Dataset TODO list

[phalem]

Dataset Todo

• Add "synthetic" data New Task: Add "synthetic" data #13 [nice-to-have]
• Run ChemDataExtractor on Free Text New Task: Run ChemDataExtractor on Free Text #18 [needs-discussion]
• Prepare PubChem dataset New Task: Prepare PubChem dataset #19 [priority-high]
• Add CheMBL dataset New Task: Add CheMBL dataset #24 [priority-high]
• Add ESOL dataset New task: Add ESOL dataset #33 [priority-high]

Dataset In Progress

• Add Papyrus dataset Add Papyrus dataset #335 Add Papyrus 3 Million data point pchembl for 7k protein #340

• Add papyrus protein targets Add papyrus protein targets #336

• Adding data from the Human Metabolome Database (HMDB) New Task: Adding data from the Human Metabolome Database (HMDB) #136 [adamoyoung]

• Adding Data from MassBank of North America (MoNA) New Task: Adding Data from MassBank of North America (MoNA) #137 [adamoyoung]

• Add Open Targets datasets for drug information Add Open Targets datasets for drug information #138 FDA Adverse reactions datasets - We can add a dataset containing the frequency of adverse reaction events for individual drugs identified by their CHEMBL ID. #139 Drug disease indications - Add a dataset of drug disease indications by CHEMBL ID. #140 Mechanisms of action - Add a dataset of mechanism for multiple CHEMBL ID's. #141 Drug descriptions & approval - Add a dataset containing metadata identifiers (SMILES, size, names, years, etc) and approval results in different countries. #142 [jackapbutler]

• Adding the europepmc dataset Adding the europepmc dataset #162 [hssn-20]

• Adding Uniprot, X-linking to reaction DBs for enzymes Adding Uniprot, X-linking to reaction DBs for enzymes #191 [hypnopump]

• Add DrugChat data Add DrugChat data #293 [alxfgh]

• Adding Suzuki Miyaura yield prediction dataset Adding Suzuki Miyaura yield prediction dataset #212 [pschwllr]

• Add QMOF dataset Add QMOF dataset #235 [kjappelbaum]

• Add SuperCon dataset Add SuperCon dataset #236 [kjappelbaum]

• Add QMUG dataset Add QMUG dataset #237 [kjappelbaum]

• Add Enamine dataset Add Enamine dataset #238 [kjappelbaum]

• Add ORD dataset Add ORD dataset #239 [kjappelbaum]

• Refactor rhea_db into csv files refactor rhea_db into csv files #242 [kjappelbaum]

• Add Drug-Target Interaction data New Task: Add Drug-Target Interaction data #68 [strubeyj]

• H2_storage_materials_database H2_storage_materials_database #64 [bethanyconnolly] created h2 storage dataset #76

• Add EuroPMC Dataset New Task: Add EuroPMC Dataset #32 [abhinav-kashyap-asus]

• Add Buchwald Hartwig dataset[pschwllr] Add Buchwald Hartwig dataset #81

• Add Drug-Drug Interaction Data from nSIDES [apoorvasrinivasan26] New Task: Add Drug-Drug Interaction Data #89

• Add uspto data from drfp Add uspto data from drfp #95

• Add NLMChem Add NLMChem #114 [apoorvasrinivasan26]

• Add ThermoML Archive dataset Add ThermoML Archive dataset #118

• Adding the Chemistry textbooks from LibreTexts library New Task: Adding the Chemistry textbooks from LibreTexts library  #134

• Add Therapeutic Data Commons dataset New Task: Add Therapeutic Data Commons dataset #27 [priority-high]

  -[ ] Single-instance [phalem] New Task | Finish Single-instance remaining data & Generation Datasets from TDC #90

  • Add ADME Property [phalem] New Task : Add ADME Property data from TDC #84
    • Absorption Adding ADME absorption TDC #85
      • Caco-2 (Cell Effective Permeability), Wang et al.[MicPie] New task: caco2_wang via tdcommons.ai #37
      • PAMPA Permeability, NCATS [MicPie] New task: Add PAMPA Permeability, NCATS dataset #41
      • HIA (Human Intestinal Absorption), Hou et al. Adding ADME absorption TDC #85
      • Pgp (P-glycoprotein) Inhibition, Broccatelli et al. Adding ADME absorption TDC #85
      • Bioavailability, Ma et al. Adding ADME absorption TDC #85
      • Lipophilicity, AstraZeneca [MicPie] New task: Add lipophilicity dataset #22
      • Solubility, AqSolDB Adding ADME absorption TDC #85
      • Hydration Free Energy, FreeSolv Adding ADME absorption TDC #85
    • Distribution Add ADME Distribution data from TDC #86
      • BBB (Blood-Brain Barrier), Martins et al. Add ADME Distribution data from TDC #86
      • PPBR (Plasma Protein Binding Rate), AstraZeneca Add ADME Distribution data from TDC #86
      • VDss (Volumn of Distribution at steady state), Lombardo et al. Add ADME Distribution data from TDC #86
    • Metabolism Add ADME metabolism from TDC #88
      • CYP P450 2C19 Inhibition, Veith et al. Add ADME metabolism from TDC #88
      • CYP P450 2D6 Inhibition, Veith et al. Add ADME metabolism from TDC #88
      • CYP P450 3A4 Inhibition, Veith et al. Add ADME metabolism from TDC #88
      • CYP P450 1A2 Inhibition, Veith et al. Add ADME metabolism from TDC #88
      • CYP P450 2C9 Inhibition, Veith et al. Add ADME metabolism from TDC #88
      • CYP2C9 Substrate, Carbon-Mangels et al. Add ADME metabolism from TDC #88
      • CYP2D6 Substrate, Carbon-Mangels et al. Add ADME metabolism from TDC #88
      • CYP3A4 Substrate, Carbon-Mangels et al. Add ADME metabolism from TDC #88
    • Excretion Add ADME Excretion from tdc #87
      • Half Life, Obach et al. Add ADME Excretion from tdc #87
      • Clearance, AstraZeneca Add ADME Excretion from tdc #87
  • Add Toxicity [phalem]
    • Acute Toxicity LD50 feat: add acute toxicity ld50 from TDC #54
    • hERG blockers Add h erg blocker from TDC #53
    • hERG Central Add hERG Central with multiple target #61
    • hERG Karim et al. Add h erg karim et al from TDC #52
    • Ames Mutagenicity Add Ames Mutagenicity from TDC #56
    • DILI (Drug Induced Liver Injury) Add DILI from TDC #51
    • Skin Reaction Add Skin Reaction from TDC #49
    • Carcinogens Add Carcinogens from TDC #55
    • Tox21 Add Tox21 consist of 12 assay with URI include #77
    • ToxCast Tabular data issues | ToxCast consist of 615 columns toward 615 dataset #79 Add Toxcast dataset for 8k compound agaist 615 target #343 Add ToxCast 1.5m datapoint for 8K mol on 617 assay #345 Add Toxcast with an assay description 90k datapoint for 158 assay #346
    • ClinTox feat: add ClinTox from TDC #50
  • Add High-throughput Screening [phalem]
    • SARS-CoV-2 In Vitro, Touret et al. Add HTS SARSCoV2 Vitro Touret et.al data #59
    • SARS-CoV-2 3CL Protease, Diamond. Add HTS SARSCoV2 3CLPro Diamond from TDC #94
    • HIV Add HTS HIV data #60
    • Butkiewicz et al. feat: add HTS Butkiewicz et al of 9 Target #62
  • Add Quantum Mechanics Modeling Tabular data issues | Complex data structure identifier #78
    • QM7b
    • QM8
    • QM9
  • Add Reaction Yields Tabular data issues | Complex data structure identifier #78
    • Buchwald-Hartwig Add Buchwald Hartwig dataset #81
    • USPTO
  • Add Epitope(Immunotherapy under Target discovery) Issue | Need to know Epitope data given active indices start 0 or 1 #97
    • IEDB, Jespersen et al. Add Epitope data from TDC #96
    • PDB, Jespersen et al. Add Epitope data from TDC #96
  • Add Antibody Developability Tabular data issues | Complex data structure identifier #78
    • TAP add antibody developability from TDC #99
    • SAbDab, Chen et al. add antibody developability from TDC #99
  • Add CRISPR Repair Outcome[apoorvasrinivasan26]
    • Leenay et al.

  -[ ] Multi-instance

  • Add Drug-Target Interaction data New Task: Add Drug-Target Interaction data #68[strubeyj]
    • BindingDB
    • DAVIS
    • KIBA
  • Add Drug-Drug Interaction
    • DrugBank Multi-Typed DDI
    • TWOSIDES Polypharmacy Side Effects
  • Add Gene-Disease Association
    • DisGeNET
  • Add Drug Response
    • GDSC1
    • GDSC2
  • Add Peptide-MHC Binding
    • MHC Class I, IEDB-IMGT, Nielsen et al.
    • MHC Class II, IEDB, Jensen et al.
  • Add Antibody-antigen Affinity
    • SAbDab
  • Add MicroRNA-Target Interaction
    • miRTarBase
  • Add Catalyst
    • USPTO
  • Add TCR-Epitope Binding Affinity [strubeyj] Add tcr epitope binding dataset #67
    • Weber et al.

  -[ ] Generation data [phalem] New Task | Finish Single-instance remaining data & Generation Datasets from TDC #90

  • Add Molecule Generation Added Molegen datasets #178 [arkadiusz-czerwinski]
    • MOSES Added Molegen datasets #178 [arkadiusz-czerwinski]
    • ZINC Added Molegen datasets #178 [arkadiusz-czerwinski]
    • ChEMBL Added Molegen datasets #178 [arkadiusz-czerwinski]
  • Add Retrosynthesis
    • USPTO-50K
    • USPTO
  • Add Reaction Outcome
    • USPTO
  • Add Structure-based Drug Design
    • PDBBind
    • DUD-E
    • scPDB

Done ✓

• Add flashpoint dataset feat: add flashpoint dataset #43 [othertea]
• add initial model pipeline [maw501] [bethanyconnolly][kjappelbaum][MicPie] feat: add initial model pipeline #71
• Add iupac goldbook Add iupac goldbook #187 add iupac goldbook #188 [MicPie]
• Add RXN-SMILES as identifier type Add RXN-SMILES as identifier type #113 [kjappelbaum]
• Add benchmark field feat: implement benchmark field #116
• Add entos protonation energy add entos protonation energy #244 feat: entos dataset #233 [kjappelbaum]
• Add chebi-20 dataset New Task: Add chebi-20 dataset #63 feat: add chebi 20 to datasets #108 [jackapbutler]
• Add FDA Adverse reactions datasets FDA Adverse reactions datasets - We can add a dataset containing the frequency of adverse reaction events for individual drugs identified by their CHEMBL ID. #139 feat: add fda dataset #143 [jackapbutler]
• Add Natural text dataset elsevier_oa_cc-by_corpus Natural text dataset elsevier_oa_cc-by_corpus #216