A High-Performance Computing Implementation of Iterative Random Forest for the Creation of Predictive Expression Networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Cliff A
PROVIDER: S-EPMC6947651 | biostudies-literature | 2019 Dec
REPOSITORIES: biostudies-literature
Publications
A High-Performance Computing Implementation of Iterative Random Forest for the Creation of Predictive Expression Networks.
Cliff Ashley A Romero Jonathon J Kainer David D Walker Angelica A Furches Anna A Jacobson Daniel D
Genes 20191202 12
As time progresses and technology improves, biological data sets are continuously increasing in size. New methods and new implementations of existing methods are needed to keep pace with this increase. In this paper, we present a high-performance computing (HPC)-capable implementation of Iterative Random Forest (iRF). This new implementation enables the explainable-AI eQTL analysis of SNP sets with over a million SNPs. Using this implementation, we also present a new method, iRF Leave One Out Pr ...[more]
Similar Datasets
Project description:Genomics has revolutionized biology, enabling the interrogation of whole transcriptomes, genome-wide binding sites for proteins, and many other molecular processes. However, individual genomic assays measure elements that interact in vivo as components of larger molecular machines. Understanding how these high-order interactions drive gene expression presents a substantial statistical challenge. Building on random forests (RFs) and random intersection trees (RITs) and through extensive, biologically inspired simulations, we developed the iterative random forest algorithm (iRF). iRF trains a feature-weighted ensemble of decision trees to detect stable, high-order interactions with the same order of computational cost as the RF. We demonstrate the utility of iRF for high-order interaction discovery in two prediction problems: enhancer activity in the early Drosophila embryo and alternative splicing of primary transcripts in human-derived cell lines. In Drosophila, among the 20 pairwise transcription factor interactions iRF identifies as stable (returned in more than half of bootstrap replicates), 80% have been previously reported as physical interactions. Moreover, third-order interactions, e.g., between Zelda (Zld), Giant (Gt), and Twist (Twi), suggest high-order relationships that are candidates for follow-up experiments. In human-derived cells, iRF rediscovered a central role of H3K36me3 in chromatin-mediated splicing regulation and identified interesting fifth- and sixth-order interactions, indicative of multivalent nucleosomes with specific roles in splicing regulation. By decoupling the order of interactions from the computational cost of identification, iRF opens additional avenues of inquiry into the molecular mechanisms underlying genome biology.
| S-EPMC5828575 | biostudies-literature
Project description:BackgroundThe wealth of gene expression values being generated by high throughput microarray technologies leads to complex high dimensional datasets. Moreover, many cohorts have the problem of imbalanced classes where the number of patients belonging to each class is not the same. With this kind of dataset, biologists need to identify a small number of informative genes that can be used as biomarkers for a disease.ResultsThis paper introduces a Balanced Iterative Random Forest (BIRF) algorithm to select the most relevant genes for a disease from imbalanced high-throughput gene expression microarray data. Balanced iterative random forest is applied on four cancer microarray datasets: a childhood leukaemia dataset, which represents the main target of this paper, collected from The Children's Hospital at Westmead, NCI 60, a Colon dataset and a Lung cancer dataset. The results obtained by BIRF are compared to those of Support Vector Machine-Recursive Feature Elimination (SVM-RFE), Multi-class SVM-RFE (MSVM-RFE), Random Forest (RF) and Naive Bayes (NB) classifiers. The results of the BIRF approach outperform these state-of-the-art methods, especially in the case of imbalanced datasets. Experiments on the childhood leukaemia dataset show that a 7% ∼ 12% better accuracy is achieved by BIRF over MSVM-RFE with the ability to predict patients in the minor class. The informative biomarkers selected by the BIRF algorithm were validated by repeating training experiments three times to see whether they are globally informative, or just selected by chance. The results show that 64% of the top genes consistently appear in the three lists, and the top 20 genes remain near the top in the other three lists.ConclusionThe designed BIRF algorithm is an appropriate choice to select genes from imbalanced high-throughput gene expression microarray data. BIRF outperforms the state-of-the-art methods, especially the ability to handle the class-imbalanced data. Moreover, the analysis of the selected genes also provides a way to distinguish between the predictive genes and those that only appear to be predictive.
| S-EPMC3766035 | biostudies-literature
Project description:BACKGROUND:Biological Regulatory Networks (BRNs) are responsible for developmental and maintenance related functions in organisms. These functions are implemented by the dynamics of BRNs and are sensitive to regulations enforced by specific activators and inhibitors. The logical modeling formalism by René Thomas incorporates this sensitivity with a set of logical parameters modulated by available regulators, varying with time. With the increase in complexity of BRNs in terms of number of entities and their interactions, the task of parameters estimation becomes computationally expensive with existing sequential SMBioNET tool. We extend the existing sequential implementation of SMBioNET by using a data decomposition approach using a Java messaging library called MPJ Express. The approach divides the parameters space into different regions and each region is then explored in parallel on High Performance Computing (HPC) hardware. RESULTS:The performance of the parallel approach is evaluated on BRNs of different sizes, and experimental results on multicore and cluster computers showed almost linear speed-up. This parallel code can be executed on a wide range of concurrent hardware including laptops equipped with multicore processors, and specialized distributed memory computer systems. To demonstrate the application of parallel implementation, we selected a case study of Hexosamine Biosynthetic Pathway (HBP) in cancer progression to identify potential therapeutic targets against cancer. A set of logical parameters were computed for HBP model that directs the biological system to a state of recovery. Furthermore, the parameters also suggest a potential therapeutic intervention that restores homeostasis. Additionally, the performance of parallel application was also evaluated on a network (comprising of 23 entities) of Fibroblast Growth Factor Signalling in Drosophila melanogaster. CONCLUSIONS:Qualitative modeling framework is widely used for investigating dynamics of biological regulatory networks. However, computation of model parameters in qualitative modeling is computationally intensive. In this work, we presented results of our Java based parallel implementation that provides almost linear speed-up on both multicore and cluster platforms. The parallel implementation is available at https://psmbionet.github.io .
| S-EPMC6311083 | biostudies-other
Project description:IntroductionDespite a recent global decrease in suicide rates, death by suicide has increased in the United States. It is therefore imperative to identify the risk factors associated with suicide attempts to combat this growing epidemic. In this study, we aim to identify potential risk factors of suicide attempt using geospatial features in an Artificial intelligence framework.MethodsWe use iterative Random Forest, an explainable artificial intelligence method, to predict suicide attempts using data from the Million Veteran Program. This cohort incorporated 405,540 patients with 391,409 controls and 14,131 attempts. Our predictive model incorporates multiple climatic features at ZIP-code-level geospatial resolution. We additionally consider demographic features from the American Community Survey as well as the number of firearms and alcohol vendors per 10,000 people to assess the contributions of proximal environment, access to means, and restraint decrease to suicide attempts. In total 1,784 features were included in the predictive model.ResultsOur results show that geographic areas with higher concentrations of married males living with spouses are predictive of lower rates of suicide attempts, whereas geographic areas where males are more likely to live alone and to rent housing are predictive of higher rates of suicide attempts. We also identified climatic features that were associated with suicide attempt risk by age group. Additionally, we observed that firearms and alcohol vendors were associated with increased risk for suicide attempts irrespective of the age group examined, but that their effects were small in comparison to the top features.DiscussionTaken together, our findings highlight the importance of social determinants and environmental factors in understanding suicide risk among veterans.
| S-EPMC10433206 | biostudies-literature
Project description:In the last decade, bioinformatics has become an indispensable branch of modern science research, experiencing an explosion in financial support, developed applications and data collection. The growth of the datasets that are emerging from research laboratories, industry, the health sector, etc., are increasingly raising the levels of demand in computing power and storage. Processing biological data, in the large scales of these datasets, often requires the use of High Performance Computing (HPC) resources, especially when dealing with certain types of omics data, such as genomic and metagenomic data. Such computational resources not only require substantial investments, but they also involve high maintenance costs. More importantly, in order to keep good returns from the investments, specific training needs to be put in place to ensure that wasting is minimized. Furthermore, given that bioinformatics is a highly interdisciplinary field where several other domains intersect (such as biology, chemistry, physics and computer science), researchers from these areas also require bioinformatics-specific training in HPC, in order to fully take advantage of supercomputing centers. In this document, we describe our experience in training researchers from several different disciplines in HPC, as applied to bioinformatics under the framework of the leading European bioinformatics platform ELIXIR, and analyze both the content and outcomes of the course.
| S-EPMC6299036 | biostudies-literature
Project description:Random Forest has become a standard data analysis tool in computational biology. However, extensions to existing implementations are often necessary to handle the complexity of biological datasets and their associated research questions. The growing size of these datasets requires high performance implementations. We describe CloudForest, a Random Forest package written in Go, which is particularly well suited for large, heterogeneous, genetic and biomedical datasets. CloudForest includes several extensions, such as dealing with unbalanced classes and missing values. Its flexible design enables users to easily implement additional extensions. CloudForest achieves fast running times by effective use of the CPU cache, optimizing for different classes of features and efficiently multi-threading. https://github.com/ilyalab/CloudForest.
| S-EPMC4692062 | biostudies-literature
Project description:Technological advances in the past decade, hardware and software alike, have made access to high-performance computing (HPC) easier than ever. We review these advances from a statistical computing perspective. Cloud computing makes access to supercomputers affordable. Deep learning software libraries make programming statistical algorithms easy and enable users to write code once and run it anywhere-from a laptop to a workstation with multiple graphics processing units (GPUs) or a supercomputer in a cloud. Highlighting how these developments benefit statisticians, we review recent optimization algorithms that are useful for high-dimensional models and can harness the power of HPC. Code snippets are provided to demonstrate the ease of programming. We also provide an easy-to-use distributed matrix data structure suitable for HPC. Employing this data structure, we illustrate various statistical applications including large-scale positron emission tomography and ℓ1-regularized Cox regression. Our examples easily scale up to an 8-GPU workstation and a 720-CPU-core cluster in a cloud. As a case in point, we analyze the onset of type-2 diabetes from the UK Biobank with 200,000 subjects and about 500,000 single nucleotide polymorphisms using the HPC ℓ1-regularized Cox regression. Fitting this half-million-variate model takes less than 45 minutes and reconfirms known associations. To our knowledge, this is the first demonstration of the feasibility of penalized regression of survival outcomes at this scale.
| S-EPMC10168006 | biostudies-literature
Project description:Identifying genetic variants associated with complex disease in high-dimensional data is a challenging problem, and complicated etiologies such as gene-gene interactions are often ignored in analyses. The data-mining method Random Forests (RF) can handle high-dimensions; however, in high-dimensional data, RF is not an effective filter for identifying risk factors associated with the disease trait via complex genetic models such as gene-gene interactions without strong marginal components. Here we propose an extension called Weighted Random Forests (wRF), which incorporates tree-level weights to emphasize more accurate trees in prediction and calculation of variable importance. We demonstrate through simulation and application to data from a genetic study of addiction that wRF can outperform RF in high-dimensional data, although the improvements are modest and limited to situations with effect sizes that are larger than what is realistic in genetics of complex disease. Thus, the current implementation of wRF is unlikely to improve detection of relevant predictors in high-dimensional genetic data, but may be applicable in other situations where larger effect sizes are anticipated.
| S-EPMC3912194 | biostudies-literature
Project description:Single nucleotide polymorphisms (SNPs) may be correlated due to linkage disequilibrium (LD). Association studies look for both direct and indirect associations with disease loci. In a Random Forest (RF) analysis, correlation between a true risk SNP and SNPs in LD may lead to diminished variable importance for the true risk SNP. One approach to address this problem is to select SNPs in linkage equilibrium (LE) for analysis. Here, we explore alternative methods for dealing with SNPs in LD: change the tree-building algorithm by building each tree in an RF only with SNPs in LE, modify the importance measure (IM), and use haplotypes instead of SNPs to build a RF.We evaluated the performance of our alternative methods by simulation of a spectrum of complex genetics models. When a haplotype rather than an individual SNP is the risk factor, we find that the original Random Forest method performed on SNPs provides good performance. When individual, genotyped SNPs are the risk factors, we find that the stronger the genetic effect, the stronger the effect LD has on the performance of the original RF. A revised importance measure used with the original RF is relatively robust to LD among SNPs; this revised importance measure used with the revised RF is sometimes inflated. Overall, we find that the revised importance measure used with the original RF is the best choice when the genetic model and the number of SNPs in LD with risk SNPs are unknown. For the haplotype-based method, under a multiplicative heterogeneity model, we observed a decrease in the performance of RF with increasing LD among the SNPs in the haplotype.Our results suggest that by strategically revising the Random Forest method tree-building or importance measure calculation, power can increase when LD exists between SNPs. We conclude that the revised Random Forest method performed on SNPs offers an advantage of not requiring genotype phase, making it a viable tool for use in the context of thousands of SNPs, such as candidate gene studies and follow-up of top candidates from genome wide association studies.
| S-EPMC2666661 | biostudies-literature
Project description:MotivationThe principle of Breiman's random forest (RF) is to build and assemble complementary classification trees in a way that maximizes their variability. We propose a new type of random forest that disobeys Breiman's principles and involves building trees with no classification errors in very large quantities. We used a new type of decision tree that uses a neuron at each node as well as an in-innovative half Christmas tree structure. With these new RFs, we developed a score, based on a family of ten new statistical information criteria, called Nguyen information criteria (NICs), to evaluate the predictive qualities of features in three dimensions.ResultsThe first NIC allowed the Akaike information criterion to be minimized more quickly than data obtained with the Gini index when the features were introduced in a logistic regression model. The selected features based on the NICScore showed a slight advantage compared to the support vector machines-recursive feature elimination (SVM-RFE) method. We demonstrate that the inclusion of artificial neurons in tree nodes allows a large number of classifiers in the same node to be taken into account simultaneously and results in perfect trees without classification errors.Availability and implementationThe methods used to build the perfect trees in this article were implemented in the "ROP" R package, archived at https://cran.r-project.org/web/packages/ROP/index.html.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8352507 | biostudies-literature