AI Case Study
Monsanto plans to speed up crop protection product development using Atomwise's convolutional neural network technology for molecule interaction discovery
Monsanto has partnered with a biochemistry research start-up, Atomwise, to make development of crop-protecting products more efficient. Atomwise uses convolutional neural networks to discover and predict molecule interactions, avoiding traditional testing processes.
Forbes reports that "Monsanto and Atomwise, a startup utilizing AI to develop novel therapeutics for hard to treat diseases, formed a unique research collaboration to increase the speed and probability of discovering new crop protection products. This collaboration is leveraging AI based pattern recognition to reduce the amount of trial-and-error based laboratory testing in early stage chemical discovery." According to World of Chemicals, Atomwise's "AtomNet technology aims to streamline the initial phase of discovery by analysing how different molecules interact with one another. AtomNet accelerates this process using deep learning to predict which molecules could have a positive effect in controlling harmful diseases or insects. The software teaches itself about molecular interactions by identifying patterns, similar to how artificial intelligence learns to recognize images.
R And D
Core Research And Development
From Forbes: "While the on-farm AgTech applications of AI are certainly important, the application of AI to the discovery and development of new, more efficient agricultural inputs is equally important. However, until very recently, AI systems have not been tuned to analyze data about chemical and biological systems. Thus, there are tremendous untapped opportunities for leveraging AI in plant breeding, biotechnology, agrochemical discovery, and supply chains."
Planned; results not yet available
From Atomwise's website: "Convolutional networks are known to achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. This idea was applied to chemistry to predict the bioactivity of small molecules for drug discovery applications. This research and subsequent developments led to AtomNet. AtomNet showed that the convolutional concepts of feature locality and hierarchical composition could be applied to the modeling of bioactivity and chemical interactions. Specifically, where an image is represented as a 2-dimensional grid of pixels containing channels for red, green, and blue colors, AtomNet represents a protein-ligand pair as a set of 3-dimensional volumetric pixels containing channels for carbon, oxygen, nitrogen, etc atom types. In this way, AtomNet autonomously learns the features governing molecular binding, and avoids the manual process of tweaking and over-parameterizing binding features that typified traditional computational methods. AtomNet’s application of local convolutional filters to structural target information was able to successfully predict new active molecules for targets with no previously known modulators. Biochemical interactions are primarily local, and can be modelled by similarly-constrained machine learning architectures."
The Atomwise AtomNet uses "millions of experimental affinity measurements and thousands of protein structures" according to its website.