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

AbstractThe 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 first 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 insufficient 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 hyper LOPIT datasets validates its utility by recovering enrichment with chromatin-associated proteins without annotation and uncovers sub-nuclear compartmentalisation which was not identified in the original analysis. Moreover, using sub-cellular proteomics data from Saccharomyces cerevisiae, we uncover a novel group of proteins trafficking 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.

Download Full-text

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

PLoS Computational Biology ◽

10.1371/journal.pcbi.1008288 ◽

2020 ◽

Vol 16 (11) ◽

pp. e1008288 ◽

Cited By ~ 1

Author(s):

Oliver M. Crook ◽

Aikaterini Geladaki ◽

Daniel J. H. Nightingale ◽

Owen L. Vennard ◽

Kathryn S. Lilley ◽

...

Keyword(s):

Mass Spectrometry ◽

Bayesian Approach ◽

Novelty Detection ◽

Machine Learning Algorithms ◽

Proteomics Data ◽

Diverse Range ◽

Biologically Relevant ◽

Cellular Localisation ◽

Associated Proteins ◽

Experimental Protocols

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 first 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 insufficient 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 identified in the original analysis. Moreover, using sub-cellular proteomics data from Saccharomyces cerevisiae, we uncover a novel group of proteins trafficking 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.

Download Full-text

A Bioconductor workflow for processing and analysing spatial proteomics data

F1000Research ◽

10.12688/f1000research.10411.1 ◽

2016 ◽

Vol 5 ◽

pp. 2926 ◽

Cited By ~ 10

Author(s):

Lisa M. Breckels ◽

Claire M. Mulvey ◽

Kathryn S. Lilley ◽

Laurent Gatto

Keyword(s):

Novelty Detection ◽

Data Quality Control ◽

Proteomics Data ◽

Quantitative Mass Spectrometry ◽

Software Infrastructure ◽

Embryonic Mouse ◽

Processing Data ◽

Cellular Localisation ◽

Cellular Marker ◽

Proteomics Experiment

Spatial proteomics is the systematic study of protein sub-cellular localisation. In this workflow, we describe the analysis of a typical quantitative mass spectrometry-based spatial proteomics experiment using the MSnbase and pRoloc Bioconductor package suite. To walk the user through the computational pipeline, we use a recently published experiment predicting protein sub-cellular localisation in pluripotent embryonic mouse stem cells. We describe the software infrastructure at hand, importing and processing data, quality control, sub-cellular marker definition, visualisation and interactive exploration. We then demonstrate the application and interpretation of statistical learning methods, including novelty detection using semi-supervised learning, classification, clustering and transfer learning and conclude the pipeline with data export. The workflow is aimed at beginners who are familiar with proteomics in general and spatial proteomics in particular.

Download Full-text

PolySTest: Robust statistical testing of proteomics data with missing values improves detection of biologically relevant features

10.1101/765818 ◽

2019 ◽

Cited By ~ 1

Author(s):

Veit Schwämmle ◽

Christina E Hagensen ◽

Adelina Rogowska-Wrzesinska ◽

Ole N. Jensen

Keyword(s):

Mass Spectrometry ◽

Large Scale ◽

Missing Values ◽

Statistical Tests ◽

Ground Truth ◽

Statistical Testing ◽

Molecular Networks ◽

Proteomics Data ◽

Biologically Relevant ◽

Data Browsing

AbstractStatistical testing remains one of the main challenges for high-confidence detection of differentially regulated proteins or peptides in large-scale quantitative proteomics experiments by mass spectrometry. Statistical tests need to be sufficiently robust to deal with experiment intrinsic data structures and variations and often also reduced feature coverage across different biological samples due to ubiquitous missing values. A robust statistical test provides accurate confidence scores of large-scale proteomics results, regardless of instrument platform, experimental protocol and software tools. However, the multitude of different combinations of experimental strategies, mass spectrometry techniques and informatics methods complicate the decision of choosing appropriate statistical approaches. We address this challenge by introducing PolySTest, a user-friendly web service for statistical testing, data browsing and data visualization. We introduce a new method, Miss Test, that simultaneously tests for missingness and feature abundance, thereby complementing common statistical tests by rescuing otherwise discarded data features. We demonstrate that PolySTest with integrated Miss Test achieves higher confidence and higher sensitivity for artificial and experimental proteomics data sets with known ground truth. Application of PolySTest to mass spectrometry based large-scale proteomics data obtained from differentiating muscle cells resulted in the rescue of 10%-20% additional proteins in the identified molecular networks relevant to muscle differentiation. We conclude that PolySTest is a valuable addition to existing tools and instrument enhancements that improve coverage and depth of large-scale proteomics experiments. A fully functional demo version of PolySTest and Miss Test is available via http://computproteomics.bmb.sdu.dk/Apps/PolySTest.

Download Full-text

A Bioconductor workflow for processing and analysing spatial proteomics data

F1000Research ◽

10.12688/f1000research.10411.2 ◽

2018 ◽

Vol 5 ◽

pp. 2926 ◽

Cited By ~ 5

Author(s):

Lisa M. Breckels ◽

Claire M. Mulvey ◽

Kathryn S. Lilley ◽

Laurent Gatto

Keyword(s):

Novelty Detection ◽

Data Quality Control ◽

Proteomics Data ◽

Quantitative Mass Spectrometry ◽

Software Infrastructure ◽

Embryonic Mouse ◽

Link Type ◽

Cellular Localisation ◽

Cellular Marker ◽

Proteomics Experiment

Download Full-text

PolySTest: Robust Statistical Testing of Proteomics Data with Missing Values Improves Detection of Biologically Relevant Features

Molecular & Cellular Proteomics ◽

10.1074/mcp.ra119.001777 ◽

2020 ◽

Vol 19 (8) ◽

pp. 1396-1408 ◽

Cited By ~ 2

Author(s):

Veit Schwämmle ◽

Christina E. Hagensen ◽

Adelina Rogowska-Wrzesinska ◽

Ole N. Jensen

Keyword(s):

Mass Spectrometry ◽

Large Scale ◽

Missing Values ◽

Statistical Tests ◽

Ground Truth ◽

Statistical Testing ◽

Molecular Networks ◽

Proteomics Data ◽

Biologically Relevant ◽

Data Browsing

Statistical testing remains one of the main challenges for high-confidence detection of differentially regulated proteins or peptides in large-scale quantitative proteomics experiments by mass spectrometry. Statistical tests need to be sufficiently robust to deal with experiment intrinsic data structures and variations and often also reduced feature coverage across different biological samples due to ubiquitous missing values. A robust statistical test provides accurate confidence scores of large-scale proteomics results, regardless of instrument platform, experimental protocol and software tools. However, the multitude of different combinations of experimental strategies, mass spectrometry techniques and informatics methods complicate the decision of choosing appropriate statistical approaches. We address this challenge by introducing PolySTest, a user-friendly web service for statistical testing, data browsing and data visualization. We introduce a new method, Miss test, that simultaneously tests for missingness and feature abundance, thereby complementing common statistical tests by rescuing otherwise discarded data features. We demonstrate that PolySTest with integrated Miss test achieves higher confidence and higher sensitivity for artificial and experimental proteomics data sets with known ground truth. Application of PolySTest to mass spectrometry based large-scale proteomics data obtained from differentiating muscle cells resulted in the rescue of 10–20% additional proteins in the identified molecular networks relevant to muscle differentiation. We conclude that PolySTest is a valuable addition to existing tools and instrument enhancements that improve coverage and depth of large-scale proteomics experiments. A fully functional demo version of PolySTest and Miss test is available via http://computproteomics.bmb.sdu.dk/Apps/PolySTest.

Download Full-text

CHICKN: extraction of peptide chromatographic elution profiles from large scale mass spectrometry data by means of Wasserstein compressive hierarchical cluster analysis

BMC Bioinformatics ◽

10.1186/s12859-021-03969-0 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Olga Permiakova ◽

Romain Guibert ◽

Alexandra Kraut ◽

Thomas Fortin ◽

Anne-Marie Hesse ◽

...

Keyword(s):

Mass Spectrometry ◽

Large Scale ◽

Clustering Algorithm ◽

Optimal Transport ◽

State Of The Art ◽

Data Representation ◽

Machine Learning Algorithms ◽

Mass Spectrometry Data ◽

Proteomics Data ◽

Chromatographic Elution

Abstract Background The clustering of data produced by liquid chromatography coupled to mass spectrometry analyses (LC-MS data) has recently gained interest to extract meaningful chemical or biological patterns. However, recent instrumental pipelines deliver data which size, dimensionality and expected number of clusters are too large to be processed by classical machine learning algorithms, so that most of the state-of-the-art relies on single pass linkage-based algorithms. Results We propose a clustering algorithm that solves the powerful but computationally demanding kernel k-means objective function in a scalable way. As a result, it can process LC-MS data in an acceptable time on a multicore machine. To do so, we combine three essential features: a compressive data representation, Nyström approximation and a hierarchical strategy. In addition, we propose new kernels based on optimal transport, which interprets as intuitive similarity measures between chromatographic elution profiles. Conclusions Our method, referred to as CHICKN, is evaluated on proteomics data produced in our lab, as well as on benchmark data coming from the literature. From a computational viewpoint, it is particularly efficient on raw LC-MS data. From a data analysis viewpoint, it provides clusters which differ from those resulting from state-of-the-art methods, while achieving similar performances. This highlights the complementarity of differently principle algorithms to extract the best from complex LC-MS data.

Download Full-text

treeClust improves protein co-regulation analysis due to robust selectivity for close linear relationships

10.1101/578971 ◽

2019 ◽

Cited By ~ 1

Author(s):

Georg Kustatscher ◽

Piotr Grabowski ◽

Juri Rappsilber

Keyword(s):

Machine Learning ◽

Learning Algorithm ◽

Synthetic Data ◽

Transcriptome Profiling ◽

Machine Learning Algorithms ◽

Proteomics Data ◽

Unsupervised Machine Learning ◽

Biologically Relevant ◽

Linear Relationships ◽

Improved Performance

Gene co-expression analysis is a widespread method to identify the potential biological function of uncharacterised genes. Recent evidence suggests that proteome profiling may provide more accurate results than transcriptome profiling. However, it is unclear which statistical measure is best suited to detect proteins that are co-regulated. We have previously shown that expression similarities calculated using treeClust, an unsupervised machine-learning algorithm, outperformed correlation-based analysis of a large proteomics dataset. The reason for this improvement is unknown. Here we systematically explore the characteristics of treeClust similarities. Leveraging synthetic data, we find that tree-based similarities are exceptionally robust against outliers and detect only close-fitting, linear protein – protein associations. We then use proteomics data to demonstrate that both of these features contribute to the improved performance of treeClust relative to Pearson, Spearman and robust correlation. Our results suggest that, for large proteomics datasets, unsupervised machine-learning algorithms such as treeClust may significantly improve the detection of biologically relevant protein – protein associations relative to correlation metrics.

Download Full-text