GRASMOS: Graph Signage Model Selection for Gene Regulatory Networks

Authors: Angelina Brilliantova, Hannah Miller, Ivona Bezáková

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluated the results of our algorithms on synthetic datasets and real-world large GRNs. Empirical Evaluation Data Collection and Setup Synthetic datasets To validate that our algorithms can correctly identify the GRASMOS parameters, we created synthetic datasets with known Θ, resembling real-world GRNs by their network parameters and size.
Researcher Affiliation Academia Angelina Brilliantova, Hannah Miller, Ivona Bez akov a Rochester Institute of Technology, 102 Lomb Memorial Drive, Rochester, NY 14623 lb9849@rit.edu, hm@mail.rit.edu, ib@cs.rit.edu
Pseudocode No The paper describes algorithmic approaches but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes 1https://github.com/Restel/grasmos
Open Datasets Yes We used two public databases: Regulon DB (Santos-Zavaleta et al. 2019) and Subti Wiki (Pedreira, Elfmann, and St ulke 2022; Fl orez et al. 2009).
Dataset Splits No The paper refers to using 'synthetic datasets' and 'real-world GRN datasets E.coli and B.subtilis' for evaluation. However, it does not explicitly specify exact training, validation, and test splits (e.g., percentages or sample counts) for these datasets.
Hardware Specification Yes We estimated L(Θ) of the BNC parameters using a parallel implementation on the RIT research computing cluster. We used up to 432 nodes with each core estimating a likelihood of a single Θ-candidate via MCMC sampling. Each core is equipped with Intel Xeon Gold 6150 CPU @ 2.70GHz. The RAM upper limit for our computation was 2048 MB.
Software Dependencies No The paper describes algorithmic approaches and computational setup but does not specify any software dependencies with version numbers.
Experiment Setup Yes The parameters within the Θ-candidates varied between 0.1 and 0.9, with an increment step of 0.1. We tested 4 different Θ-generators in the generation part and for each of 1458 of Θ-candidates in the reconstruction part. For fitting the GRASMOS parameters of real-world GRNs, we: used a fine-grained exploration of parameters varying in [0.1, 0.9] with an increment of 0.05 belonging to the SC, TC, and NO models; and, for complexity reasons, we evaluated the BNC model subspace using a coarse-grid with each parameter varying in {0.25, 0.5, 0.75}.