Using genes which have been experimentally-validated for diseases (functions) can develop machine learning methods to predict new disease/function-genes. However, the prediction of both function-genes and disease-genes faces the same problem: there are only certain positive examples, but no negative examples. To solve this problem, we proposed a function/disease-genes prediction algorithm based on network embedding (Variational Graph Auto-Encoders, VGAE) and one-class classification (Fast Minimum Covariance Determinant, Fast-MCD): VGAEMCD. Firstly, we constructed a protein-protein interaction (PPI) network centered on experimentally-validated genes; then VGAE was used to get the embeddings of nodes (genes) in the network; finally, the embeddings were input into the improved deep learning one-class classifier based on Fast-MCD to predict function/disease-genes. VGAEMCD can predict function-gene and disease-gene in a unified way, and only the experimentally-verified genes are needed to provide (no need for expression profile). VGAEMCD outperforms classical one-class classification algorithms in Recall, Precision, F-measure, Specificity, and Accuracy. Further experiments show that seven metrics of VGAEMCD are higher than those of state-of-art function/disease-genes prediction algorithms. The above results indicate that VGAEMCD can well learn the distribution characteristics of positive examples and accurately identify function/disease-genes.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s12539-024-00638-7 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Integrating hyperspectrograms with class modeling techniques for the construction of an effective expert system: Quality control of pharmaceutical tablets based on near-infrared hyperspectral imaging.
J Pharm Biomed Anal
January 2025
Institute of Chemistry, University of Silesia in Katowice, 9 Szkolna Street, Katowice 40-006, Poland; SPIN-Lab Centre for Microscopic Studies on Matter, University of Silesia in Katowice, 75 Pulku Piechoty Street 1, Chorzow 41-500, Poland. Electronic address:
Near-infrared hyperspectral imaging (NIR-HSI) integrated with expert systems can support the monitoring of active pharmaceutical ingredients (APIs) and provide effective quality control of tablet formulations. However, existing quality control methods usually test a limited number of variability sources affecting the final product. This study examines the potential of NIR-HSI (in the spectral range of 935.
View Article and Find Full Text PDFC-parameter version of robust bounded one-class support vector classification.
Sci Rep
January 2025
College of Mathematics and Systems Science, Xinjiang University, Urumqi , 830046, China.
ν-one-class support vector classification (ν-OCSVC) has garnered significant attention for its remarkable performance in handling single-class classification and anomaly detection. Nonetheless, the model does not yield a unique decision boundary, and potentially compromises learning performance when the training data is contaminated by some outliers or mislabeled observations. This paper presents a novel C-parameter version of bounded one-class support vector classification (C-BOCSVC) to determine a unique decision boundary.
View Article and Find Full Text PDFApplication of Online Anomaly Detection Using One-Class Classification to the Z24 Bridge.
Sensors (Basel)
December 2024
Department of Computer Science, ETH Zürich, 8092 Zurich, Switzerland.
The usage of anomaly detection is of critical importance to numerous domains, including structural health monitoring (SHM). In this study, we examine an online setting for damage detection in the Z24 bridge. We evaluate and compare the performance of the elliptic envelope, incremental one-class support vector classification, local outlier factor, half-space trees, and entropy-guided envelopes.
View Article and Find Full Text PDFPan-Ret: a semi-supervised framework for scalable detection of pan-retinal diseases.
Med Biol Eng Comput
December 2024
Jadavpur University, Kolkata, India.
It has been shown in recent years that a range of optical diseases have early manifestation in retinal fundus images. It is becoming increasingly important to separate the regions of interest (RoI) upfront in the automated classification pipeline in order to ensure the alignment of the disease diagnosis with clinically relevant visual features. In this work, we introduce Pan-Ret, a semi-supervised framework which starts with locating the abnormalities in the biomedically relevant RoIs of a retinal image in an "annotation-agnostic" fashion.
View Article and Find Full Text PDFApplication of one-class classification using deep learning technique improves the classification of subvisible particles.
J Pharm Sci
November 2024
Laboratory of Clinical Science and Biomedicine, Graduate School of Pharmaceutical Sciences, Osaka University, Suita, Osaka, Japan; Integrated Frontier Research for Medical Science Division, Institute for Open and Transdisciplinary Research Initiatives, Osaka University, Suita, Japan. Electronic address:
Article Synopsis
- Capturing subvisible particles with flow imaging microscopy helps evaluate protein aggregates that could cause immunogenic reactions, requiring effective differentiation of harmless components like silicone oil from these particles.
- One-class classifiers, which use only data from the target class, can be utilized in machine learning to distinguish heterogeneous distributions, but their effectiveness on subvisible particles was previously uncertain.
- This study explores deep learning's role in enhancing classification accuracy for protein aggregates, finding that it significantly improves one-class classification, particularly for immunoglobulin G-derived aggregates.
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!