Title:
深層ニューラルネットワークに基づくバリアント分類器
Document Type and Number:
Japanese Patent JP6907344
Kind Code:
B2
Abstract:
We introduce a variant classifier that uses trained deep neural networks to predict whether a given variant is somatic or germline. Our model has two deep neural networks: a convolutional neural network (CNN) and a fully connected neural network (FCNN), and two inputs: a DNA sequence with a variant and a set of metadata features correlated with the variant. The metadata features represent the variant's mutation characteristics, read mapping statistics, and occurrence frequency. The CNN processes the DNA sequence and produces an intermediate convolved feature. A feature sequence is derived by concatenating the metadata features with the intermediate convolved feature. The FCNN processes the feature sequence and produces probabilities for the variant being somatic, germline, or noise. A transfer learning strategy is used to train the model on two mutation datasets. Results establish advantages and superiority of our model over traditional classifiers.
More Like This:
Inventors:
Aaron Wise
Christina M. Courgliac
Christina M. Courgliac
Application Number:
JP2019567521A
Publication Date:
July 21, 2021
Filing Date:
April 12, 2019
Export Citation:
Assignee:
Illumina Incorporated
International Classes:
G06N3/04; G06N5/04
Foreign References:
| US20180060482 | ||||
| US20170286594 | ||||
| US6260034 | ||||
| WO2017114810A1 |
Other References:
上野翔子、杉山 治、西尾瑞穂、八上全弘、山本豪志朗、岡本和也、南部雅幸、黒田知宏,患者情報を考慮した胸部CT画像の診断支援の試み,人工知能学会 AIMED:医用人工知能研究会資料[online],日本,一般社団法人 人工知能学会,2017年11月24日,pp.1-4(SIG-AIMED-004-04)
Attorney, Agent or Firm:
Yasuhiko Murayama
Shinya Mitsuhiro
Tatsuhiko Abe
Shinya Mitsuhiro
Tatsuhiko Abe