Dataset: Drug Classification Dataset

About this Dataset

Drug Classification Dataset

Toxic Chemical Compounds Dataset: Properties, Effects, and Classification

Description:

The Toxic Chemical Compounds Dataset from Kaggle provides comprehensive information on various hazardous chemical compounds, including their structure, toxicity levels, chemical properties, and classification. It is designed for use in toxicology research, environmental analysis, and machine learning applications in chemistry. The dataset includes crucial attributes such as compound names, molecular formulas, toxicity classification (carcinogenic, mutagenic, corrosive, etc.), hazard levels, and regulatory status.

Researchers can leverage this dataset to predict toxicity levels, analyze chemical interactions, and study the environmental and health impacts of hazardous substances. It is valuable for chemists, environmental scientists, and AI researchers developing predictive models for toxicity assessment and chemical safety.

This dataset can also be utilized in pharmaceutical and industrial applications to assess the safety of compounds before large-scale production. Additionally, it aids in regulatory compliance research, helping industries understand the risks associated with chemical exposure. With its structured format, this dataset supports data-driven decision-making in public health, medicine, and environmental protection.

For machine learning, the dataset can be used to train models for chemical property prediction, hazard classification, and risk assessment, making it a valuable resource for computational toxicology and AI-driven chemical analysis.

Tables

Pubchem Compound Cache

@kaggle.yxshee_toxic_chemical_compounds.pubchem_compound_cache

68.32 MB
117477 rows
38 columns


CREATE TABLE pubchem_compound_cache (
  "n__cid" BIGINT,
  "cmpdname" VARCHAR,
  "cmpdsynonym" VARCHAR,
  "mw" DOUBLE,
  "mf" VARCHAR,
  "polararea" DOUBLE,
  "complexity" DOUBLE,
  "xlogp" DOUBLE,
  "heavycnt" BIGINT,
  "hbonddonor" BIGINT,
  "hbondacc" BIGINT,
  "rotbonds" BIGINT,
  "inchi" VARCHAR,
  "smiles" VARCHAR,
  "inchikey" VARCHAR,
  "iupacname" VARCHAR,
  "exactmass" DOUBLE,
  "monoisotopicmass" DOUBLE,
  "charge" BIGINT,
  "covalentunitcnt" BIGINT,
  "isotopeatomcnt" BIGINT,
  "totalatomstereocnt" BIGINT,
  "definedatomstereocnt" BIGINT,
  "undefinedatomstereocnt" BIGINT,
  "totalbondstereocnt" BIGINT,
  "definedbondstereocnt" BIGINT,
  "undefinedbondstereocnt" BIGINT,
  "pclidcnt" BIGINT,
  "gpidcnt" BIGINT,
  "gpfamilycnt" BIGINT,
  "meshheadings" VARCHAR,
  "annothits" VARCHAR,
  "annothitcnt" BIGINT,
  "aids" VARCHAR,
  "cidcdate" BIGINT,
  "sidsrcname" VARCHAR,
  "depcatg" VARCHAR,
  "annotation" VARCHAR
);