Access Chemical Big Data with Quality and Integrity

Input a chemical compound consisting of C, H, N, O, S, F, Cl, Br, I, Si, P, and/or As atom(s)

Examples of Chemical Identifiers

Examples of Chemical Identifiers:

  • Name: ethanol
  • CAS #: 64-17-5
  • Formula: C2H5OH
  • Smiles: CCO
  • InChI: InChI=1S/C2H6O/c1-2-3/h3H,2H2,1H3

What Is Deep Data?

Deep data refers to big data with quality and integrity. The deep data we provide are large-scale datasets representing fundamental and scientific information of chemical compounds, which are essential for a wide range of chemical applications and advanced research & development.

What Data Are Available?

Currently, more than 8 billion datasets comprising property data, spectra data, quantum data, and molecular descriptor data of chemical compounds are available, which continuously increases at a rate of over 200 million data per month. The IK-Cape File is available as well for the process simulation software such as Aspen Plus. A total of more than 2,100 data per single compound are provided. For a detailed list, have a look at the full dataset list page. View Complete List of Deep Data

What Are These Data Used For?

Our Deep Data are used for most of the major chemical applications including chemical AI, machine learning, energy efficiency and renewable energy (bioenergy), drug design & discovery, flavor & fragrance compounds design, and chemical safety & management (REACH & TSCA). Our Deep Data are essential for the important R&D areas such as QSAR/QSPR, toxicity prediction, combustion kinetics, reaction kinetics & reactor design, and chemical process design and simulation. For more information, have a look at the “application” page. View Application

How to Obtain These Deep Data?

Three simple plans (i.e. Delivery, Subscription, and Pay Per Dataset) are available to choose from, offering easy and fast acquisition of the data. For more information, have a look at the “how to obtain deep data” page. View How to Obtain Deep Data

Where Do These Deep Data Come From?

The deep data are originated from our online subscription services, Mol-Instincts database and ChemRTP, which are determined by 41 patented QSQN technology, QN technology, quantum chemical computations, and/or some traditional methods for comparison. A description on our technologies for the deep data determination are available. View Technology Description

Who’s Using These Deep Data?

Our deep data have been cited a number of times in the scientific publications of high-impact journals including NATURE, ELSEVIER, Springer, American Chemical Society, Royal Society of Chemistry, and Wiley. A partial list of the publications which cite our deep data is available for your information. View a List of Publications Citing Our Deep Data

More than 490,000 individuals, 1,400 universities, 300 global companies, and 100 national organizations around the world have used our data. View a Detailed User List

What Are the Costs?

Our prices start as low as $0.5 USD per data for academic users in case our data delivery service is used. A more detailed outline of the prices are available for your review. View Prices Outline

Further Information?

We offer some special services named as Deep Services, in addition to providing the deep data. A detailed description is available. View Deep Services

An outline of deep data compounds provides what chemical compounds are applicable to produce the deep data, and what compounds have been processed. View Outline of Deep Data Compounds

An overview of our vision describes what we would like to contribute to chemical world. View Our Vision


Subscribe to our newsletter

Join our subscribers list to get the latest news, updates and special offers delivered directly in your inbox.