Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Support vector machines (SVMs) have become a popular technique in the chemometrics and bioinformatics field, and other fields, for the classification of complex data sets. Especially because SVMs are able to model nonlinear relationships, the usage of this technique has increased substantially. This modeling is obtained by mapping the data in a higher-dimensional feature space. The disadvantage of such a transformation is, however, that information about the contribution of the original variables in the classification is lost. In this paper we introduce an innovative method which can retrieve the information about the variables of complex data sets. We apply the proposed method to several benchmark data sets and a metabolomics data set to illustrate that we can determine the contribution of the original variables in SVM classifications. The corresponding visualization of the contribution of the variables can assist in a better understanding of the underlying chemical or biological process.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1021/ac101338y | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Predicting HOMO-LUMO Gaps Using Hartree-Fock Calculated Data and Machine Learning Models.
J Chem Inf Model
September 2025
Department of Chemistry, Delaware State University, Dover, Delaware 19901, United States.
The calculation of the highest occupied molecular orbital-lowest unoccupied molecular orbital (HOMO-LUMO) gap for chemical molecules is computationally intensive using quantum mechanics (QM) methods, while experimental determination is often costly and time-consuming. Machine Learning (ML) offers a cost-effective and rapid alternative, enabling efficient predictions of HOMO-LUMO gap values across large data sets without the need for extensive QM computations or experiments. ML models facilitate the screening of diverse molecules, providing valuable insights into complex chemical spaces and integrating seamlessly into high-throughput workflows to prioritize candidates for experimental validation.
View Article and Find Full Text PDFThe Minoan Thera eruption predates Pharaoh Ahmose: Radiocarbon dating of Egyptian 17th to early 18th Dynasty museum objects.
PLoS One
September 2025
University of Groningen, Centre for Isotope Research, Groningen, the Netherlands.
The huge volcanic eruption at Thera (Santorini), situated in the Aegean Sea, occurred within the Late Minoan IA archaeological period. However, its temporal association with Egyptian history has long been a controversial subject. Traditionally, the eruption was placed in the early 18th Dynasty, associated with Pharaoh Thutmose III as the youngest option or with Pharaoh Nebpehtire Ahmose as the oldest possibility.
View Article and Find Full Text PDFIdentification and prioritization of gene sets associated with schizophrenia risk by network analysis.
Psychopharmacology (Berl)
September 2025
Institute of Cardiovascular Research, Sleep Medical Center, Department of Psychiatry, Fundamental and Clinical Research on Mental Disorders Key Laboratory of Luzhou, Affiliated Hospital, Southwest Medical University, Luzhou, Sichuan Province, 646000, China.
Rationale: Genome-wide association studies (GWASs) are used to identify genetic variants for association with schizophrenia (SCZ) risk; however, each GWAS can only reveal a small fraction of this association.
Objectives: This study systematically analyzed multiple GWAS data sets to identify gene subnetwork and pathways associated with SCZ.
Methods: We identified gene subnetwork using dmGWAS program by combining SCZ GWASs and a human interaction network, performed gene-set analysis to test the association of gene subnetwork with clinical symptom scores and disease state, meanwhile, conducted spatiotemporal and tissue-specific expression patterns and cell-type-specific analysis of genes in the subnetwork.
Nisin-like biosynthetic gene clusters are widely distributed across microbiomes.
mBio
September 2025
APC Microbiome Ireland, Biosciences Institute, Biosciences Research Institute, University College, Cork, Ireland.
Bacteriocins are antimicrobial peptides/proteins that can have narrow or broad inhibitory spectra and remarkable potency against clinically relevant pathogens. One such bacteriocin that is extensively used in the food industry and with potential for biotherapeutic application is the post-translationally modified peptide, nisin. Recent studies have shown the impact of nisin on the gastrointestinal microbiome, but relatively little is known of how abundant nisin production is in nature, the breadth of existing variants, and their antimicrobial potency.
View Article and Find Full Text PDFDevelopment of Coarse-Grained Lipid Force Fields Based on a Graph Neural Network.
J Chem Theory Comput
September 2025
Department of Materials Science and Engineering, City University of Hong Kong, Kowloon 999077, Hong Kong China.
Coarse-grained (CG) lipid models enable efficient simulations of large-scale membrane events. However, achieving both speed and atomic-level accuracy remains challenging. Graph neural networks (GNNs) trained on all-atom (AA) simulations can serve as CG force fields, which have demonstrated success in CG simulations of proteins.
View Article and Find Full Text PDF