Learning a functional grammar of protein domains using natural language word embedding techniques

Buchan, Daniel W. A.; Jones, David T.

doi:10.1002/prot.25842

Cited by 22 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, when analysing a new FA-like protein, a potential annotated adhesive domain can infer the existence of a specific stalk domain and vice versa. Domain grammar approaches have shown that a knowledge of the domain grammar of proteins can enhance sequence similarity searching [ 32 , 33 ]. For a representative analysis of the phylogenetic distribution of FA-like proteins we decided to use the UniProt Reference Proteomes sequences only.…”

Section: Discussionmentioning

confidence: 99%

Discovery of fibrillar adhesins across bacterial species

2021

View full text Add to dashboard Cite

Background Fibrillar adhesins are long multidomain proteins that form filamentous structures at the cell surface of bacteria. They are an important yet understudied class of proteins composed of adhesive and stalk domains that mediate interactions of bacteria with their environment. This study aims to characterize fibrillar adhesins in a wide range of bacterial phyla and to identify new fibrillar adhesin-like proteins to improve our understanding of host-bacteria interactions. Results Through careful literature and computational searches, we identified 82 stalk and 27 adhesive domain families in fibrillar adhesins. Based on the presence of these domains in the UniProt Reference Proteomes database, we identified and analysed 3,542 fibrillar adhesin-like proteins across species of the most common bacterial phyla. We further enumerate the adhesive and stalk domain combinations found in nature and demonstrate that fibrillar adhesins have complex and variable domain architectures, which differ across species. By analysing the domain architecture of fibrillar adhesins, we show that in Gram positive bacteria, adhesive domains are mostly positioned at the N-terminus and cell surface anchors at the C-terminus of the protein, while their positions are more variable in Gram negative bacteria. We provide an open repository of fibrillar adhesin-like proteins and domains to enable further studies of this class of bacterial surface proteins. Conclusion This study provides a domain-based characterization of fibrillar adhesins and demonstrates that they are widely found in species across the main bacterial phyla. We have discovered numerous novel fibrillar adhesins and improved our understanding of pathogenic adhesion and invasion mechanisms.

show abstract

Section: Discussionmentioning

confidence: 99%

Discovery of fibrillar adhesins across bacterial species

2021

View full text Add to dashboard Cite

show abstract

“…For instance, when analysing a new FA-like protein, a potential annotated adhesive domain can infer the existence of a specific stalk domain and vice versa. Domain grammar approaches have shown that a knowledge of the domain grammar of proteins can enhance sequence similarity searching [28,29]. For a representative analysis of the phylogenetic distribution of FA-like proteins we decided to use the UniProt Reference Proteomes sequences only.…”

Section: Discussionmentioning

confidence: 99%

Discovery of Fibrillar Adhesins across Bacterial Species

Monzon

Lafita

Bateman

2020

Preprint

View full text Add to dashboard Cite

BackgroundFibrillar adhesins are long multidomain proteins attached at the cell surface and composed of at least one adhesive domain and multiple tandemly repeated domains, which build an elongated stalk that projects the adhesive domain beyond the bacterial cell surface. They are an important yet understudied class of proteins that mediate interactions of bacteria with their environment. This study aims to characterize fibrillar adhesins in a wide range of bacterial phyla and to identify new fibrillar adhesin-like proteins to improve our understanding of host-bacteria interactions.ResultsBy careful search for fibrillar adhesins in the literature and by computational analysis we identified 75 stalk domains and 24 adhesive domains. Based on the presence of these domains in the UniProt Reference Proteomes database, we identified and analysed 3,388 fibrillar adhesin-like proteins across species of the most common bacterial phyla. We found that the bacterial proteomes with the highest fraction of fibrillar adhesins include several known pathogens. We further enumerate the adhesive and stalk domain combinations found in nature and demonstrate that fibrillar adhesins have complex and variable domain architectures, which differ across species. By analysing the domain architecture of fibrillar adhesins we show that in Gram positive bacteria adhesive domains are mostly positioned at the N-terminus of the protein with the cell surface anchor at the C-terminus, while their positions are more variable in Gram negative bacteria. We provide an open repository of fibrillar adhesin-like proteins and domains to facilitate downstream studies of this class of bacterial surface proteins.ConclusionThis study provides a domain-based characterization of fibrillar adhesins and demonstrates that they are widely found across the main bacterial phyla. We have discovered numerous novel fibrillar adhesins and improved the understanding of how pathogens might adhere to and subsequently invade into host cells.

show abstract

“…Comparison with Pfam domain embeddings From all proposed protein embeddings works, only [22] developed intrinsic quantitative benchmarks. They applied word2vec for Pfam domain annotations for only eykaryotic proteins.…”

Section: Discussionmentioning

confidence: 99%

“…Various methods to create embeddings for proteins were proposed [16,17,18,19,20,21,22]. ProtVec fragmented the protein sequence in 3-mers for all possible starting shifts.…”

Section: Introductionmentioning

confidence: 99%

dom2vec: Capturing domain structure and function using self-supervision on protein domain architectures

Melidis¹,

Malone²,

Nejdl³

2020

Preprint

View full text Add to dashboard Cite

Background: Word embedding approaches have revolutionized natural language processing (NLP) research. These approaches aim to map words to a low-dimensional vector space, in which words with similar linguistic features cluster together. Embedding-based methods have also been developed for proteins, where words are amino acids and sentences are proteins. The learned embeddings have been evaluated qualitatively, via visual inspection of the embedding space and extrinsically, via performance comparison on downstream protein prediction tasks. However, these sequence embeddings have the caveat that biological metadata do not exist for each amino acid, in order to measure the quality of each unique learned embedding vector. Results: Here, we present dom2vec, an approach for learning protein domain embeddings using word2vec on InterPro annotations. In contrast to sequence embeddings, biological metadata do exist for protein domains, related to each domain separately. Therefore, we present four intrinsic evaluation strategies to quantitatively assess the quality of the learned embedding space. To perform a reliable evaluation in terms of biology knowledge, we selected the metadata related to the most distinctive biological characteristics of domains. These are the structure, enzymatic and molecular function of a given domain. Notably, dom2vec obtains adequate level of performance in the intrinsic assessment, therefore we can draw an analogy between the local linguistic features in natural languages and the domain structure and function information in domain architectures. Moreover, we demonstrate the dom2vec applicability on protein prediction tasks, by comparing it with state-of-the-art sequence embeddings in three downstream tasks. We show that dom2vec outperform sequence embeddings for toxin and enzymatic function prediction and is comparable with sequence embeddings in cellular location prediction. Conclusions: We report that the application of word2vec on InterPro annotations produces domain embeddings with two significant advantages over sequence embeddings. First, each unique dom2vec vector can be quantitatively evaluated towards its available structure and function metadata. Second, the produced embeddings can outperform the sequence embeddings for a subset of downstream tasks. Overall, dom2vec embeddings are able to capture the most important biological properties of domains and surpass sequence embeddings for a subset of prediction tasks.

show abstract

Learning a functional grammar of protein domains using natural language word embedding techniques

Cited by 22 publications

References 27 publications

Discovery of fibrillar adhesins across bacterial species

Discovery of fibrillar adhesins across bacterial species

Discovery of Fibrillar Adhesins across Bacterial Species

dom2vec: Capturing domain structure and function using self-supervision on protein domain architectures

Contact Info

Product

Resources

About