This study focuses on improving the multi-objective memetic algorithm for protein-protein interaction (PPI) network alignment, Optimizing Network Aligner - OptNetAlign, via integration with other existing network alignment methods such as SPINAL, NETAL and HubAlign. The output of this algorithm is an elite set of aligned networks all of which are optimal with respect to multiple user-defined criteria. However, OptNetAlign is an unsupervised genetic algorithm that initiates its search with completely random solutions and it requires substantial running times to generate an elite set of solutions that have high scores with respect to the given criteria. In order to improve running time, the search space of the algorithm can be narrowed down by focusing on remarkably qualified alignments and trying to optimize the most desired criteria on a more limited set of solutions. The method presented in this study improves OptNetAlign in a supervised fashion by utilizing the alignment results of different network alignment algorithms with varying parameters that depend upon user preferences. Therefore, the user can prioritize certain objectives upon others and achieve better running time performance while optimizing the secondary objectives.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.compbiolchem.2016.03.003 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
scMMAE: masked cross-attention network for single-cell multimodal omics fusion to enhance unimodal omics.
Brief Bioinform
November 2024
Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems, Great Bay University, No. 16 Daxue Rd, Songshanhu District, Dongguan, Guangdong, 523000, China.
Multimodal omics provide deeper insight into the biological processes and cellular functions, especially transcriptomics and proteomics. Computational methods have been proposed for the integration of single-cell multimodal omics of transcriptomics and proteomics. However, existing methods primarily concentrate on the alignment of different omics, overlooking the unique information inherent in each omics type.
View Article and Find Full Text PDFMulti-Label Zero-Shot Learning Via Contrastive Label-Based Attention.
Int J Neural Syst
January 2025
Alibaba Cloud, Hangzhou, P. R. China.
Multi-label zero-shot learning (ML-ZSL) strives to recognize all objects in an image, regardless of whether they are present in the training data. Recent methods incorporate an attention mechanism to locate labels in the image and generate class-specific semantic information. However, the attention mechanism built on visual features treats label embeddings equally in the prediction score, leading to severe semantic ambiguity.
View Article and Find Full Text PDFA novel domain feature disentanglement method for multi-target cross-domain mechanical fault diagnosis.
ISA Trans
January 2025
State Key Laboratory of Computer-Aided Design and Computer Graphics, Zhejiang University, Hangzhou, 310027, China; Key Laboratory of Intelligent Rescue Equipment for Collapse Accidents, Ministry of Emergency Management, Hangzhou, 310030, China; Zhejiang Laboratory, Hangzhou, 311121, China. Electronic address:
Existing cross-domain mechanical fault diagnosis methods primarily achieve feature alignment by directly optimizing interdomain and category distances. However, this approach can be computationally expensive in multi-target scenarios or fail due to conflicting objectives, leading to decreased diagnostic performance. To avoid these issues, this paper introduces a novel method called domain feature disentanglement.
View Article and Find Full Text PDFMVGNN-PPIS: A novel multi-view graph neural network for protein-protein interaction sites prediction based on Alphafold3-predicted structures and transfer learning.
Int J Biol Macromol
January 2025
College of Information Science and Engineering, Northeastern University, China.
Protein-protein interactions (PPI) are crucial for understanding numerous biological processes and pathogenic mechanisms. Identifying interaction sites is essential for biomedical research and targeted drug development. Compared to experimental methods, accurate computational approaches for protein-protein interaction sites (PPIS) prediction can save significant time and costs.
View Article and Find Full Text PDFThe ReAct project: Analysis of data from 23 different laboratories to characterise DNA recovery given two sets of activity level propositions.
Forensic Sci Int Genet
January 2025
Bundeskriminalamt, Wiesbaden, Germany; International Commission on Missing Persons, The Hague, The Netherlands.
The ReAct (Recovery, Activity) project is an ENFSI (European Network of Forensic Science Institutes) supported initiative comprising a large consortium of laboratories. Here, the results from more than 23 laboratories are presented. The primary purpose was to design experiments simulating typical casework circumstances; collect data and to implement Bayesian networks to assess the value (i.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!