Computational modeling of <i>in vivo</i> and <i>in vitro</i> protein-DNA interactions by multiple instance learning

Ruan, Jianhua

doi:10.1093/bioinformatics/btx115

Cited by 19 publications

(14 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in k -mer-based SVM models, there can be a large number of very similar k -mer features that are all significant for the prediction task ( Ghandi et al , 2014 ). To deal with such difficulties, SeqGL ( Setty and Leslie, 2015 ) and MIL ( Gao and Ruan, 2017 ) similarly adopt a DML method (HOMER) to interpret their outputs, while gkmSVM ( Ghandi et al , 2014 ) would cluster k -mers into PWMs for further analysis, which could be viewed as a simplified version of motif learning methods such as ( Liu et al , 2016 ).…”

Section: Discussionmentioning

confidence: 99%

Direct AUC optimization of regulatory motifs

2017

View full text Add to dashboard Cite

MotivationThe discovery of transcription factor binding site (TFBS) motifs is essential for untangling the complex mechanism of genetic variation under different developmental and environmental conditions. Among the huge amount of computational approaches for de novo identification of TFBS motifs, discriminative motif learning (DML) methods have been proven to be promising for harnessing the discovery power of accumulated huge amount of high-throughput binding data. However, they have to sacrifice accuracy for speed and could fail to fully utilize the information of the input sequences.ResultsWe propose a novel algorithm called CDAUC for optimizing DML-learned motifs based on the area under the receiver-operating characteristic curve (AUC) criterion, which has been widely used in the literature to evaluate the significance of extracted motifs. We show that when the considered AUC loss function is optimized in a coordinate-wise manner, the cost function of each resultant sub-problem is a piece-wise constant function, whose optimal value can be found exactly and efficiently. Further, a key step of each iteration of CDAUC can be efficiently solved as a computational geometry problem. Experimental results on real world high-throughput datasets illustrate that CDAUC outperforms competing methods for refining DML motifs, while being one order of magnitude faster. Meanwhile, preliminary results also show that CDAUC may also be useful for improving the interpretability of convolutional kernels generated by the emerging deep learning approaches for predicting TF sequences specificities.Availability and ImplementationCDAUC is available at: https://drive.google.com/drive/folders/0BxOW5MtIZbJjNFpCeHlBVWJHeW8.Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

Section: Discussionmentioning

confidence: 99%

Direct AUC optimization of regulatory motifs

2017

View full text Add to dashboard Cite

show abstract

“…Considering the weakly supervised information of DNA sequences, thus it is reasonable to use the concepts of MIL to deal with DNA sequences. Therefore we divided them into multiple overlapping instances following the works 18,20 , which ensures that (1) the weakly supervised information can be retained, and that (2) a large amount of instances containing TFBS are generated. This method is defined as a sliding window of length c , which divides DNA sequences of length l into multiple overlapping instances by a stride s .…”

Section: Methodsmentioning

confidence: 99%

“…In consideration of this information, Gao et al . 18 developed a multiple-instance learning (MIL) based algorithm, which combines MIL with TeamD 19 , for modeling protein-DNA binding, and recently Zhang et al . 20 also developed a weakly supervised convolutional neural network (WSCNN), which combines MIL with CNN, for modeling protein-DNA binding.…”

Section: Introductionmentioning

confidence: 99%

Modeling in-vivo protein-DNA binding by combining multiple-instance learning with a hybrid deep neural network

Zhang

Shen

2019

Sci Rep

View full text Add to dashboard Cite

Modeling in-vivo protein-DNA binding is not only fundamental for further understanding of the regulatory mechanisms, but also a challenging task in computational biology. Deep-learning based methods have succeed in modeling in-vivo protein-DNA binding, but they often (1) follow the fully supervised learning framework and overlook the weakly supervised information of genomic sequences that a bound DNA sequence may has multiple TFBS(s), and, (2) use one-hot encoding to encode DNA sequences and ignore the dependencies among nucleotides. In this paper, we propose a weakly supervised framework, which combines multiple-instance learning with a hybrid deep neural network and uses k -mer encoding to transform DNA sequences, for modeling in-vivo protein-DNA binding. Firstly, this framework segments sequences into multiple overlapping instances using a sliding window, and then encodes all instances into image-like inputs of high-order dependencies using k -mer encoding. Secondly, it separately computes a score for all instances in the same bag using a hybrid deep neural network that integrates convolutional and recurrent neural networks. Finally, it integrates the predicted values of all instances as the final prediction of this bag using the Noisy-and method. The experimental results on in-vivo datasets demonstrate the superior performance of the proposed framework. In addition, we also explore the performance of the proposed framework when using k -mer encoding, and demonstrate the performance of the Noisy-and method by comparing it with other fusion methods, and find that adding recurrent layers can improve the performance of the proposed framework.

show abstract

“…In addition, protein binding microarrays (PBM) can be used to measure in vitro transcription factor binding through the array of exhaustive short amino acid sequences on microarrays [12]. Since the common confounding factor was eliminated in the ChIP-Seq experiment [13], PBM data conveyed perfect information in a more direct manner for the modeling of transcription factor binding sites [14].…”

Section: Introductionmentioning

confidence: 99%

MD-SVM: a novel SVM-based algorithm for the motif discovery of transcription factor binding sites

Wang

Lin

et al. 2019

BMC Bioinformatics

View full text Add to dashboard Cite

Background: Transcription factors (TFs) play important roles in the regulation of gene expression. They can activate or block transcription of downstream genes in a manner of binding to specific genomic sequences. Therefore, motif discovery of these binding preference patterns is of central significance in the understanding of molecular regulation mechanism. Many algorithms have been proposed for the identification of transcription factor binding sites. However, it remains a challengeable problem. Results: Here, we proposed a novel motif discovery algorithm based on support vector machine (MD-SVM) to learn a discriminative model for TF binding sites. MD-SVM firstly obtains position weight matrix (PWM) from a set of training datasets. Then it translates the MD problem into a computational framework of multiple instance learning (MIL). It was applied to several real biological datasets. Results show that our algorithm outperforms MI-SVM in terms of both accuracy and specificity. Conclusions: In this paper, we modeled the TF motif discovery problem as a MIL optimization problem. The SVM algorithm was adapted to discriminate positive and negative bags of instances. Compared to other svm-based algorithms, MD-SVM show its superiority over its competitors in term of ROC AUC. Hopefully, it could be of benefit to the research community in the understanding of molecular functions of DNA functional elements and transcription factors.

show abstract

Computational modeling of in vivo and in vitro protein-DNA interactions by multiple instance learning

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 19 publications

References 41 publications

Direct AUC optimization of regulatory motifs

Direct AUC optimization of regulatory motifs

Modeling in-vivo protein-DNA binding by combining multiple-instance learning with a hybrid deep neural network

MD-SVM: a novel SVM-based algorithm for the motif discovery of transcription factor binding sites

Contact Info

Product

Resources

About