Fast and interpretable genomic data analysis using multiple approximate kernel learning.
Ontology highlight
ABSTRACT: Motivation
Dataset sizes in computational biology have been increased drastically with the help of improved data collection tools and increasing size of patient cohorts. Previous kernel-based machine learning algorithms proposed for increased interpretability started to fail with large sample sizes, owing to their lack of scalability. To overcome this problem, we proposed a fast and efficient multiple kernel learning (MKL) algorithm to be particularly used with large-scale data that integrates kernel approximation and group Lasso formulations into a conjoint model. Our method extracts significant and meaningful information from the genomic data while conjointly learning a model for out-of-sample prediction. It is scalable with increasing sample size by approximating instead of calculating distinct kernel matrices.Results
To test our computational framework, namely, Multiple Approximate Kernel Learning (MAKL), we demonstrated our experiments on three cancer datasets and showed that MAKL is capable to outperform the baseline algorithm while using only a small fraction of the input features. We also reported selection frequencies of approximated kernel matrices associated with feature subsets (i.e. gene sets/pathways), which helps to see their relevance for the given classification task. Our fast and interpretable MKL algorithm producing sparse solutions is promising for computational biology applications considering its scalability and highly correlated structure of genomic datasets, and it can be used to discover new biomarkers and new therapeutic guidelines.Availability and implementation
MAKL is available at https://github.com/begumbektas/makl together with the scripts that replicate the reported experiments. MAKL is also available as an R package at https://cran.r-project.org/web/packages/MAKL.Supplementary information
Supplementary data are available at Bioinformatics online.
SUBMITTER: Bektas AB
PROVIDER: S-EPMC9235505 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundAdvances in medical technology have allowed for customized prognosis, diagnosis, and treatment regimens that utilize multiple heterogeneous data sources. Multiple kernel learning (MKL) is well suited for the integration of multiple high throughput data sources. MKL remains to be under-utilized by genomic researchers partly due to the lack of unified guidelines for its use, and benchmark genomic datasets.ResultsWe provide three implementations of MKL in R. These methods are applied to simulated data to illustrate that MKL can select appropriate models. We also apply MKL to combine clinical information with miRNA gene expression data of ovarian cancer study into a single analysis. Lastly, we show that MKL can identify gene sets that are known to play a role in the prognostic prediction of 15 cancer types using gene expression data from The Cancer Genome Atlas, as well as, identify new gene sets for the future research.ConclusionMultiple kernel learning coupled with modern optimization techniques provides a promising learning tool for building predictive models based on multi-source genomic data. MKL also provides an automated scheme for kernel prioritization and parameter tuning. The methods used in the paper are implemented as an R package called RMKL package, which is freely available for download through CRAN at https://CRAN.R-project.org/package=RMKL .
| S-EPMC6694479 | biostudies-literature
Project description:It is very significant to explore the intrinsic differences in breast cancer subtypes. These intrinsic differences are closely related to clinical diagnosis and designation of treatment plans. With the accumulation of biological and medicine datasets, there are many different omics data that can be viewed in different aspects. Combining these multiple omics data can improve the accuracy of prediction. Meanwhile; there are also many different databases available for us to download different types of omics data. In this article, we use estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2) to define breast cancer subtypes and classify any two breast cancer subtypes using SMO-MKL algorithm. We collected mRNA data, methylation data and copy number variation (CNV) data from TCGA to classify breast cancer subtypes. Multiple Kernel Learning (MKL) is employed to use these omics data distinctly. The result of using three omics data with multiple kernels is better than that of using single omics data with multiple kernels. Furthermore; these significant genes and pathways discovered in the feature selection process are also analyzed. In experiments; the proposed method outperforms other state-of-the-art methods and has abundant biological interpretations.
| S-EPMC6471546 | biostudies-literature
Project description:BACKGROUND:Agglomerative hierarchical clustering (AHC) is a common unsupervised data analysis technique used in several biological applications. Standard AHC methods require that all pairwise distances between data objects must be known. With ever-increasing data sizes this quadratic complexity poses problems that cannot be overcome by simply waiting for faster computers. RESULTS:We propose an approximate AHC algorithm HappieClust which can output a biologically meaningful clustering of a large dataset more than an order of magnitude faster than full AHC algorithms. The key to the algorithm is to limit the number of calculated pairwise distances to a carefully chosen subset of all possible distances. We choose distances using a similarity heuristic based on a small set of pivot objects. The heuristic efficiently finds pairs of similar objects and these help to mimic the greedy choices of full AHC. Quality of approximate AHC as compared to full AHC is studied with three measures. The first measure evaluates the global quality of the achieved clustering, while the second compares biological relevance using enrichment of biological functions in every subtree of the clusterings. The third measure studies how well the contents of subtrees are conserved between the clusterings. CONCLUSION:The HappieClust algorithm is well suited for large-scale gene expression visualization and analysis both on personal computers as well as public online web applications. The software is available from the URL http://www.quretec.com/HappieClust.
| S-EPMC2561018 | biostudies-literature
Project description:BACKGROUND: This paper introduces the notion of optimizing different norms in the dual problem of support vector machines with multiple kernels. The selection of norms yields different extensions of multiple kernel learning (MKL) such as L(infinity), L1, and L2 MKL. In particular, L2 MKL is a novel method that leads to non-sparse optimal kernel coefficients, which is different from the sparse kernel coefficients optimized by the existing L(infinity) MKL method. In real biomedical applications, L2 MKL may have more advantages over sparse integration method for thoroughly combining complementary information in heterogeneous data sources. RESULTS: We provide a theoretical analysis of the relationship between the L2 optimization of kernels in the dual problem with the L2 coefficient regularization in the primal problem. Understanding the dual L2 problem grants a unified view on MKL and enables us to extend the L2 method to a wide range of machine learning problems. We implement L2 MKL for ranking and classification problems and compare its performance with the sparse L(infinity) and the averaging L1 MKL methods. The experiments are carried out on six real biomedical data sets and two large scale UCI data sets. L2 MKL yields better performance on most of the benchmark data sets. In particular, we propose a novel L2 MKL least squares support vector machine (LSSVM) algorithm, which is shown to be an efficient and promising classifier for large scale data sets processing. CONCLUSIONS: This paper extends the statistical framework of genomic data fusion based on MKL. Allowing non-sparse weights on the data sources is an attractive option in settings where we believe most data sources to be relevant to the problem at hand and want to avoid a "winner-takes-all" effect seen in L(infinity) MKL, which can be detrimental to the performance in prospective studies. The notion of optimizing L2 kernels can be straightforwardly extended to ranking, classification, regression, and clustering algorithms. To tackle the computational burden of MKL, this paper proposes several novel LSSVM based MKL algorithms. Systematic comparison on real data sets shows that LSSVM MKL has comparable performance as the conventional SVM MKL algorithms. Moreover, large scale numerical experiments indicate that when cast as semi-infinite programming, LSSVM MKL can be solved more efficiently than SVM MKL. AVAILABILITY: The MATLAB code of algorithms implemented in this paper is downloadable from http://homes.esat.kuleuven.be/~sistawww/bioi/syu/l2lssvm.html.
| S-EPMC2906488 | biostudies-literature
Project description:Reliable identification of molecular biomarkers is essential for accurate patient stratification. While state-of-the-art machine learning approaches for sample classification continue to push boundaries in terms of performance, most of these methods are not able to integrate different data types and lack generalization power, limiting their application in a clinical setting. Furthermore, many methods behave as black boxes, and we have very little understanding about the mechanisms that lead to the prediction. While opaqueness concerning machine behavior might not be a problem in deterministic domains, in health care, providing explanations about the molecular factors and phenotypes that are driving the classification is crucial to build trust in the performance of the predictive system. We propose Pathway-Induced Multiple Kernel Learning (PIMKL), a methodology to reliably classify samples that can also help gain insights into the molecular mechanisms that underlie the classification. PIMKL exploits prior knowledge in the form of a molecular interaction network and annotated gene sets, by optimizing a mixture of pathway-induced kernels using a Multiple Kernel Learning (MKL) algorithm, an approach that has demonstrated excellent performance in different machine learning applications. After optimizing the combination of kernels to predict a specific phenotype, the model provides a stable molecular signature that can be interpreted in the light of the ingested prior knowledge and that can be used in transfer learning tasks.
| S-EPMC6401099 | biostudies-literature
Project description:Predicting disease risk and progression is one of the main goals in many clinical research studies. Cohort studies on the natural history and etiology of chronic diseases span years and data are collected at multiple visits. Although, kernel-based statistical learning methods are proven to be powerful for a wide range of disease prediction problems, these methods are only well studied for independent data, but not for longitudinal data. It is thus important to develop time-sensitive prediction rules that make use of the longitudinal nature of the data. In this paper, we develop a novel statistical learning method for longitudinal data by introducing subject-specific short-term and long-term latent effects through a designed kernel to account for within-subject correlation of longitudinal measurements. Since the presence of multiple sources of data is increasingly common, we embed our method in a multiple kernel learning framework and propose a regularized multiple kernel statistical learning with random effects to construct effective nonparametric prediction rules. Our method allows easy integration of various heterogeneous data sources and takes advantage of correlation among longitudinal measures to increase prediction power. We use different kernels for each data source taking advantage of the distinctive feature of each data modality, and then optimally combine data across modalities. We apply the developed methods to two large epidemiological studies, one on Huntington's disease and the other on Alzheimer's Disease (Alzheimer's Disease Neuroimaging Initiative, ADNI) where we explore a unique opportunity to combine imaging and genetic data to study prediction of mild cognitive impairment, and show a substantial gain in performance while accounting for the longitudinal aspect of the data.
| S-EPMC4713389 | biostudies-literature
Project description:BackgroundIdentification of molecular mechanisms that determine tumour progression in cancer patients is a prerequisite for developing new disease treatment guidelines. Even though the predictive performance of current machine learning models is promising, extracting significant and meaningful knowledge from the data simultaneously during the learning process is a difficult task considering the high-dimensional and highly correlated nature of genomic datasets. Thus, there is a need for models that not only predict tumour volume from gene expression data of patients but also use prior information coming from pathway/gene sets during the learning process, to distinguish molecular mechanisms which play crucial role in tumour progression and therefore, disease prognosis.ResultsIn this study, instead of initially choosing several pathways/gene sets from an available set and training a model on this previously chosen subset of genomic features, we built a novel machine learning algorithm, PrognosiT, that accomplishes both tasks together. We tested our algorithm on thyroid carcinoma patients using gene expression profiles and cancer-specific pathways/gene sets. Predictive performance of our novel multiple kernel learning algorithm (PrognosiT) was comparable or even better than random forest (RF) and support vector regression (SVR). It is also notable that, to predict tumour volume, PrognosiT used gene expression features less than one-tenth of what RF and SVR algorithms used.ConclusionsPrognosiT was able to obtain comparable or even better predictive performance than SVR and RF. Moreover, we demonstrated that during the learning process, our algorithm managed to extract relevant and meaningful pathway/gene sets information related to the studied cancer type, which provides insights about its progression and aggressiveness. We also compared gene expressions of the selected genes by our algorithm in tumour and normal tissues, and we then discussed up- and down-regulated genes selected by our algorithm while learning, which could be beneficial for determining new biomarkers.
| S-EPMC8561914 | biostudies-literature
Project description:Background: Assessment of cerebral aneurysm rupture risk is an important task, but it remains challenging. Recent works applying machine learning to rupture risk evaluation presented positive results. Yet they were based on limited aspects of data, and lack of interpretability may limit their use in clinical setting. We aimed to develop interpretable machine learning models on multidimensional data for aneurysm rupture risk assessment. Methods: Three hundred seventy-four aneurysms were included in the study. Demographic, medical history, lifestyle behaviors, lipid profile, and morphologies were collected for each patient. Prediction models were derived using machine learning methods (support vector machine, artificial neural network, and XGBoost) and conventional logistic regression. The derived models were compared with the PHASES score method. The Shapley Additive Explanations (SHAP) analysis was applied to improve the interpretability of the best machine learning model and reveal the reasoning behind the predictions made by the model. Results: The best machine learning model (XGBoost) achieved an area under the receiver operating characteristic curve of 0.882 [95% confidence interval (CI) = 0.838-0.927], significantly better than the logistic regression model (0.779; 95% CI = 0.729-0.829; P = 0.002) and the PHASES score method (0.758; 95% CI = 0.713-0.800; P = 0.001). Location, size ratio, and triglyceride level were the three most important features in predicting rupture. Two typical cases were analyzed to demonstrate the interpretability of the model. Conclusions: This study demonstrated the potential of using machine learning for aneurysm rupture risk assessment. Machine learning models performed better than conventional statistical model and the PHASES score method. The SHAP analysis can improve the interpretability of machine learning models and facilitate their use in a clinical setting.
| S-EPMC7785850 | biostudies-literature
Project description:BackgroundThe Approximate Bayesian Computation (ABC) approach has been used to infer demographic parameters for numerous species, including humans. However, most applications of ABC still use limited amounts of data, from a small number of loci, compared to the large amount of genome-wide population-genetic data which have become available in the last few years.ResultsWe evaluated the performance of the ABC approach for three 'population divergence' models - similar to the 'isolation with migration' model - when the data consists of several hundred thousand SNPs typed for multiple individuals by simulating data from known demographic models. The ABC approach was used to infer demographic parameters of interest and we compared the inferred values to the true parameter values that was used to generate hypothetical "observed" data. For all three case models, the ABC approach inferred most demographic parameters quite well with narrow credible intervals, for example, population divergence times and past population sizes, but some parameters were more difficult to infer, such as population sizes at present and migration rates. We compared the ability of different summary statistics to infer demographic parameters, including haplotype and LD based statistics, and found that the accuracy of the parameter estimates can be improved by combining summary statistics that capture different parts of information in the data. Furthermore, our results suggest that poor choices of prior distributions can in some circumstances be detected using ABC. Finally, increasing the amount of data beyond some hundred loci will substantially improve the accuracy of many parameter estimates using ABC.ConclusionsWe conclude that the ABC approach can accommodate realistic genome-wide population genetic data, which may be difficult to analyze with full likelihood approaches, and that the ABC can provide accurate and precise inference of demographic parameters from these data, suggesting that the ABC approach will be a useful tool for analyzing large genome-wide datasets.
| S-EPMC3368717 | biostudies-literature
Project description:The emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8-15%. A lack of transparency of "black-box" deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.
| S-EPMC8275610 | biostudies-literature