Sökning: id:"swepub:oai:lup.lub.lu.se:4c4d0359-e5be-4657-8c26-f47af388e476" >
Multienzyme deep le...
-
Gueto-Tettay, CarlosLund University,Lunds universitet,epIgG,Forskargrupper vid Lunds universitet,Lund University Research Groups
(författare)
Multienzyme deep learning models improve peptide de novo sequencing by mass spectrometry proteomics
- Artikel/kapitelEngelska2023
Förlag, utgivningsår, omfång ...
-
2023-01-20
-
Public Library of Science (PLoS),2023
Nummerbeteckningar
-
LIBRIS-ID:oai:lup.lub.lu.se:4c4d0359-e5be-4657-8c26-f47af388e476
-
https://lup.lub.lu.se/record/4c4d0359-e5be-4657-8c26-f47af388e476URI
-
https://doi.org/10.1371/journal.pcbi.1010457DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:art swepub-publicationtype
-
Ämneskategori:ref swepub-contenttype
Anmärkningar
-
Generating and analyzing overlapping peptides through multienzymatic digestion is an efficient procedure for de novo protein using from bottom-up mass spectrometry (MS). Despite improved instrumentation and software, de novo MS data analysis remains challenging. In recent years, deep learning models have represented a performance breakthrough. Incorporating that technology into de novo protein sequencing workflows require machine-learning models capable of handling highly diverse MS data. In this study, we analyzed the requirements for assembling such generalizable deep learning models by systemcally varying the composition and size of the training set. We assessed the generated models' performances using two test sets composed of peptides originating from the multienzyme digestion of samples from various species. The peptide recall values on the test sets showed that the deep learning models generated from a collection of highly N- and C-termini diverse peptides generalized 76% more over the termini-restricted ones. Moreover, expanding the training set's size by adding peptides from the multienzymatic digestion with five proteases of several species samples led to a 2-3 fold generalizability gain. Furthermore, we tested the applicability of these multienzyme deep learning (MEM) models by fully de novo sequencing the heavy and light monomeric chains of five commercial antibodies (mAbs). MEMs extracted over 10000 matching and overlapped peptides across six different proteases mAb samples, achieving a 100% sequence coverage for 8 of the ten polypeptide chains. We foretell that the MEMs' proven improvements to de novo analysis will positively impact several applications, such as analyzing samples of high complexity, unknown nature, or the peptidomics field.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Tang, DiLund University,Lunds universitet,Infection Medicine Proteomics,Forskargrupper vid Lunds universitet,Lund University Research Groups(Swepub:lu)di6882ta
(författare)
-
Happonen, LottaLund University,Lunds universitet,Molekylär patogenes,Forskargrupper vid Lunds universitet,Molecular Pathogenesis,Lund University Research Groups(Swepub:lu)immu-loh
(författare)
-
Heusel, MoritzLund University,Lunds universitet,Infection Medicine Proteomics,Forskargrupper vid Lunds universitet,epIgG,Lund University Research Groups(Swepub:lu)mo3350he
(författare)
-
Khakzad, HamedSwiss Federal Institute of Technology
(författare)
-
Malmström, JohanLund University,Lunds universitet,Infection Medicine Proteomics,Forskargrupper vid Lunds universitet,SEBRA Sepsis and Bacterial Resistance Alliance,epIgG,LTH profilområde: Teknik för hälsa,LTH profilområden,Lunds Tekniska Högskola,Lund University Research Groups,LTH Profile Area: Engineering Health,LTH Profile areas,Faculty of Engineering, LTH(Swepub:lu)medk-jma
(författare)
-
Malmström, LarsLund University,Lunds universitet,epIgG,Forskargrupper vid Lunds universitet,Lund University Research Groups(Swepub:lu)elma-lma
(författare)
-
epIgGForskargrupper vid Lunds universitet
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:PLoS Computational Biology: Public Library of Science (PLoS)19:11553-734X1553-7358
Internetlänk
Hitta via bibliotek
Till lärosätets databas