Prediction Errors and Filtering the ChemSpider Database – How Accurate Does a Prediction Need to Be?

22 May

A number of comments have been made regarding the appropriateness of the prediction of physicochemical parameters for the structures in ChemSpider. This culminated with me recently suggesting that certain types of compounds in the database should not have these certain parameters calculated. Specifically the suggestions were to:

Filter the ChemSpider database and remove the following PhysChem predictions (ACD/LogP, ACD/LogD (pH 5.5), ACD/LogD (pH 7.4), Number of Rule of 5 Violations, Number of H bond acceptors, Number of H bond donors, Number of Freely Rotating Bonds, Polar Surface Area) for substances with the following properties:

• Exclude multi-component substances
• Exclude substances represented as a single atom
• Exclude radicals
• Exclude structures with a delocalized charge
• Exclude structures containing isotopes
• Exclude substances containing elements not supported by the prediction algorithms (self-excluding really!)

PMR had previously added comments to his post regarding my questions. Based on this feedback and other comments on blog postings and email exchanges it’s time to summarize our path forward and the reasons for our decisions.

Regarding isotopes. I see no reason to exclude isotopes at this point. True, D2O does have a different boiling point that H2O, by 1.4 degrees. However, we are considering the prediction of properties for what is now a database containing almost 13.4 million chemical structures. Some of the properties being predicted are not easy to measure reproducibly and with high accuracy (think LogP and LogD) while for others, for example boiling point, predictions within a few percent should suffice. I very much doubt that the labeling of a couple of isolated sites with either C13 or N15 for example would make any significant difference. Deuterium labeling might have a small effect on pKa for teh ionizable protons and thereby change the logD values. However I doubt that the difference could be measured experimentally in terms of logD values. These are predictions and such be treated as such. Details regarding prediction accuracy for some of the properties are given elsewhere (1,2).

What we will likely proceed with is to:

1)Exclude multi-component substances (but be very careful about waters of crystallization and counterions)

2)Exclude substances represented as a single atom

3)Exclude radicals

4)Exclude structures with a delocalized charge


About tony

Antony (Tony) J. Williams received his BSc in 1985 from the University of Liverpool (UK) and PhD in 1988 from the University of London (UK). His PhD research interests were in studying the effects of high pressure on molecular motions within lubricant related systems using Nuclear Magnetic Resonance. He moved to Ottawa, Canada to work for the National Research Council performing fundamental research on the electron paramagnetic resonance of radicals trapped in single crystals. Following his postdoctoral position he became the NMR Facility Manager for Ottawa University. Tony joined the Eastman Kodak Company in Rochester, New York as their NMR Technology Leader. He led the laboratory to develop quality control across multiple spectroscopy labs and helped establish walk-up laboratories providing NMR, LC-MS and other forms of spectroscopy to hundreds of chemists across multiple sites. This included the delivery of spectroscopic data to the desktop, automated processing and his initial interests in computer-assisted structure elucidation (CASE) systems. He also worked with a team to develop the worlds’ first web-based LIMS system, WIMS, capable of allowing chemical structure searching and spectral display. With his developing cheminformatic skills and passion for data management he left corporate America to join a small start-up company working out of Toronto, Canada. He joined ACD/Labs as their NMR Product Manager and various roles, including Chief Science Officer, during his 10 years with the company. His responsibilities included managing over 50 products at one time prior to developing a product management team, managing sales, marketing, technical support and technical services. ACD/Labs was one of Canada’s Fast 50 Tech Companies, and Forbes Fast 500 companies in 2001. His primary passions during his tenure with ACD/Labs was the continued adoption of web-based technologies and developing automated structure verification and elucidation platforms. While at ACD/Labs he suggested the possibility of developing a public resource for chemists attempting to integrate internet available chemical data. He finally pursued this vision with some close friends as a hobby project in the evenings and the result was the ChemSpider database ( Even while running out of a basement on hand built servers the website developed a large community following that eventually culminated in the acquisition of the website by the Royal Society of Chemistry (RSC) based in Cambridge, United Kingdom. Tony joined the organization, together with some of the other ChemSpider team, and became their Vice President of Strategic Development. At RSC he continued to develop cheminformatics tools, specifically ChemSpider, and was the technical lead for the chemistry aspects of the Open PHACTS project (, a project focused on the delivery of open data, open source and open systems to support the pharmaceutical sciences. He was also the technical lead for the UK National Chemical Database Service ( and the RSC lead for the PharmaSea project ( attempting to identify novel natural products from the ocean. He left RSC in 2015 to become a Computational Chemist in the National Center of Computational Toxicology at the Environmental Protection Agency where he is bringing his skills to bear working with a team on the delivery of a new software architecture for the management and delivery of data, algorithms and visualization tools. The “Chemistry Dashboard” was released on April 1st, no fooling, at, and provides access to over 700,000 chemicals, experimental and predicted properties and a developing link network to support the environmental sciences. Tony remains passionate about computer-assisted structure elucidation and verification approaches and continues to publish in this area. He is also passionate about teaching scientists to benefit from the developing array of social networking tools for scientists and is known as the ChemConnector on the networks. Over the years he has had adjunct roles at a number of institutions and presently enjoys working with scientists at both UNC Chapel Hill and NC State University. He is widely published with over 200 papers and book chapters and was the recipient of the Jim Gray Award for eScience in 2012. In 2016 he was awarded the North Carolina ACS Distinguished Speaker Award.
Leave a comment

Posted by on May 22, 2007 in ChemSpider Services


Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.