Skip to main content

Target Prediction Models Update



In case you have been too busy to notice, ChEMBL_21 has arrived with the usual additions, improvements and enhancements both on the data/annotation side, as well as on the interface/services. To complement this, we have also updated the target prediction models, which can be downloaded from our ftp here

The good news is that, besides the increase in terms of training data (compounds and targets), the new models were built using the latest stable versions of RDKit (2015.09.2) and scikit-learn (0.17). The latter was upgraded from the much older 0.14 version, which was causing incompatibility issues (see MultiLabelBinarizer) to several of you while trying to use the models.

We've also put together a quick Jupyter Notebook demo on how to get predictions from the models here: 

The new models will also be available on myChEMBL 21 along with a more detailed and elaborate Jupyter Notebook.


On a side note, am I allowed to be impressed by how easy it is nowadays to install Python and RDKit? 
It is literally just a matter of 6 commands and 5 minutes (on my Mac): 

curl -o miniconda.sh http://repo.continuum.io/miniconda/Miniconda3-3.8.3-MacOSX-x86_64.sh
bash miniconda.sh
conda create -n rd27 python=2.7
source activate rd27
conda install ipython ipython-notebook pillow pandas requests
conda install -c https://conda.anaconda.org/rdkit rdkit

To put things in perspective: the first time I tried to compile Python and RDKit from scratch was in 2010 (on a RedHat 5.6 machine, of course); it took me about 4 days :) 


George

Comments

Popular posts from this blog

PKIS data in ChEMBL

The Protein Kinase Inhibitor Set (PKIS) made available by GSK was recently mentioned on  In the Pipeline .  In collaboration with GSK, we are making the data being generated on these compounds available via  the ChEMBL database.  We are also creating a portal for the compound set, where the structures can be browsed and downloaded, direct links to the data are provided and useful information can be posted. A preliminary version is available  here : feedback would be appreciated. The data generated on the PKIS set and deposited in ChEMBL may be downloaded in CSV format here  (note that the Luciferase dataset described in the recent PLoS paper will be in the next release of ChEMBL). Alternatively, to view the data in the ChEMBL web interface, follow these steps: On the home page, enter 'GSK_PKIS' in the search box and click on the 'Assays' button... On the 'Please select...' menu on the right, choose 'Display Bioactivities'...

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

Release of ChEMBL 33

We are pleased to announce the release of ChEMBL 33! This fresh release comes with a few new data soures and also some new features: we added bioactivity data for understudied SLC targets from the RESOLUTE project and included a flag for Natural Products and for Chemical Probes. An annotation for the ACTION_TYPE of a measurement was included for approx. 270 K bioactivities. We also time-stamped every document in ChEMBL with their CREATION_DATE! Have fun playing around with ChEMBL 33 over the summer and please send feedback via chembl-help@ebi.ac.uk .   ChEMBL database version ChEMBL 33 release notes ___________________________________________ # This version of the database, prepared on 31/05/2023 contains:      2,399,743 compounds (of which 2,372,674 have mol files)      3,051,613 compound records (non-unique compounds)        20,334,684 activities         1,610,596 assays      15,398 targets      88,630 documents BioAssay Data Sources:    Number Assays:    Number

Chemistry and Nature

  As the Great Big Green Week (UK) draws to a close, so does EMBL-EBI’s own Sustainability week. The Wellcome Genome Campus held events in the areas of recycling, energy use, and biodiversity. The ChEMBL team was keen to get involved and we developed our own Nature Trail event highlighting some of the bioactive compounds from the flora and fauna found on-site, and elsewhere. Our favourite examples include the sensation of mint and chilli and the glorious smell of rain! The full Nature Trail can be made available for external Public Engagement events upon request . Databases, such as ChEMBL , are large stores of structured data, including genetic, biological, and chemistry data for life sciences research. Data on the natural world is often held by wildlife organisations; this can be used to research biodiversity and species decline. Various Citizen Science initiatives mean that everyone can get involved in submitting nature records. So why not join in with the Butterfly Conservation’s B

Accessing SureChEMBL data in bulk

It is the peak of the summer (at least in this hemisphere) and many of our readers/users will be on holiday, perhaps on an island enjoying the sea. Luckily, for the rest of us there is still the 'sea' of SureChEMBL data that awaits to be enjoyed and explored for hidden 'treasures' (let me know if I pushed this analogy too far). See here and  here for a reminder of SureChEMBL is and what it does.  This wealth of (big) data can be accessed via the SureChEMBL interface , where users can submit quite sophisticated and granular queries by combining: i) Lucene fields against full-text and bibliographic metadata and ii) advanced structure query features against the annotated compound corpus. Examples of such queries will be the topic of a future post. Once the search results are back, users can browse through and export the chemistry from the patent(s) of interest. In addition to this functionality, we've been receiving user requests for  local (behind the