Promethean Proteins

Understanding life from the inside out

Every living cell has thousands of different proteins inside that keep it alive and well.

Proteins carry out the labour within our cells. Their shape determines their function, and those shapes are called folds.

The possible combinations of amino acid sequences are immense, each producing different folds in three-dimensional space. Most yield nothing functional, and malformed proteins (prions) can be actively harmful, spreading to other tissue and potentially to other organisms that consume them.

Proteins have a long sequence of amino acids which fold into these structures. All the information required for a fold is encoded by the amino acids and their sequence, which is in turn encoded by DNA. In theory, knowing only a DNA sequence should be enough to work out both the resulting protein and its structure.

Resolving a protein structure is painstaking work: a blend of human and machine labour, inferring properties from a snapshot captured in crystallised form.

Scientists have been researching the processes of protein folding for decades, working to map the three-dimensional shapes of the proteins that are responsible for a vast number of biological processes. Only a tiny portion of the known proteins have ever been accurately modelled.

Google’s DeepMind claims to have created a machine learning system, AlphaFold 2.0, that can resolve those problems in days, given only the primary structure (the sequence of amino acids in the polypeptide chain). This approximate solution arrived far sooner than most expected -- something of a Sputnik moment in structural biology.

If one can predict the structure of a protein given a certain sequence, biology becomes an open book instead of a confetti of letters.

This could lead to drugs that work more efficiently and with fewer side effects, cures for diseases including cancer, more nutritious plants, and plastic-deconstructing enzymes. Perhaps even lifespan extension.

Advances in cultured protein such as meat and bioprinting of organs may develop more quickly. There’s even potential within evolutionary research. We can rewind the tape of evolution by experimenting with amino acids one by one.

There are limitations. The reported precision is not perfect, though it is generally a decent approximation. Results still lean heavily on existing input data and known references; the system appears to predict that certain exotic proteins fold like common ones, and reportedly only around two-thirds of DeepMind’s predictions matched empirical truth.

Knowing the structure of a protein alone doesn’t tell you what ligands will bind it. (Drugs are ligands.) That’s likely to be a significant next challenge, as we already have structures available for most proteins of particular interest.

Despite reports to the contrary, protein folding has not been “solved”. But this is one of the hardest and most important problems in computer science, and AlphaFold appears to be a genuinely significant advance. Right now we have access to a tiny percentage of all known protein structures. Soon, we may have an educated guess about all of them.

The impact of derivatives of this research is likely to be profound across a wide number of sectors, far beyond mere drug discovery.