In silico advantages for antibiotic development

Cresset Discovery Services has extensive experience working on established and novel anti-microbial targets. We understand the unique challenges of antibiotic development and bacterial resistance and can partner with your development team to reduce your development costs and decrease time to market for new antibiotics.

Bacteria are among the most prolific and successful organisms on the face of the earth. They are essential for life and for the most part we live in harmony. However, the wrong bacteria in the wrong place can lead to serious problems, which is when we turn to antibiotics for help.

The media is predicting an antibiotic resistance apocalypse, talking up superbugs, MRSA and the failure to develop new antibiotics. Behind these headlines there is a growing need for new and novel antibiotic drugs.

Developing new antibiotic drugs has always been difficult. Many of the easier targets have been successfully used, but resistant mechanisms are constantly evolving, limiting the efficacy of current antibiotics. Most of the larger pharmaceutical companies have moved out of the area, so the development of new antibiotics has fallen to small/medium biotechs, new start-up companies, academic researchers and public private partnerships, who are all trying to fill this crucial development void. Any help in identifying and prioritizing where chemical and biological effort should be focused will only to reduce development costs but also minimize the time required to develop these much need antibiotics.

The challenges for antibiotic drug design are comparable to those for traditional drug discovery, plus the additional obstacle of the established resistance mechanisms of bacteria:

  • The first and physically obstructive problem is getting antibiotics through the bacterial cell wall. This is especially true for gram negative bacteria which have an additional lipid membrane.
  • Once inside the cells there is an array of efflux pumps waiting to transport the compound back out of the cell before it can have an effect.
  • Bacteria have also developed enzymes specifically designed to stop antibiotics working. The best example of this is the b-lactamase proteins that decarboxylate b-lactam rings rendering penicillin and related antibiotics ineffective (figure 1).
  • The final trick up the bacterial sleeve is mutagenesis. Since bacteria grow rapidly there are multiple strains of the same bacteria in a single infection event. If just one of these strains is viable and infers resistance to the prescribed antibiotic then an antibiotic resistant infection is promoted through the whole infection.


Figure 1: The electrostatic protein surface of staphylococcus aureus beta-lactamase with a decarboxylated beta-lactamase from the 1GHP Crystal Structure1 highlighting a resistance mechanism for this class of antibiotics.

How can in silico methods help to address this growing need?

Through our extensive experience working on anti-microbial targets, both novel and currently established, we understand the challenges that this class of targets offer. For example, how simply designing Lipinski type molecules that fit into an active site without the consideration of the additional bacterial resistant mechanisms is unlikely to yield favorable results.

Computational techniques such as 3D electrostatic field comparisons (figure 2) and multi-parameter optimization are key in this field where cell penetration, efflux rates, frequency of mutation are factors. Potentially, other project-specific properties must also be considered in addition to normal drug properties.


Figure 2: Field comparison of a set of fluoroquinolones antibiotic compounds displaying the conserved electrostatic nature of this class of compounds which is key for DNA intercalation and complex stability.


These advanced techniques in addition to traditional methods provide customers with the rationalization underpinning the predictions. This means that Cresset Discovery Services adds value to your project long after our direct engagement has finished. In addition, Cresset’s exceptional visual analysis tools help to understand and share ideas.

We collaborate with your development team to leverage experience to identify the key proteins to investigate, identify the best hypothesis to test, and ultimately to choose the most promising compounds for synthesis, accelerating your antibacterial project towards successful completion.

Advance your antibiotic project

Contact us for a free confidential discussion to see how we can advance your antibiotic project.

Reference

1. Structures of the Acyl−Enzyme Complexes of the Staphylococcus aureus β-Lactamase Mutant Glu166Asp:Asn170Gln with Benzylpenicillin and Cephaloridine Celia C. H. Chen and Osnat Herzberg Biochemistry, 2001, 40 (8), pp 2351–2358

Enhancements in Flare V2 allow our scientists to spend more time on your design and analysis project

The release of Flare V2 brings quicker analysis of new design ideas and more automation of workflow processes. Andy Smith explains the advantages that Flare V2 brings to Cresset Discovery Services customers, including more time spent on high-value design and analysis work.

Why wait for the full release of Cresset software?

Before a new version of the software is released, we have already applied the new functionality to our customers’ projects once it has been fully validated by our development team. This means that in additional to the existing available packages within our software Cresset Discovery Services customers get to the added benefit of the upcoming functionality before it is generally released. We always send files which are compatible with customer’s software: if pre-release functionality is used to illuminate our analysis, we save the data in a format so that customers can still review the analysis. Flare V2 opens up exciting new functionality to Cresset’s software customers that invariably has already been extensively tried out by the Cresset Discovery Services team.

Electrostatic Complementarity™ – intuitive SAR and great pictures

The Flare development which has us most excited and is likely to benefit our customers the most is the ability to calculate the Electrostatic Complementarity (EC) of protein-ligand complexes, and project the values onto surfaces for both the proteins and ligands.

EC is a new method developed inhouse by Cresset scientists that distils complex protein ligand interactions into an obvious and informative pair of surfaces which are accessible and understandable to a broad-spectrum audience.

I recently showed the EC feature in Flare V2 to a group of senior medicinal chemists. They were very impressed with the intuitive representation. They commented that the visual surfaces were consistent with their understanding of the SAR of the system, and also added, ‘This will make a great series of pictures for the CEO to use.’ I took this as a huge endorsement of the EC calculations and visualization!

 


Figure 1: Electrostatic Complementarity surfaces for the Aurora A kinase 6hjk crystal structure.

Get a live analysis of good and bad design ideas

The data available from an EC calculation feels similar to that obtained from a Fragment Molecular Orbital (FMO) approach but at a small fraction of the computational expense and in a more visually intuitive form. Within Flare it is possible to process hundreds or thousands of ligands in a reasonable time frame, allowing for live EC analysis of ideas during meetings.

We worked with a team in a brain storming session and used the EC surfaces to quickly highlight the good and bad ideas and emphasize regions of the ligand that required additional attention.

At Cresset Discovery Services we are now using EC as an additional scoring and filtration method for docking and virtual screening ranking, and to further evaluate protein ligand interactions.

Automate day to day workflows with the Python API and RDKit integration

Python has become an increasingly popular and useful scripting language amongst the chemistry and cheminformatics communities, particularly when combined with the RDKit. Flare V2 features a Python API that provides access to all functionality available within the Flare graphical user interface from a Python script. Furthermore, the Flare V2 Python environment allows tight integration with the RDKit: native Cresset methods and RDKit methods can be used interchangeably on molecules loaded into a Flare project. The Python API and the RDKit integration also have an important automation focus feature rather than a purely scientific advancement, and the ability to use Python and the RDKit from within Flare allows fully customizable workflows to be designed and executed.

More time for interesting design and analysis

Including Python and the RDKit directly into Flare makes the process of using Python and the RDKit far smoother. Coupled with the support expertise available from Cresset and the vibrant Python RDKit community it makes this an exciting addition.

I’ve been using the Python RDKit integrated tools and workflow to automate standard protocols, which frees more of my time for the interesting design and analysis work for which Cresset Discovery Services are known. Processing and managing molecules in Flare V2 just got a whole lot more efficient, which means we can pass on this time saving to customers as extra time for analysis or design.

Free confidential discussion

If you’d like to discuss how Cresset Discovery Services can deploy these new tools to advance your project, please contact us for a free confidential discussion.

A measure of success: Being named on patents and references

The most common question asked of every contract research organization is, ‘What have you produced?’ or, in other words, ‘What evidence is there that you will provide value for our money?’

In industries that produce products to order it’s easy to calculate metrics for total output and time and cost per item. But in the scientific service industry the outcomes are less tangible: knowledge, ideas and computational models that usually form part of a wider discovery pathway.

One important endorsement is the number of returning customers and on that front Cresset Discovery Services has a very strong track record. Indeed, the majority of our customers come back to us for repeat business. An alternative metric is the number of patents and references that Cresset Discovery Services and its employees are named on jointly with customers.

The rightly rare nature of CRO patents

Most CROs, including Cresset Discovery Services, are employed to be anonymous. All of the scientific work and all associated IP is rightly the property of the customer, and there is no obligation whatsoever for a customer to name Cresset on any subsequent patents or scientific papers. It is, therefore, highly unusual for any contract research organization to be included on any patent.

Despite this, we’re proud to say that several customers over the years have chosen to name Cresset employees on their patents. This speaks volumes to the quality of the research and the relationship between Cresset Discovery Services and the customer. The diversity of the targets in these patents also demonstrates the broad spectrum of projects we tackle at Cresset Discovery Services.

Table: Patents naming Cresset or Cresset employees.

Company

Patent  number

Target area

Patent date

Monsanto Technology LLC

US20160130229A1

US20180070589A1

Acetyl-coa carboxylase modulators

2016

2018

Drexel University WO2015051230A1 Novel compositions useful for inhibiting hiv-1 infection and methods using same 2015
Redx WO2012063085A2 Drug derivatives 2012

 

A steady track record of references

Cresset Discovery Services has always had strong relationships with the academic community and there is a growing number of scientific papers in which our work is directly referenced. For example, the following references are based on HIV-1 work from Cresset Discovery Services.

  • Bioorganic Medicinal Chemistry Letters 2016, 26(3) 824 – 828
  • Bioorganic Medicinal Chemistry Letters 2016, 26(1) 228-234
  • Bioorganic Medicinal Chemistry Letters 2014, 24(23) 5439 – 5445

A description of work carried out as part of a project with Manchester Fungal Infection Group, Institute of Inflammation and Repair, University of Manchester, published in PNAS 2016 113 (45) 12809-12814 can be found on Wikipedia.

These references show not only the quality of the work from Cresset Discovery services but also the duration of collaborations and the lasting impact that insightful computational chemistry can have on a project.

We do not exclusively use Cresset software. Citations for these applications cover a very wide range of targets and industries, and demonstrate the varied projects that our expertise can help to progress.

At Cresset Discovery Services we are committed to propelling your project forward towards patents. We really don’t mind not been included on them, but we greatly appreciate the repeated business our customers provide.

Find out how our experts can help advance your project

Contact us for a free confidential discussion.

Introducing Andy Smith, Discovery Services Scientist

The last time I worked for Cresset I ended up being outsourced to a customer – but it was all part of the service! I’m delighted to be back at Cresset Discovery Services to work on a new set of customer projects. Here’s a brief overview of my computational chemistry journey so far.

An early sniff at GPCRs

I was introduced to computational chemistry when I stayed on at Warwick for a research MSc. The project was an SAR analysis of bell pepper odorants predicting the structural and electronic features that are important for olfactory recognition. My sponsor, Ernest Pollack, was getting very excited about proteins called GPCRs, which had just been identified as the receptors responsible for smell, and could possibly be the largest collection of proteins yet found. Meanwhile, I moved on to a PhD using quantum mechanics to investigate the Heck reaction.

Working closely with synthetic chemists

In 2001 I joined Proteus (later Protherics, then Tularik), who had a history with Factor Xa and already had a licensing agreement with Lilly for LY517717 established. After the takeover by Tularik the focus moved onto kinases which were difficult for our in-house software to model accurately. It was here that, with help from Mick Knaggs, I moved back into ligand-based design. I started homology modeling to augment the range of targets available for the in-house structure-based design methods and to expand the range of target we could work on using ligand-based design tools.

A narrow focus on structure-based design

I joined Sterix/Ipsen in 2004. Sterix had three areas of research: tubulin, hydroxysteroid dehydrogenase and dual aromatase-sulfatase inhibitors. Frustratingly, our work on these projects was limited to structure-based design, due to the fact that the group had made a large investment in the GOLD docking package from CCDC.

Back to the full range of computational chemistry methods

Upon moving to Peakdale Molecular in 2006 I worked on a range of diverse and interesting projects using a wide range of computational chemistry methods, including structure-based, ligand-based, ADMET predictions, homology modeling, molecular dynamics, quantum mechanics, cheminformatics, bioinformatics, library design, diversity and similarity analysis. The diversity of the projects meant I quickly learned to adapt to customer priorities, selecting the most appropriate method for the best possible modeling solution, whilst maintaining value for money.

It was here that I first used Cresset software. Torch (then FieldAlign) and Forge (then FieldTemplater) provided intuitive and visually informative methods for analyzing molecules which were understandable to our customers. These applications offered very useful methods of treating molecules which were different from other approaches I’d used before; both tools gave a more insightful understanding of ligand similarities and a deeper understanding of the features driving activity across a wide range of chemotypes and targets.

My first move to Cresset

Redx were working closely with Cresset, but were unsure how much support they would need, so in 2013 I took on the joint role of computational chemist at Redx and application scientist at Cresset.

Redx had fully functional medicinal chemistry projects in anti-infectives, oncology and crop protection, with large repositories of data. The established computational methods from Cresset Discovery Services showed the potential of computational chemistry and was the reason for Redx wanting to bring computational chemistry in-house. I provided the computational chemistry component and established a close working relationship with the medicinal chemistry teams.

Spark, Cresset’s scaffold hopping and R-group exploration application was integral to the development of a patent busting portfolio. As the company matured, Spark was used for backup series generation and to prevent the same patent busting approach to be applied to our own patents.

As an application scientist at Cresset, I carried out a very preliminary investigation of protein fields to determine whether we could transfer the Cresset methodology from ligands to proteins. It’s very gratifying to see the evolution of this early work brought to market in Flare, which provides fresh insights into structure-based design by integrating cutting edge approaches in an accessible and flexible user interface.

Outsourced to a customer

I joined Redx full time when it became clear that they needed more computational support. Working closely with Cresset software support, synthetic chemists were trained on Forge, a powerful ligand-focused workbench for SAR and design, and were encouraged to undertake general computational chemistry project related tasks. This freed up my time to provide more in-depth investigations to several key problems on projects.

A significant success was a compound that was sold to LOXO Oncology for $40 million. The computational work for this project was originally outsourced to Cresset Discovery Services. The compound was developed in 5 years and is a testament to the quality science undertaken at Redx.

In fact, the Redx CEO at the time was so impressed with the contribution of Cresset Discovery Services that he wrote:

“Cresset is a valuable partner in our drug discovery programs. Their deep knowledge of computational chemistry and its application to drug discovery is enabling us to progress multiple projects across a wide range of target classes very quickly and cost-effectively.

“Cresset has consistently delivered insightful support to our drug discovery efforts. In our experience, their knowledge, responsiveness and collaborative approach have set them apart from their competitors.”

 Dr Neil Murray, CEO, Redx Pharma, UK

Back to Cresset Discovery Services

I was delighted when I heard that Cresset Discovery Services was looking for a computational chemist to join the team. I’m very pleased to be back to working on a wide range of challenges on varied customer projects and putting my skills to use in the real world of modeling.

Contact us for a free confidential discussion to see how Cresset Discovery Services can work alongside your chemists to solve problems, provide fresh ideas, remove roadblocks and add direction and insight to you project. If you’re based near Alderley Park and would like to meet for a confidential chat, get in touch as I’m based at the BioHub part-time.

Artificial Intelligence and machine learning: Where’s the intelligence?

“Of course we have Artificial Intelligence (AI), who doesn’t?” This was a throw-away line, during the closing remarks at a recent conference about future directions in medicinal chemistry. Currently it seems that every company inside drug discovery has an AI project or collaboration. But what is AI in drug discovery, what is it being used for, what are the challenges and what are the opportunities?

The distinction between AI and machine learning

Whilst the phrases ‘Artificial Intelligence’ (AI) and ‘Machine Learning’ (ML) are often used interchangeably, they are subtly different. A true AI method would have the ability to make decisions and propose new ideas from outside its knowledge base, whereas machine learning methods can only use the information from within their knowledge base. In fact, many AI systems are built on a foundation of one or more ML techniques – particularly neural networks. If you were to give the two methods human characteristics, you could say that AI is imaginative and might suggest a completely new series, whereas machine learning is intuitive – it could identify improvements within a compound series, but it would be limited to the transformations present within the training set.

Given that presently, most applications referred to as using ‘AI methods’ in drug discovery utilize modern machine learning methods, we will also utilize the shorthand of talking about “AI” to mean machine learning methods such as ‘deep learning’ which is a method of training very complex neural networks to find patterns in large volumes of complex data (so called ‘big data’). Most of these applications in drug discovery could equally utilize other machine learning methods, such as regular neural networks, support vector machines or random forest regression models as data sets are generally not that complex and not that large. However, there are areas where AI methods have real traction, for example for those working on genomics data, the separation in performance between traditional machine learning and modern AI methods starts to become tangible due to the large size and complex inter-relationships of the data sets involved.

Mining big data in drug discovery

The biggest promise of AI and machine learning for drug discovery is the capability of mining big data. AI methods such as deep learning have been deployed effectively in other industries, most notably in social media interactions.

Most established pharmaceutical companies have large repositories of data stored in large corporate databases built up over many years. This data tends to be noisy simply because of the volume, number of sources and the long time frame during which the data was collected. AI methods are tolerant and accepting of this type of data, providing the data sets are large enough, which makes them eminently suitable for extracting and analysing data from corporate databases. The ability to leverage this corporate knowledge to current targets has the potential to provide tremendous benefit, both in direction and speed of development, which translates to lower development costs.

Over recent years, a number of leading companies have formed strategic partnerships to investigate whether these methods can be transferred to drug discovery (Table 1). AI and machine learning methods are being deployed in a diverse range of areas, ranging from identifying compounds from existing libraries, target identification, target validation to new target discovery. There are also genomics companies who are looking to provide custom drug therapies based on an individual’s bio markers.

However, as with any emerging technology, there are very few case studies where these methods have successfully been applied, so at present these methods remain exciting, but generally unproven.

Table 1: Non-exhaustive list of companies who have formed strategic partnerships involving use of AI.

Company Partner Date Started Target Area
Roche1 GNS Healthcare 2018 Drug candidates
Pfizer2 IBM 2016 Drug candidates
Sanofi3 Berg 2017 Vaccines efficiency
Merck4 Numerate 2012 Drug candidates
Amgen5 GNS Healthcare 2018 Drug candidates
AstraZeneca6 Berg 2017 Drug candidates
Evotec6 Exscientia 2016 Drug candidates
Genentech8 GNS Healthcare 2017 Target validation
Takeda9 Numerate 2017 Target validation
GSK

Exscientia10

Insilico11

Cloud Pharmaceuticals12

2017

2017

2018

10 disease targets

Biological targets

Multiple targets

 

Prediction and understanding for smaller data sets

Big data applications are not the sole domain of AI and machine learning; smaller data sets can also be used to generate focused models which are suitable only for a single chemotype. These models can be used to progress a series toward the desired goal, usually removal of some unwanted toxicology, and there are numerous examples where this has been applied – both successfully and unsuccessfully.

Most computational chemists have, at some point, applied machine learning methods to a particularly intractable problem. However, it tends to be a second-tier resource, not because these methods are particularly difficult to employ, but because extracting understanding from these methods is often difficult. Whilst the predictions these models generate tend to be highly reliable, understanding the factors governing the predictability can be difficult or impossible depending on the properties used. If the properties used are chemical drug relevant properties (e.g., logP, PSA, pKa, etc.) then the underlying factors controlling the property under investigation maybe illuminated, but the predictability of the model tends to be lower. If, as often happens, all possible calculated molecular properties are used, then the model predictability tends to increase but the underlying factors controlling the models predictive mechanism can remain a mystery and the user gains no practical insight into the problem, just a method of prediction.

Therefore, there could be a lot of potential in analysing the AI systems currently in operation to confirm the validity of their predictions. It may be possible to use these methods in a way that makes it possible to glean more information about the interplay of factors that govern the predictability of the models, making them more useful to computational chemists.

AI and machine learning at Cresset Discovery Services

Cresset Discovery Services have successfully used machine learning methods when the data is amenable. Of course, producing a ‘black box’ predictive model is not generally enough for us or our customers. Instead, we look for a deeper understanding so a customer can make informed decisions in the context of the rationale behind the predictions made.

AI and machine learning methods are exciting new tools in a growing tool box of approaches which we can apply to bring value to customer projects. The real intelligence lies with the operator in being able to select the appropriate tool for the job. Another comment from the conference mentioned at the start of this blog post: “will AI techniques replace chemists in drug discovery? Probably not for the foreseeable future, but it is clear that chemists who use AI will replace chemists who don’t in the very near future.” Contact us for a free confidential discussion and to discover how we can apply intelligence to your drug discovery challenges.

1) https://www.roche.com/partnering/partnering-in-a-digital-era.htm
2) https://www.pfizer.com/news/press-release/press-release-detail/ibm_and_pfizer_to_accelerate_immuno_oncology_research_with_watson_for_drug_discovery
3) https://www.sanofi.com/en/science-and-innovation/artificial-intelligence-in-healthcare-created-by-humans-to-do-no-harm/
4) http://www.numerate.com/numerate-forms-drug-discovery-collaboration-merck-utilize-numerates-silico-drug-design-technology/
5) https://www.gnshealthcare.com/news/ai-collaboration-gns-amgen-alliance-colorectal-cancer/
6) https://www.astrazeneca.com/content/dam/az/PDF/2018/Pages%2046-49.pdf
7) https://www.evotec.com/en/invest/news–announcements/press-releases/p/evotec-invests-in-exscientia-to-advance-ai-driven-drug-discovery-5502
8) https://www.gene.com/stories/personalizing-the-future-of-healthcare
9) http://www.numerate.com/numerate-takeda-enter-agreement-generate-novel-clinical-candidates-using-ai-driven-drug-discovery/
10) https://www.exscientia.co.uk/news/2017/7/2/exscientia-collaboration-gsk
11) https://www.eurekalert.org/pub_releases/2017-08/imi-iec081417.php
12) https://www.businesswire.com/news/home/20180530006184/en/Cloud-Pharmaceuticals-forms-Drug-Design-Collaboration-GSK