Skip to main content

Compound Clean Up and Mapping (Posted by Louisa)

This new blog post has been created due to popular demand and user requests. I hope that this is useful for you.

After being manually extracted from the primary literature, a compound can be only loaded into the ChEMBL database after it has been run through our in-house clean-up protocol. This protocol utilises Accelrys's Pipeline Pilot software and has evolved a lot over the past three years. The clean-up protocol is used to prevent any structures from being loaded that could be incorrect, not properly charged or contain bad valences. We also use it to map the structures to already existing compounds in ChEMBL.

Historically, the clean-up protocol was very simple with just a few components to squeeze out any unwanted structures. Initially, we were mostly concerned about having uneven charges (e.g. charged counter ion but neutral parent) or quaternary nitrogen-containing compounds without a counter ion at all. Over the past 14 releases, the clean-up has become more sophisticated and now takes into account steroid backbone stereochemistry, inorganic salts and bad valences, amongst other things. A lot of the additions and adjustments have come from stumbling across little subsets of compounds that we hadn't thought of looking for before, and then warranted a consistent cleanup. This work has also led to the development of a series of business rules applied to consistently represent a functional group (for example, nitro groups).

Once the new compounds have been cleaned up, they need to be checked to see if they already exist in the database. Initially, this was done by mapping to the standard InChI,  but it was soon realised that not all papers display the correct structure, if any structure at all, or it may not be extracted from the publication exactly as shown. This was causing duplicate compounds to be loaded into ChEMBL. Therefore, it was decided that a better initial mapping would be to use the extracted compound name and compare it to the many stored compound names in the database. This reduced a lot the duplicate entries. Once the new compounds have been mapped on the name, the remaining compounds are then mapped on their standard InChI. For those that don't match either a name or an InChI, I create a text file of their names and cast an eye over them to see if there are any that can still be mapped. I have been able to catch a couple of odd ones now and again via this last check, so it's definitely worth doing.

The compound clean-up is always a 'work in progress' and open to new suggestions for filtering out any compound or group of compounds that could do with further checking. If anyone would like to know more about the clean-up protocol or to send us some suggestions, please email


Popular posts from this blog

UniChem 2.0

UniChem new beta interface and web services We are excited to announce that our UniChem beta site will become the default one on the 11th of May. The new system will allow us to better maintain UniChem and to bring new functionality in a more sustainable way. The current interface and web services will still be reachable for a period of time at . In addition to it, the most popular legacy REST endpoints will also remain implemented in the new web services: Some downtime is expected during the swap.  What's new? UniChem’s current API and web application is implemented with a framework version that’s not maintained and the cost of updating it surpasses the cost of rebuilding it. In order to improve stability, security, and support the implementation and fast delivery of new features, we have decided to revamp our user-facing systems using the latest version of widely used and maintained frameworks, i

A python client for accessing ChEMBL web services

Motivation The CheMBL Web Services provide simple reliable programmatic access to the data stored in ChEMBL database. RESTful API approaches are quite easy to master in most languages but still require writing a few lines of code. Additionally, it can be a challenging task to write a nontrivial application using REST without any examples. These factors were the motivation for us to write a small client library for accessing web services from Python. Why Python? We choose this language because Python has become extremely popular (and still growing in use) in scientific applications; there are several Open Source chemical toolkits available in this language, and so the wealth of ChEMBL resources and functionality of those toolkits can be easily combined. Moreover, Python is a very web-friendly language and we wanted to show how easy complex resource acquisition can be expressed in Python. Reinventing the wheel? There are already some libraries providing access to ChEMBL d

ChEMBL 30 released

  We are pleased to announce the release of ChEMBL 30. This version of the database, prepared on 22/02/2022 contains: 2,786,911 compound records 2,157,379 compounds (of which 2,136,187 have mol files) 19,286,751 activities 1,458,215 assays 14,855 targets 84,092 documents Data can be downloaded from the ChEMBL FTP site: Please see ChEMBL_30 release notes for full details of all changes in this release: New Deposited Datasets EUbOPEN Chemogenomic Library (src_id = 55, ChEMBL Document ID CHEMBL4689842):   The EUbOPEN consortium is an Innovative Medicines Initiative (IMI) funded project to enable and unlock biology in the open. The aims of the project are to assemble an open access chemogenomic library comprising about 5,000 well annotated compounds covering roughly 1,000 different proteins, to synthesize at least

LSH-based similarity search in MongoDB is faster than postgres cartridge.

TL;DR: In his excellent blog post , Matt Swain described the implementation of compound similarity searches in MongoDB . Unfortunately, Matt's approach had suboptimal ( polynomial ) time complexity with respect to decreasing similarity thresholds, which renders unsuitable for production environments. In this article, we improve on the method by enhancing it with Locality Sensitive Hashing algorithm, which significantly reduces query time and outperforms RDKit PostgreSQL cartridge . myChEMBL 21 - NoSQL edition    Given that NoSQL technologies applied to computational chemistry and cheminformatics are gaining traction and popularity, we decided to include a taster in future myChEMBL releases. Two especially appealing technologies are Neo4j and MongoDB . The former is a graph database and the latter is a BSON document storage. We would like to provide IPython notebook -based tutorials explaining how to use this software to deal with common cheminformatics p

Multi-task neural network on ChEMBL with PyTorch 1.0 and RDKit

  Update: KNIME protocol with the model available thanks to Greg Landrum. Update: New code to train the model and ONNX exported trained models available in github . The use and application of multi-task neural networks is growing rapidly in cheminformatics and drug discovery. Examples can be found in the following publications: - Deep Learning as an Opportunity in VirtualScreening - Massively Multitask Networks for Drug Discovery - Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set But what is a multi-task neural network? In short, it's a kind of neural network architecture that can optimise multiple classification/regression problems at the same time while taking advantage of their shared description. This blogpost gives a great overview of their architecture. All networks in references above implement the hard parameter sharing approach. So, having a set of activities relating targets and molecules we can tra