24th International Mass Spectrometry Conference (IMSC)
August 27 – September 2, 2022
At this year's IMSC, MSAID will present the intelligent search algorithm CHIMERYS and AI-driven applications for proteomics
OUR POSTER PRESENTATIONS AT IMSC
-
Poster IM-PA-020: An end-to-end machine learning workflow for MS-based proteomics
Poster Session A – Monday 29th and Tuesday 30th August 2022
In proteomics, machine learning augments various steps in the data analysis, from predicting peptide properties that serve as priors for experimental data, to training target/decoy classifiers for error estimation. How a model is integrated into production systems determines its requirements. However, generating, evaluating and integrating such models remains manual labor. Here we present a workflow that automates all steps from raw data to production-ready model. First, it imports identified spectra and transforms them to training datasets for various peptide properties. Second, a set of model architectures are trained, evaluated, and their hyperparameters optimized. Hyperparameter optimization automatically balances conflicting requirements such as speed and accuracy and is use-case specific. Third, the models are optimized and exported for different deployment scenarios.
-
Poster IM-PA-019: A unifying, spectrum-centric approach for the analysis of peptide tandem mass spectra
Poster Session A – Monday 29th and Tuesday 30th August 2022
Mass spectrometry-based proteomics data is acquired using data dependent (DDA), data independent (DIA) or targeted acquisition (PRM) methods. Typically, the former is analyzed using spectrum-centric algorithms assuming that it generates non-chimeric spectra, while the latter two are analyzed in a peptide-centric fashion. However, peptide-centric approaches often struggle to control for the contribution of multiple peptides to the experimental fragment ion intensity. Recently, we showed that DDA, and by extension PRM, spectra can be substantially chimeric and introduced an approach that deconvolutes spectra irrespective of isolation window size, thereby substantially boosting the number of identified peptides for DDA. Here, we demonstrate that the same approach generalizes to any chimeric MS2 spectrum, unifying the analysis of DDA, DIA and PRM data.
