Dataset Information

Genomic Feature Selection by Coverage Design Optimization.

ABSTRACT: We introduce a novel data reduction technique whereby we select a subset of tiles to "cover" maximally events of interest in large-scale biological datasets (e.g., genetic mutations), while minimizing the number of tiles. A tile is a genomic unit capturing one or more biological events, such as a sequence of base pairs that can be sequenced and observed simultaneously. The goal is to reduce significantly the number of tiles considered to those with areas of dense events in a cohort, thus saving on cost and enhancing interpretability. However, the reduction should not come at the cost of too much information, allowing for sensible statistical analysis after its application. We envisage application of our methods to a variety of high throughput data types, particularly those produced by next generation sequencing (NGS) experiments. The procedure is cast as a convex optimization problem, which is presented, along with methods of its solution. The method is demonstrated on a large dataset of somatic mutations spanning 5000+ patients, each having one of 29 cancer types. Applied to these data, our method dramatically reduces the number of gene locations required for broad coverage of patients and their mutations, giving subject specialists a more easily interpretable snapshot of recurrent mutational profiles in these cancers. The locations identified coincide with previously identified cancer genes. Finally, despite considerable data reduction, we show that our covering designs preserve the cancer discrimination ability of multinomial logistic regression models trained on all of the locations (> 1M).

SUBMITTER: Reid S

PROVIDER: S-EPMC6173524 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Genomic Feature Selection by Coverage Design Optimization.

Reid Stephen S Newman Aaron M AM Diehn Maximilian M Alizadeh Ash A AA Tibshirani Robert R

Journal of applied statistics 20180207 14

We introduce a novel data reduction technique whereby we select a subset of tiles to "cover" maximally events of interest in large-scale biological datasets (e.g., genetic mutations), while minimizing the number of tiles. A tile is a genomic unit capturing one or more biological events, such as a sequence of base pairs that can be sequenced and observed simultaneously. The goal is to reduce significantly the number of tiles considered to those with areas of dense events in a cohort, thus saving ...[more]

PMID: 30294060

Similar Datasets

Project description:BackgroundExisting feature selection methods typically do not consider prior knowledge in the form of structural relationships among features. In this study, the features are structured based on prior knowledge into groups. The problem addressed in this article is how to select one representative feature from each group such that the selected features are jointly discriminating the classes. The problem is formulated as a binary constrained optimization and the combinatorial optimization is relaxed as a convex-concave problem, which is then transformed into a sequence of convex optimization problems so that the problem can be solved by any standard optimization algorithm. Moreover, a block coordinate gradient descent optimization algorithm is proposed for high dimensional feature selection, which in our experiments was four times faster than using a standard optimization algorithm.ResultsIn order to test the effectiveness of the proposed formulation, we used microarray analysis as a case study, where genes with similar expressions or similar molecular functions were grouped together. In particular, the proposed block coordinate gradient descent feature selection method is evaluated on five benchmark microarray gene expression datasets and evidence is provided that the proposed method gives more accurate results than the state-of-the-art gene selection methods. Out of 25 experiments, the proposed method achieved the highest average AUC in 13 experiments while the other methods achieved higher average AUC in no more than 6 experiments.ConclusionA method is developed to select a feature from each group. When the features are grouped based on similarity in gene expression, we showed that the proposed algorithm is more accurate than state-of-the-art gene selection methods that are particularly developed to select highly discriminative and less redundant genes. In addition, the proposed method can exploit any grouping structure among features, while alternative methods are restricted to using similarity based grouping.

Project description:Metaheuristic optimization algorithms manage the search process to explore search domains efficiently and are used efficiently in large-scale, complex problems. Transient Search Algorithm (TSO) is a recently proposed physics-based metaheuristic method inspired by the transient behavior of switched electrical circuits containing storage elements such as inductance and capacitance. TSO is still a new metaheuristic method; it tends to get stuck with local optimal solutions and offers solutions with low precision and a sluggish convergence rate. In order to improve the performance of metaheuristic methods, different approaches can be integrated and methods can be hybridized to achieve faster convergence with high accuracy by balancing the exploitation and exploration stages. Chaotic maps are effectively used to improve the performance of metaheuristic methods by escaping the local optimum and increasing the convergence rate. In this study, chaotic maps are included in the TSO search process to improve performance and accelerate global convergence. In order to prevent the slow convergence rate and the classical TSO algorithm from getting stuck in local solutions, 10 different chaotic maps that generate chaotic values instead of random values in TSO processes are proposed for the first time. Thus, ergodicity and non-repeatability are improved, and convergence speed and accuracy are increased. The performance of Chaotic Transient Search Algorithm (CTSO) in global optimization was investigated using the IEEE Congress on Evolutionary Computation (CEC)'17 benchmarking functions. Its performance in real-world engineering problems was investigated for speed reducer, tension compression spring, welded beam design, pressure vessel, and three-bar truss design problems. In addition, the performance of CTSO as a feature selection method was evaluated on 10 different University of California, Irvine (UCI) standard datasets. The results of the simulation showed that Gaussian and Sinusoidal maps in most of the comparison functions, Sinusoidal map in most of the real-world engineering problems, and finally the generally proposed CTSOs in feature selection outperform standard TSO and other competitive metaheuristic methods. Real application results demonstrate that the suggested approach is more effective than standard TSO.

Dataset Information

Genomic Feature Selection by Coverage Design Optimization.

Publications

Genomic Feature Selection by Coverage Design Optimization.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets