A framework combines supervised learning and dense subgraphs discovery to predict protein complexes

Mei, Suyu

doi:10.1007/s11704-021-0476-8

Cited by 7 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is considered the best clustering output ( HMs best ), and its parameters are appropriate for the input PPI network of the MP algorithm. At this time, this harmony is the identified protein complexes (IPCs)(lines [40][41][42].…”

Section: Mp-ahsa Algorithmmentioning

confidence: 98%

“…In 2021, Zaki et al [39] introduced graph convolutional network approaches to improve the ability to detect protein complexes. Mei et al [40] proposed a computational framework that combines supervised learning and dense subgraph to predict protein complexes. Furthermore, Liu et al [41] proposed a new algorithm based on a semi-supervised model to identify significant protein complexes with clear module structures.…”

Section: Data Integrationmentioning

confidence: 99%

See 1 more Smart Citation

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

Wang

Wang²,

Ma³

2022

BMC Bioinformatics

View full text Add to dashboard Cite

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.

show abstract

Section: Mp-ahsa Algorithmmentioning

confidence: 98%

Section: Data Integrationmentioning

confidence: 99%

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

Wang

Wang²,

Ma³

2022

BMC Bioinformatics

View full text Add to dashboard Cite

show abstract

“…This is followed by the establishment of protein–protein interaction (PPI) networks through non-covalent forces [ 3 ], regulating both structure and function. Subsequently, PPI networks assemble into protein complexes [ 4 , 5 ], which serve as molecular machines for realizing protein functions and executing life activities. It is noteworthy that not all proteins require complex formation and some can independently execute their functions.…”

Section: Introductionmentioning

confidence: 99%

A comprehensive review and comparison of existing computational methods for protein function prediction

Lin,

Luo,

Liu

et al. 2024

Briefings in Bioinformatics

View full text Add to dashboard Cite

Protein function prediction is critical for understanding the cellular physiological and biochemical processes, and it opens up new possibilities for advancements in fields such as disease research and drug discovery. During the past decades, with the exponential growth of protein sequence data, many computational methods for predicting protein function have been proposed. Therefore, a systematic review and comparison of these methods are necessary. In this study, we divide these methods into four different categories, including sequence-based methods, 3D structure-based methods, PPI network-based methods and hybrid information-based methods. Furthermore, their advantages and disadvantages are discussed, and then their performance is comprehensively evaluated and compared. Finally, we discuss the challenges and opportunities present in this field.

show abstract

“…In esophageal cancer (EC), the long noncoding RNA ADAMTS9-AS2 effectively suppresses cancer cell proliferation, invasion, and migration processes . Therefore, investigating potential associations between LncRNAs and diseases contributes to the prevention, detection, and treatment of relevant diseases in humans. − While traditional biological experimental methods exhibit high accuracy in discovering potential correlations, the process is intricate and time-consuming. , Hence, capitalizing on the rapid development of computer technology, developing an efficient and convenient computational method for detecting the correlation between LncRNAs and diseases is of significant importance. − Cheng et al presented the first solution for predicting associations in LncRNA-disease relationships. Subsequently, an increasing number of computational prediction models, , including matrix factorization, have been applied to predict LncRNA-disease associations.…”

Section: Introductionmentioning

confidence: 99%

HPTRMF: Collaborative Matrix Factorization-Based Prediction Method for LncRNA-Disease Associations Using High-Order Perturbation and Flexible Trifactor Regularization

Xie,

Li,

Lin

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Existing matrix factorization methods face challenges, including the cold start problem and global nonlinear data loss during similarity learning, particularly in predicting associations between long noncoding RNAs (LncRNAs) and diseases. To overcome these issues, we introduce HPTRMF, a matrix factorization approach incorporating high-order perturbation and flexible trifactor regularization. HPTRMF constructs a high-order correlation matrix utilizing the known association matrix, leveraging highorder perturbation to effectively address the cold start problem caused by data sparsity. Additionally, HPTRMF incorporates a flexible trifactor regularization term to capture similarity information on LncRNAs and diseases, enabling the effective handling of global nonlinear data loss by capturing such data in the similarity matrix. Experimental results demonstrate the superiority of HPTRMF over nine state-of-the-art algorithms in Leave-One-Out Cross-Validation (LOOCV) and Five-Fold Cross-Validation (5-Fold CV) on three data sets.HPTRMF and data sets are available in https://github.com/Llvvvv/HPTRMF.

show abstract

A framework combines supervised learning and dense subgraphs discovery to predict protein complexes

Cited by 7 publications

References 44 publications

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

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

A comprehensive review and comparison of existing computational methods for protein function prediction

HPTRMF: Collaborative Matrix Factorization-Based Prediction Method for LncRNA-Disease Associations Using High-Order Perturbation and Flexible Trifactor Regularization

Contact Info

Product

Resources

About