Cheminformatics modeling has always drawn heavily on compilations as a source of data. The most desirable ones were assembled by experts in a particular field, typically as literature reviews. Compilations assembled by cheminformatics groups specifically for model building purposes tended to be less carefully curated but were attractive because they were typically large - sometimes because they were compilations of compilations. The advent of sophisticated data mining tools has made it much easier to automate compilation, and the need for big data to drive deep learning has brought us into the age of Big Data. The sheer size of the data sets involved has driven development of automated curation techniques, particularly ones focused on standardizing structures. Unfortunately, the tools involved sometimes introduce systematic errors or over-standardize data; this talk will explore examples of the kinds of errors that can be inadvertently introduced in the process.

Big errors in big data: When automated data curation misses the mark

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.