Skip to main content

ChEMBL_22 Data and Web Services Update

ChEMBL_22_1 data update:

We would like to inform users that an update to ChEMBL_22 has been released. 

The new version, ChEMBL_22_1, corrects an issue with the targets assigned to some BindingDB assays in ChEMBL (src_id = 37). If you are using the BindingDB data from ChEMBL, we recommend you download this update. This update also incorporates the mol file/canonical smiles correction announced previously.

Updates have been made to BindingDB data in the ASSAYS, ACTIVITIES, CHEMBL_ID_LOOKUP, LIGAND_EFF and PREDICTED_BINDING_DOMAINS tables. Corrections have also been made to molfiles and canonical_smiles in the COMPOUND_STRUCTURES table. No changes have been made to other data sets or to other drug/compound/target tables in ChEMBL_22.

The new release files can be downloaded from:

A new version of the ChEMBL RDF is also available from:

Improvements to Web Services:

1. Support for SDF format.

The "molecule" endpoint now supports the SDF format. For example, if you access this URL: you will get information about 20 first compounds in JSON format. This URL will return an SDF file of the same molecule page. Please note, that there will be only 18 compounds in SDF output because two compounds from (CHEMBL6961 and CHEMBL6963) have no structure defined. You can easily join the information about the compound provided via JSON, XML or YML format with the structure by inspecting the

> <chembl_id>
sdf property.

Obviously the same format works for a single compound so this URL: will provide an information about Aspirin while this URL (or will return its structure.

The same can be applied to filters, for example this URL returns information about compounds with molecular weight <= 300 AND pref_name ending with nib. The in turn will return corresponding structures.

We also released a new version of Python client (version 0.8.50 available from PyPI and GitHub) that is aware about molfile support. Example code:

from chembl_webresource_client.new_client import new_client
molecules = new_client.molecule
molstring =  molecules.all()[0]

Iterating through all molecules you can get an sdf files with all the structures from chembl, pagination is handled by the client.

2. Structural alerts.

This new API endpoint provides information about compound's structural alerts. For example, on order to get structural alerts for CHEMBL266429, you can use this URL:

Then you can render each of the alerts to image, for example

As you can see, the corresponding fragment is highlighted.You can add all parameters that are present in the standard "image" endpoint so format (png or svg), engine (rdkit or indigo), ignoreCoords to recompute coordinates from scratch and dimensions to change image size.

3. Document terms (keywords)

We used pytextrank package to extract most relevant terms from all document abstracts stored in ChEMBL, along with their significance score against each document (the code we used to perform the extraction is available).

For example, in order to get all the relevant terms for CHEMBL1124199 document, ordered by the significance score descending, you can use this URL:

By parsing the results you can extract (term, score) pairs and multiply the score to get this list:

590 Inverse agonist activity
548 Thien-2-yl analogues
493 Pentylenetetrazole-induced convulsions
490 5'-alkyl group
477 Agonist activity
472 Inverse agonist
449 5-methylthien-3-yl derivative
427 Potent compounds
417 Vivo activity
403 Magnitude higher affinity

you can now use the HTML5 based word cloud and feed the list into this tool providing the following configuration:

  gridSize: Math.round(16 * $('#canvas').width() / 1024),
  drawOutOfBound: true,
  weightFactor: function (size) {
    return Math.pow(size/100.0, 2.3) * $('#canvas').width() / 1024;
  fontFamily: 'Times, serif',
  hover: function(){},
  color: function (word, weight) {
    return (weight > 500) ? '#f02222' : '#c09292';
  rotateRatio: 0.0,
  backgroundColor: '#ffe0e0'

and you will get this wordcloud:

We are planning to add this component to the new document report card.

It may be also interesting to ask about all the documents for a given keyword, for example in order to get all the documents for the "inverse agonist activity" term ordered by score descending, the following URL can be used:

4. Document similarity

As the last endpoint we added "document_similarity". For example to get all documents similar to CHEMBL1122254 document this URL can be used:

The endpoint uses the same protocol we use to generate the "Related Documents" section in the Document Report Card (

The current protocol is fairly simple (measuring overlap in compounds and targets between the two documents) and not very granular (it can be difficult to choose N most relevant documents from the 50 documents that the protocol returns). However, we are currently investigating alternative methods such as topic modelling.

5. Other improvements

There are some minor improvements as well:
 - Molecule endpoint includes three more properties as described in GitHub issue #106.
 - Target endpoint can be filtered by synonym name, in other words you can get a list of targets for a given gene name, for example:
or using a shortcut:
 - Target relation endpoint can be accessed by primary ID as described in GitHub issue #114.
 - parent_chembl_id filter working correctly for the molecule_form endpoint (for example ) as described in GitHub issue #113

The ChEMBL Team


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

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

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

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