We've updated our Privacy Policy to make it clearer how we use your personal data.
We use cookies to provide you with a better experience, read our Cookie Policy

EP38471
Poster Title: Application of TIMScore to De Novo Search Engine, DeepNovo in PaSER
Submitted on 09 Mar 2022
Author(s): Robin Park1; Patrick Garrett2; Wojciech Marszałek1; Tharan Srikumar1; Sven Brehmer1; Titus Jung2; Marc-Antoine Beauvais1; Hyunsoo Kim2; Chistopher Adams1; Dennis Trede1; John R. Yates, III2; Rohan Thakur1
Affiliations: 1Bruker Daltonik GmbH; 2Scripps Research, La Jolla, CA
Poster Views: 534
Submitted on 09 Mar 2022
Author(s): Robin Park1; Patrick Garrett2; Wojciech Marszałek1; Tharan Srikumar1; Sven Brehmer1; Titus Jung2; Marc-Antoine Beauvais1; Hyunsoo Kim2; Chistopher Adams1; Dennis Trede1; John R. Yates, III2; Rohan Thakur1
Affiliations: 1Bruker Daltonik GmbH; 2Scripps Research, La Jolla, CA
Poster Views: 534
Abstract: We have recently integrated a de novo peptide sequencing tool, DeepNovo, into PaSER (Parallel Search Engine in Real-time) to sequence peptides in real-time by using deep learning and dynamic programming. To address the de novo peptide candidate ambiguity problem for a given spectrum, we have extended previously developed CCSaware search scoring function, TIMScore, to de novo search results.
Methods
We developed a CCS prediction module and integrated it into the PaSER platform to dynamically generate predicted ion mobility values on the fly for de novo search. Similar to how TIMScore has been used for the database search, the search engine feeds the top five peptide candidates for each spectrum to the CCS prediction model to generate ion mobility values. Then, PaSER calculates TIMScore for each candidate. The program evaluates the ambiguity of the peptide candidates and applies TIMScore to attempt to clarify true peptide candidates.Summary: We have recently integrated a de novo peptide sequencing tool, DeepNovo, into PaSER (Parallel Search Engine in Real-time) to sequence peptides in real-time by using deep learning and dynamic programming. To address the de novo peptide candidate ambiguity problem for a given spectrum, we have extended previously developed CCSaware search scoring function, TIMScore, to de novo search results.
Methods
We developed a CCS prediction module and integrated it into the PaSER platform to dynamically generate predicted ion mobility values on the fly for de novo search. Similar to how TIMScore has been used for the database search, the search engine feeds the top five peptide candidates for each spectrum to the CCS prediction model to generate ion mobility values. Then, PaSER calculates TIMScore for each candidate. The program evaluates the ambiguity of the peptide candidates and applies TIMScore to attempt to clarify true peptide candidates.Summary: We have recently integrated a de novo peptide sequencing tool, DeepNovo, into PaSER (Parallel Search Engine in Real-time) to sequence peptides in real-time by using deep learning and dynamic programming. To address the de novo peptide candidate ambiguity problem for a given spectrum, we have extended previously developed CCSaware search scoring function, TIMScore, to de novo search results.
Ask the author a question about this poster.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Related Posters
Targeted and Discovery Proteomics
Creative Proteomics
Characteristics of ITRAQ, TMT, and SILAC
Creative Proteomics
Three Methods for Protein Sequencing
Creative Proteomics
Abstract 23: Precision medicine approaches to Fanconi anemia oral cancer personalized prevention and treatment
Daniel K. Swenson; Beverly R. Wuertz; Mustafa M. Ali; Gretchen M. Unger; Frank G. Ondrey
Method of Host Cell Protein Analysis
Creative Proteomics