TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Text+Chem T5 base

Text+Chem T5 base

Reported on 18 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical18 results

  • Drug DiscoveryonChEBI-20
    BLEU· 2023-01-29
    75
    best: 92.6 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    Exact Match· 2023-01-29
    21.2
    best: 53.3 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    Frechet ChemNet Distance (FCD)· 2023-01-29
    0.061
    best: 2.49 (MolT5-small)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    Levenshtein· 2023-01-29
    27.39
    best: 28.54 (Text+Chem T5 small)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    MACCS FTS· 2023-01-29
    87.4
    best: 97.3 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    Morgan FTS· 2023-01-29
    69.7
    best: 93.1 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    Parameter Count· 2023-01-29
    220000000
    best: 770000000 (MolT5-Large)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    RDK FTS· 2023-01-29
    76.7
    best: 95 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Drug DiscoveryonChEBI-20
    Validity· 2023-01-29
    79.2
    best: 100 (BioT5+)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    BLEU· 2023-01-29
    75
    best: 92.6 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    Exact Match· 2023-01-29
    21.2
    best: 53.3 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    Frechet ChemNet Distance (FCD)· 2023-01-29
    0.061
    best: 2.49 (MolT5-small)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    Levenshtein· 2023-01-29
    27.39
    best: 28.54 (Text+Chem T5 small)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    MACCS FTS· 2023-01-29
    87.4
    best: 97.3 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    Morgan FTS· 2023-01-29
    69.7
    best: 93.1 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    Parameter Count· 2023-01-29
    220000000
    best: 770000000 (MolT5-Large)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    RDK FTS· 2023-01-29
    76.7
    best: 95 (LDMol)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586
  • Text-based de novo Molecule GenerationonChEBI-20
    Validity· 2023-01-29
    79.2
    best: 100 (BioT5+)
    Unifying Molecular and Textual Representations via Multi-task Language ModellingarXiv:2301.12586