FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4282964887> ?p ?o ?g. }

• W4282964887 abstract "Abstract Background Despite the immense importance of transmembrane proteins (TMP) for molecular biology and medicine, experimental 3D structures for TMPs remain about 4-5 times underrepresented compared to non-TMPs. Today’s top methods such as AlphaFold2 accurately predict 3D structures for many TMPs, but annotating transmembrane regions remains a limiting step for proteome-wide predictions. Results Here, we present TMbed, a novel method inputting embeddings from protein Language Models (pLMs, here ProtT5), to predict for each residue one of four classes: transmembrane helix (TMH), transmembrane strand (TMB), signal peptide, or other. TMbed completes predictions for entire proteomes within hours on a single consumer-grade desktop machine at performance levels similar or better than methods, which are using evolutionary information from multiple sequence alignments (MSAs) of protein families. On the per-protein level, TMbed correctly identified 94±8% of the beta barrel TMPs (53 of 57) and 98±1% of the alpha helical TMPs (557 of 571) in a non-redundant data set, at false positive rates well below 1% (erred on 30 of 5654 non-membrane proteins). On the per-segment level, TMbed correctly placed, on average, 9 of 10 transmembrane segments within five residues of the experimental observation. Our method can handle sequences of up to 4200 residues on standard graphics cards used in desktop PCs (e.g., NVIDIA GeForce RTX 3060). Conclusions Based on embeddings from pLMs and two novel filters (Gaussian and Viterbi), TMbed predicts alpha helical and beta barrel TMPs at least as accurately as any other method but at lower false positive rates. Given the few false positives and its outstanding speed, TMbed might be ideal to sieve through millions of 3D structures soon to be predicted, e.g., by AlphaFold2. Availability Our code, method, and data sets are freely available in the GitHub repository, https://github.com/BernhoferM/TMbed ." @default.
• W4282964887 created "2022-06-17" @default.
• W4282964887 creator A5035722235 @default.
• W4282964887 creator A5064905883 @default.
• W4282964887 date "2022-06-15" @default.
• W4282964887 modified "2023-10-03" @default.
• W4282964887 title "TMbed – Transmembrane proteins predicted through Language Model embeddings" @default.
• W4282964887 cites W1501531009 @default.
• W4282964887 cites W1515959604 @default.
• W4282964887 cites W1786434256 @default.
• W4282964887 cites W1938173378 @default.
• W4282964887 cites W1939505221 @default.
• W4282964887 cites W1967513793 @default.
• W4282964887 cites W1968682237 @default.
• W4282964887 cites W1974789047 @default.
• W4282964887 cites W1995808589 @default.
• W4282964887 cites W2022428986 @default.
• W4282964887 cites W2029653438 @default.
• W4282964887 cites W2035784781 @default.
• W4282964887 cites W2056402029 @default.
• W4282964887 cites W2057013716 @default.
• W4282964887 cites W2095467724 @default.
• W4282964887 cites W2105537627 @default.
• W4282964887 cites W2110425545 @default.
• W4282964887 cites W2129838159 @default.
• W4282964887 cites W2137670821 @default.
• W4282964887 cites W2137827030 @default.
• W4282964887 cites W2140831051 @default.
• W4282964887 cites W2145020089 @default.
• W4282964887 cites W2149407349 @default.
• W4282964887 cites W2150853746 @default.
• W4282964887 cites W2151156268 @default.
• W4282964887 cites W2156125289 @default.
• W4282964887 cites W2158623906 @default.
• W4282964887 cites W2158714788 @default.
• W4282964887 cites W2159136327 @default.
• W4282964887 cites W2164025376 @default.
• W4282964887 cites W2169317607 @default.
• W4282964887 cites W2170463736 @default.
• W4282964887 cites W2170747616 @default.
• W4282964887 cites W2190900687 @default.
• W4282964887 cites W2292314415 @default.
• W4282964887 cites W2412885026 @default.
• W4282964887 cites W2510407459 @default.
• W4282964887 cites W2517405041 @default.
• W4282964887 cites W2534377269 @default.
• W4282964887 cites W2886471703 @default.
• W4282964887 cites W2898210859 @default.
• W4282964887 cites W2900674118 @default.
• W4282964887 cites W2901361432 @default.
• W4282964887 cites W2951149542 @default.
• W4282964887 cites W2980789587 @default.
• W4282964887 cites W2995514860 @default.
• W4282964887 cites W3108574850 @default.
• W4282964887 cites W3112376646 @default.
• W4282964887 cites W3118936575 @default.
• W4282964887 cites W3144701084 @default.
• W4282964887 cites W3146944767 @default.
• W4282964887 cites W3158236124 @default.
• W4282964887 cites W3159719254 @default.
• W4282964887 cites W3163595068 @default.
• W4282964887 cites W3163970098 @default.
• W4282964887 cites W3166142427 @default.
• W4282964887 cites W3170504813 @default.
• W4282964887 cites W3177828909 @default.
• W4282964887 cites W3183475563 @default.
• W4282964887 cites W3191896067 @default.
• W4282964887 cites W3199468887 @default.
• W4282964887 cites W3210500140 @default.
• W4282964887 cites W3211795435 @default.
• W4282964887 cites W3212761619 @default.
• W4282964887 cites W4200552574 @default.
• W4282964887 cites W4205172550 @default.
• W4282964887 cites W4205620281 @default.
• W4282964887 cites W4206950245 @default.
• W4282964887 cites W4223551334 @default.
• W4282964887 cites W4225438928 @default.
• W4282964887 cites W4280577818 @default.
• W4282964887 cites W4281903464 @default.
• W4282964887 cites W4282562958 @default.
• W4282964887 doi "https://doi.org/10.1101/2022.06.12.495804" @default.
• W4282964887 hasPublicationYear "2022" @default.
• W4282964887 type Work @default.
• W4282964887 citedByCount "2" @default.
• W4282964887 countsByYear W42829648872022 @default.
• W4282964887 crossrefType "posted-content" @default.
• W4282964887 hasAuthorship W4282964887A5035722235 @default.
• W4282964887 hasAuthorship W4282964887A5064905883 @default.
• W4282964887 hasBestOaLocation W42829648871 @default.
• W4282964887 hasConcept C104397665 @default.
• W4282964887 hasConcept C118892022 @default.
• W4282964887 hasConcept C121684516 @default.
• W4282964887 hasConcept C153180895 @default.
• W4282964887 hasConcept C154945302 @default.
• W4282964887 hasConcept C170493617 @default.
• W4282964887 hasConcept C185592680 @default.
• W4282964887 hasConcept C21442007 @default.
• W4282964887 hasConcept C24530287 @default.
• W4282964887 hasConcept C41008148 @default.
• W4282964887 hasConcept C41625074 @default.

• next