Copy Number Variation Detection of BP Neural Network Based on Genetic Algorithm

doi:10.3778/j.issn.1002-8331.2007-0331

Abstract

Abstract: Copy number variation（CNV） is a major form of genome structural variation, which will lead to amplification or deletion of different sizes in the genome region. Aiming at the problem that the existing copy number variation detection algorithm is affected by factors such as GC-content bias and sequencing errors, resulting in low detection ability. A copy number variation detection algorithm based on genetic algorithm optimized BP neural network is proposed. The algorithm fully considers the inherent correlation between adjacent positions of the genome, fuse multiple features and training a neural network to solve the joint effect of each feature to predict CNV. In view of the existing problems of the BP neural network model, the genetic algorithm is used to optimize the weights and thresholds of the BP neural network to improve the CNV prediction performance of the algorithm. Experimental results show that the proposed algorithm has an average detection sensitivity, average detection accuracy and average [F1] score of 300 samples with different sequencing coverage and tumor purity of 97.27%, 97.78% and 97.53%, which are superior to other algorithms, and can significantly reduce the sample boundary bias value.

Key words: copy number variation（CNV）, BP neural network, genetic algorithm, read depth

摘要： 拷贝数变异是一种主要的基因组结构变异形式，会导致基因组区域中出现大小不等的扩增或缺失。针对现有拷贝数变异检测算法受GC含量偏差、测序误差等因素影响而导致检测能力低的问题，提出了一种基于遗传算法优化的BP神经网络拷贝数变异检测算法。该算法充分考虑基因组相邻位置之间的内在相关性，融合多个特征，并使用BP神经网络解决各个特征之间的联合作用以预测CNV；针对现有的BP神经网络模型存在的问题，利用遗传算法优化BP神经网络的权值和阈值，以提高该算法的CNV检测性能。实验结果表明，该算法对不同测序覆盖深度和肿瘤纯度共300个样本的平均检测灵敏度、平均检测精度和平均[F1]评分分别为97.27%、97.78%和97.53%，均优于其他几种算法，且能够显著降低样本边界偏差值。

关键词: 拷贝数变异, BP神经网络, 遗传算法, 读取深度

HUANG Tihao, LI Junqing, ZHAO Haiyong. Copy Number Variation Detection of BP Neural Network Based on Genetic Algorithm[J]. Computer Engineering and Applications, 2022, 58(1): 274-281.

黄体浩, 李俊青, 赵海勇. 遗传算法优化的BP神经网络拷贝数变异检测[J]. 计算机工程与应用, 2022, 58(1): 274-281.

References

[1] XIE C，TAMMI M T.CNV-seq，a new method to detect copy number variation using high-throughput sequencing[J].BMC Bioinformatics，2009，10：80.
[2] YOON S，XUAN Z，MAKAROV V，et al.Sensitive and accurate detection of copy number variants using read depth of coverage[J].Genome Res，2009，19（9）：1586-1592.
[3] IVAKHNO S，ROYCE T，COX A J，et al.CNAseg：A novel framework for identification of copy number changes in cancer from second-generation sequencing data[J].Bioinformatics，2010，26（24）：3051-3058.
[4] ABYZOV A，URBAN A E，SNYDER M，et al.CNVnator：An approach to discover，genotype，and characterize typical and atypical CNVs from family and population genome sequencing[J].Genome Res，2011，21（6）：974-984.
[5] XI R，HADJIPANAYIS A G，LUQUETTE L J，et al.Copy number variation detection in whole-genome sequencing data using the Bayesian information criterion[J].Proceedings of the National Academy of Sciences，2011，108：1128-1136.
[6] MILLER C A，HAMPTON O，COARFA C，et al.ReadDepth：A parallel R package for detecting copy number alterations from short sequencing reads[J].PLoS One，2011，6（1）：e16327.
[7] BOEVA V，POPOVA T，BLEAKLEY K，et al.Control-FREEC：A tool for assessing copy number and allelic content using next-generation sequencing data[J].Bioinformatics，2012，28（3）：423-425.
[8] GUSNANTO A，WOOD H M，PAWITAN Y，et al.Correcting for cancer genome size and tumour cell content enables better estimation of copy number alterations from next-generation sequence data[J].Bioinformatics，2012，28（1）：40-47.
[9] WANG H，NETTLETON D，YING K.Copy number variation detection using next generation sequencing read counts[J].BMC Bioinformatics，2014，109：1-14.
[10] SHEN R，YING K，WANG Z，et al.Algorithm for DNA copy number variation detection with read depth and paramorphism information[C]//Proceedings of 2016 IEEE International Conference on Acoustics，Speech and Signal Processing（ICASSP），2016.
[11] YU Z.Study on detection algorithms for tumor genomic copy number alterations based on next-generation sequencing[D].Hefei：University of Science and Technology of China，2016
[12] ONSONGO G，BAUGHN L B，BOWER M，et al.CNV-RF is a random forest-based copy number variation detection method using next-generation sequencing[J].Journal of Mol Diagn，2016，18（6）：872-881.
[13] JOHANSSON L F，VAN D F，DE B E N，et al.CoNVaDING：Single exon variation detection in targeted NGS data[J].Hum Mutat，2016，37（5）：457-464.
[14] DHARANIPRAGADA P，PAREKH N.Copy number variation detection workflow using next generation sequencing data[C]//Proceedings of 2016 International Conference on Bioinformatics & Systems Biology，2016：1-5.
[15] CHEN Y，ZHAO L，WANG Y，et al.SeqCNV：A novel method for identification of copy number variations in targeted next-generation sequencing data[J].BMC Bioinformatics，2017，18（1）：147.
[16] MELCHER U，DHARANIPRAGADA P，VOGETI S，et al.iCopyDAV：Integrated platform for copy number variations—Detection，annotation and visualization[J].Plos One，2018，13（4）：e0195334.
[17] JUGAS R，VITEK M，MADERANKOVA D，et al.Signal processing based CNV detection in bacterial genomes[C]//Proceedings of International Work-Conference on Bioinformatics and Biomedical Engineering，2019.
[18] YUAN X G，BAI J，ZHANG J Y，et al.CONDEL：Detecting copy number variation and genotyping deletion zygosity from single tumor samples using sequence data[J].IEEE/ACM Transactions on Comput Biol Bioinform，2020，17（4）：1141-1153.
[19] XIAO F，LUO X，HAO N，et al.An accurate and powerful method for copy number variation detection[J].Bioinformatics，2019，35（17）：2891-2898.
[20] LI Y，ZHANG J，YUAN X G.BagGMM：Calling copy number variation by bagging multiple Gaussian mixture models from tumor and matched normal next-generation sequencing data[J].Digital Signal Processing，2019，88：90-100.
[21] YUAN X G，YU J A，XI J N，et al.CNV_IFTV：An isolation forest and total variation-based detection of CNVs from short-read sequencing data[J].IEEE/ACM Transactions on Comput Biol Bioinform，2021，18（2）：539-549.
[22] LI Y Y，YUAN X G，ZHANG J Y，et al.SM-RCNV：A statistical method to detect recurrent copy number variations in sequenced samples[J].Genes Genomics，2019，41（5）：529-536.
[23] YUAN X G，LI J Q，BAI J，et al.A local outlier factor-based detection of copy number variations from NGS data[J].IEEE/ACM Transactions on Comput Biol Bioinform，2021，18（5）：1811-1820.
[24] YUAN X G，LI Z，ZHAO H，et al.Accurate inference of tumor purity and absolute copy numbers from high-throughput sequencing data[J].Frontiers in Genet，2020，11：458.
[25] ZHAO H，HUANG T，LI J，et al.MFCNV：A new method to detect copy number variations from next-generation sequencing data[J].Frontiers in Genet，2020，11：434.
[26] CHEN N，YUAN X G.An individual copy number variation detection algorithm based on hierarchical matrix energy spectrum[J].Journal of Liaocheng University（Natural Science Edition），2020，33（5）：16-26.
[27] YUAN X G，ZHANG J G，YANG L Y.IntSIM：An integrated simulator of next-generation sequencing data[J].IEEE Transactions on Biomedical Engineering，2017，64（2）：441-451.
[28] SMITH S D，KAWASH J K，GRIGORIEV A.GROM-RD：Resolving genomic biases to improve read depth detection of copy number variants[J].PeerJ，2015，3：e836.
[29] 李俊青，潘全科.求解模糊作业车间调度问题的混合优化算法[J].机械工程学报，2013，49（23）：142-149.
LI J Q，PAN Q K.Solving fuzzy job-shop scheduling problems by a hybrid optimization algorithm[J].Journal of Mechanical Engineering，2013，49（23）：142-149.
[30] 李俊青，杜宇，田杰，等.带运输资源约束柔性作业车间调度问题的人工蜂群算法[J].电子学报，2021，49（2）：324-330.
LI J Q，DU Y，TIAN J，et al.An artificial bee colony algorithm for flexible job shop scheduling with transportation resource constraints[J].Acta Electronica Sinica，2021，49（2）：324-330.
[31] 李俊青，李文涵，陶昕瑞，等.时间约束混合流水车间调度问题综述[J].控制理论与应用，2020，37（11）：2273-2290.
LI J Q，LI W H，TAO X R，et al.A survey on time constrained hybrid flow shop scheduling problems[J].Control Theory and Applications，2020，37（11）：2273-2290.