Resampling-based similarity measures for high-dimensional data

Derivation and validation of different machine-learning models in mortality prediction of trauma in motorcycle riders: a cross-sectional retrospective study in southern Taiwan

OBJECTIVES

This study aimed to build and test the models of machine learning (ML) to predict the mortality of hospitalised motorcycle riders.

SETTING

The study was conducted in a level-1 trauma centre in southern Taiwan.

PARTICIPANTS

Motorcycle riders who were hospitalised between January 2009 and December 2015 were classified into a training set (n=6306) and test set (n=946). Using the demographic information, injury characteristics and laboratory data of patients, logistic regression (LR), support vector machine (SVM) and decision tree (DT) analyses were performed to determine the mortality of individual motorcycle riders, under different conditions, using all samples or reduced samples, as well as all variables or selected features in the algorithm.

PRIMARY AND SECONDARY OUTCOME MEASURES

The predictive performance of the model was evaluated based on accuracy, sensitivity, specificity and geometric mean, and an analysis of the area under the receiver operating characteristic curves of the two different models was carried out.

RESULTS

In the training set, both LR and SVM had a significantly higher area under the receiver operating characteristic curve (AUC) than DT. No significant difference was observed in the AUC of LR and SVM, regardless of whether all samples or reduced samples and whether all variables or selected features were used. In the test set, the performance of the SVM model for all samples with selected features was better than that of all other models, with an accuracy of 98.73%, sensitivity of 86.96%, specificity of 99.02%, geometric mean of 92.79% and AUC of 0.9517, in mortality prediction.

CONCLUSION

ML can provide a feasible level of accuracy in predicting the mortality of motorcycle riders. Integration of the ML model, particularly the SVM algorithm in the trauma system, may help identify high-risk patients and, therefore, guide appropriate interventions by the clinical staff.

Spatiotemporal multistage consensus clustering in molecular dynamics studies of large proteins

The aim of this work is to find semi-rigid domains within large proteins as reference structures for fitting molecular dynamics trajectories. We propose an algorithm, multistage consensus clustering, MCC, based on minimum variation of distances between pairs of Cα-atoms as target function. The whole dataset (trajectory) is split into sub-segments. For a given sub-segment, spatial clustering is repeatedly started from different random seeds, and we adopt the specific spatial clustering with minimum target function: the process described so far is stage 1 of MCC. Then, in stage 2, the results of spatial clustering are consolidated, to arrive at domains stable over the whole dataset. We found that MCC is robust regarding the choice of parameters and yields relevant information on functional domains of the major histocompatibility complex (MHC) studied in this paper: the α-helices and β-floor of the protein (MHC) proved to be most flexible and did not contribute to clusters of significant size. Three alleles of the MHC, each in complex with ABCD3 peptide and LC13 T-cell receptor (TCR), yielded different patterns of motion. Those alleles causing immunological allo-reactions showed distinct correlations of motion between parts of the peptide, the binding cleft and the complementary determining regions (CDR)-loops of the TCR. Multistage consensus clustering reflected functional differences between MHC alleles and yields a methodological basis to increase sensitivity of functional analyses of bio-molecules. Due to the generality of approach, MCC is prone to lend itself as a potent tool also for the analysis of other kinds of big data.

Avoiding common pitfalls when clustering biological data

Clustering is an unsupervised learning method, which groups data points based on similarity, and is used to reveal the underlying structure of data. This computational approach is essential to understanding and visualizing the complex data that are acquired in high-throughput multidimensional biological experiments. Clustering enables researchers to make biological inferences for further experiments. Although a powerful technique, inappropriate application can lead biological researchers to waste resources and time in experimental follow-up. We review common pitfalls identified from the published molecular biology literature and present methods to avoid them. Commonly encountered pitfalls relate to the high-dimensional nature of biological data from high-throughput experiments, the failure to consider more than one clustering method for a given problem, and the difficulty in determining whether clustering has produced meaningful results. We present concrete examples of problems and solutions (clustering results) in the form of toy problems and real biological data for these issues. We also discuss ensemble clustering as an easy-to-implement method that enables the exploration of multiple clustering solutions and improves robustness of clustering solutions. Increased awareness of common clustering pitfalls will help researchers avoid overinterpreting or misinterpreting the results and missing valuable insights when clustering biological data.

Providing data science support for systems pharmacology and its implications to drug discovery

INTRODUCTION

The conventional one-drug-one-target-one-disease drug discovery process has been less successful in tracking multi-genic, multi-faceted complex diseases. Systems pharmacology has emerged as a new discipline to tackle the current challenges in drug discovery. The goal of systems pharmacology is to transform huge, heterogeneous, and dynamic biological and clinical data into interpretable and actionable mechanistic models for decision making in drug discovery and patient treatment. Thus, big data technology and data science will play an essential role in systems pharmacology.

AREAS COVERED

This paper critically reviews the impact of three fundamental concepts of data science on systems pharmacology: similarity inference, overfitting avoidance, and disentangling causality from correlation. The authors then discuss recent advances and future directions in applying the three concepts of data science to drug discovery, with a focus on proteome-wide context-specific quantitative drug target deconvolution and personalized adverse drug reaction prediction.

EXPERT OPINION

Data science will facilitate reducing the complexity of systems pharmacology modeling, detecting hidden correlations between complex data sets, and distinguishing causation from correlation. The power of data science can only be fully realized when integrated with mechanism-based multi-scale modeling that explicitly takes into account the hierarchical organization of biological systems from nucleic acid to proteins, to molecular interaction networks, to cells, to tissues, to patients, and to populations.