Gene Regulatory Network Inference as Relaxed Graph Matching

Authors: Deborah Weighill, Marouen Ben Guebila, Camila Lopes-Ramos, Kimberly Glass, John Quackenbush, John Platig, Rebekka Burkholz10263-10272

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

Reproducibility Variable Result LLM Response
Research Type Experimental Using three cancer-related data sets, we show that OTTER outperforms state-of-the-art inference methods in predicting transcription factor binding to gene regulatory regions. ... Experiments on Synthetic Data ... Experiments on Cancer Data ... Table 1: TF binding prediction for different cancer tissues.
Researcher Affiliation Academia 1 Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA 02115 2 Channing Division of Network Medicine, Brigham and Women s Hospital, 3 Harvard Medical School, Boston, MA 02115
Pseudocode No The paper describes algorithms but does not provide pseudocode or algorithm blocks. It refers to detailed algorithms in the supplement.
Open Source Code Yes OTTER is available in R, Python, and MATLAB through the net Zoo packages: net Zoo R v0.7 (https://github. com/net Zoo/net Zoo R), net Zoo Py v0.7 (https://github.com/ net Zoo/net Zoo Py), and net Zoo M v0.5 (https://github.com/ net Zoo/net Zoo M). We provide a tutorial to walk the users through the usage of OTTER in R (https://netzoo.github.io/net Zoo R/).
Open Datasets Yes We obtained bulk RNA-seq data from the Cancer Genome Atlas (TCGA) (Tomczak, Czerwi nska, and Wiznerowicz 2015). The data is downloaded from recount2 (Collado-Torres et al. 2017).
Dataset Splits Yes Breast and cervix data serve therefore as training data while the liver cancer data is an independent test set. Hyperparameter tuning of OTTER was assisted by MATLAB s bayesopt function utilizing a Gaussian process prior to maximize the joint AUC-PR for breast and cervix cancer, max AUPRbreast AUPRcervix.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., CPU, GPU models).
Software Dependencies No The paper mentions using the 'ADAM method (Kingma and Ba 2014)' and 'MATLAB s bayesopt function' but does not specify version numbers for these or other software dependencies.
Experiment Setup Yes ADAM gradient descent for the OTTER objective is run for 10^4 steps with the default ADAM parameters, as detailed in the supplement. For both the gradient decent and the spectral approach, we use parameters γ = σ^2 p/c = σ^2 p = σ^2 c and λ = 0.5. Hyperparameter tuning of OTTER was assisted by MATLAB s bayesopt function utilizing a Gaussian process prior to maximize the joint AUC-PR for breast and cervix cancer, max AUPRbreast AUPRcervix.