Molecular Representation Learning

Molecular Representation Learning is a computational approach in cheminformatics that, by belonging to the class of representation learning methods, specifically focuses on automatically deriving low-dimensional, informative embeddings of molecular structures to capture their chemical and functional similarity through patterns learned from data.

734

Publications

71.8K

Citations

2.6K

Authors

771

Institutions

Publications per year

2017–2026

675

Authors

2.6K

  1. RB
    Regina Barzilay

    Massachusetts Institute of Technology, United States

    20 publications · 4.7K citations

    18

    h-index

  2. TJ
    Tommi Jaakkola

    Massachusetts Institute of Technology, United States

    19 publications · 4.4K citations

    17

    h-index

  3. WJ
    Wengong Jin

    Massachusetts Institute of Technology, United States

    15 publications · 3.8K citations

    14

    h-index

  4. AA
    Alán Aspuru‐Guzik

    Harvard University, United States

    14 publications · 4.9K citations

    14

    h-index

  5. OE
    Ola Engkvist

    AstraZeneca (Sweden), Sweden

    17 publications · 1.5K citations

    14

    h-index

1–5 of 2.6K

Venues

  1. arXiv (Cornell University)

    Repository · 112 publications · 8.1K citations

    38

    h-index

  2. Journal of Chemical Information and Modeling

    JCIM · 56 publications · 7.6K citations

    33

    h-index

  3. Briefings in Bioinformatics

    29 publications · 1.9K citations

    24

    h-index

  4. ChemRxiv

    Repository · 38 publications · 2.3K citations

    23

    h-index

  5. Nature Communications

    24 publications · 2.1K citations

    22

    h-index

1–5