Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach

Artificial intelligence and the hunt for immunological disorders

PURPOSE OF REVIEW

Artificial intelligence has pervasively transformed many industries and is beginning to shape medical practice. New use cases are being identified in subspecialty domains of medicine and, in particular, application of artificial intelligence has found its way to the practice of allergy-immunology. Here, we summarize recent developments, emerging applications and obstacles to realizing full potential.

RECENT FINDINGS

Artificial/augmented intelligence and machine learning are being used to reduce dimensional complexity, understand cellular interactions and advance vaccine work in the basic sciences. In genomics, bioinformatic methods are critical for variant calling and classification. For clinical work, artificial intelligence is enabling disease detection, risk profiling and decision support. These approaches are just beginning to have impact upon the field of clinical immunology and much opportunity exists for further advancement.

SUMMARY

This review highlights use of computational methods for analysis of large datasets across the spectrum of research and clinical care for patients with immunological disorders. Here, we discuss how big data methods are presently being used across the field clinical immunology.

Machine learning-based approaches for disease gene prediction

Disease gene prediction is an essential issue in biomedical research. In the early days, annotation-based approaches were proposed for this problem. With the development of high-throughput technologies, interaction data between genes/proteins have grown quickly and covered almost genome and proteome; thus, network-based methods for the problem become prominent. In parallel, machine learning techniques, which formulate the problem as a classification, have also been proposed. Here, we firstly show a roadmap of the machine learning-based methods for the disease gene prediction. In the beginning, the problem was usually approached using a binary classification, where positive and negative training sample sets are comprised of disease genes and non-disease genes, respectively. The disease genes are ones known to be associated with diseases; meanwhile, non-disease genes were randomly selected from those not yet known to be associated with diseases. However, the later may contain unknown disease genes. To overcome this uncertainty of defining the non-disease genes, more realistic approaches have been proposed for the problem, such as unary and semi-supervised classification. Recently, more advanced methods, including ensemble learning, matrix factorization and deep learning, have been proposed for the problem. Secondly, 12 representative machine learning-based methods for the disease gene prediction were examined and compared in terms of prediction performance and running time. Finally, their advantages, disadvantages, interpretability and trust were also analyzed and discussed.

Simulation of the Dynamics of Primary Immunodeficiencies in B Cells

Primary immunodeficiencies (PIDs) are a group of over 300 hereditary, heterogeneous, and mainly rare disorders that affect the immune system. Various aspects of immune system and PID proteins and genes have been investigated and facilitate systems biological studies of effects of PIDs on B cell physiology and response. We reconstructed a B cell network model based on data for the core B cell receptor activation and response processes and performed semi-quantitative dynamic simulations for normal and B cell PID failure modes. The results for several knockout simulations correspond to previously reported molecular studies and reveal novel mechanisms for PIDs. The simulations for CD21, CD40, LYN, MS4A1, ORAI1, PLCG2, PTPRC, and STIM1 indicated profound changes to major transcription factor signaling and to the network. Significant effects were observed also in the BCL10, BLNK, BTK, loss-of-function CARD11, IKKB, MALT1, and NEMO, simulations whereas only minor effects were detected for PIDs that are caused by constitutively active proteins (PI3K, gain-of-function CARD11, KRAS, and NFKBIA). This study revealed the underlying dynamics of PID diseases, confirms previous observations, and identifies novel candidates for PID diagnostics and therapy.

Tuning of in vivo cognate B-T cell interactions by Intersectin 2 is required for effective anti-viral B cell immunity

Wiskott-Aldrich syndrome (WAS) is an immune pathology associated with mutations in WAS protein (WASp) or in WASp interacting protein (WIP). Together with the small GTPase Cdc42 and other effectors, these proteins participate in the remodelling of the actin network downstream of BCR engagement. Here we show that mice lacking the adaptor protein ITSN2, a G-nucleotide exchange factor (GEF) for Cdc42 that also interacts with WASp and WIP, exhibited increased mortality during primary infection, incomplete protection after Flu vaccination, reduced germinal centre formation and impaired antibody responses to vaccination. These defects were found, at least in part, to be intrinsic to the B cell compartment. In vivo, ITSN2 deficient B cells show a reduction in the expression of SLAM, CD84 or ICOSL that correlates with a diminished ability to form long term conjugates with T cells, to proliferate in vivo, and to differentiate into germinal centre cells. In conclusion, our study not only revealed a key role for ITSN2 as an important regulator of adaptive immune-response during vaccination and viral infection but it is also likely to contribute to a better understanding of human immune pathologies.

Simulation of the dynamics of primary immunodeficiencies in CD4+ T-cells

Primary immunodeficiencies (PIDs) form a large and heterogeneous group of mainly rare disorders that affect the immune system. T-cell deficiencies account for about one-tenth of PIDs, most of them being monogenic. Apart from genetic and clinical information, lots of other data are available for PID proteins and genes, including functions and interactions. Thus, it is possible to perform systems biology studies on the effects of PIDs on T-cell physiology and response. To achieve this, we reconstructed a T-cell network model based on literature mining and TPPIN, a previously published core T-cell network, and performed semi-quantitative dynamic network simulations on both normal and T-cell PID failure modes. The results for several loss-of-function PID simulations correspond to results of previously reported molecular studies. The simulations for TCR PTPRC, LCK, ZAP70 and ITK indicate profound changes to numerous proteins in the network. Significant effects were observed also in the BCL10, CARD11, MALT1, NEMO, IKKB and MAP3K14 simulations. No major effects were observed for PIDs that are caused by constitutively active proteins. The T-cell model facilitates the understanding of the underlying dynamics of PID disease processes. The approach confirms previous knowledge about T-cell signaling network and indicates several new important proteins that may be of interest when developing novel diagnosis and therapies to treat immunological defects.

New KEGG pathway-based interpretable features for classifying ageing-related mouse proteins

MOTIVATION

The incidence of ageing-related diseases has been constantly increasing in the last decades, raising the need for creating effective methods to analyze ageing-related protein data. These methods should have high predictive accuracy and be easily interpretable by ageing experts. To enable this, one needs interpretable classification models (supervised machine learning) and features with rich biological meaning. In this paper we propose two interpretable feature types based on Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways and compare them with traditional feature types in hierarchical classification (a more challenging classification task regarding predictive performance) and binary classification (a classification task producing easier to interpret classification models). As far as we know, this work is the first to: (i) explore the potential of the KEGG pathway data in the hierarchical classification setting, (i) use the graph structure of KEGG pathways to create a feature type that quantifies the influence of a current protein on another specific protein within a KEGG pathway graph and (iii) propose a method for interpreting the classification models induced using KEGG features.

RESULTS

We performed tests measuring predictive accuracy considering hierarchical and binary class labels extracted from the Mouse Phenotype Ontology. One of the KEGG feature types leads to the highest predictive accuracy among five individual feature types across three hierarchical classification algorithms. Additionally, the combination of the two KEGG feature types proposed in this work results in one of the best predictive accuracies when using the binary class version of our datasets, at the same time enabling the extraction of knowledge from ageing-related data using quantitative influence information.

AVAILABILITY AND IMPLEMENTATION

The datasets created in this paper will be freely available after publication.

CONTACT

ff79@kent.ac.uk

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Proteomics research in India: an update

After a successful completion of the Human Genome Project, deciphering the mystery surrounding the human proteome posed a major challenge. Despite not being largely involved in the Human Genome Project, the Indian scientific community contributed towards proteomic research along with the global community. Currently, more than 76 research/academic institutes and nearly 145 research labs are involved in core proteomic research across India. The Indian researchers have been major contributors in drafting the "human proteome map" along with international efforts. In addition to this, virtual proteomics labs, proteomics courses and remote triggered proteomics labs have helped to overcome the limitations of proteomics education posed due to expensive lab infrastructure. The establishment of Proteomics Society, India (PSI) has created a platform for the Indian proteomic researchers to share ideas, research collaborations and conduct annual conferences and workshops. Indian proteomic research is really moving forward with the global proteomics community in a quest to solve the mysteries of proteomics. A draft map of the human proteome enhances the enthusiasm among intellectuals to promote proteomic research in India to the world.This article is part of a Special Issue entitled: Proteomics in India.

Computational approaches to disease-gene prediction: rationale, classification and successes

The identification of genes involved in human hereditary diseases often requires the time-consuming and expensive examination of a great number of possible candidate genes, since genome-wide techniques such as linkage analysis and association studies frequently select many hundreds of 'positional' candidates. Even considering the positive impact of next-generation sequencing technologies, the prioritization of candidate genes may be an important step for disease-gene identification. In this paper we develop a basic classification scheme for computational approaches to disease-gene prediction and apply it to exhaustively review bioinformatics tools that have been developed for this purpose, focusing on conceptual aspects rather than technical detail and performance. Finally, we discuss some past successes obtained by computational approaches to illustrate their beneficial contribution to medical research.

Human protein reference database and human proteinpedia as discovery resources for molecular biotechnology

In the recent years, research in molecular biotechnology has transformed from being small scale studies targeted at a single or a small set of molecule(s) into a combination of high throughput discovery platforms and extensive validations. Such a discovery platform provided an unbiased approach which resulted in the identification of several novel genetic and protein biomarkers. High throughput nature of these investigations coupled with higher sensitivity and specificity of Next Generation technologies provided qualitatively and quantitatively richer biological data. These developments have also revolutionized biological research and speed of data generation. However, it is becoming difficult for individual investigators to directly benefit from this data because they are not easily accessible. Data resources became necessary to assimilate, store and disseminate information that could allow future discoveries. We have developed two resources--Human Protein Reference Database (HPRD) and Human Proteinpedia, which integrate knowledge relevant to human proteins. A number of protein features including protein-protein interactions, post-translational modifications, subcellular localization, and tissue expression, which have been studied using different strategies were incorporated in these databases. Human Proteinpedia also provides a portal for community participation to annotate and share proteomic data and uses HPRD as the scaffold for data processing. Proteomic investigators can even share unpublished data in Human Proteinpedia, which provides a meaningful platform for data sharing. As proteomic information reflects a direct view of cellular systems, proteomics is expected to complement other areas of biology such as genomics, transcriptomics, molecular biology, cloning, and classical genetics in understanding the relationships among multiple facets of biological systems.

A computational approach to candidate gene prioritization for X-linked mental retardation using annotation-based binary filtering and motif-based linear discriminatory analysis

Background

Several computational candidate gene selection and prioritization methods have recently been developed. These in silico selection and prioritization techniques are usually based on two central approaches - the examination of similarities to known disease genes and/or the evaluation of functional annotation of genes. Each of these approaches has its own caveats. Here we employ a previously described method of candidate gene prioritization based mainly on gene annotation, in accompaniment with a technique based on the evaluation of pertinent sequence motifs or signatures, in an attempt to refine the gene prioritization approach. We apply this approach to X-linked mental retardation (XLMR), a group of heterogeneous disorders for which some of the underlying genetics is known.

Results

The gene annotation-based binary filtering method yielded a ranked list of putative XLMR candidate genes with good plausibility of being associated with the development of mental retardation. In parallel, a motif finding approach based on linear discriminatory analysis (LDA) was employed to identify short sequence patterns that may discriminate XLMR from non-XLMR genes. High rates (>80%) of correct classification was achieved, suggesting that the identification of these motifs effectively captures genomic signals associated with XLMR vs. non-XLMR genes. The computational tools developed for the motif-based LDA is integrated into the freely available genomic analysis portal Galaxy (http://main.g2.bx.psu.edu/). Nine genes (APLN, ZC4H2, MAGED4, MAGED4B, RAP2C, FAM156A, FAM156B, TBL1X, and UXT) were highlighted as highly-ranked XLMR methods.

Conclusions

The combination of gene annotation information and sequence motif-orientated computational candidate gene prediction methods highlight an added benefit in generating a list of plausible candidate genes, as has been demonstrated for XLMR.

Reviewers: This article was reviewed by Dr Barbara Bardoni (nominated by Prof Juergen Brosius); Prof Neil Smalheiser and Dr Dustin Holloway (nominated by Prof Charles DeLisi).

svdPPCS: an effective singular value decomposition-based method for conserved and divergent co-expression gene module identification

Background

Comparative analysis of gene expression profiling of multiple biological categories, such as different species of organisms or different kinds of tissue, promises to enhance the fundamental understanding of the universality as well as the specialization of mechanisms and related biological themes. Grouping genes with a similar expression pattern or exhibiting co-expression together is a starting point in understanding and analyzing gene expression data. In recent literature, gene module level analysis is advocated in order to understand biological network design and system behaviors in disease and life processes; however, practical difficulties often lie in the implementation of existing methods.

Results

Using the singular value decomposition (SVD) technique, we developed a new computational tool, named svdPPCS (SVD-based Pattern Pairing and Chart Splitting), to identify conserved and divergent co-expression modules of two sets of microarray experiments. In the proposed methods, gene modules are identified by splitting the two-way chart coordinated with a pair of left singular vectors factorized from the gene expression matrices of the two biological categories. Importantly, the cutoffs are determined by a data-driven algorithm using the well-defined statistic, SVD-p. The implementation was illustrated on two time series microarray data sets generated from the samples of accessory gland (ACG) and malpighian tubule (MT) tissues of the line W¹¹⁸ of M. drosophila. Two conserved modules and six divergent modules, each of which has a unique characteristic profile across tissue kinds and aging processes, were identified. The number of genes contained in these models ranged from five to a few hundred. Three to over a hundred GO terms were over-represented in individual modules with FDR < 0.1. One divergent module suggested the tissue-specific relationship between the expressions of mitochondrion-related genes and the aging process. This finding, together with others, may be of biological significance. The validity of the proposed SVD-based method was further verified by a simulation study, as well as the comparisons with regression analysis and cubic spline regression analysis plus PAM based clustering.

Conclusions

svdPPCS is a novel computational tool for the comparative analysis of transcriptional profiling. It especially fits the comparison of time series data of related organisms or different tissues of the same organism under equivalent or similar experimental conditions. The general scheme can be directly extended to the comparisons of multiple data sets. It also can be applied to the integration of data sets from different platforms and of different sources.