AF2Complex predicts direct physical interactions in multimeric proteins with deep learning

Gao, Mu; An, Davi Nakajima; Parks, Jerry M.; Skolnick, Jeffrey

doi:10.1038/s41467-022-29394-2

Cited by 201 publications

(222 citation statements)

References 65 publications

Supporting

Mentioning

211

Contrasting

Order By: Relevance

“…Additionally, they involve probing interactions outside their native environment, either by lysing the cell or by creating fusion constructs. Nevertheless, these experimental methods provide some information to PPI databases which was used as a basis for AlphaFold protein interaction screens in Escherichia coli (Gao et al, 2022), Saccharomyces cerevisiae (Humphreys et al, 2021) and human proteomes (Burke et al, 2021). Unfortunately, it is unknown how many false positive or false negative predictions this produces.…”

Section: Introductionmentioning

confidence: 99%

Protein complexes in cells by AI-assisted structural proteomics

O’Reilly

Graziadei

Forbrig

et al. 2022

Preprint

View full text Add to dashboard Cite

Accurately modeling the structures of proteins and their complexes using artificial intelligence is revolutionizing molecular biology. Experimental data enable a candidate-based approach to systematically model novel protein assemblies. Here, we use a combination of in-cell crosslinking mass spectrometry, co-fractionation mass spectrometry and the SubtiWiki database to identify protein-protein interactions in the model Gram-positive bacterium Bacillus subtilis. Pairing this with structure prediction by AIphaFold-Multimer, we identify novel interactors of central machineries that include the ribosome, RNA polymerase and pyruvate dehydrogenase, as well as interactions involving uncharacterized proteins, which we functionally validate. After controlling for the false-positive rate of the AlphaFold approach, we propose novel structural models of 153 dimeric and 14 trimeric protein assemblies. We show that crosslinking MS data can independently validate AlphaFold predictions in situ. Our approach uncovers protein-protein interactions inside cells, provides structural insight into their interaction interface, and is applicable to genetically intractable organisms, including pathogenic bacteria.

show abstract

Section: Introductionmentioning

confidence: 99%

Protein complexes in cells by AI-assisted structural proteomics

O’Reilly

Graziadei

Forbrig

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These molecular-level dynamics are expected to lead to a diversity of interactions between the pathogen and the host that altogether cause a robust host response. The methods to study this area, especially in molecular dynamics, are dependent on an information-based perspective, and often a dependency on very large datasets, particularly in the case of employing deep-learning methods [81][82][83][84][85].…”

Section: Future Directions Of Studymentioning

confidence: 99%

A Perspective on Information Optimality in a Neural Circuit and Other Biological Systems

Friedman

2022

Signals

View full text Add to dashboard Cite

The nematode worm Caenorhabditis elegans has a relatively simple neural system for analysis of information transmission from sensory organ to muscle fiber. Consequently, this study includes an example of a neural circuit from the nematode worm, and a procedure is shown for measuring its information optimality by use of a logic gate model. This approach is useful where the assumptions are applicable for a neural circuit, and also for choosing between competing mathematical hypotheses that explain the function of a neural circuit. In this latter case, the logic gate model can estimate computational complexity and distinguish which of the mathematical models require fewer computations. In addition, the concept of information optimality is generalized to other biological systems, along with an extended discussion of its role in genetic-based pathways of organisms.

show abstract

“…AlphaFold Multimer scoring is based on an interface predicted template modelling (ipTM) score that takes into account protein-protein interactions. It was shown to be more advantageous over the pTM and pLDDT scores used in AlphaFold 2 48 . The best ranked models on this case are a good indicator of model confidence based on the RMSD values.…”

Section: Application: Adhesin Folding Domainsmentioning

confidence: 99%

Protein structure prediction in the era of AI: challenges and limitations when applying toin-silicoforce spectroscopy

Gomes

Bernardi

2022

Preprint

View full text Add to dashboard Cite

Mechanoactive proteins are essential for a myriad of physiological and pathological processes. Guided by the advances in single-molecule force spectroscopy (SMFS), we have reached a molecular-level understanding of how several mechanoactive proteins respond to mechanical forces. However, even SMFS has its limitations, including the lack of detailed structural information during force-loading experiments. That is where molecular dynamics (MD) methods shine, bringing atomistic details with femtosecond time-resolution. However, MD heavily relies on the availability of high-resolution structures, which is not available for most proteins. For instance, the Protein Data Bank currently has 192K structures deposited, against 231M protein sequences available on Uniprot. But many are betting that this gap might become much smaller soon. Over the past year, the AI-based AlphaFold created a buzz on the structural biology field by being able to, for the first time, predict near-native protein folds from their sequences. For some, AlphaFold is causing the merge of structural biology with bioinformatics. In this perspective, using an in silico SMFS approach, we investigate how reliable AlphaFold structure predictions are to investigate mechanical properties of staph bacteria adhesins proteins. Our results show that AlphaFold produce extremally reliable protein folds, but in many cases is unable to predict high-resolution protein complexes accurately. Nonetheless, the results show that AlphaFold can revolutionize the investigation of these proteins, particularly by allowing high-throughput scanning of protein structures. Meanwhile, we show that the AlphaFold results need to be validated and should not be employed blindly, with the risk of obtaining an erroneous protein mechanism.

show abstract

AF2Complex predicts direct physical interactions in multimeric proteins with deep learning

Cited by 201 publications

References 65 publications

Protein complexes in cells by AI-assisted structural proteomics

Protein complexes in cells by AI-assisted structural proteomics

A Perspective on Information Optimality in a Neural Circuit and Other Biological Systems

Protein structure prediction in the era of AI: challenges and limitations when applying toin-silicoforce spectroscopy

Contact Info

Product

Resources

About