Name: Wikipedia Molecules
Creator: Kaggle
License: https://creativecommons.org/licenses/by/4.0/

About this Dataset

Wikipedia Molecules

Wikipedia is undoubtedly one of the most important freely available sources of knowledge on the internet. Many thousand of its articles are about chemical substances. This dataset contains an up-to-date list of all Wikipedia compound structures with their names and formulas. I've converted the data to csv and calculated the molecular properties of the substances.

Tables

Molecules

@kaggle.joebeachcapital_wikipedia_molecules.molecules

1.89 MB
15,166 rows
33 columns

CREATE TABLE molecules (
  "row_id" VARCHAR,
  "molecule" VARCHAR,
  "molecule_name" VARCHAR,
  "mannhold_logp" DOUBLE,
  "atomic_polarizabilities" VARCHAR,
  "aromatic_atoms_count" BIGINT,
  "aromatic_bonds_count" BIGINT,
  "element_count" BIGINT,
  "bond_polarizabilities" VARCHAR,
  "bond_count" BIGINT,
  "eccentric_connectivity_index" BIGINT,
  "fragment_complexity" DOUBLE,
  "vabc_volume_descriptor" VARCHAR,
  "hydrogen_bond_acceptors" BIGINT,
  "hydrogen_bond_donors" BIGINT,
  "largest_chain" BIGINT,
  "largest_pi_chain" BIGINT,
  "petitjean_number" DOUBLE,
  "rotatable_bonds_count" BIGINT,
  "lipinski_s_rule_of_five" BIGINT  -- Lipinski\u0027s Rule Of Five,
  "topological_polar_surface_area" VARCHAR,
  "vertex_adjacency_information_magnitude" DOUBLE,
  "molecular_weight" VARCHAR,
  "xlogp" DOUBLE,
  "zagreb_index" BIGINT,
  "molecular_formula" VARCHAR,
  "formal_charge" BIGINT,
  "formal_charge_pos" BIGINT  -- Formal Charge (pos),
  "formal_charge_neg" BIGINT  -- Formal Charge (neg),
  "heavy_atoms_count" BIGINT,
  "molar_mass" VARCHAR,
  "sp3_character" DOUBLE,
  "rotatable_bonds_count_non_terminal" BIGINT  -- Rotatable Bonds Count (non Terminal)
);