TY - GEN
T1 - Identification of Autistic Risk Genes Using Developmental Brain Gene Expression Data
AU - Huang, Zhi-An
AU - Huang, Yu-An
AU - You, Zhu-Hong
AU - Zhang, Shanwen
AU - Yu, Chang-Qing
AU - Huang, Wenzhun
PY - 2020/10
Y1 - 2020/10
N2 - Recently, the serious impairments of ASD cause a series of pending issues to increase a major burden of health and finance globally. In this work, we propose an effective convolutional neural network (CNN) - based model to identify the potential autistic risk genes based on the developmental brain gene expression profiles. Based on the 10-fold cross validations, the simulation experiments demonstrate that the proposed model shows supreme classification results as compared to the other state-of-the-art classifiers. In such an imbalanced dataset, the proposed CNN model achieves the F1-score of 63.07 ± 3.9 and the area under ROC curve of 0.6940. In case study, 70% out of the top-10 predicted risk genes have been confirmed to increase the risk of developing ASD via published literatures. The effectiveness enables our model to serve as a candidate tool for accelerating the identification of autistic genetic abnormalities.
AB - Recently, the serious impairments of ASD cause a series of pending issues to increase a major burden of health and finance globally. In this work, we propose an effective convolutional neural network (CNN) - based model to identify the potential autistic risk genes based on the developmental brain gene expression profiles. Based on the 10-fold cross validations, the simulation experiments demonstrate that the proposed model shows supreme classification results as compared to the other state-of-the-art classifiers. In such an imbalanced dataset, the proposed CNN model achieves the F1-score of 63.07 ± 3.9 and the area under ROC curve of 0.6940. In case study, 70% out of the top-10 predicted risk genes have been confirmed to increase the risk of developing ASD via published literatures. The effectiveness enables our model to serve as a candidate tool for accelerating the identification of autistic genetic abnormalities.
KW - Autism spectrum disorders (ASD)
KW - Autistic biomarkers
KW - Developmental brain gene expression data
KW - Gene prioritization
KW - Autism spectrum disorders (ASD)
KW - Autistic biomarkers
KW - Developmental brain gene expression data
KW - Gene prioritization
KW - Autism spectrum disorders (ASD)
KW - Autistic biomarkers
KW - Developmental brain gene expression data
KW - Gene prioritization
UR - https://www.scopus.com/pages/publications/85094150318
UR - https://www.scopus.com/pages/publications/85094150318#tab=impact
U2 - 10.1007/978-3-030-60802-6_29
DO - 10.1007/978-3-030-60802-6_29
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9783030608019
VL - Part II
T3 - Lecture Notes in Computer Science
SP - 326
EP - 338
BT - Intelligent Computing Theories and Application - 16th International Conference, ICIC 2020, Proceedings
A2 - Huang, De-Shuang
A2 - Jo, Kang-Hyun
PB - Springer Nature Switzerland AG
T2 - 16th International Conference on Intelligent Computing (ICIC 2020)
Y2 - 2 October 2020 through 5 October 2020
ER -