Novel Geometric Approach for Global Alignment of PPI Networks

Authors: Yangwei Liu, Hu Ding, Danyang Chen, Jinhui Xu

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments We compare our algorithm with 4 popular alignment algorithms, including Iso Rank, MI-GRAAL, GHOST and NETAL. We choose the value of λ and μ in Geo Align using a 10-fold cross-validation on the NAPAbench CG data optimizing the specificity. Datasets For synthetic data, we use the NAPAbench (Sahraeian and Yoon 2012), which is a widely accepted synthetic benchmark dataset with functional annotation of proteins. [...] Results on Synthetic Dataset Results on the NAPAbench dataset are summarized in Tables 1 to 3. Note that for MNE, smaller value is better, while for other metrics, larger value is better. The best performer in each row is shown in black.
Researcher Affiliation Academia Yangwei Liu,1 Hu Ding,2 Danyang Chen,1 Jinhui Xu1 1Department of Computer Science and Engineering, State University of New York at Buffalo 2Department of Computer Science and Engineering, Michigan State University
Pseudocode Yes Algorithm 1 Structure Preserving Embedding; Algorithm 2 Preprocessing; Algorithm 3 Iterative Closest Point; Algorithm 4 Geo Align
Open Source Code No The paper does not include any explicit statement about providing open-source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes For synthetic data, we use the NAPAbench (Sahraeian and Yoon 2012), which is a widely accepted synthetic benchmark dataset with functional annotation of proteins. [...] For real world data, we use the PPI networks of C.elegans, D.melanogaster, S.cerevisiae, and H.sapiens from the Iso Base data set (Park et al. 2011).
Dataset Splits Yes We choose the value of λ and μ in Geo Align using a 10-fold cross-validation on the NAPAbench CG data optimizing the specificity.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiments.
Experiment Setup No The paper states that the values of λ and μ were chosen using cross-validation ('We choose the value of λ and μ in Geo Align using a 10-fold cross-validation...'), but it does not explicitly list their specific values or other concrete hyperparameter settings.