A comparison of univariate and multivariate gene selection techniques for classification of cancer datasets

Background  

Gene selection is an important step when building predictors of disease state based on gene expression data. Gene selection generally improves performance and identifies a relevant subset of genes. Many univariate and multivariate gene selection approaches have been proposed. Frequently the claim is made that genes are co-regulated (due to pathway dependencies) and that multivariate approaches are therefore per definition more desirable than univariate selection approaches. Based on the published performances of all these approaches a fair comparison of the available results can not be made. This mainly stems from two factors. First, the results are often biased, since the validation set is in one way or another involved in training the predictor, resulting in optimistically biased performance estimates. Second, the published results are often based on a small number of relatively simple datasets. Consequently no generally applicable conclusions can be drawn.     

Using mobility data in the design of optimal lockdown strategies for the COVID-19 pandemic

A mathematical model for the COVID-19 pandemic spread, which integrates age-structured Susceptible-Exposed-Infected-Recovered-Deceased dynamics with real mobile phone data accounting for the population mobility, is presented. The dynamical model adjustment is performed via Approximate Bayesian Computation. Optimal lockdown and exit strategies are determined based on nonlinear model predictive control, constrained to public-health and socio-economic factors. Through an extensive computational validation of the methodology, it is shown that it is possible to compute robust exit strategies with realistic reduced mobility values to inform public policy making, and we exemplify the applicability of the methodology using datasets from England and France.     

An evaluation protocol for subtype-specific breast cancer event prediction

In recent years increasing evidence appeared that breast cancer may not constitute a single disease at the molecular level, but comprises a heterogeneous set of subtypes. This suggests that instead of building a single monolithic predictor, better predictors might be constructed that solely target samples of a designated subtype, which are believed to represent more homogeneous sets of samples. An unavoidable drawback of developing subtype-specific predictors, however, is that a stratification by subtype drastically reduces the number of samples available for their construction. As numerous studies have indicated sample size to be an important factor in predictor construction, it is therefore questionable whether the potential benefit of subtyping can outweigh the drawback of a severe loss in sample size. Factors like unequal class distributions and differences in the number of samples per subtype, further complicate comparisons. We present a novel experimental protocol that facilitates a comprehensive comparison between subtype-specific predictors and predictors that do not take subtype information into account. Emphasis lies on careful control of sample size as well as class and subtype distributions. The methodology is applied to a large breast cancer compendium involving over 1500 arrays, using a state-of-the-art subtyping scheme. We show that the resulting subtype-specific predictors outperform those that do not take subtype information into account, especially when taking sample size considerations into account.     

Improving the Spatial Prediction of Soil Organic Carbon Stocks in a Complex Tropical Mountain Landscape by Methodological Specifications in Machine Learning Approaches

Tropical forests are significant carbon sinks and their soils’ carbon storage potential is immense. However, little is known about the soil organic carbon (SOC) stocks of tropical mountain areas whose complex soil-landscape and difficult accessibility pose a challenge to spatial analysis. The choice of methodology for spatial prediction is of high importance to improve the expected poor model results in case of low predictor-response correlations. Four aspects were considered to improve model performance in predicting SOC stocks of the organic layer of a tropical mountain forest landscape: Different spatial predictor settings, predictor selection strategies, various machine learning algorithms and model tuning. Five machine learning algorithms: random forests, artificial neural networks, multivariate adaptive regression splines, boosted regression trees and support vector machines were trained and tuned to predict SOC stocks from predictors derived from a digital elevation model and satellite image. Topographical predictors were calculated with a GIS search radius of 45 to 615 m. Finally, three predictor selection strategies were applied to the total set of 236 predictors. All machine learning algorithms—including the model tuning and predictor selection—were compared via five repetitions of a tenfold cross-validation. The boosted regression tree algorithm resulted in the overall best model. SOC stocks ranged between 0.2 to 17.7 kg m^-2, displaying a huge variability with diffuse insolation and curvatures of different scale guiding the spatial pattern. Predictor selection and model tuning improved the models’ predictive performance in all five machine learning algorithms. The rather low number of selected predictors favours forward compared to backward selection procedures. Choosing predictors due to their indiviual performance was vanquished by the two procedures which accounted for predictor interaction.     

An efficient hybridized genetic algorithm architecture for the flexible job shop scheduling problem

The work presented in this paper proposes hybridized genetic algorithm architecture for the Flexible Job Shop Scheduling Problem (FJSP). The efficiency of the genetic algorithm is enhanced by integrating it with an initial population generation algorithm and a local search method. The usefulness of the proposed methodology is illustrated with the aid of an extensive computational study on 184 benchmark problems with the objective of minimizing the makespan. Results highlight the ability of the proposed algorithm to first obtain optimal or near-optimal solutions, and second to outperform or produce comparable results with these obtained by other best-known approaches in literature.     

Integration of multi-objective PSO based feature selection and node centrality for medical datasets

In the past decades, the rapid growth of computer and database technologies has led to the rapid growth of large-scale medical datasets. On the other, medical applications with high dimensional datasets that require high speed and accuracy are rapidly increasing. One of the dimensionality reduction approaches is feature selection that can increase the accuracy of the disease diagnosis and reduce its computational complexity. In this paper, a novel PSO-based multi objective feature selection method is proposed. The proposed method consists of three main phases. In the first phase, the original features are showed as a graph representation model. In the next phase, feature centralities for all nodes in the graph are calculated, and finally, in the third phase, an improved PSO-based search process is utilized to final feature selection. The results on five medical datasets indicate that the proposed method improves previous related methods in terms of efficiency and effectiveness.     

Simple and robust methods for remote sensing of canopy chlorophyll content: a comparative analysis of hyperspectral data for different types of vegetation

Canopy chlorophyll content (CCC) is an essential ecophysiological variable for photosynthetic functioning. Remote sensing of CCC is vital for a wide range of ecological and agricultural applications. The objectives of this study were to explore simple and robust algorithms for spectral assessment of CCC. Hyperspectral datasets for six vegetation types (rice, wheat, corn, soybean, sugar beet and natural grass) acquired in four locations (Japan, France, Italy and USA) were analysed. To explore the best predictive model, spectral index approaches using the entire wavebands and multivariable regression approaches were employed. The comprehensive analysis elucidated the accuracy, linearity, sensitivity and applicability of various spectral models. Multivariable regression models using many wavebands proved inferior in applicability to different datasets. A simple model using the ratio spectral index (RSI; R815, R704) with the reflectance at 815 and 704 nm showed the highest accuracy and applicability. Simulation analysis using a physically based reflectance model suggested the biophysical soundness of the results. The model would work as a robust algorithm for canopy‐chlorophyll‐metre and/or remote sensing of CCC in ecosystem and regional scales. The predictive‐ability maps using hyperspectral data allow not only evaluation of the relative significance of wavebands in various sensors but also selection of the optimal wavelengths and effective bandwidths.     

MSLoc-DT: A new method for predicting the protein subcellular location of multispecies based on decision templates

Revealing the subcellular location of newly discovered protein sequences can bring insight to their function and guide research at the cellular level. The rapidly increasing number of sequences entering the genome databanks has called for the development of automated analysis methods. Currently, most existing methods used to predict protein subcellular locations cover only one, or a very limited number of species. Therefore, it is necessary to develop reliable and effective computational approaches to further improve the performance of protein subcellular prediction and, at the same time, cover more species. The current study reports the development of a novel predictor called MSLoc-DT to predict the protein subcellular locations of human, animal, plant, bacteria, virus, fungi, and archaea by introducing a novel feature extraction approach termed Amino Acid Index Distribution (AAID) and then fusing gene ontology information, sequential evolutionary information, and sequence statistical information through four different modes of pseudo amino acid composition (PseAAC) with a decision template rule. Using the jackknife test, MSLoc-DT can achieve 86.5, 98.3, 90.3, 98.5, 95.9, 98.1, and 99.3% overall accuracy for human, animal, plant, bacteria, virus, fungi, and archaea, respectively, on seven stringent benchmark datasets. Compared with other predictors (e.g., Gpos-PLoc, Gneg-PLoc, Virus-PLoc, Plant-PLoc, Plant-mPLoc, ProLoc-Go, Hum-PLoc, GOASVM) on the gram-positive, gram-negative, virus, plant, eukaryotic, and human datasets, the new MSLoc-DT predictor is much more effective and robust. Although the MSLoc-DT predictor is designed to predict the single location of proteins, our method can be extended to multiple locations of proteins by introducing multilabel machine learning approaches, such as the support vector machine and deep learning, as substitutes for the K-nearest neighbor (KNN) method. As a user-friendly web server, MSLoc-DT is freely accessible at http://bioinfo.ibp.ac.cn/MSLOC_DT/index.html.     

Dynamic clinical prediction models for discrete time‐to‐event data with competing risks—A case study on the OUTCOMEREA database

The development of clinical prediction models requires the selection of suitable predictor variables. Techniques to perform objective Bayesian variable selection in the linear model are well developed and have been extended to the generalized linear model setting as well as to the Cox proportional hazards model. Here, we consider discrete time‐to‐event data with competing risks and propose methodology to develop a clinical prediction model for the daily risk of acquiring a ventilator‐associated pneumonia (VAP) attributed to P. aeruginosa (PA) in intensive care units. The competing events for a PA VAP are extubation, death, and VAP due to other bacteria. Baseline variables are potentially important to predict the outcome at the start of ventilation, but may lose some of their predictive power after a certain time. Therefore, we use a landmark approach for dynamic Bayesian variable selection where the set of relevant predictors depends on the time already spent at risk. We finally determine the direct impact of a variable on each competing event through cause‐specific variable selection.     

hCKSAAP_UbSite: Improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties

As one of the most common post-translational modifications, ubiquitination regulates the quantity and function of a variety of proteins. Experimental and clinical investigations have also suggested the crucial roles of ubiquitination in several human diseases. The complicated sequence context of human ubiquitination sites revealed by proteomic studies highlights the need of developing effective computational strategies to predict human ubiquitination sites. Here we report the establishment of a novel human-specific ubiquitination site predictor through the integration of multiple complementary classifiers. Firstly, a Support Vector Machine (SVM) classier was constructed based on the composition of k-spaced amino acid pairs (CKSAAP) encoding, which has been utilized in our previous yeast ubiquitination site predictor. To further exploit the pattern and properties of the ubiquitination sites and their flanking residues, three additional SVM classifiers were constructed using the binary amino acid encoding, the AAindex physicochemical property encoding and the protein aggregation propensity encoding, respectively. Through an integration that relied on logistic regression, the resulting predictor termed hCKSAAP_UbSite achieved an area under ROC curve (AUC) of 0.770 in 5-fold cross-validation test on a class-balanced training dataset. When tested on a class-balanced independent testing dataset that contains 3419 ubiquitination sites, hCKSAAP_UbSite has also achieved a robust performance with an AUC of 0.757. Specifically, it has consistently performed better than the predictor using the CKSAAP encoding alone and two other publicly available predictors which are not human-specific. Given its promising performance in our large-scale datasets, hCKSAAP_UbSite has been made publicly available at our server (http://protein.cau.edu.cn/cksaap_ubsite/).     

Protein-RNA interface residue prediction using machine learning: an assessment of the state of the art

ABSTRACT: BACKGROUND: RNA molecules play diverse functional and structural roles in cells. They function as messengers for transferring genetic information from DNA to proteins, as the primary genetic material in many viruses, as catalysts (ribozymes) important for protein synthesis and RNA processing, and as essential and ubiquitous regulators of gene expression in living organisms. Many of these functions depend on precisely orchestrated interactions between RNA molecules and specific proteins in cells. Understanding the molecular mechanisms by which proteins recognize and bind RNA is essential for comprehending the functional implications of these interactions, but the recognition 'code' that mediates interactions between proteins and RNA is not yet understood. Success in deciphering this code would dramatically impact the development of new therapeutic strategies for intervening in devastating diseases such as AIDS and cancer. Because of the high cost of experimental determination of protein-RNA interfaces, there is an increasing reliance on statistical machine learning methods for training predictors of RNA-binding residues in proteins. However, because of differences in the choice of datasets, performance measures, and data representations used, it has been difficult to obtain an accurate assessment of the current state of the art in protein-RNA interface prediction. RESULTS: We provide a review of published approaches for predicting RNA-binding residues in proteins and a systematic comparison and critical assessment of protein-RNA interface residue predictors trained using these approaches on three carefully curated non-redundant datasets. We directly compare two widely used machine learning algorithms (Naive Bayes (NB) and Support Vector Machine (SVM)) using three different data representations in which features are encoded using either sequence- or structure-based windows. Our results show that (i) Sequence-based classifiers that use a position-specific scoring matrix (PSSM)-based representation (PSSMSeq) outperform those that use an amino acid identity based representation (IDSeq) or a smoothed PSSM (SmoPSSMSeq); (ii) Structure-based classifiers that use smoothed PSSM representation (SmoPSSMStr) outperform those that use PSSM (PSSMStr) as well as sequence identity based representation (IDStr). PSSMSeq classifiers, when tested on an independent test set of 44 proteins, achieve performance that is comparable to that of three state-of-the-art structure-based predictors (including those that exploit geometric features) in terms of Matthews Correlation Coefficient (MCC), although the structure-based methods achieve substantially higher Specificity (albeit at the expense of Sensitivity) compared to sequence-based methods. We also find that the expected performance of the classifiers on a residue level can be markedly different from that on a protein level. Our experiments show that the classifiers trained on three different non-redundant protein-RNA interface datasets achieve comparable cross-validation performance. However, we find that the results are significantly affected by differences in the distance threshold used to define interface residues. CONCLUSIONS: Our results demonstrate that protein-RNA interface residue predictors that use a PSSM-based encoding of sequence windows outperform classifiers that use other encodings of sequence windows. While structure-based methods that exploit geometric features can yield significant increases in the Specificity of protein-RNA interface residue predictions, such increases are offset by decreases in Sensitivity. These results underscore the importance of comparing alternative methods using rigorous statistical procedures, multiple performance measures, and datasets that are constructed based on several alternative definitions of interface residues and redundancy cutoffs as well as including evaluations on independent test sets into the comparisons.     

Modelling habitat selection of the cryptic Hazel Grouse Bonasa bonasia in a montane forest

The Hazel Grouse Bonasa bonasia is strongly affected by forest dynamics, and populations in many areas within Europe are declining. As a result of the ‘wilding’ concept implemented in the National Park Bavarian Forest, this area is one of the refuges for the species in Germany. Even though the effects of prevailing processes make the situation there particularly interesting, no recent investigation about habitat selection in the rapidly changing environment of the national park has been undertaken. We modelled the species–habitat relationship to derive the important habitat features in the national park as well as factors and critical threshold for monitoring, and to evaluate the predictive power of models based on field surveys compared to an analysis of infrared aerial photographs. We conducted our surveys on 49 plots of 25 ha each where Hazel Grouse was recorded and on an equally sized set of plots with no grouse occurrence, and used this dataset to build a predictive habitat-suitability model using logistic regression with backward stepwise variable selection. Habitat heterogeneity, stand structure, presence of mountain ash and willow, root plates, forest aisles, and young broadleaf stands proved to be predictive habitat variables. After internal validation via bootstrapping, our model shows an AUC value of 0.91 and a correct classification rate of 87%. Considering the methodological difficulties attached to backward selection, we applied Bayesian model averaging as an alternative. This multi-model approach also yielded similar results. To derive simple thresholds for important predictors as a basis for management decisions, we alternatively ran tree-based modelling, which also leads to a very similar selection of predictors. Performance of our different survey approaches was assessed by comparing two independent models with a model including both data resources: one constructed only from field survey data, the other based on data derived from aerial photographs. Models based on field data seem to perform slightly better than those based on aerial photography, but models using both predictor datasets provided the highest predictive accuracy.     

Developing seed zones and transfer guidelines with multivariate regression trees

Managing seed movement is an important component of forest resource management to minimize maladaptation of planting stock in forest plantations. Here, we describe a new approach to analyze geographic patterns of adaptive and neutral genetic variation in forest trees and to link this genetic information to geographic variables for the delineation of seed zones and the development of seed transfer guidelines. We apply multivariate regression trees to partition genetic variation, using a set of environmental or geographic predictor variables as partitioning criteria in a series of dichotomous splits of the genetic dataset. The method can be applied to any type of genetic data (growth, adaptive, or marker traits) and can simultaneously evaluate multiple traits observed over several environments. The predictor variables can be categorical (e.g., ecosystem of seed source), continuous (e.g., geographic or climate variables), or a combination of both. Different sets of predictor variables can be used for different purposes: In two case studies for aspen and red alder, we show (1) how latitude, longitude, and elevation of seed sources in a provenance trial can be used to develop simple seed transfer guidelines; (2) how ecosystem classes and elevation as predictor variables can be used to delineate seed zones and breeding regions; and (3) how climate variables as predictors can reveal adaptation of genotypes to the environments in which they occur. Partitioning of genetic variation appears very robust regarding the choice of predictor variables, and we find that the method is a powerful aid for interpreting complex genetic datasets.     

The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures

Biomarker discovery from high-dimensional data is a crucial problem with enormous applications in biology and medicine. It is also extremely challenging from a statistical viewpoint, but surprisingly few studies have investigated the relative strengths and weaknesses of the plethora of existing feature selection methods. In this study we compare 32 feature selection methods on 4 public gene expression datasets for breast cancer prognosis, in terms of predictive performance, stability and functional interpretability of the signatures they produce. We observe that the feature selection method has a significant influence on the accuracy, stability and interpretability of signatures. Surprisingly, complex wrapper and embedded methods generally do not outperform simple univariate feature selection methods, and ensemble feature selection has generally no positive effect. Overall a simple Student's t-test seems to provide the best results.     

MEM-FET: Essential protein prediction using membership feature and machine learning approach

Proteins are played key roles in different functionalities in our daily life. All functional roles of a protein are a bit enhanced in interaction compared to individuals. Identification of essential proteins of an organism is a time consume and costly task during observation in the wet lab. The results of observation in wet lab always ensure high reliability and accuracy in the biological ground. Essential protein prediction using computational approaches is an alternative choice in research. It proves its significance rapidly in day-to-day life as well as reduces the experimental cost of wet lab effectively. Existing computational methods were implemented using Protein interaction networks (PPIN), Sequence, Gene Expression Dataset (GED), Gene Ontology (GO), Orthologous groups, and Subcellular localized datasets. Machine learning has diverse categories of features that enable to model and predict essential macromolecules of understudied organisms. A novel methodology MEM-FET (membership feature) is predicted based on features, that is, edge clustering coefficient, Average clustering coefficient, subcellular localization, and Gene Ontology within a compartment of common neighbors. The accuracy (ACC) values of the predicted true positive (TP) essential proteins are 0.79, 0.74, 0.78, and 0.71 for YHQ, YMIPS, YDIP, and YMBD datasets. An enriched set of essential proteins are also predicted using the MEM-FET algorithm. Ensemble ML also validated the proposed model with an accuracy of 60%. It has been predicted that MEM-FET algorithms outperform other existing algorithms with an ACC value of 80% for the yeast dataset.     

Gene selection using support vector machines with non-convex penalty

MOTIVATION: With the development of DNA microarray technology, scientists can now measure the expression levels of thousands of genes simultaneously in one single experiment. One current difficulty in interpreting microarray data comes from their innate nature of 'high-dimensional low sample size'. Therefore, robust and accurate gene selection methods are required to identify differentially expressed group of genes across different samples, e.g. between cancerous and normal cells. Successful gene selection will help to classify different cancer types, lead to a better understanding of genetic signatures in cancers and improve treatment strategies. Although gene selection and cancer classification are two closely related problems, most existing approaches handle them separately by selecting genes prior to classification. We provide a unified procedure for simultaneous gene selection and cancer classification, achieving high accuracy in both aspects. RESULTS: In this paper we develop a novel type of regularization in support vector machines (SVMs) to identify important genes for cancer classification. A special nonconvex penalty, called the smoothly clipped absolute deviation penalty, is imposed on the hinge loss function in the SVM. By systematically thresholding small estimates to zeros, the new procedure eliminates redundant genes automatically and yields a compact and accurate classifier. A successive quadratic algorithm is proposed to convert the non-differentiable and non-convex optimization problem into easily solved linear equation systems. The method is applied to two real datasets and has produced very promising results. AVAILABILITY: MATLAB codes are available upon request from the authors.     

HiTRACE: high-throughput robust analysis for capillary electrophoresis

MOTIVATION: Capillary electrophoresis (CE) of nucleic acids is a workhorse technology underlying high-throughput genome analysis and large-scale chemical mapping for nucleic acid structural inference. Despite the wide availability of CE-based instruments, there remain challenges in leveraging their full power for quantitative analysis of RNA and DNA structure, thermodynamics and kinetics. In particular, the slow rate and poor automation of available analysis tools have bottlenecked a new generation of studies involving hundreds of CE profiles per experiment. RESULTS: We propose a computational method called high-throughput robust analysis for capillary electrophoresis (HiTRACE) to automate the key tasks in large-scale nucleic acid CE analysis, including the profile alignment that has heretofore been a rate-limiting step in the highest throughput experiments. We illustrate the application of HiTRACE on 13 datasets representing 4 different RNAs, 3 chemical modification strategies and up to 480 single mutant variants; the largest datasets each include 87 360 bands. By applying a series of robust dynamic programming algorithms, HiTRACE outperforms prior tools in terms of alignment and fitting quality, as assessed by measures including the correlation between quantified band intensities between replicate datasets. Furthermore, while the smallest of these datasets required 7-10 h of manual intervention using prior approaches, HiTRACE quantitation of even the largest datasets herein was achieved in 3-12 min. The HiTRACE method, therefore, resolves a critical barrier to the efficient and accurate analysis of nucleic acid structure in experiments involving tens of thousands of electrophoretic bands.