Blackgrass is one of the most economically damaging weeds in northern Europe and is exceptionally difficult for farmers to control.
In this short video, Dr Virginia Corless and Alice Hannam take you behind the scenes at our Yorkshire glasshouse research facility for a sneak peek at one of our most exciting novel mode of action discoveries yet: a new post-emergent herbicide targeting blackgrass in cereal crops.
Today weed resistance affects more than 250 weed species infesting nearly 100 crops. As a result, weed management costs have doubled for many farmers, and we’re overusing a dwindling number of herbicides at ever higher rates. The root of the problem is the difficulty in finding new molecules which can selectively control weed plants via novel mode of actions (MoAs). We therefore need to discover new improved herbicides with novel MoAs using innovative tools and techniques so we can keep our crops safe.
A good herbicide molecule should have the following characteristics:
Like drug discovery, finding a good herbicide molecule with a novel MoAs, is often compared to finding a needle in a haystack and is an enormous complex challenge. In this analogy, the haystack consists of order of 1060 to 10100 synthetically feasible molecules [1]. For context there are 1022 to 1024 stars in the observable universe. This is a gigantic chemical space in which to search and find a novel chemical compound that satisfies the plethora of desirable characteristics listed above. In addition, currently only a fraction of this chemical space has been synthesized, let alone tested on weed plants in an efficient data informative way. State of the art Artificial Intelligence (AI) algorithms offers a possible solution, by designing and assessing huge numbers of molecules virtually, thereby reducing the chemical search space into something more manageable for the search of the needle.
Artificial neural network (ANN) has been successfully applied in the process of searching for novel molecules in drug discovery. In fact, a type of ANN known as Recurrent Neural Network (RNN) have been used successfully for tasks such as natural language processing, music and painting generation. Generative Pre-trained Transformer (GPT) which is the adaptation of RNN for natural language processing is employed to understand and generate human-like text based on the input it receives. One such example is the well known ChatGPT application.
Similarly, there are multiple examples where this kind of adaptation has been applied to enable successful de novo design of novel drug molecules. However, it should be noted success is dependent on the availability of high-quality data.
Like ChatGPT which has been trained on huge and diverse dataset of text such as books, articles, websites etc, a model for herbicide can be trained to generate novel herbicide using public and inhouse chemical data. Ideally this data would be the chemical structures of molecules which has been tested on known species of weed plants in the lab and glass house and shown to control/inhibit their growth. Given the complexity involved in such task, Transfer learning (TL) strategy is used commonly. Transfer learning is a technique in machine learning (ML) in which knowledge gained from one task is utilized to enhance performance on a related task. For example, we can first train the model on large herbicide-like or drug-like molecule structure to generate novel and valid chemical molecules to get an initial model. This model (also known as Prior) can then further fine-tune using a small but focused set of chemical compounds which has shown to inhibit weed plants. Effectively, this gives us a model which has learned to generate not only valid but novel molecules with potential herbicidal activity. The strategy is depicted in Figure 2 as published here [2] where Prior (the initial model) is trained on ChEMBL data (a manually curated chemical database of bioactive molecules) [3] followed by two stages of fine tuning, first with molecules shown to control weeds in our glass house experiments and then a finally on a focused ‘project’ specific dataset. Since the training of the model is done in stages, this is also known as ‘staged learning’.
At Moa we have implemented a staged learning strategy to train Generative AI models using our unique high quality data sets. These models are routinely used to design novel herbicide molecules belonging to specific chemical classes using data associated with their respective projects. By integrating generative AI alongside traditional design methods not only are we able to expand our search space but also generate new molecules with desirable herbicidal properties within significantly reduced timeframes. Preliminary results show that the model can design compounds which inhibits growth of weed plants in our early lab tests with a hit rate of around 24%.
Given the complexity and low success rate of discovering new herbicides, along with the rising costs of managing resistant weed species, we must employ every possible technique to maximize our chances of success. By adopting Generative AI techniques, we can increase the chance of finding new and better herbicide molecules. Ultimately reducing the burden on the farming community and ensuring future food safety.
Dr Shuji Hachisu, Moa Technology’s Chief Technology Officer, has written a paper on herbicide discovery, just published in a leading peer-reviewed scientific journal.
‘Strategies for discovering resistance-breaking, safe and sustainable commercial herbicides with novel modes of action and chemotypes’ is published in Pest Management Science. [LINK]
In the face of mounting pressures from resistant weeds, safe and effective new herbicides are an imperative for global food security.
Fundamentally, there are two strategies: an in vivo glasshouse-based approach focused on spraying compounds on weeds or in vitro laboratory screens studying inhibitory activity on selected target enzymes. From both starting points, promising active compounds are then taken through chemical optimization processes and robust herbicidal activity is confirmed in lead candidates. Safety to humans and the environment must be demonstrated before commercialisation.
The in vivo strategy has been successful in the past but needs large amounts of chemical samples for screening and is time and resource demanding. An in vitro strategy can vastly increase the number of compounds screened, but the track record of finding new herbicides good enough to be commercialised has been disappointing.
Moa Technology’s own approach is to bring together the best of both strategies using Moa’s GALAXY high throughput in vivo screening platform. In addition, GALAXY highlights novel modes of action and gives early information on sustainability profiles of hits. Moa SELECT then not only validates the mode of action and efficacy but also points to novel chemistry.
Moa has been highlighted as a company with an innovative approach to the discovery process for new crop protection chemistry.
An article in Chemistry and Engineering News contrasts screening strategies of the major players in crop protection R&D with Moa’s platforms, GALAXY, Target and Select.
High throughput in vitro screening, which became de rigueur in the 1990s in the search for new active ingredients did not result in the anticipated new wave of exciting chemistry.
Instead, attention has moved to a variety of other ways to protect crops, including biopesticides, precision application, robotics and digital technologies. Yet, resistant weeds, pests and diseases dominate the concerns of the industry. This has been the result of failing to find new modes of action, especially for herbicides.
Moa’s own approach is an in vivo one using whole plants. In essence, this has the same advantages of traditional screening for herbicides that resulted in blockbuster active ingredients such as glyphosate, sulfonylureas and many others. However, Moa’s platforms are also high throughput, with a focus on finding new modes of action, which have proved elusive for decades.
Read the article here.
