What's next for AlphaFold and the AI protein-folding revolution.

@article{Callaway2022WhatsNF,
  title={What's next for AlphaFold and the AI protein-folding revolution.},
  author={Ewen Callaway},
  journal={Nature},
  year={2022},
  volume={604 7905},
  pages={
          234-238
        }
}

Computational approaches for predicting variant impact: An overview from resources, principles to applications

One objective of human genetics is to unveil the variants that contribute to human diseases. With the rapid development and wide use of next-generation sequencing (NGS), massive genomic sequence data

Importins involved in the nuclear transportation of steroid hormone receptors: In silico and in vitro data

TLDR
In silico data is provided, followed by experimental in vitro validation, showing that these alternative importins are responsible for the nuclear transportation of steroid hormone receptors such as ERα, AR and PR, and therefore they may consist of alternative targets for the pharmacological manipulation of steroids hormone actions.

Uni-Fold: An Open-Source Platform for Developing Protein Folding Models beyond AlphaFold

TLDR
This work reimplementedAlphaFold and AlphaFold-Multimer in the PyTorch framework, and reproduced their from-scratch training processes with equivalent or better accuracy, and presented Uni-Fold as a thoroughly open-source platform for developing protein folding models beyond AlphaFolds.

Effect of Delta and Omicron Mutations on the RBD-SD1 Domain of the Spike Protein in SARS-CoV-2 and the Omicron Mutations on RBD-ACE2 Interface Complex

TLDR
The results show that the interaction of Omicron RBD with ACE2 significantly increased its bonding between amino acids at the interface providing information on the implications of penetration of S-protein into ACE2, and thus offering a possible explanation for its high infectivity.

Diving into the Deep End: Machine Learning for the Chemist

TLDR
The perceived usefulness of AI at this time in some fields of the chemical sciences and related areas is presented, based on recently published reviews and perspectives by experts in the area, as well as other resources.

Opportunities and Challenges for In Silico Drug Discovery at Delta Opioid Receptors

TLDR
Overall, it is posed that there are multiple opportunities to enable in silico drug discovery at the delta opioid receptor to identify novel delta opioid modulators potentially with unique pharmacological properties, such as biased signaling.

Protein structure prediction in the era of AI: challenges and limitations when applying to in-silico force spectroscopy

TLDR
The results show thatAlphaFold can revolutionize the investigation of these proteins, particularly by allowing high-throughput scanning of protein structures, and show that the AlphaFold results need to be validated and should not be employed blindly, with the risk of obtaining an erroneous protein mechanism.

From Traditional Ethnopharmacology to Modern Natural Drug Discovery: A Methodology Discussion and Specific Examples

TLDR
This work discusses the evolution of ideas and methods, from traditional ethnopharmacology to in silico drug discovery, applied to natural products, and reports the isolation of novel antiviral compounds, based on natural products active against influenza and SARS-CoV-2 and novel substances active on a specific GPCR, OXER1.

What geometrically constrained protein models can tell us about real-world protein contact maps

TLDR
The emergent behavior of protein contact maps derived from a geometrically constrained random interaction model in comparison to real-world proteins is investigated and seems that the amino acid distance distributions can be attributed to geometric constraints of protein chains in bulk and amino acid sequences only play a secondary role.

References

SHOWING 1-7 OF 7 REFERENCES

Computed structures of core eukaryotic protein complexes

TLDR
A coevolution-guided protein interaction identification pipeline that incorporates a rapidly computable version of RoseTTAFold with the slower but more accurate AlphaFold to systematically evaluate interactions between 8.3 million pairs of yeast proteins is developed.

Improved prediction of protein-protein interactions using AlphaFold2

TLDR
AF2 is utilised to optimise a protocol for predicting the structure of heterodimeric protein complexes using only sequence information and it is found that using the default AF2 protocol, 32% of the models in the Dockground test set can be modelled accurately.

Accurate prediction of protein structures and interactions using a 3-track neural network

TLDR
A three-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables the rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure.

Highly accurate protein structure prediction with AlphaFold

TLDR
This work validated an entirely redesigned version of the neural network-based model, AlphaFold, in the challenging 14th Critical Assessment of protein Structure Prediction (CASP14)15, demonstrating accuracy competitive with experiment in a majority of cases and greatly outperforming other methods.

De novo protein design by deep network hallucination

TLDR
Deep networks trained to predict native protein structures from their sequences can be inverted to design new proteins, and such networks and methods should contribute alongside traditional physics-based models to the de novo design of proteins with new functions.

Molecular architecture of the inner ring scaffold of the human nuclear pore complex

TLDR
This architectural map explains the vast majority of the electron density of the scaffold, and concludes that despite obvious differences in morphology and composition, the higher-order structure of the inner and outer rings is unexpectedly similar.

Can AlphaFold2 predict the impact of missense mutations on structure?

  • Nature Structural & Molecular Biology
  • 2022