Predicting receptor-ligand pairs through kernel learning.

BMC Bioinformatics

SCD-ESAT, Department of Electrical Engineering, Katholieke Universiteit Leuven, Kasteelpark Arenberg 10, Leuven 3001, Belgium.

Published: August 2011

AI Article Synopsis

  • Extracellular signaling initiates cellular events by ligands interacting with membrane-bound receptors, making the identification of receptor-ligand pairs crucial for predicting protein-protein interactions (PPIs).
  • Utilizing various data sources like expression data and phylogenetic profiles, we developed a combined kernel classifier to predict new receptor-ligand pairs, achieving notable results for the tgfβ family.
  • Our method outperformed previous approaches, improving precision and recall rates, highlighting the effectiveness of multi-source kernel learning in addressing the challenges of receptor-ligand prediction.

Article Abstract

Background: Regulation of cellular events is, often, initiated via extracellular signaling. Extracellular signaling occurs when a circulating ligand interacts with one or more membrane-bound receptors. Identification of receptor-ligand pairs is thus an important and specific form of PPI prediction.

Results: Given a set of disparate data sources (expression data, domain content, and phylogenetic profile) we seek to predict new receptor-ligand pairs. We create a combined kernel classifier and assess its performance with respect to the Database of Ligand-Receptor Partners (DLRP) 'golden standard' as well as the method proposed by Gertz et al. Among our findings, we discover that our predictions for the tgfβ family accurately reconstruct over 76% of the supported edges (0.76 recall and 0.67 precision) of the receptor-ligand bipartite graph defined by the DLRP "golden standard". In addition, for the tgfβ family, the combined kernel classifier is able to relatively improve upon the Gertz et al. work by a factor of approximately 1.5 when considering that our method has an F-measure of 0.71 while that of Gertz et al. has a value of 0.48.

Conclusions: The prediction of receptor-ligand pairings is a difficult and complex task. We have demonstrated that using kernel learning on multiple data sources provides a stronger alternative to the existing method in solving this task.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3199765PMC
http://dx.doi.org/10.1186/1471-2105-12-336DOI Listing

Publication Analysis

Top Keywords

receptor-ligand pairs
12
kernel learning
8
extracellular signaling
8
data sources
8
combined kernel
8
kernel classifier
8
tgfβ family
8
predicting receptor-ligand
4
kernel
4
pairs kernel
4

Similar Publications

Diversity in Notch ligand-receptor signaling interactions.

Elife

January 2025

Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, United States.

The Notch signaling pathway uses families of ligands and receptors to transmit signals to nearby cells. These components are expressed in diverse combinations in different cell types, interact in a many-to-many fashion, both within the same cell (in cis) and between cells (in trans), and their interactions are modulated by Fringe glycosyltransferases. A fundamental question is how the strength of Notch signaling depends on which pathway components are expressed, at what levels, and in which cells.

View Article and Find Full Text PDF

Background: Many putative factors may contribute to the neurodegeneration seen in Alzheimer's Disease (AD), including the build-up of toxic amyloid-beta plaques and the aberrant reactivity of non-neuronal cell types such as astrocytes and microglia. However, the precise contribution of these factors to normal and disease states of neurons remains poorly defined.

Method: We employed in vitro rat neural co-culture models to determine how changes in cell interactions alter the transcriptional response of neural cell types to agents associated with neurodegeneration.

View Article and Find Full Text PDF

PD-L1 upregulation in activated fibroblasts promotes silica particle-induced pulmonary fibrosis.

Int J Biol Macromol

December 2024

Department of Occupational Health and Occupational Disease, College of Public Health, Zhengzhou University, Zhengzhou, Henan, China. Electronic address:

Silicosis is a severe interstitial lung disease resulting from prolonged exposure to silica dust in working environment, characterized by inflammation and fibrosis. This condition is closely associated with immune dysregulation, although the precise regulatory mechanisms remain elusive. Immune checkpoints (ICs) comprise receptor-ligand pairs crucial for immune cell activation and coordination of immune responses.

View Article and Find Full Text PDF

Schwann Cell-Mediated M2-Like Macrophage Polarization in Rhabdomyosarcoma.

Oral Dis

December 2024

Department of Oral Maxillofacial-Head Neck Oncology, Shanghai Ninth People's Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.

Article Synopsis
  • The study aimed to explore the cellular and immunological features of the rhabdomyosarcoma (RMS) microenvironment using single-cell transcriptomics and various analytical methods.
  • Results indicated a significantly lower presence of neutrophils in RMS samples, while increased M2-like macrophages were associated with higher Schwann cell infiltration, revealing specific cellular interactions.
  • The findings highlight the unique characteristics of the RMS microenvironment, paving the way for potential research advancements and therapeutic developments.
View Article and Find Full Text PDF

Biased cell adhesion organizes the Drosophila visual motion integration circuit.

Dev Cell

November 2024

MCD, Centre de Biologie Intégrative (CBI), CNRS, Université de Toulouse, UT3, Toulouse, France. Electronic address:

Layer-specific brain computations depend on neurons synapsing with specific partners in distinct laminae. In the Drosophila lobula plate, axons of the four subtypes of T4 and T5 visual motion direction-selective neurons segregate into four layers, where they synapse with distinct subsets of postsynaptic neurons. Here, we identify a layer-specific expression of different receptor-ligand pairs of the Beat and Side families of cell adhesion molecules between T4/T5s and their postsynaptic partners.

View Article and Find Full Text PDF

Want 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!