A semi-supervised Bayesian approach for simultaneous protein sub-cellular localisation assignment and novelty detection

Abstract

The cell is compartmentalised into complex micro-environments allowing an array of specialised biological processes to be carried out in synchrony. Determining a protein's sub-cellular localisation to one or more of these compartments can therefore be a rst step in determining its function. High-throughput and high-accuracy mass spectrometry-based sub-cellular proteomic methods can now shed light on the localisation of thousands of proteins at once. Machine learning algorithms are then typically employed to make protein-organelle assignments. However, these algorithms are limited by insucient and incomplete annotation. We propose a semi-supervised Bayesian approach to novelty detection, allowing the discovery of additional, previously unannotated sub-cellular niches. Inference in our model is performed in a Bayesian framework, allowing us to quantify uncertainty in the allocation of proteins to new sub-cellular niches, as well as in the number of newly discovered compartments. We apply our approach across 10 mass spectrometry based spatial proteomic datasets, representing a diverse range of experimental protocols. Application of our approach to hyperLOPIT datasets validates its utility by recovering enrichment with chromatin-associated proteins without annotation and uncovers sub-nuclear compartmentalisation which was not identied in the original analysis. Moreover, using sub-cellular proteomics data from Saccharomyces cerevisiae, we uncover a novel group of proteins tracking from the ER to the early Golgi apparatus. Overall, we demonstrate the potential for novelty detection to yield biologically relevant niches that are missed by current approaches. * ksl23@cam.ac.uk

Spatial proteomics defines the content of trafficking vesicles captured by golgin tethers

“…1d) 25 . The latter takes into account the uncertainty that arises when classifying proteins that reside in multiple locations, or unknown functional compartments and also those that dynamically move within the cell, and so provides a richer overall analysis of spatial proteomics data [25][26][27][28] .…”

Moving Profiling Spatial Proteomics Beyond Discrete Classification

“…For example, Crook et al propose a semi-supervised Bayesian approach and uncover a novel group of Saccharomyces cerevisiae proteins trafficking from the ER to the early Golgi apparatus. [52] Additionally, differential localization could also be elucidated using joint models across conditions, with uncertainty quantification to assist in ranking candidates for future experimental investigation. Similarly, the relationship between post-translational modification and differential localization could be examined by comparing profiles for the modified and unmodified protein forms.…”

Spatiotemporal proteomic profiling of the pro-inflammatory response to lipopolysaccharide in the THP-1 human leukaemia cell line

“…Multivariate data analysis is conducted using the MS proteomics packages MSnbase 29 and pRoloc 30 , which provide a robust framework for processing, visualisation, and interrogation of spatial proteomics data as part of the open-source, open-development Bioconductor 31,32 suite of R software 33 . Additional modalities for phenotype discovery 34,35 , transfer learning from heterogeneous data sources 36 , assessment of cluster separation as a data resolution metric 37 and probabilistic classifiers such as Bayesian mixture modelling 38 have recently been integrated into the pRoloc pipeline.…”