Development and experimental validation of a deep-learning based pipeline for user-centric protein design.

Proteins are the molecules that provide most of the complex functionality in all living things. They are made of 20 different building-block types called amino acids, which are combined in different sequences to make long chains. The varying shapes and chemistries of the amino acids cause the chains to fold into a distinct 3D structure. It is this structure that enables proteins to perform the different roles they have in nature, whether it's digesting your food, moving you around or simply keeping the top of your head warm.

Even though life emerged over 4 billion years ago, only a small number of possible protein structures have been explored by evolution due to their inherent complexity. As protein structure is directly related to function, this means that there is a huge pool of unexplored proteins with functions that could be applied to solve problems in medicine, biotechnology, energy and agriculture. If we can design new proteins from scratch, we can address some of these problems with the new proteins that we create.

As mentioned previously, proteins are complex, and so it is difficult to design new proteins, but to make it easier we can write programs that can create and test huge numbers of designs in computer simulations. This improves the chance of designing a sequence of amino acids that will adopt our desired structure when we create it in the laboratory. However, even with state-of-the-art methods for designing proteins on a computer, only a small number of sequences adopt the structures we intend them to, making protein design costly and unreliable.

I intend to create a new method for designing proteins that uses a type of artificial intelligence called a deep-neural network (see http://playground.tensorflow.org for an interactive example). This technique will be used to learn the complex rules for generating stable proteins that are hidden inside the amino-acid sequences of protein structures we have already observed. Once the rules have been learned, we can use them to create new sequences of amino acids that are good candidates for adopting the structure we require. This method will form part of an automated pipeline that will create and test protein structures in computer simulations, before recommending the best designs for our intended application. This will make the process of protein design much more reliable.

To get an understanding of how effective this method is, I will test it by creating hundreds of the protein designs recommended by the pipeline in the laboratory, using robotics to accelerate this process. Once tested, I plan to showcase the method by designing new proteins that can perform chemical reactions that are useful industrially. This will make performing these chemical reactions much cheaper and more environmentally friendly, paving the way for the design of many more proteins with useful functions that address the challenges that the human race currently faces.

RESEARCH COMMERCIALISATION

The user-centric protein design pipeline and designed proteins described in this proposal have clear routes to commercialisation. There are three main approaches that could be taken:

(1) The software produced could be sold through licensing to industrial partners. The software is likely to be of significant interest to the biotechnology/pharmaceutical industry, as it will allow for the robust design of proteins to strict design specifications in order to perform required functions.
(2) The proteins that are designed could be sold as products. Some of the proteins designed in this proposal have clear applications in industrial biotechnology. The amino-acid sequences for these and related designs could be patented if appropriate.
(3) Protein design as a service. The full user-centric protein design pipeline has been designed to produce proteins that fit a strict specification for a targeted application. As a result, it could form the core enabling technology behind a company that performs protein design as a service for the biotechnology industry.

All research-commercialisation activities will be performed with support from the commercialisation office at University of Edinburgh, Edinburgh Innovations, who have a strong track record in tech transfer from academia to industry.

PUBLIC ENGAGEMENT

Protein design is an excellent vehicle for demonstrating interdisciplinary research. It covers many STEM areas and has a creative aspect, allowing it to reach a broad audience. I have previously developed a workshop aimed at secondary school pupils in years 9 and 10, which was run both in schools and at the university. The sessions were very well received, with excellent feedback from both teachers and students.

I will continue to develop this workshop, refining the activities as well as creating versions to fit the requirements of different teachers and schools, given their curriculum and available time. Furthermore, I will design a new workshop focused on protein structure aimed at primary school pupils, which will be taken to schools and science festivals. These activities will be organised in cooperation with the Beltane Network.