This capability could unlock new possibilities in medicine
Artificial intelligence has altered the practise of science by enabling researchers to examine the vast volumes of data generated by current scientific instruments. Using deep learning, it can learn from the data itself and can locate a needle in a million haystacks of information. AI is advancing the development of gene searching, medicine, medication design, and chemical compound synthesis.
To extract information from fresh data, deep learning employs algorithms, often neural networks trained on massive volumes of data. With its step-by-step instructions, it is considerably different from traditional computing. It instead learns from data. Deep learning is far less transparent than conventional computer programming, leaving vital concerns unanswered: what has the system learnt and what does it know?
As a chemistry professor, I enjoy creating exams with at least one challenging question that challenges students’ ability to connect and synthesise diverse concepts and ideas. We have designed such a question for the poster child of AI proponents, AlphaFold, which has solved the challenge of protein folding.
Proteins are found in every living creature. They give structure to the cells, catalyse chemical processes, transport tiny molecules, digest food, and perform many other functions. They consist of lengthy chains of amino acids strung together like beads on a thread. For a protein to perform its function within the cell, however, it must fold into a complicated three-dimensional structure, a process known as protein folding. Proteins that fold improperly can cause illness.
Christiaan Anfinsen hypothesised in his 1972 Nobel acceptance speech for chemistry that it should be feasible to compute the three-dimensional structure of a protein from its sequence of amino acids.
In the same way as the order and spacing of the letters in this article give it meaning and message, the arrangement of the amino acids defines the identity and form of the protein, which ultimately dictates its function.
Due to the intrinsic flexibility of amino acid building blocks, a typical protein may assume around 10 to the power 300 distinct configurations. This quantity is more than the total number of atoms in the cosmos. Yet, within a millisecond, every protein in an organism will fold into its own unique form — the lowest-energy configuration of all the chemical bonds that comprise the protein. Change only one of the hundreds of amino acids generally contained in a protein, and it may no longer fold properly or function.