Transport proteins are responsible for the continuous movement of substrates into and out of a biological cell. However, it is difficult to determine which substrates a specific protein can transport. Bioinformaticians at Heinrich Heine University Düsseldorf (HHU) have developed a model, called SPOT, that can predict this with a high degree of accuracy using artificial intelligence (AI). They now present their method, which can be used with arbitrary transport proteins, in the scientific journal. More biology.
Biological cell substrates must be continually transported in and out across the cell membrane to ensure the survival of the cells and allow them to perform their function. However, not all substrates moving through the body should be allowed to enter the cells. And some of these transport processes must be controllable so that they only occur at a particular time or under specific conditions to trigger a cellular function.
The role of these active and specialized transport channels is assumed by the so-called transport proteins, or simply transporters, which are largely integrated into cell membranes. A carrier protein is made up of a large number of individual amino acids, which together form a complex three-dimensional structure.
Each transporter is designed for a specific molecule (the so-called substrate) or a small group of substrates. But which one exactly? Researchers are constantly looking for matching transporter-substrate pairs.
Professor Dr. Martin Lercher from the Computational Cell Biology research group and corresponding author of a study now published in PLOS Biology: “Experimentally determining which substrates match which transporters is difficult. Even determining the three-dimensional structure of a transporter – – from which it is possible to identify the substrates – is a challenge, since proteins become unstable as soon as they are isolated from the cell membrane.
“We have chosen a different approach, based on AI,” says Dr. Alexander Kroll, lead author of the study and a postdoc in Professor Lercher’s research group. “Our method, called SPOT, used more than 8,500 transporter-substrate pairs, which have already been experimentally validated, as a training data set for a deep learning model.”
So that the carrier proteins and substrate molecules can be processed by a computer, the Düsseldorf bioinformaticians first convert the protein sequences and substrate molecules into numerical vectors that can be processed by AI models. Once the learning process is complete, vectors for a new transporter and those for potentially suitable substrates can be introduced into the AI system. The model then predicts the probability that certain substrates match the transporter.
Kroll: “We have validated our trained model using an independent test data set where we also knew the transporter-substrate pairs. SPOT predicts with greater than 92% accuracy whether an arbitrary molecule is a substrate for a specific transporter.”
Therefore, SPOT suggests very promising substrate candidates. “This allows us to greatly limit the scope of the search for experimenters, which in turn speeds up the process of identifying in the laboratory which substrate is exactly compatible with a transporter,” says Professor Lercher, explaining the relationship between bioinformatics prediction and experimental verification.
Kroll adds: “And this applies to any arbitrary transport protein, not just limited classes of similar proteins, as with other approaches to date.”
There are several potential areas of application for the model. Lercher: “In biotechnology, metabolic pathways can be modified to allow the manufacture of specific products such as biofuels. Or drugs can be tailored to transporters to facilitate their entry into precisely those cells on which they are intended to have an effect.”