Full Speed Ahead: What DeepMind’s Newest Revelation means for Scientific/Research Advancement

Last Week, DeepMind announced on their blog that they had made available, in collaboration with EMBL-EBI, the structures of all the proteins in 20 species as computed by AlphaFold. Thousands more species are to follow. What’s more, they published the full details of the AlphaFold method, which should enable researchers to build their own proteome structures.

This is a triumphant moment for Open Science. I believe that this will go down in history as one of the most impactful contributions to science, right up there alongside determining the molecular structure of DNA, genome editing, and CRISPR. 

As most will recall, AlphaFold created a stir at the 2018 and 2020 CASP meetings, by winning the protein structure prediction competition by a large margin, causing most in the field to declare the longstanding protein folding problem solved. We had our own take at the time, somewhat nostalgic for the original “pure” protein folding problem that has fallen by the wayside, but excited by the practical implications of accurate structure prediction. The one big remaining criticism of the work, that it was not made available to everyone, has now been addressed.

At Cyclica, we are excited about two things: AlphaFold generated proteomes will be used as input to our proteome processing pipeline, expanding proteome screening to more non-human organisms and offering new opportunities in preclinical research, infectious disease, animal health and agriculture. The scale and impact that we will have as a result will be unparalleled in drug discovery as we are the only company that has a computationally driven proteome screening approach with MatchMaker.  Drug discovery tools like MatchMaker that focus on local substructure rather than detailed atomistic positions suffer fewer trade offs when expanding coverage through modeled protein structures.  More far out, AlphaFold could close the sequence-structure gap in the effort to rapidly repurpose existing drugs to combat epidemic outbreaks. This could enable a rapid epidemic response to new pathogens that leads to drug candidates for field testing in the span of a week from the time a novel pathogen is first isolated (more on that here, near the end).

We are examining the new data as we speak, and will be reporting on our findings soon. Stay tuned! We believe it’s going to be a groundbreaking shift in the way in which drug discovery is done. 

Naheed Kurji, Chief Executive Officer

Naheed Kurji, Chief Executive Officer

Naheed Kurji is the Co-Founder, President and CEO of Cyclica. Naheed is passionate about building AI-augmented technologies that enable researchers to make more strategic and informed decisions in Healthcare and the life sciences. He spends the majority of his time obsessing over Cyclica’s culture, defining its strategy to best effect change in the pharma industry to achieve the company’s vision, and exploring opportunities for continued innovation.

Related Posts

Cyclica successfully integrates DeepMind’s AlphaFold 2

AlphaFold 2 has provided structures for a large percentage of the proteome, perfectly complementary...


A closer look at the coverage of the AlphaFold Human Proteome

In this post of our AlphaFold Series, we look at the gaps in proteome coverage addressed by...


Protein residue characterization using AlphaFold

In this post of our AlphaFold Series, we present the new technology developed at Cyclica Inc. in...