Skip to main content

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

 Image result for one man band

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 train a single neural network as a binary multi-label classifier that will output the probability of activity/inactivity for each of the targets (tasks) for a given query molecule.

PyTorch is one of the most popular open source AI libraries at present. It's getting a lot of traction in research environments, it's deeply integrated with the NumPy ecosystem and it also implements a dynamic graph approach making it easier to debug.

We have some interesting references, we have data in ChEMBL, we have PyTorch and RDKit... what are we waiting for?

First of all we'll need to extract the data from ChEMBL and format it for our purpose. The following notebook explains step by step how to do it. The output will be a H5 file that you can also download from here in case you want go directly to the network training phase.

Notebook to extract the data

Nice! We have the data, let's go then through the main notebook and train a model!

Notebook to train the model

This was a simple example. We hope you enjoyed it and will be inspired to experiment with deeper architectures, skipping connections, different learning rate strategies, more epochs, early stopping... and so on!

Notebooks also available in GitHub


Popular posts from this blog

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 wishes you a Merry Christmas: A look back and a glimpse into 2023!

 The ChEMBL Team heads off soon on their Christmas holidays! Before we leave, we would like to remember  some highlights of 2022 and share some outlook for the next year! 2022 was an extraordinary year for the UK and also for the ChEMBL Team! It was a year of celebrations, farewells, and new beginnings....   The ChEMBL team underwent major personnel changes in 2022 , with Anna and Patricia leaving the team, and Barbara, Eloy and Fiona taking on new roles within the ChEMBL leadership team. 2022 was a year of extremes as well. The UK recorded >40C in July and -6C in the past few days in December.  During the hot summer months the ChEMBL Team went on a punting excursion on the River Cam. In 2022, the ChEMBL Team delivered lots of training and outreach activities including a "Wetland Nature Trail" on Campus organised by Emma and James. We also participated in the "School of Chemoinformatics in Latin America", where the ChEMBL web-interface and API were explained

This Python InChI Key resolver will blow your mind

This scientific clickbait title introduces our promised blog post about the integration of UniChem into our ChEMBL python client. UniChem is a very important resource, as it contains information about 134 million (and counting) unique compound structures and cross references between various chemistry resources. Since UniChem is developed in-house and provides its own web services , we thought it would make sense to integrate it with our python client library . Before we present a systematic translation between raw HTTP calls described in the UniChem API documentation and client calls, let us provide some preliminary information: In order to install the client, you should use pip : pip install -U chembl_webresource_client Once you have it installed, you can import the unichem module: from chembl_webresource_client.unichem import unichem_client as unichem OK, so how to resolve an InChI Key to InChI string? It's very simple: Of course in order to reso

ChEMBL 26 Released

We are pleased to announce the release of ChEMBL_26 This version of the database, prepared on 10/01/2020 contains: 2,425,876 compound records 1,950,765 compounds (of which 1,940,733 have mol files) 15,996,368 activities 1,221,311 assays 13,377 targets 76,076 documents You can query the ChEMBL 26 data online via the ChEMBL Interface and you can also download the data from the ChEMBL FTP site . Please see ChEMBL_26 release notes for full details of all changes in this release. Changes since the last release: * Deposited Data Sets: CO-ADD antimicrobial screening data: Two new data sets have been included from the Community for Open Access Drug Discovery (CO-ADD). These data sets are screening of the NIH NCI Natural Product Set III in the CO-ADD assays (src_id = 40, Document ChEMBL_ID = CHEMBL4296183, DOI = 10.6019/CHEMBL4296183) and screening of the NIH NCI Diversity Set V in the CO-ADD assays (src_id = 40, Document ChEMBL_ID = CHEMBL4296182, DOI = 10.601