Genome‐wide prediction of chromatin accessibility based on gene expression

Zhou, Weiqiang

doi:10.1002/wics.1544

Cited by 5 publications

(1 citation statement)

References 46 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou and Ji discussed another example, wherein chromatin accessibility was evaluated using genomic data via the big data improved reliability (BIRD) method. The suggested model used genomic data along with chromatin accessibility and temporal genomic information in order to predict chromatic accessibility with an accuracy of 85%, thereby improving its deployment capabilities [ 68 ].…”

Section: Genome Sequence Processing Modelsmentioning

confidence: 99%

Heuristic Analysis of Genomic Sequence Processing Models for High Efficiency Prediction: A Statistical Perspective

Shrimankar

Durge

Sawarkar

2022

View full text Add to dashboard Cite

Genome sequences indicate the wide variety of characteristics which include species & sub-species type, genotype, diseases, growth indicators, yield quality, etc. To analyze and study these characteristics of the genome sequences across different species, various deep learning models have been proposed by researchers such as Convolutional Neural Networks (CNNs), Deep Belief Networks (DBNs), Multilayer Perceptron’s (MLPs), etc. which vary in terms of evaluation performance, area of application and species that are processed. Due to a wide differentiation between the algorithmic implementations, it becomes difficult for research programmer to select the best possible genome processing model for their application. In order to facilitate this selection, the paper reviews a wide variety of such models and compares their performance in terms of accuracy, area of application, computational complexity, processing delay, precision and recall. Thus, in the present review, various deep learning and machine learning models have different accuracies for different applications. For multiple genomic data, Repeated Incremental Pruning to Produce Error Reduction with Support Vector Machine (Ripper SVM) outputs 99.7% of accuracy and for cancer genomic data it gives 99.27% of accuracy using CNN Bayesian method. Whereas for Covid genome analysis Bidirectional Long Short-Term Memory with CNN (BiLSTM CNN) is having highest accuracy of 99.95%. The similar analysis of precision and recall of different models have been reviewed. Finally, this paper review concludes with some interesting observations about the genomic processing models and recommends applications for their efficient use.

show abstract

Section: Genome Sequence Processing Modelsmentioning

confidence: 99%