Table 3 Biclustering algorithms considered for this study. Additionally, they will be compared to three popular clustering algorithms: k-means, spectral, and ward’s hierarchical methods. For clustering, we use scikit-learn implementations [64]
Algorithm | Type of search | Available at | References | Reason to choose it |
|---|---|---|---|---|
BicPAM | Exhaustive | BicPAMS | State-of-the-art pattern mining based biclustering method | |
CCC | Exhaustive | BiGGEsTS | Allows to obtain temporal contiguous biclusters efficiently | |
ISA | Greedy | isa2 | [35] | State-of-the-art greedy algorithm able to deal with real data |
XMotifs | Greedy | biclust | State-of-the-art greedy algorithm based on a strategy of discretizating data | |
Bimax | Divide and conquer | biclust | Very fast algorithm able to detect simple structures | |
FABIA | Distribution parameter identification | FABIA | [38] | State-of-the-art algorithm |
Spectral Biclustering | Distribution parameter identification | biclust | State-of-the-art algorithm able to detect a specific type of bicluster structures |