several body sites in healthy adults. The benchmark uses MGnify InterPro abundances to predict the recorded isolation source of each sample.","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,"description":"Human fecal microbiome samples from a study of HIV infection, originally described as 16S rRNA sequencing. The benchmark uses MGnify InterPro functional-abundance profiles to predict recorded host sex.","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,"description":"Gut microbiome sequencing from preterm infants, reassembled and annotated by MGnify. InterPro functional-abundance profiles summarize microbial protein functions, and the benchmark uses these profiles to predict recorded host sex.","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,"description":"Gut microbiome data from a study of type 2 diabetes, reassembled and annotated by MGnify. The benchmark uses InterPro functional-abundance profiles of the microbial community to predict recorded host sex.","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,"description":"Microbial functional profiles from the Gene-Environment Interactions at the Skin Surface project. The benchmark uses MGnify InterPro abundances from assembled sequences to predict the recorded environmental material associated with each sample.","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,"description":"Assembled Human Microbiome Project sequences from samples collected across several body sites in healthy adults. The benchmark uses MGnify InterPro functional-abundance profiles to predict each sample's recorded isolation source.","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,"description":"Microbiome sequencing from a study of antibiotic resistance exchange in resource-poor Latin American settings, reassembled by MGnify. The benchmark uses InterPro functional-abundance profiles to predict the recorded environmental biome of each sample.","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,"description":"Skin microbiome data from a study that sequenced both virus-like particles and total microbial communities. The benchmark uses MGnify InterPro functional-abundance profiles to predict the recorded sex of the human host.","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,"description":"Gut microbiome sequencing from a dietary intervention study involving cholesterol-lowering vegetable oils, reassembled by MGnify. The benchmark uses InterPro functional-abundance profiles of microbial communities to predict recorded host sex.","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":"OpenML-1083","display_name":"mouseType","source":"openml","source_url":"https://www.openml.org/search?type=data&sort=runs&id=1083&status=active","citation":null,"description":"This dataset contains normalized gene expression measurements from DNA microarrays in the RSCTC 2010 challenge collection. The benchmark predicts one of seven supplied sample classes, although the OpenML documentation does not explain their biological meaning.","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,"description":"The BurkittLymphoma dataset contains normalized gene expression measurements from DNA microarrays. The benchmark predicts one of three supplied lymphoma sample classes; OpenML identifies these only by numeric labels and does not document the distinctions between them.","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,"description":"The variousCancers_final dataset contains normalized microarray gene expression measurements from the RSCTC 2010 challenge collection. The benchmark predicts the supplied cancer sample class, but the OpenML documentation does not name the individual classes.","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,"description":"Microarrays measure gene expression in human tumor samples spanning several cancer types. This benchmark predicts which of fourteen tumor classes a sample belongs to, using the class labels supplied with the Global Cancer Map dataset.","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,"description":"These microarray gene expression profiles come from human tumor samples collected by the Expression Project for Oncology and assembled in GEMLeR. The benchmark predicts whether each sample comes from colon or kidney tissue.","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,"description":"These microarray gene expression profiles come from human tumor samples collected by the Expression Project for Oncology and assembled in GEMLeR. The benchmark predicts whether a sample comes from the uterus or from another tissue.","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,"description":"These microarray gene expression profiles come from human tumor samples collected by the Expression Project for Oncology and assembled in GEMLeR. The benchmark predicts whether each sample comes from ovary or lung tissue.","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,"description":"ARCENE combines mass spectrometry measurements of protein abundance in human serum with synthetic distractor features added for a feature selection challenge. The task is to distinguish cancer samples from normal samples using the publicly labelled data.","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,"description":"The mtp2 dataset represents drug-like molecules with numerical molecular descriptors calculated using Adriana.Code. Its regression target, stored as oz1143, is the compound's melting point, drawn from a study of molecular structure and the melting behavior of solid drugs.","data_type":"Molecular properties","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,"description":"This dataset pairs gene expression measurements in the bacterium Bacillus subtilis with its production of riboflavin, also called vitamin B2. The benchmark predicts the logarithmically scaled riboflavin production rate from logarithmically scaled gene expression values.","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,"description":"RNA sequencing measures gene expression in breast tissue samples from The Cancer Genome Atlas breast cancer project. The benchmark uses normalized expression values to predict whether each sample is labelled as tumor or normal tissue.","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,"description":"RNA sequencing measures gene expression in tissue samples from The Cancer Genome Atlas head and neck squamous cell carcinoma project. The benchmark uses normalized expression values to predict whether each sample is labelled as tumor or normal tissue.","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://tdcommons.ai/single_pred_tasks/tox/#ames-mutagenicity","citation":"Hansen K et al. (2009), Benchmark data set for in silico prediction of Ames mutagenicity.","description":"The Ames dataset records whether compounds cause mutations in a bacterial test. Using molecular fingerprints, the benchmark predicts the mutagenic or non-mutagenic label assigned to each compound.","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://tdcommons.ai/single_pred_tasks/adme/#solubility-aqsoldb","citation":"Sorkun MC et al. (2019), AqSolDB, a curated reference set of aqueous solubility.","description":"AqSolDB collects experimental measurements of how readily compounds dissolve in water. The benchmark predicts logS from molecular fingerprints, with logS defined as the base-10 logarithm of solubility in moles per litre.","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://tdcommons.ai/single_pred_tasks/adme/#bbb-blood-brain-barrier-martins-et-al","citation":"Martins IF et al. (2012), A Bayesian approach to in silico blood-brain barrier penetration modeling.","description":"The Martins dataset labels compounds by whether they cross the blood-brain barrier. The benchmark uses molecular fingerprints to distinguish compounds labelled as penetrating the barrier from those labelled as non-penetrating.","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://tdcommons.ai/single_pred_tasks/adme/#cyp-p450-3a4-inhibition-veith-et-al","citation":"Veith H et al. (2009), Comprehensive characterization of cytochrome P450 isozyme selectivity.","description":"This dataset records whether compounds inhibit CYP3A4, a human enzyme involved in drug metabolism. The benchmark uses molecular fingerprints to predict the inhibition labels from the screening study by Veith and colleagues.","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://tdcommons.ai/single_pred_tasks/tox/#acute-toxicity-ld50","citation":"Zhu H et al. (2009), Quantitative structure-activity relationship modeling of rat acute toxicity.","description":"The Zhu dataset contains acute oral toxicity measurements in rats. The benchmark predicts pLD50 from molecular fingerprints: the negative base-10 logarithm of the median lethal dose, measured in moles per kilogram of body weight.","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://tdcommons.ai/single_pred_tasks/adme/#lipophilicity-astrazeneca","citation":"AstraZeneca / MoleculeNet lipophilicity benchmark, distributed by Therapeutics Data Commons.","description":"AstraZeneca's lipophilicity dataset measures how compounds distribute between octanol and water at pH 7.4. The benchmark uses molecular fingerprints to predict logD, the logarithm of this distribution coefficient.","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.","description":"This maize panel pairs genome-wide SNP genotypes with flowering-time measurements for individual plant lines. The regression task uses genetic marker values to predict flowering time, drawing on the crop datasets assembled by Azodi and colleagues.","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.","description":"This rice panel contains SNP genotype profiles and flowering-time measurements, with one row per plant line. The regression task predicts flowering time from genetic markers using the data assembled for Azodi and colleagues' genomic-prediction comparison.","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.","description":"Soybean plant lines are described by SNP genotype values and paired with their measured yield trait. The regression task predicts yield from these genetic markers using the soybean panel in Azodi and colleagues' genomic-prediction study.","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.","description":"This switchgrass panel pairs SNP genotype profiles with plant-height measurements for individual plant lines. The regression task predicts height from genetic markers using the data assembled for Azodi and colleagues' comparison of genomic-prediction methods.","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,"description":"Stool metagenomes from the Qin liver cirrhosis study, represented as the presence or absence of microbial genetic markers in MetAML. The benchmark predicts whether a sample came from a participant with cirrhosis or a healthy control.","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":"REMOVED","citation":null,"description":"BRCA sequence variants are represented by Evo2 embeddings of their reference and altered DNA sequences, averaged over each sequence and joined together. The target assigns each variant to its recorded functional-effect class: FUNC, LOF, or INT.","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":"https://services.healthtech.dtu.dk/services/DeepLoc-2.0/","citation":null,"description":"Fungal proteins from the DeepLoc 2.0 training and validation collection are represented by ESM-2 sequence embeddings, averaged across amino-acid residues. The task classifies each protein as membrane-associated or soluble using the source annotations.","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":"https://github.com/DeepGraphLearning/PEER_Benchmark","citation":null,"description":"Single-amino-acid mutants of TEM-1 beta-lactamase are represented by ESM-2 embeddings averaged across the protein sequence. The regression target is each mutant's scaled experimental activity value from the PEER benchmark.","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"}]}
