Prediction of Disease Gene Based on Fusion Features and GA-SVM Algorithm

doi:10.3778/j.issn.1002-8331.2206-0472

Abstract

Abstract: The feature information provided by a single biological data network is limited. Aiming at this problem, a multi-network feature fusion method based on semi-supervised autoencoder is proposed to enrich feature information. In addition, in order to solve the problem of artificially setting the hyperparameters of the model, it is easy to cause problems such as low model performance and falling into local optimum, it is further proposed to use the genetic algorithm to optimize the support vector machine（GA-SVM algorithm） to improve the predictive performance of brain disease genes. First, the similarity data networks from different data sources are constructed, then the features are extracted from the four data networks by using the random walk with restart algorithm, and processed and fused by semi-supervised autoencoder, finally, under the strategy of 10-fold cross validation, GA-SVM algorithm model is used to predict disease genes, and compared with other algorithms. The experimental results show that the AUC and AUPR values on the PD dataset are 0.805 and 0.792, respectively, while the AUC and AUPR values on the MDD dataset are 0.825 and 0.823, respectively, which are superior to the existing models. It is proved that this method can effectively improve the prediction effect of brain disease genes.

Key words: GA-SVM algorithm, multi-network fusion, semi-supervised autoencoder, brain disease genes, 10-fold cross validation

摘要： 单一生物数据网络提供的特征信息是十分受限的，针对这一问题，提出了一种基于半监督自编码器的多网络特征融合方法，丰富特征信息。此外，为解决在人为设置模型的超参数时，易出现模型性能较低、陷入局部最优等问题，进一步提出了利用遗传算法优化支持向量机（GA-SVM算法）模型的方法，提高脑部疾病基因的预测性能。构建来自不同数据源的相似性数据网络，利用重启随机游走算法从四个数据网络中提取特征，通过半监督自编码器进行处理及融合，在十折交叉验证的策略下使用GA-SVM算法模型预测脑部疾病基因，并与其他算法进行比较。实验结果表明，在PD数据集上的AUC和AUPR值分别为0.805、0.792，而在MDD数据集上的AUC和AUPR值分别为0.825、0.823，均优于已有的预测模型，有效证明了该方法能够提高脑部疾病基因的预测效果。

关键词: GA-SVM算法, 多网络融合, 半监督自编码器, 脑部疾病基因, 十折交叉验证

TAN Zhuokun, LUO Longfei, WANG Shunfang. Prediction of Disease Gene Based on Fusion Features and GA-SVM Algorithm[J]. Computer Engineering and Applications, 2023, 59(5): 70-77.

谭卓昆, 罗龙飞, 王顺芳. 基于融合特征与GA-SVM算法的脑疾病基因预测[J]. 计算机工程与应用, 2023, 59(5): 70-77.

References

[1] ZHANG Y，GUO P，MA Z，et al.Combination of cell-penetrating peptides with nanomaterials for the potential therapeutics of central nervous system disorders：a review[J].J Nanobiotechnology，2021，19（1）：255.
[2] LUO P，TIAN L P，RUAN J，et al.Disease gene prediction by integrating PPI networks，clinical RNA-seq data andomim data[J].IEEE/ACM Trans Comput Biol Bioinform，2017，16（1）：222-232.
[3] ZHANG Y D，DONG Z，WANG S H，et al.Advances in multi-modal data fusion in neuroimaging：overview，challenges，and novel orientation[J].Information Fusion，2020，64：149-187.
[4] GAO J，LI P，CHEN Z，et al.A survey on deep learning for multimodal data fusion[J].Neural Comput，2020，32（5）：829-864.
[5] 秦小麟.基于脑功能超网络的多特征融合分类方法研究[D].太原：太原理工大学，2021.
QIN X L.Research on multi-feature fusion classification method based on brain function super network[D].Taiyuan：Taiyuan University of Technology，2021.
[6] 胡春荣，杜欣娜，李凤君，等.脑源性神经营养因子相互作用蛋白质间的相互作用网络及功能[J].中国老年学杂志，2018，38（7）：1707-1709.
HU C R，DU X N，LI F J，et al.Interaction network and function of brain-derived neurotrophic factor interacting proteins[J].Chinese Journal of Gerontology，2018，38（7）：1707-1709.
[7] YE J，WANG S，YANG X，et al.Gene prediction of aging-related diseases based on DNN and Mashup[J].BMC Bioinformatics，2021，22（1）：597.
[8] GLIGORIJEVI?V，BAROT M，BONNEAU R.DeepNF：deep network fusion for protein function prediction[J].Bioinformatics，2018，34（22）：3873-3881.
[9] PENG J，XUE H，WEI Z，et al.Integrating multi-network topology for gene function prediction using deep neural networks[J].Brief Bioinform，2021，22（2）：2096-2105.
[10] WANG W，HAN R，ZHANG M，et al.A network-based method for brain disease gene prediction by integrating brain connectome and molecular network[J].Brief Bioinform，2022，23（1）：bbab459.
[11] 朱震强.一种癌症分型的网络集成方法[D].西安：西安电子科技大学，2021.
ZHU Z Q.A method of network integration for cancer subtyping[D].Xi’an：Xidian University，2021.
[12] CHO H，BERGER B，PENG J.Compact integration of multi-network topology for functional analysis of genes[J].Cell Systems，2016，3（6）：540-548.
[13] 任巍，翟博豪，彭炜淞.基于半监督堆叠自编码器的轧制力预报建模研究[J].电气传动，2022，52（14）：70-74.
REN W，ZHAI B H，PENG W S.Rolling force prediction modeling based on semi-supervised stacked autoencoder[J].Electric Drive，2022，52（14）：70-74.
[14] 李景文，俞娜，姜建武，等.改进的遗传神经网络优化选址方法[J].计算机工程与设计，2021，42（1）：150-155.
LI J W，YU N，JIANG J W，et al.Improved genetic neural network optimized location method[J].Computer Engineering and Design，2021，42（1）：150-155.
[15] JI J L，SPRONK M，KULKARNI K，et al.Mapping the human brain’s cortical-subcortical functional network organization[J].Neuroimage，2019，185：35-57.
[16] SZKLARCZYK D，FRANCESCHINI A，WYDER S，et al.STRING v10：protein-protein interaction networks，integrated over the tree of life[J].Nucleic Acids Research，2015，43：447-452.
[17] SCHRIML L M，MITRAKA E，MUNRO J，et al.Human disease ontology 2018 update：classification，content and workflow expansion[J].Nucleic Acids Research，2019，47：955-962.
[18] LE D H.Random walk with restart：a powerful network propagation algorithm in bioinformatics field[C]//2017 4th NAFOSTED Conference on Information and Computer Science，2017：242-247.