Global organization of a binding site network gives insight into evolution and structure-function relationships of proteins

Lee, Juyong; Konc, Janez; Janežič, Dušanka; Brooks, Bernard R.

doi:10.1038/s41598-017-10412-z

“…The next significantly enriched fold (p=3.1e‐12) corresponds to the NAD(P) – binding Rossmann‐fold domains (c.2 fold). This agrees with the findings on the protein‐small molecule binding site similarity network), where this fold was found as one of the most ancient. The agreement of our results with previous studies suggests that protein‐ion binding site network and protein‐compound binding network are related, and that they most likely co‐evolve with each other.…”

Section: Resultssupporting

confidence: 92%

“…Although existing studies provide possible mechanistic explanations on the level of protein domain networks, there are currently very few reports on evolution of protein binding sites. Recently, global small molecule (compound) binding site similarity network was investigated, where the compound binding site community network was found to be scale‐free, thus, a few of communities covering the majority of the network.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Insights from Ion Binding Site Network Analysis into Evolution and Functions of Proteins

Škrlj

¹

,

Kunej

²

,

Konc

³

2018

Molecular Informatics

Self Cite

View full text Add to dashboard Cite

Many biological phenomena can be represented as complex networks. Using a protein binding site comparison approach, we generated a network of ion binding sites on the scale of all known protein structures from the Protein Data Bank. We found that this ion binding site similarity network is scale‐free, indicating a network in which a few ion binding site scaffolds are the network hubs, and these are connected to hundreds of nodes, whereas the vast majority of nodes have only a few neighbors. Enrichment and statistical analysis of the network components and communities yielded insights into underlying processes from the functional and the structural perspective. Largest components and communities were observed to be closely related to basic metabolic processes and some of the most common structural folds, which, from the evolutionary point of view, indicates that they may be the oldest ones. Further, we derived the first comprehensive map of ion interchangeability, based on binding site similarity. Several highly interchangeable protein‐ion binding site pairs emerged (e.g., Ca2+ and Mg2+), as well as structurally distinct ones. The constructed network of ion binding site similarities will aid in understanding the general principles of protein‐ion binding sites structure, function and evolution. We demonstrate potential uses of the network on proteins involved in cancer development and immune response, where individual ions play prominent roles in disease development.

show abstract

“…Proteins largely function to bind to other molecules, whether small molecules, proteins, or other macromolecules. Past work has shown that binding sites can reveal evolutionary relationships among proteins [42] and that particular structural motifs in binding sites are mainly restricted to specific families or superfamilies of proteins [37]. Thus binding sites provide a high-level characterization of the protein that may be relevant for the model throughout the sequence.…”

Section: Binding Sitesmentioning

confidence: 99%

BERTology Meets Biology: Interpreting Attention in Protein Language Models

Vig

¹

,

Madani

²

,

Varshney

³

et al. 2020

Preprint

View full text Add to dashboard Cite

Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. Through the lens of attention, we analyze the inner workings of the Transformer and explore how the model discerns structural and functional properties of proteins. We show that attention (1) captures the folding structure of proteins, connecting amino acids that are far apart in the underlying sequence, but spatially close in the three-dimensional structure, (2) targets binding sites, a key functional component of proteins, and (3) focuses on progressively more complex biophysical properties with increasing layer depth. We also present a three-dimensional visualization of the interaction between attention and protein structure. Our findings align with known biological processes and provide a tool to aid discovery in protein engineering and synthetic biology. The code for visualization and analysis is available at https://github.com/salesforce/provis.

show abstract

“…Proteins largely function to bind to other molecules, whether small molecules, proteins, or other macromolecules. Past work has shown that binding sites can reveal evolutionary relationships among proteins [40] and that particular structural motifs in binding sites are mainly restricted to specific families or superfamilies of proteins [35]. Thus binding sites provide a high-level characterization of the protein that may be relevant for the model throughout the sequence.…”

Section: Binding Sitesmentioning

confidence: 99%

BERTology Meets Biology: Interpreting Attention in Protein Language Models

Vig¹,

Madani²,

Varshney³

et al. 2020

Preprint

View full text Add to dashboard Cite

Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. Through the lens of attention, we analyze the inner workings of the Transformer and explore how the model discerns structural and functional properties of proteins. We show that attention (1) captures the folding structure of proteins, connecting amino acids that are far apart in the underlying sequence, but spatially close in the three-dimensional structure, (2) targets binding sites, a key functional component of proteins, and (3) focuses on progressively more complex biophysical properties with increasing layer depth. We also present a three-dimensional visualization of the interaction between attention and protein structure. Our findings align with known biological processes and provide a tool to aid discovery in protein engineering and synthetic biology. The code for visualization and analysis is available at https://github.com/salesforce/provis.Preprint. Under review.

show abstract

Global organization of a binding site network gives insight into evolution and structure-function relationships of proteins

Cited by 6 publications

References 69 publications

Insights from Ion Binding Site Network Analysis into Evolution and Functions of Proteins

Insights from Ion Binding Site Network Analysis into Evolution and Functions of Proteins

BERTology Meets Biology: Interpreting Attention in Protein Language Models

BERTology Meets Biology: Interpreting Attention in Protein Language Models

Contact Info

Product

Resources

About