datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
MoleculeNet_Tox21
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Nuclear-receptor and stress-response toxicity assays from the Tox21 challenge. Multi-task classification.
Rows: 7,831 (tox21.csv 7,831)
Pairs with Aurigene-AI/ChemBERTa-77M-MTR from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_Tox21 - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_Tox21.MoleculeNet_HIV
Mirrored by Aurigene AI
Discovery stage: Hit generation
Compounds screened for inhibition of HIV replication. The classic large-scale virtual screening benchmark.
Rows: 41,127 (hiv.csv 41,127)
Pairs with Aurigene-AI/MoLFormer-XL-both-10pct from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_HIV - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_HIV.MoleculeNet_Lipophilicity
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Octanol/water distribution coefficient (logD at pH 7.4). Regression, a core ADMET endpoint.
Rows: 4,200 (lipophilicity.csv 4,200)
Pairs with Aurigene-AI/MoLFormer-XL-both-10pct from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_Lipophilicity - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_Lipophilicity.MoleculeNet_BACE
Mirrored by Aurigene AI
Discovery stage: Lead optimization
BACE-1 (beta-secretase 1) inhibition, a validated Alzheimer's disease target. Binary classification.
Rows: 1,513 (bace.csv 1,513)
Pairs with Aurigene-AI/ChemBERTa-77M-MTR from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_BACE - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the catalogue:… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_BACE.MoleculeNet_ClinTox
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Clinical trial toxicity outcomes alongside FDA approval status. Two binary tasks.
Rows: 1,477 (clintox.csv 1,477)
Pairs with Aurigene-AI/ChemBERTa-77M-MTR from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_ClinTox - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the catalogue: Molecule… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_ClinTox.MoleculeNet_FreeSolv
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Experimental and calculated hydration free energies in water. Regression.
Rows: 642 (freesolv.csv 642)
Pairs with Aurigene-AI/MoLFormer-XL-both-10pct from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_FreeSolv - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the catalogue: Molecule Explorer -… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_FreeSolv.MoleculeNet_BBBP
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Blood-brain barrier penetration for small drug-like molecules. Binary classification, scaffold split, AUROC.
Rows: 2,039 (bbbp.csv 2,039)
Pairs with Aurigene-AI/ChemBERTa-77M-MTR from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_BBBP - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_BBBP.MoleculeNet_SIDER
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Marketed-drug side effects grouped into MedDRA system organ classes. Multi-task classification.
Rows: 1,427 (sider.csv 1,427)
Pairs with Aurigene-AI/ChemBERTa-77M-MTR from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_SIDER - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the catalogue:… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_SIDER.MoleculeNet_ESOL
Mirrored by Aurigene AI
Discovery stage: Lead optimization
Aqueous solubility (log mol/L) for small organic molecules. Regression, the standard solubility benchmark.
Rows: 1,128 (esol.csv 1,128)
Pairs with Aurigene-AI/MoLFormer-XL-both-10pct from our model catalogue.
Upstream: scikit-fingerprints/MoleculeNet_ESOL - all credit to the original authors and to the researchers who produced the underlying data; the dataset card and licence below are theirs.
Explore the rest of the… See the full description on the dataset page: https://huggingface.co/datasets/Aurigene-AI/MoleculeNet_ESOL.