Reverse vaccinology (RV) is a bioinformatics approach that can predict antigens with protective potential from the protein coding genomes of bacterial pathogens for subunit vaccine design. RV has become firmly established following the development of the BEXSERO® vaccine against Neisseria meningitidis serogroup B. RV studies have begun to incorporate machine learning (ML) techniques to distinguish bacterial protective antigens (BPAs) from non-BPAs. This research contributes significantly to the RV field by using permutation analysis to demonstrate that a signal for protective antigens can be curated from published data. Furthermore, the effects of the following on an ML approach to RV were also assessed: nested cross-validation, balancing selection of non-BPAs for subcellular localization, increasing the training data, and incorporating greater numbers of protein annotation tools for feature generation. These enhancements yielded a support vector machine (SVM) classifier that could discriminate BPAs (n = 200) from non-BPAs (n = 200) with an area under the curve (AUC) of 0.787. In addition, hierarchical clustering of BPAs revealed that intracellular BPAs clustered separately from extracellular BPAs. However, no immediate benefit was derived when training SVM classifiers on data sets exclusively containing intra- or extracellular BPAs. In conclusion, this work demonstrates that ML classifiers have great utility in RV approaches and will lead to new subunit vaccines in the future.
Motivation: Despite much dynamical cellular behaviour being achieved by accurate regulation of protein concentrations, messenger RNA abundances, measured by microarray technology, and more recently by deep sequencing techniques, are widely used as proxies for protein measurements. Although for some species and under some conditions, there is good correlation between transcriptome and proteome level measurements, such correlation is by no means universal due to post-transcriptional and post-translational regulation, both of which are highly prevalent in cells. Here, we seek to develop a data-driven machine learning approach to bridging the gap between these two levels of high-throughput omic measurements on Saccharomyces cerevisiae and deploy the model in a novel way to uncover mRNA-protein pairs that are candidates for post-translational regulation. Results: The application of feature selection by sparsity inducing regression (l1 norm regularization) leads to a stable set of features: i.e. mRNA, ribosomal occupancy, ribosome density, tRNA adaptation index and codon bias while achieving a feature reduction from 37 to 5. A linear predictor used with these features is capable of predicting protein concentrations fairly accurately ( ). Proteins whose concentration cannot be predicted accurately, taken as outliers with respect to the predictor, are shown to have annotation evidence of post-translational modification, significantly more than random subsets of similar size . In a data mining sense, this work also shows a wider point that outliers with respect to a learning method can carry meaningful information about a problem domain. Contact: mn@ecs.soton.ac.uk
Background: It is estimated that up to 50% of all disease causing variants disrupt splicing. Due to its complexity, our ability to predict which variants disrupt splicing is limited, meaning missed diagnoses for patients. The emergence of machine learning for targeted medicine holds great potential to improve prediction of splice disrupting variants. The recently published SpliceAI algorithm utilises deep neural networks and has been reported to have a greater accuracy than other commonly used methods. Methods and findings: The original SpliceAI was trained on splice sites included in primary isoforms combined with novel junctions observed in GTEx data, which might introduce noise and de-correlate the machine learning input with its output. Limiting the data to only validated and manual annotated primary and alternatively spliced GENCODE sites in training may improve predictive abilities. All of these gene isoforms were collapsed (aggregated into one pseudo-isoform) and the SpliceAI architecture was retrained (CI-SpliceAI). Predictive performance on a newly curated dataset of 1,316 functionally validated variants from the literature was compared with the original SpliceAI, alongside MMSplice, MaxEntScan, and SQUIRLS. Both SpliceAI algorithms outperformed the other methods, with the original SpliceAI achieving an accuracy of ∼91%, and CI-SpliceAI showing an improvement at ∼92% overall. Predictive accuracy increased in the majority of curated variants. Conclusions: We show that including only manually annotated alternatively spliced sites in training data improves prediction of clinically relevant variants, and highlight avenues for further performance improvements.
18 September 2009 in IEEE Transactions on Signal Processing
This paper derives the asymptotic analytical forms of the mean and variance of the Gini correlation (GC) with respect to samples drawn from bivariate normal populations. The asymptotic relative efficiency (ARE) of the Gini correlation to Pearson's product moment correlation coefficient (PPMCC) is investigated under the normal assumptions. To gain further insight into GC, we also compare the Gini correlation to other two closely related correlation coefficients, namely, the order statistics correlation coefficient (OSCC) and Spearman's rho (SR). Theoretical and simulation results suggest that the performance of GC lies in between those of OSCC and SR when estimating the correlation coefficient of the bivariate normal population. The newly found theoretical results along with other desirable properties enable GC to be a useful alternative to the existing coefficients, especially when one wants to make a trade-off between the efficiency and robustness to monotone nonlinearity.
Nonnegative matrix factorization (NMF) is primarily a linear dimensionality reduction technique that factorizes a nonnegative data matrix into two smaller nonnegative matrices: one that represents the basis of the new subspace and the second that holds the coefficients of all the data points in that new space. In principle, the nonnegativity constraint forces the representation to be sparse and parts based. Instead of extracting holistic features from the data, real parts are extracted that should be significantly easier to interpret and analyze. The size of the new subspace selects how many features will be extracted from the data. An effective choice should minimize the noise while extracting the key features. We propose a mechanism for selecting the subspace size by using a minimum description length technique. We demonstrate that our technique provides plausible estimates for real data as well as accurately predicting the known size of synthetic data. We provide an implementation of our code in a Matlab format.
About Me
{Mahesan Niranjan} received the B.Sc. degree from the University of Peradeniya, Sri Lanka, in 1982, the M.E.E. degree from Eindhoven University of Technology, The Netherlands, in 1985, both in electronic engineering, and the Ph.D. degree from the University of Cambridge, Cambridge,
UK in 1990. He is currently a Professor of Electronics and Computer Science at the University
of Southampton, Southampton, UK, where he was Head of the Information: Signals, Images and Systems (ISIS) research group. Prior to this
appointment in February 2008, he has held a professorship in the University of Sheffield (1999–2008) and a lectureship in the University
of Cambridge (1990–1998). At the University of Sheffield, he served as Head of Computer Science (2002–2004) and Dean of the Faculty of
Engineering (2006–2008). His research interests are in the algorithmic and applied aspects of machine learning, and he has authored or coauthored about 100 papers in peer reviewed journals and conferences. He has been Program Chair of several international workshops and has acted as a co-organizer of a six-month program on neural networks and machine learning at the Isaac Newton Institute for Mathematical Sciences, Cambridge, UK. His current research has a strong focus on computational biology and biomedical signal processing.
{Mahesan Niranjan} received the B.Sc. degree from the University of Peradeniya, Sri Lanka, in 1982, the M.E.E. degree from Eindhoven University of Technology, The Netherlands, in 1985, both in electronic engineering, and the Ph.D. degree from the University of Cambridge, Cambridge,
UK in 1990. He is currently a Professor of Electronics and Computer Science at the University
of Southampton, Southampton, UK, where he was Head of the Information: Signals, Images and Systems (ISIS) research group. Prior to this
appointment in February 2008, he has held a professorship in the University of Sheffield (1999–2008) and a lectureship in the University
of Cambridge (1990–1998). At the University of Sheffield, he served as Head of Computer Science (2002–2004) and Dean of the Faculty of
Engineering (2006–2008). His research interests are in the algorithmic and applied aspects of machine learning, and he has authored or coauthored about 100 papers in peer reviewed journals and conferences. He has been Program Chair of several international workshops and has acted as a co-organizer of a six-month program on neural networks and machine learning at the Isaac Newton Institute for Mathematical Sciences, Cambridge, UK. His current research has a strong focus on computational biology and biomedical signal processing.