The Chemical Checker

The Chemical Checker (CC) is a data-driven resource of small molecule bioactivity data. The main goal of the CC is to express data in a format that can be used off-the-shelf in daily computational drug discovery tasks. The resource is organized in 5 levels of increasing complexity, ranging from the chemical properties of the compounds to their clinical outcomes. In between, we consider targets, off-targets, perturbed biological networks and several cell-based assays, including gene expression, growth inhibition, and morphological profiles. The CC is different to other integrative compounds database in almost every aspect. The classical, relational representation of the data is surpassed here by a less explicit, more machine-learning-friendly abstraction of the data (see the CC Manifesto).

The CC resource is ever-growing and maintained by the Structural Bioinformatics & Network Biology Laboratory at the Institute for Research in Biomedicine (IRB Barcelona). Should you have any questions, please send an email to miquel.duran@irbbarcelona.org or patrick.aloy@irbbarcelona.org.

This project was first presented to the scientific community in the following paper:

Duran-Frigola M, et al “Extending the small-molecule similarity principle to all levels of biology with the Chemical Checker.” Nature Biotechnology (2020) [link]

and has since produced a number of related publications.

Note

For an overview of the CC universe please visit bioactivitysignatures.org

Source data and datasets

The CC is built from public bioactivity data. We are committed to updating the resource every 6 months (versions named accordingly, e.g. chemical_checker_2019_01). New datasets may be incorporated upon request.

The basic data unit of the CC is the dataset. There are 5 data levels (A Chemistry, B Targets, C Networks, D Cells and E Clinics) and, in turn, each level is divided into 5 sublevels or coordinates (A1-E5). Each dataset belongs to one and only one of the 25 coordinates, and each coordinate can have a finite number of datasets (e.g. A1.001), one of which is selected as being exemplary.

The CC is a chemistry-first biomedical resource and, as such, it contains several predefined compound collections that are of interest to drug discoverers, including approved drugs, natural products, and commercial screening libraries (see the Sources section).

Signaturization of the data

The main task of the CC is to convert raw data into formats that are suitable inputs for machine-learning toolkits such as scikit-learn.

Accordingly, the backbone pipeline of the CC is devoted to processing every dataset and converting it to a series of formats that may be readily useful for machine learning. The main assets of the CC are the so-called CC signatures:

Signature	Abbreviation	Description	Advantages	Disadvantages
Type 0	sign0	Raw dataset data, expressed in a matrix format.	Explicit data.	Possibly sparse, het erogeneous, u nprocessed.
Type 1	sign1	PCA/LSI projections of the data, accounting for 90% of the data.	Biological signatures of this type can be obtained by simple projection. Easy to compute and require no f ine-tuning.	Variables dimensions, they may still be sparse.
Type 2	sign2	Networ k-embedding of the similarity network.	Fixed -length, usually acceptably short. Suitable for machine learning. Capture global properties of the similarity network.	Information leak due to similarity measures. Hype r-parameter tunning.
Type 3	sign3	Siamese Neural Network embedding derived from all 25 spaces.	Fixed dimension and available for many molecule.	Possibly very noisy, hence useless, especially for low-data datasets.
Type 4	sign4	DNN multioutput regression of sign3.	Fixed dimension and available for any molecule.	Possibly very noisy, subject to out of distribution bias.

For further details see the Signaturization section.

Note

A Signaturizer module for direct molecule signaturization is also available.

API Reference

All data in the CC resource are stored as HDF5 files and can be accessed with a simple API defined in the Chemical Checker Package that you find documented in following pages.

chemicalchecker

Welcome to the Chemical Checker Package documentation!

Contents:

• Chemical Checker Manifesto
  • Chemistry first
  • The small molecule similarity principle simply makes sense
  • All molecules are equally interesting
  • Infinite data, finite types of data
  • Others are better curators than us
  • It is time to go predictive
  • We don’t need another chemoinformatics library
• Datasets
  • Levels, coordinates and datasets
  • Dataset characteristics
  • Dataset pre-processing
• Signaturization
  • Signature characteristics
  • Signatures type 0
  • Signatures type 1
  • Signatures type 2
  • Signatures type 3
  • Signatures type 4

• Module Index

• Index