Publications by authors named "Edmund H Wilkes"

9 Publications

  • Page 1 of 1

A Machine Learning Approach for the Automated Interpretation of Plasma Amino Acid Profiles.

Clin Chem 2020 09;66(9):1210-1218

Biochemical Sciences, Viapath, Guys & St Thomas' NHS Foundation Trust, London, UK.

Background: Plasma amino acid (PAA) profiles are used in routine clinical practice for the diagnosis and monitoring of inherited disorders of amino acid metabolism, organic acidemias, and urea cycle defects. Interpretation of PAA profiles is complex and requires substantial training and expertise to perform. Given previous demonstrations of the ability of machine learning (ML) algorithms to interpret complex clinical biochemistry data, we sought to determine if ML-derived classifiers could interpret PAA profiles with high predictive performance.

Methods: We collected PAA profiling data routinely performed within a clinical biochemistry laboratory (2084 profiles) and developed decision support classifiers with several ML algorithms. We tested the generalization performance of each classifier using a nested cross-validation (CV) procedure and examined the effect of various subsampling, feature selection, and ensemble learning strategies.

Results: The classifiers demonstrated excellent predictive performance, with the 3 ML algorithms tested producing comparable results. The best-performing ensemble binary classifier achieved a mean precision-recall (PR) AUC of 0.957 (95% CI 0.952, 0.962) and the best-performing ensemble multiclass classifier achieved a mean F4 score of 0.788 (0.773, 0.803).

Conclusions: This work builds upon previous demonstrations of the utility of ML-derived decision support tools in clinical biochemistry laboratories. Our findings suggest that, pending additional validation studies, such tools could potentially be used in routine clinical practice to streamline and aid the interpretation of PAA profiles. This would be particularly useful in laboratories with limited resources and large workloads. We provide the necessary code for other laboratories to develop their own decision support tools.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/clinchem/hvaa134DOI Listing
September 2020

Using Machine Learning to Aid the Interpretation of Urine Steroid Profiles.

Clin Chem 2018 11 10;64(11):1586-1595. Epub 2018 Aug 10.

Department of Clinical Biochemistry, University College London Hospitals, London, UK.

Background: Urine steroid profiles are used in clinical practice for the diagnosis and monitoring of disorders of steroidogenesis and adrenal pathologies. Machine learning (ML) algorithms are powerful computational tools used extensively for the recognition of patterns in large data sets. Here, we investigated the utility of various ML algorithms for the automated biochemical interpretation of urine steroid profiles to support current clinical practices.

Methods: Data from 4619 urine steroid profiles processed between June 2012 and October 2016 were retrospectively collected. Of these, 1314 profiles were used to train and test various ML classifiers' abilities to differentiate between "No significant abnormality" and "?Abnormal" profiles. Further classifiers were trained and tested for their ability to predict the specific biochemical interpretation of the profiles.

Results: The best performing binary classifier could predict the interpretation of No significant abnormality and ?Abnormal profiles with a mean area under the ROC curve of 0.955 (95% CI, 0.949-0.961). In addition, the best performing multiclass classifier could predict the individual abnormal profile interpretation with a mean balanced accuracy of 0.873 (0.865-0.880).

Conclusions: Here we have described the application of ML algorithms to the automated interpretation of urine steroid profiles. This provides a proof-of-concept application of ML algorithms to complex clinical laboratory data that has the potential to improve laboratory efficiency in a setting of limited staff resources.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1373/clinchem.2018.292201DOI Listing
November 2018

PHLDA1 Mediates Drug Resistance in Receptor Tyrosine Kinase-Driven Cancer.

Cell Rep 2018 02;22(9):2469-2481

Centre for Tumour Biology, Barts Cancer Institute-a CRUK Centre of Excellence, Queen Mary University of London, London EC1M 6BQ, UK. Electronic address:

Development of resistance causes failure of drugs targeting receptor tyrosine kinase (RTK) networks and represents a critical challenge for precision medicine. Here, we show that PHLDA1 downregulation is critical to acquisition and maintenance of drug resistance in RTK-driven cancer. Using fibroblast growth factor receptor (FGFR) inhibition in endometrial cancer cells, we identify an Akt-driven compensatory mechanism underpinned by downregulation of PHLDA1. We demonstrate broad clinical relevance of our findings, showing that PHLDA1 downregulation also occurs in response to RTK-targeted therapy in breast and renal cancer patients, as well as following trastuzumab treatment in HER2 breast cancer cells. Crucially, knockdown of PHLDA1 alone was sufficient to confer de novo resistance to RTK inhibitors and induction of PHLDA1 expression re-sensitized drug-resistant cancer cells to targeted therapies, identifying PHLDA1 as a biomarker for drug response and highlighting the potential of PHLDA1 reactivation as a means of circumventing drug resistance.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.celrep.2018.02.028DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5848852PMC
February 2018

Kinase activity ranking using phosphoproteomics data (KARP) quantifies the contribution of protein kinases to the regulation of cell viability.

Mol Cell Proteomics 2017 09 3;16(9):1694-1704. Epub 2017 Jul 3.

From the ‡Integrative Cell Signalling & Proteomics, Centre for Haemato-Oncology, Barts Cancer Institute, Queen Mary University of London, Charterhouse Square, London, EC1M 6BQ

Cell survival is regulated by a signaling network driven by the activity of protein kinases; however, determining the contribution that each kinase in the network makes to such regulation remains challenging. Here, we report a computational approach that uses mass spectrometry-based phosphoproteomics data to rank protein kinases based on their contribution to cell regulation. We found that the scores returned by this algorithm, which we have termed kinase activity ranking using phosphoproteomics data (KARP), were a quantitative measure of the contribution that individual kinases make to the signaling output. Application of KARP to the analysis of eight hematological cell lines revealed that cyclin-dependent kinase (CDK) 1/2, casein kinase (CK) 2, extracellular signal-related kinase (ERK), and p21-activated kinase (PAK) were the most frequently highly ranked kinases in these cell models. The patterns of kinase activation were cell-line specific yet showed a significant association with cell viability as a function of kinase inhibitor treatment. Thus, our study exemplifies KARP as an untargeted approach to empirically and systematically identify regulatory kinases within signaling networks.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1074/mcp.O116.064360DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5587867PMC
September 2017

A Strong B-cell Response Is Part of the Immune Landscape in Human High-Grade Serous Ovarian Metastases.

Clin Cancer Res 2017 Jan 27;23(1):250-262. Epub 2016 Jun 27.

Barts Cancer Institute, Queen Mary University of London, London, UK.

Purpose: In high-grade serous ovarian cancer (HGSOC), higher densities of both B cells and the CD8 T-cell infiltrate were associated with a better prognosis. However, the precise role of B cells in the antitumor response remains unknown. As peritoneal metastases are often responsible for relapse, our aim was to characterize the role of B cells in the antitumor immune response in HGSOC metastases.

Experimental Design: Unmatched pre and post-chemotherapy HGSOC metastases were studied. B-cell localization was assessed by immunostaining. Their cytokines and chemokines were measured by a multiplex assay, and their phenotype was assessed by flow cytometry. Further in vitro and in vivo assays highlighted the role of B cells and plasma cell IgGs in the development of cytotoxic responses and dendritic cell activation.

Results: B cells mainly infiltrated lymphoid structures in the stroma of HGSOC metastases. There was a strong B-cell memory response directed at a restricted repertoire of antigens and production of tumor-specific IgGs by plasma cells. These responses were enhanced by chemotherapy. Interestingly, transcript levels of CD20 correlated with markers of immune cytolytic responses and immune complexes with tumor-derived IgGs stimulated the expression of the costimulatory molecule CD86 on antigen-presenting cells. A positive role for B cells in the antitumor response was also supported by B-cell depletion in a syngeneic mouse model of peritoneal metastasis.

Conclusions: Our data showed that B cells infiltrating HGSOC omental metastases support the development of an antitumor response. Clin Cancer Res; 23(1); 250-62. ©2016 AACR.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1158/1078-0432.CCR-16-0081DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5928522PMC
January 2017

Large-scale models of signal propagation in human cells derived from discovery phosphoproteomic data.

Nat Commun 2015 Sep 10;6:8033. Epub 2015 Sep 10.

European Molecular Biology Laboratory-European Bioinformatics Institute (EMBL-EBI), Wellcome Trust Genome Campus, Hinxton, Cambridge CB10 1SD, UK.

Mass spectrometry is widely used to probe the proteome and its modifications in an untargeted manner, with unrivalled coverage. Applied to phosphoproteomics, it has tremendous potential to interrogate phospho-signalling and its therapeutic implications. However, this task is complicated by issues of undersampling of the phosphoproteome and challenges stemming from its high-content but low-sample-throughput nature. Hence, methods using such data to reconstruct signalling networks have been limited to restricted data sets and insights (for example, groups of kinases likely to be active in a sample). We propose a new method to handle high-content discovery phosphoproteomics data on perturbation by putting it in the context of kinase/phosphatase-substrate knowledge, from which we derive and train logic models. We show, on a data set obtained through perturbations of cancer cells with small-molecule inhibitors, that this method can study the targets and effects of kinase inhibitors, and reconcile insights obtained from multiple data sets, a common issue with these data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/ncomms9033DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4579397PMC
September 2015

Empirical inference of circuitry and plasticity in a kinase signaling network.

Proc Natl Acad Sci U S A 2015 Jun 9;112(25):7719-24. Epub 2015 Jun 9.

Centre for Haemato-Oncology, Barts Cancer Institute, Queen Mary University of London, London EC1M 6BQ, United Kingdom;

Our understanding of physiology and disease is hampered by the difficulty of measuring the circuitry and plasticity of signaling networks that regulate cell biology, and how these relate to phenotypes. Here, using mass spectrometry-based phosphoproteomics, we systematically characterized the topology of a network comprising the PI3K/Akt/mTOR and MEK/ERK signaling axes and confirmed its biological relevance by assessing its dynamics upon EGF and IGF1 stimulation. Measuring the activity of this network in models of acquired drug resistance revealed that cells chronically treated with PI3K or mTORC1/2 inhibitors differed in the way their networks were remodeled. Unexpectedly, we also observed a degree of heterogeneity in the network state between cells resistant to the same inhibitor, indicating that even identical and carefully controlled experimental conditions can give rise to the evolution of distinct kinase network statuses. These data suggest that the initial conditions of the system do not necessarily determine the mechanism by which cancer cells become resistant to PI3K/mTOR targeted therapies. The patterns of signaling network activity observed in the resistant cells mirrored the patterns of response to several drug combination treatments, suggesting that the activity of the defined signaling network truly reflected the evolved phenotypic diversity.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1073/pnas.1423344112DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4485132PMC
June 2015

Approaches for measuring signalling plasticity in the context of resistance to targeted cancer therapies.

Biochem Soc Trans 2014 Aug;42(4):791-7

*Integrative Cell Signalling and Proteomics, Centre for Haemato-Oncology, Barts Cancer Institute, Queen Mary University of London, London EC1M 6BQ, U.K.

The ability of cells in multicellular organisms to respond to signals in their environment is critical for their survival, development and differentiation. Once differentiated and occupying their functional niche, cells need to maintain phenotypic stability while responding to diverse extracellular perturbations and environmental signals (such as nutrients, temperature, cytokines and hormones) in a co-ordinated manner. To achieve these requirements, cells have evolved numerous intracellular signalling mechanisms that confer on them the ability to resist, respond and adapt to external changes. Although fundamental to normal biological processes, as is evident from their evolutionary conservation, such mechanisms also allow cancer cells to evade targeted therapies, a problem of immediate clinical importance. In the present article, we discuss the role of signalling plasticity in the context of the mechanisms underlying both intrinsic and acquired resistance to targeted cancer therapies. We then examine the emerging analytical techniques and theoretical paradigms that are contributing to a greater understanding of signalling on a global and untargeted scale. We conclude with a discussion on how integrative approaches to the study of cell signalling have been used, and could be used in the future, to advance our understanding of resistance mechanisms to therapies that target the kinase signalling network.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1042/BST20140029DOI Listing
August 2014
-->