Detecting protein complexes with multiple properties by an adaptive harmony search algorithm

Abstract

Background Accurate identification of protein complexes in protein-protein interaction (PPI) networks is crucial for understanding the principles of cellular organization. Most computational methods ignore the fact that proteins in a protein complex have a functional similarity and are co-localized and co-expressed at the same place and time, respectively. Meanwhile, the parameters of the current methods are specified by users, so these methods cannot effectively deal with different input PPI networks. Result To address these issues, this study proposes a new method called MP-AHSA to detect protein complexes with Multiple Properties (MP), and an Adaptation Harmony Search Algorithm is developed to optimize the parameters of the MP algorithm. First, a weighted PPI network is constructed using functional annotations, and multiple biological properties and the Markov cluster algorithm (MCL) are used to mine protein complex cores. Then, a fitness function is defined, and a protein complex forming strategy is designed to detect attachment proteins and form protein complexes. Next, a protein complex filtering strategy is formulated to filter out the protein complexes. Finally, an adaptation harmony search algorithm is developed to determine the MP algorithm’s parameters automatically. Conclusions Experimental results show that the proposed MP-AHSA method outperforms 14 state-of-the-art methods for identifying protein complexes. Also, the functional enrichment analyses reveal that the protein complexes identified by the MP-AHSA algorithm have significant biological relevance.

Molecular complex detection in protein interaction networks through reinforcement learning

“…In contrast, the RL algorithm predicts a higher number (1157) of complexes possibly explaining the slightly higher (FMM) recall measure (Table 2 ). The RL method achieves comparable performance to the supervised method, Super.Complex and tends to outperform 4 recent unsupervised community detection methods, ClusterONE + MCL [ 6 ], PC2P [ 25 ], MP-AHSA [ 26 ], and DPCMNE [ 27 ] (Table 2 ), demonstrating the potential of applying reinforcement learning to community detection.…”

“…However, HiSCF may face challenges when applied to large interaction networks due to memory requirements and computational complexity. Recent unsupervised algorithms include PC2P, which uses a greedy approximation algorithm based on biclique subgraph properties [ 25 ], and MP-AHSA which uses a fitness function for biological similarities within complexes and optimizes a core-attachment-based algorithm for complex identification [ 26 ]. Another method, DPCMNE recursively compresses PPI networks, learns multi-level protein embeddings, and applies a core-attachment approach based on the embeddings’ similarities [ 27 ].…”

Correction: Detecting protein complexes with multiple properties by an adaptive harmony search algorithm

“…Following publication of the original article [ 1 ], the authors would like to remove the symbol of equal contribution behind the names.…”