| Work profile | https://www.cimr.cam.ac.uk/staff/professor-randy-j-read-frs |
| ORCiD | https://orcid.org/0000-0001-8273-0047 |
Advances in machine learning have transformed structural biology, enabling swift and accurate prediction of protein structure from sequence. However, challenges persist in capturing sidechain packing, condition-dependent conformational dynamics, and biomolecular interactions, primarily due to scarcity of high-quality training data. Emerging techniques, including cryo-electron tomography (cryo-ET) and high-throughput crystallography, promise vast new sources of structural data, but translating raw experimental observations into mechanistically interpretable atomic models remains a key bottleneck. Here, we aim to address these challenges by improving the efficiency of structural analysis through combining experimental measurements with a landmark protein structure prediction method -- AlphaFold2. We present an augmentation of AlphaFold2, ROCKET, that refines its predictions using cryo-EM, cryo-ET, and X-ray crystallography data, and demonstrate that this approach captures biologically important structural variation that AlphaFold2 does not. By performing structure optimization in the space of coevolutionary embeddings, rather than Cartesian coordinates, ROCKET automates difficult modeling tasks, such as flips of functional loops and domain rearrangements, that are beyond the scope of current state-ofthe-art methods and, in some instances, even manual human modeling. The ability to efficiently sample these barrier-crossing rearrangements unlocks a new horizon for scalable and automated model building. Crucially, ROCKET does not require retraining of AlphaFold2 and is readily adaptable to multimers, ligand-cofolding, and other data modalities. Conversely, our differentiable crystallographic and cryo-EM target functions are capable of augmenting other structure prediction methods. ROCKET thus provides an extensible framework for the integration of experimental observables with biomolecular machine learning. ### Competing Interest Statement MA is a member of the scientific advisory boards of Cyrus Biotechnology, Deep Forest Sciences, Nabla Bio, Oracle Therapeutics, and Achira.
Likelihood-based cryo-EM docking using the emplace_local software is faster and more sensitive than the related em_placement software when the approximate location of a component is known. It is conveniently available through a plugin to the ChimeraX visualization software.
Hi Structural biologists!
Here is our article that helps you make the case that the experiment is still very much needed: https://www.nature.com/articles/s41592-023-02087-4
"AlphaFold predictions are valuable hypotheses and accelerate but do not replace experimental structure determination." Nature Methods (2023)
#Crystallography #MX #PDB #Alphafold #StructuralBiology @strucbio
An analysis of AlphaFold protein structure predictions shows that while in many cases the predictions are highly accurate, there are also many instances where the predicted structures or parts of predicted structures do not agree with experimentally resolved data. Therefore, care must be taken when using these predictions for informing structural hypotheses.
If you ever #dock models into noisy #cryoem maps, please look at the papers we (Claudia Millán, Airlie McCoy,
@terwilltom) have just released through bioRxiv!
# 1, theory:
https://www.biorxiv.org/content/10.1101/2022.12.20.521171v1
# 2, implementation in a program called EM_placement.
https://www.biorxiv.org/content/10.1101/2022.12.20.521188v1
Find it in today's (dev-4821) build of #Phenix (https://phenix-online.org/download/nightly_builds.cgi?show_all=1), and coming soon elsewhere including a #ChimeraX plugin!
Tom Terwilliger
StructuralBiology
StructBiolCommunications