SCOPe: improvements to the structural classification of proteins – extended database to facilitate variant interpretation and machine learning

Chandonia, John-Marc; Guan, Lindsey; Lin, Shiangyi; Yu, Changhua; Fox, Naomi; Brenner, Steven E.

doi:10.1093/nar/gkab1054

Cited by 101 publications

(98 citation statements)

References 28 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the class of the domains, 29.8% map to mainly-alpha superfamilies, 23.4% to mainly-beta and 46.7% to alpha-beta, and these proportions are quite similar to those observed for experimental domain structures in CATH, albeit with a slightly lower percentage of alpha superfamilies in CATH experimental (alpha: 21.2%, beta: 23.4%, alpha/beta: 46.7%). This overabundance of mainly-alpha superfamilies has been noticed also in other AF2 domain classification efforts based on SCOPe (17). Supplementary Figure 5 shows the average expansion of each CATH architecture.…”

Section: Resultssupporting

confidence: 74%

See 1 more Smart Citation

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

Bordin

Sillitoe

Nallapareddy

et al. 2022

Preprint

View full text Add to dashboard Cite

Over the last year, there have been substantial improvements in protein structure prediction, particularly in methods like DeepMind's AlphaFold2 (AF2) that exploit deep learning strategies. Here we report a new CATH-Assign protocol which is used to analyse the first tranche of AF2 models predicted for 21 model organisms and discuss insights these models bring on the nature of protein structure space. We analyse good quality models and those with no unusual structural characteristics, i.e., features rarely seen in experimental structures. For the ~370,000 models that meet these criteria, we observe that 92% can be assigned to evolutionary superfamilies in CATH. The remaining domains cluster into 2,367 putative novel superfamilies. Detailed manual analysis on a subset of 618 of those which had at least one human relative revealed some extremely remote homologies and some further unusual features, but 26 could be confirmed as novel superfamilies and one of these has an alpha-beta propeller architectural arrangement never seen before. By clustering both experimental and predicted AF2 domain structures into distinct 'global fold' groups, we observe that the new AF2 models in CATH increase information on structural diversity by 36%. This expansion in structural diversity will help to reveal associated functional diversity not previously detected. Our novel CATH-Assign protocol scales well and will be able to harness the huge expansion (at least 100 million models) in structural data promised by DeepMind to provide more comprehensive coverage of even the most diverse superfamilies to help rationalise evolutionary changes in their functions.

show abstract

Section: Resultssupporting

confidence: 74%

“…Over the last 25 years, several domain-based protein structure classifications have emerged (SCOP (16), CATH (15), SCOPe (17), SCOP2 (18), ECOD (14)) which assign experimental structures of proteins from the Protein Data Bank (PDB) to evolutionary superfamilies. ECOD and CATH are the most comprehensive, classifying 90% or more of PDB.…”

Section: Introductionmentioning

confidence: 99%

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

Bordin

Sillitoe

Nallapareddy

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Thermodynamics spontaneously drive the protein into a stable, free-energy basin that is consistent with the environment. In proteins, structure rather than sequence tends to be conserved among proteins that perform the same function, even in proteins that are analogous across species [ 9 , 10 ]. From this perspective, a protein’s 3D structure is arguably the most important physical attribute of a protein.…”

Section: Foundational Concepts Of Protein Functionmentioning

confidence: 99%

“…However, there remain open questions about the best way to generate, represent and quantify conformational ensembles. Early work includes taking a statistical approach [ 199 ], knowledge-based analysis [ 10 ] and unsupervised clustering [ 200 , 201 ]. Eventually, neural networks were applied to recognize protein folds [ 202 ] or to self-improve a predicted folded structure [ 203 ].…”

Section: Selected Applications Of Machine Learning In Computational B...mentioning

confidence: 99%

Protein Function Analysis through Machine Learning

et al. 2022

View full text Add to dashboard Cite

Machine learning (ML) has been an important arsenal in computational biology used to elucidate protein function for decades. With the recent burgeoning of novel ML methods and applications, new ML approaches have been incorporated into many areas of computational biology dealing with protein function. We examine how ML has been integrated into a wide range of computational models to improve prediction accuracy and gain a better understanding of protein function. The applications discussed are protein structure prediction, protein engineering using sequence modifications to achieve stability and druggability characteristics, molecular docking in terms of protein–ligand binding, including allosteric effects, protein–protein interactions and protein-centric drug discovery. To quantify the mechanisms underlying protein function, a holistic approach that takes structure, flexibility, stability, and dynamics into account is required, as these aspects become inseparable through their interdependence. Another key component of protein function is conformational dynamics, which often manifest as protein kinetics. Computational methods that use ML to generate representative conformational ensembles and quantify differences in conformational ensembles important for function are included in this review. Future opportunities are highlighted for each of these topics.

show abstract

“…These same proteins have remote homologs that were not detectable by traditional sequence matching tools because of very low sequence identities. Our method is not only faster but also more accurate in application to the benchmark (21) that uses the Pfam (22), SUPERFAMILY (SCOPe 2.08) (3, 24), and CATH Gene3D (5, 26) datasets. PLAST is an alignment-free method that simply compares the embedding vectors using this accurate homology detection tool.…”

Section: Introductionmentioning

confidence: 99%

Protein Language Model Performs Efficient Homology Detection

Kilinc

Jia

Jernigan

2022

Preprint

View full text Add to dashboard Cite

Motivation: There are now 225 million sequences in the UniProtKB database, as of January 2022 and 451 million protein sequences in the NCBI non-redundant database. This huge sequence data is ripe for analysis and can be extremely informative about biological function when analyzed with the appropriate methods. Evolutionary information such as the relationship among protein sequences is key to performing sequence analyses. Since sequence matching is one of the primary ways that annotations are found, higher-quality sequence matches yield a larger number of identified homologs. Thus, there is an essential need for a faster and more accurate homolog detection method to process the huge amount of rapidly growing biological sequences. Method: Recently, we have seen major improvements in various predictive computational tasks such as structure prediction from the ever improving artificial intelligence methods. One such approach has been to use language models to represent proteins numerically in a representation matrix (embeddings) while retaining context-dependent biochemical, biophysical, and evolutionary information. Computational transformer architectures that utilize attention neural networks can generate these context-aware numerical representations in an unsupervised fashion. One such use for these protein embeddings is remote homolog detection. In this work, we utilize protein language models and then apply discrete cosine transforms to extract the essential part of these embeddings, resulting in a significantly smaller fixed-size matrix for each sequence. This allows us to numerically and efficiently calculate the distance between all pairs of proteins resulting in homolog detection. Results: Our Protein LAnguage model Search Tool (PLAST) is significantly faster, with linear runtimes in the number of sequences within the query database. With only one CPU core, it can scan a million sequences in less than a second. It essentially removes the noise in the sequence data and leads to significant improvements. PLAST is more accurate in the benchmarks tested from the PFAM, SCOP, and CATH databases than other approaches. When benchmarked with the PFAM database, the increase in the area under the receiver operating characteristic curve (AUROC) 3.1% when compared with NCBI-BLAST. The number of remote homologs that are detectable now is significantly larger and pushes sequence matches deeply into the usual twilight zone. Compared with the state-of-the-art profile-based homology search tools like CSBLAST, the increase was still 2.0%. PLAST can find remote homologs for a significant number of proteins that had been thought to be unique due to homolog detection failure. These homologs that are found usually have less than 20% sequence identity making them indistinguishable from noise with most other sequence matching methods. Conclusion: PLAST is an accurate and fast homolog detection tool essential for easy and rapid progress to utilize the vast amount of data generated by next-generation sequencing methods. Quantization of sequence embeddings into highly-compressed noise-free representations with the use of direct cosine transforms allows for the efficient and accurate detection of normal homologs and remote ones that are undetectable by other sequence similarity methods. The PLAST web server is accessible from https://mesihk.github.io/plast .

show abstract

SCOPe: improvements to the structural classification of proteins – extended database to facilitate variant interpretation and machine learning

Cited by 101 publications

References 28 publications

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

Protein Function Analysis through Machine Learning

Protein Language Model Performs Efficient Homology Detection

Contact Info

Product

Resources

About