@article {Mallikarjun295527, author = {Venkatesh Mallikarjun and Stephen M. Richardson and Joe Swift}, title = {BayesENproteomics: Bayesian elastic nets for quantification of proteoforms in complex samples}, elocation-id = {295527}, year = {2019}, doi = {10.1101/295527}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Multivariate regression modelling provides a statistically powerful means of quantifying the effects of a given treatment while compensating for sources of variation and noise, such as variability between human donors and the behaviour of different peptides during mass spectrometry. However, methods to quantify endogenous post-translational modifications (PTMs) are typically reliant on summary statistical methods that fail to consider sources of variability such as changes in levels of the parent protein. Here, we compare three multivariate regression methods, including a novel Bayesian elastic net algorithm (BayesENproteomics) that enables assessment of relative protein abundances while also quantifying identified PTMs for each protein. We tested the ability of these methods to accurately quantify expression of proteins in a mixed-species benchmark experiment, and to quantify synthetic PTMs induced by stable isotope labelling. Finally, we extended our regression pipeline to calculate fold changes at the pathway level, providing a complement to commonly used enrichment analysis. Our results show that BayesENproteomics can quantify changes to protein levels across a broad dynamic range while also accurately quantifying PTM and pathway-level fold changes. Raw data has been deposited to the ProteomeXchange with identifiers PXD012784, PXD012782 and PXD012772. BayesENproteomics is available for Matlab: www.github.com/VenkMallikarjun/BayesENproteomics and Python3: www.github.com/VenkMallikarjun/BENPPy}, URL = {https://www.biorxiv.org/content/early/2019/05/03/295527}, eprint = {https://www.biorxiv.org/content/early/2019/05/03/295527.full.pdf}, journal = {bioRxiv} }