Gene Regulatory Network Inference using 3D Convolutional Neural Network

Authors: Yue Fan, Xiuli Ma99-106

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Compared with other existing GRN inference algorithms on both in-silico datasets and sc RNA-Seq datasets, our algorithm based on deep learning shows higher stability and accuracy in the task of GRN inference.
Researcher Affiliation Academia Yue Fan, Xiuli Ma Department of Machine Intelligence, School of EECS, Key Laboratory of Machine Perception (MOE), Peking University, Beijing, China fanyue@pku.edu.cn, xlma@pku.edu.cn
Pseudocode Yes Algorithm 1 The co-expression matrix of the three genes. Algorithm 2 Synthesizing Labels to Infer the GRN.
Open Source Code Yes 1Code is avaliable at https://github.com/Yue Fan1014/3DCEMA.
Open Datasets Yes Gonadal sex determination (GSD), hematopoietic stem cell (HSC) differentiation, and mammalian cortical area development (m CAD) are published boolean models... Mouse embryonic stem cells (m ESC) (Hayashi et al. 2018) and erythroid-lineage mouse hematopoietic stem cells (m HSC-E) (Nestorowa et al. 2016) are two sc RNA-seq datasets.
Dataset Splits No The paper mentions training and testing sets, but does not explicitly describe a validation set or specific split percentages for validation.
Hardware Specification No The paper does not provide specific details about the hardware used, such as GPU models, CPU types, or memory.
Software Dependencies No The paper does not specify version numbers for any software dependencies or libraries used in the experiments.
Experiment Setup Yes Here, we set the matrix size to 16 16 16... The sum of all elements in a 3D matrix is a constant p, which is set to 4096 across our experiments. In the training phase, the proportions of class 0 and 1 are set to 0.8 and 0.2. We follow Res Net-10 structure (He et al. 2016) to build the 3D CNN as shown in Figure 3.