Datasets used for Drug Discovery Tasks.

Presented by AI Research & Bio.

Industry-Problem–ML Task-Model–Dataset-Solution

Discovery - Build - Validate - Deploy - Automate - Operate

Drug Discovery Tasks

ADME, TOX, Aaff, HTS, QM, Yields, Epitope, ADP, CRISPR, DTI, PPI, DrugRes, DrugSyn, MTI, Catalyst, MolGen, Reaction, ...

Task: ADME Pharmaco-kinetics

Absorption, Distribution, Metabolism, Excretion

-Absorption-

Caco-2 (Cell Effective Permeability), Wang et al. PAMPA Permeability, NCATS HIA (Human Intestinal Absorption), Hou et al. Pgp (P-glycoprotein) Inhibition, Broccatelli et al. Bioavailability, Ma et al. Lipophilicity, AstraZeneca Solubility, AqSolDB Hydration Free Energy, FreeSolv

-Distribution-

BBB (Blood-Brain Barrier), Martins et al. PPBR (Plasma Protein Binding Rate), AstraZeneca VDss (Volumn of Distribution at steady state), Lombardo et al.

-Metabolism-

CYP P450 2C19 Inhibition, Veith et al. CYP P450 2D6 Inhibition, Veith et al. CYP P450 3A4 Inhibition, Veith et al. CYP P450 1A2 Inhibition, Veith et al. CYP P450 2C9 Inhibition, Veith et al. CYP2C9 Substrate, Carbon-Mangels et al. CYP2D6 Substrate, Carbon-Mangels et al. CYP3A4 Substrate, Carbon-Mangels et al.

-Excretion-

Half Life, Obach et al. Clearance, AstraZenecat

Task: Toxicity Prediction

Acute Toxicity LD50 hERG blockers hERG Central hERG Karim et al. Ames Mutagenicity DILI (Drug Induced Liver Injury) Skin Reaction Carcinogens Tox21 ToxCast ClinTox

Task: High-throughput Screening Prediction

SARS-CoV-2 In Vitro, Touret et al. SARS-CoV-2 3CL Protease, Diamond. HIV Butkiewicz et al.

Task: Quantum Mechanics Modeling

QM7b, QM8, QM9

Task:Reaction Yields Prediction

Buchwald-Hartwig USPTO

Task:Epitope Prediction

IEDB, Jespersen et al. PDB, Jespersen et al.

Task: Antibody Developability Prediction

TAP SAbDab, Chen et al.

Task: CRISPR Repair Outcome Prediction

TAP SAbDab, Chen et al.

Task: Drug-Target Interaction Prediction

BindingDB DAVIS KIBA

Task: Drug-Drug Interaction Prediction

DrugBank Multi-Typed DDI TWOSIDES Polypharmacy Side Effects

Task: Protein-Protein Interaction Prediction

HuRI

Task: Gene-Disease Association Prediction

DisGeNET

Task: Drug Response Prediction

GDSC1 GDSC2

Task: Drug Synergy Prediction

OncoPolyPharmacology DrugComb

Task: Peptide-MHC Binding Prediction

MHC Class I, IEDB-IMGT, Nielsen et al. MHC Class II, IEDB, Jensen et al.

Task: Antibody-antigen Affinity Prediction

SAbDab

Task: MicroRNA-Target Interaction Prediction

miRTarBase

Task: Catalyst Prediction

USPTO

Task: Clinical Trial Outcome Prediction

Trial Outcome Prediction (TOP)

Task: Molecule Generation

MOSES ZINC ChEMBL

Task: Retrosynthesis Prediction

USPTO-50K USPTO

Task: Reaction Outcome Prediction

USPTO

Task: Structure-based Drug Design

PDBBind DUD-E scPDB