Partitioned learning of deep Boltzmann machines for SNP data

Hess, Moritz; Lenz, Stefan; Blätte, Tamara J.; Bullinger, Lars; Binder, Harald

doi:10.1093/bioinformatics/btx408

Cited by 30 publications

(35 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, new, synthetic samples can be generated that represent what kind of biological structure has been uncovered. We focus on Deep Boltzmann Machines (DBMs) (Srivastava and Salakhutdinov, 2014) because these allow for flexible conditional sampling, and we have already adapted them for training with small sample sizes (Hess et al, 2017). While our previous approach was primarily designed for handling genetic data, our Julia package "BoltzmannMachines" now can integrate data of different types, i.e.…”

Section: Motivationmentioning

confidence: 99%

Unsupervised deep learning on biomedical data with BoltzmannMachines.jl

Lenz

Hess

Binder

2019

Preprint

Self Cite

View full text Add to dashboard Cite

Deep Boltzmann machines (DBMs) are models for unsupervised learning in the field of artificial intelligence, promising to be useful for dimensionality reduction and pattern detection in clinical and genomic data. Multimodal and partitioned DBMs alleviate the problem of small sample sizes and make it possible to combine different input data types in one DBM model. We present the package "BoltzmannMachines" for the Julia programming language, which makes this model class available for practical use in working with biomedical data. AvailabilityNotebook with example data:

show abstract

Section: Motivationmentioning

confidence: 99%

Unsupervised deep learning on biomedical data with BoltzmannMachines.jl

Lenz

Hess

Binder

2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…[1][2][3][4][5][6] However, the model assumptions underlying these models, such as the proportional hazard, independence between censoring and survival times, linearity in coefficients, may not be tenable in real applications. For this reason, nonparametric approaches such as neural networks [7][8][9] can be useful alternatives. In particular, neural networks methodology has been adapted to survival analysis for more than two decades.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the structural simplicity and its popularity, several machine learning methods including the popular deep neural networks have been extended to Cox's regression analysis in conjunction with the Faraggi-Simon method. [7][8][9][22][23][24] But perhaps due to the computation burden incurred by the backpropagation algorithms that are widely employed in both multilayer perceptron (MLP) neural networks and deep neural networks, most of these proposals focus on low-dimensional survival data. These sophisticated deep learning methods have demonstrated their usefulness in high-dimensional setting.…”

Section: Introductionmentioning

confidence: 99%

Extreme learning machine Cox model for high‐dimensional survival analysis

Hong

2019

Statistics in Medicine

View full text Add to dashboard Cite

Some interesting recent studies have shown that neural network models are useful alternatives in modeling survival data when the assumptions of a classical parametric or semiparametric survival model such as the Cox (1972) model are seriously violated. However, to the best of our knowledge, the plausibility of adapting the emerging extreme learning machine (ELM) algorithm for single-hidden-layer feedforward neural networks to survival analysis has not been explored. In this paper, we present a kernel ELM Cox model regularized by an L0-based broken adaptive ridge (BAR) penalization method. Then, we demonstrate that the resulting method, referred to as ELMCoxBAR, can outperform some other state-of-art survival prediction methods such as L1-or L2-regularized Cox regression, random survival forest with various splitting rules, and boosted Cox model, in terms of its predictive performance using both simulated and real world datasets. In addition to its good predictive performance, we illustrate that the proposed method has a key computational advantage over the above competing methods in terms of computation time efficiency using an a real-world ultra-high-dimensional survival data.

show abstract

“…A few studies have considered using deep learning for genotype-phenotype association studies. Most approaches first reduced the number of variants included in the model either by selecting variants that were known to be associated with disease (Uppu and Krishna, 2017;Hess et al, 2017), or by preselecting those variants that showed a sufficiently strong correlation with phenotype in a regular GWAS (Montañez et al, 2018b;Bellot et al, 2018). Two studies combine the latter strategy with the use of autoencoders for further dimensionality reduction (Montañez et al, 2018a;Fergus et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype

Yin¹,

Balvert²,

Spek³

et al. 2019

Preprint

View full text Add to dashboard Cite

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease caused by aberrations in the genome. While several disease-causing variants have been identified, a major part of heritability remains unexplained. ALS is believed to have a complex genetic basis where nonadditive combinations of variants constitute disease, which cannot be picked up using the linear models employed in classical genotype-phenotype association studies. Deep learning on the other hand is highly promising for identifying such complex relations. We therefore developed a deep-learning based approach for the classification of ALS patients versus healthy individuals from the Dutch cohort of the ProjectMinE dataset. Based on recent insight that regulatory regions on the genome play a major role in ALS, we employ a two-step approach: first promoter regions that are likely associated to ALS are identified, and second individuals are classified based on their genotype in the selected genomic regions. Both steps employ a deep convolutional neural network. The network architecture accounts for the structure of genome data by applying convolution only to parts of the data where this makes sense from a genomics perspective.Our approach identifies potential ALS-associated genetic variants, and generally outperforms other classification methods. Test results support the hypothesis that ALS is caused by non-additive combinations of variants. Our method can be applied to large-scale whole genome data. We consider this a first step towards genotype-phenotype association with deep learning that is tailored to genomics and can deal with genome-sized data.

show abstract

Partitioned learning of deep Boltzmann machines for SNP data

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 30 publications

References 21 publications

Unsupervised deep learning on biomedical data with BoltzmannMachines.jl

Unsupervised deep learning on biomedical data with BoltzmannMachines.jl

Extreme learning machine Cox model for high‐dimensional survival analysis

Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype

Contact Info

Product

Resources

About