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 chembl-help@ebi.ac.uk

Comments

New SureChEMBL announcement

(Generated with DALL-E 3 ∙ 30 October 2023 at 1:48 pm) We have some very exciting news to report: the new SureChEMBL is now available! Hooray! What is SureChEMBL, you may ask. Good question! In our portfolio of chemical biology services, alongside our established database of bioactivity data for drug-like molecules ChEMBL , our dictionary of annotated small molecule entities ChEBI , and our compound cross-referencing system UniChem , we also deliver a database of annotated patents! Almost 10 years ago , EMBL-EBI acquired the SureChem system of chemically annotated patents and made this freely accessible in the public domain as SureChEMBL. Since then, our team has continued to maintain and deliver SureChEMBL. However, this has become increasingly challenging due to the complexities of the underlying codebase. We were awarded a Wellcome Trust grant in 2021 to completely overhaul SureChEMBL, with a new UI, backend infrastructure, and new f

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

New Drug Approvals - Pt. XVII - Telavancin (Vibativ)

The latest new drug approval, on 11th September 2009 was Telavancin - which was approved for the treatment of adults with complicated skin and skin structure infections (cSSSI) caused by susceptible Gram-positive bacteria , including Staphylococcus aureus , both methicillin-resistant (MRSA) and methicillin-susceptible (MSSA) strains. Telavancin is also active against Streptococcus pyogenes , Streptococcus agalactiae , Streptococcus anginosus group (includes S. anginosus, S. intermedius and S. constellatus ) and Enterococcus faecalis (vancomycin susceptible isolates only). Telavancin is a semisynthetic derivative of Vancomycin. Vancomycin itself is a natural product drug, isolated originally from soil samples in Borneo, and is produced by controlled fermentation of Amycolatopsis orientalis - a member of the Actinobacteria . Telavancin has a dual mechanism of action, firstly it inhibits bacterial cell wall synthesis by interfering with the polymerization and cross-linking of peptid

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

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

The ChEMBL-og

Search This Blog