Dataset Information

Expectation pooling: an effective and interpretable pooling method for predicting DNA-protein binding.

ABSTRACT: Motivation: Convolutional neural networks (CNNs) have outperformed conventional methods in modeling the sequence specificity of DNA-protein binding. While previous studies have built a connection between CNNs and probabilistic models, simple models of CNNs cannot achieve sufficient accuracy on this problem. Recently, some methods of neural networks have increased performance using complex neural networks whose results cannot be directly interpreted. However, it is difficult to combine probabilistic models and CNNs effectively to improve DNA-protein binding predictions.

Results: In this article, we present a novel global pooling method: expectation pooling for predicting DNA-protein binding. Our pooling method stems naturally from the expectation maximization algorithm, and its benefits can be interpreted both statistically and via deep learning theory. Through experiments, we demonstrate that our pooling method improves the prediction performance DNA-protein binding. Our interpretable pooling method combines probabilistic ideas with global pooling by taking the expectations of inputs without increasing the number of parameters. We also analyze the hyperparameters in our method and propose optional structures to help fit different datasets. We explore how to effectively utilize these novel pooling methods and show that combining statistical methods with deep learning is highly beneficial, which is promising and meaningful for future studies in this field.

Availability and implementation: All code is public in https://github.com/gao-lab/ePooling.

Supplementary information: Supplementary data are available at Bioinformatics online.

SUBMITTER: Luo X

PROVIDER: S-EPMC7703793 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Expectation pooling: an effective and interpretable pooling method for predicting DNA-protein binding.

Luo Xiao X Tu Xinming X Ding Yang Y Gao Ge G Deng Minghua M

Bioinformatics (Oxford, England) 20200301 5

<h4>Motivation</h4>Convolutional neural networks (CNNs) have outperformed conventional methods in modeling the sequence specificity of DNA-protein binding. While previous studies have built a connection between CNNs and probabilistic models, simple models of CNNs cannot achieve sufficient accuracy on this problem. Recently, some methods of neural networks have increased performance using complex neural networks whose results cannot be directly interpreted. However, it is difficult to combine pro ...[more]

PMID: 31598637

Similar Datasets

Project description:MotivationVast majority of human genetic disorders are associated with mutations that affect protein-protein interactions by altering wild-type binding affinity. Therefore, it is extremely important to assess the effect of mutations on protein-protein binding free energy to assist the development of therapeutic solutions. Currently, the most popular approaches use structural information to deliver the predictions, which precludes them to be applicable on genome-scale investigations. Indeed, with the progress of genomic sequencing, researchers are frequently dealing with assessing effect of mutations for which there is no structure available.ResultsHere, we report a Gradient Boosting Decision Tree machine learning algorithm, the SAAMBE-SEQ, which is completely sequence-based and does not require structural information at all. SAAMBE-SEQ utilizes 80 features representing evolutionary information, sequence-based features and change of physical properties upon mutation at the mutation site. The approach is shown to achieve Pearson correlation coefficient (PCC) of 0.83 in 5-fold cross validation in a benchmarking test against experimentally determined binding free energy change (ΔΔG). Further, a blind test (no-STRUC) is compiled collecting experimental ΔΔG upon mutation for protein complexes for which structure is not available and used to benchmark SAAMBE-SEQ resulting in PCC in the range of 0.37-0.46. The accuracy of SAAMBE-SEQ method is found to be either better or comparable to most advanced structure-based methods. SAAMBE-SEQ is very fast, available as webserver and stand-alone code, and indeed utilizes only sequence information, and thus it is applicable for genome-scale investigations to study the effect of mutations on protein-protein interactions.Availability and implementationSAAMBE-SEQ is available at http://compbio.clemson.edu/saambe_webserver/indexSEQ.php#started.Supplementary informationSupplementary data are available at Bioinformatics online.

Dataset Information

Expectation pooling: an effective and interpretable pooling method for predicting DNA-protein binding.

Publications

Expectation pooling: an effective and interpretable pooling method for predicting DNA-protein binding.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets