Predicting circRNA–Disease Associations through Multisource Domain-Aware Embeddings and Feature Projection Networks

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 19, 2025

Recent studies have highlighted the significant role of circular RNAs (circRNAs) in various diseases. Accurately predicting circRNA–disease associations is crucial for understanding their biological functions and disease mechanisms. This work introduces MNDCDA method, designed to address challenges posed by limited number known high cost experiments. integrates multiple data sources with neighborhood-aware embedding models deep feature projection networks predict potential pathways linking circRNAs Initially, comprehensive biometric are used construct four similarity networks, forming a diverse interaction framework. Next, model captures structural information about diseases, while learn high-order interactions nonlinear connections. Finally, bilinear decoder identifies novel between The achieved an AUC 0.9070 on constructed benchmark dataset. In case studies, 25 out 30 predicted pairs were validated through wet lab experiments published literature. These extensive experimental results demonstrate that robust computational tool associations, providing valuable insights helping reduce research costs.

Language: Английский

---

Determination of Colorectal Cancer and Lung Cancer Related LncRNAs based on Deep Autoencoder and Deep Neural Network

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Dec. 29, 2024

Until recently, non-coding RNAs were considered junk RNA and always ignored, but studies have revealed that many such as miRNA, lncRNA, circRNAs play important roles in biological processes. A subclass of with transcripts longer than 200 nucleotides, called lncRNAs, cellular processes gene regulation. For this reason, since wet experimental to identify disease-related lncRNA are time-consuming, computational methods used. Many researchers applied similarity-based machine learning-based achieved very successful results. Due its high success rate, the deep learning technique is fields today. In study, we used Deep Autoencoder Neural Network method predict disease related lncRNAs. As input data Autoencoder, concatenated feature vector obtained from integrated similarity was To train neural network for predicting relationships between lncRNAs diseases, features extracted autoencoder’s output utilized. The prediction performance our evaluated commonly 5-fold cross validation an AUC value 0.9575 obtained. It can be seen proposed more other compared methods. Additionally, case on colorectal cancer lung conducted confirmed literature. a result, reliably candidate

Language: Английский

---

Investigation and calculation of electrical performance of lead-free AgBiI4 perovskite based Schottky photodiode using machine learning

Journal of Materials Science Materials in Electronics, Journal Year: 2025, Volume and Issue: 36(11)

Published: April 1, 2025

Language: Английский

---

GCLNSTDA: Predicting tsRNA-Disease Association Based on Contrastive Learning and Negative Sampling

Published: Nov. 22, 2024

Language: Английский

---

Predicting human miRNA disease association with minimize matrix nuclear norm

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 28, 2024

microRNAs (miRNAs) are non-coding RNA molecules that influence the development and progression of many diseases. Research have documented miRNAs a significant role in prevention, diagnosis, treatment complex human Recently, scientists devoted extensive resources to attempting find connections between Since experimental methods used discover new miRNA-disease associations time-consuming expensive, computational been developed. In this research, novel method based on matrix decomposition was proposed predict Furthermore, nuclear norm minimization employed acquire breast cancer-associated miRNAs. We then evaluated effectiveness our by utilizing two different cross-validation techniques results were compared seven methods. Moreover, case study cancer further validated technique, confirming its predictive accuracy. These demonstrate is reliable model for uncovering potential relationships.

Language: Английский

---

An Ensemble approach for Circular RNA-Disease Association prediction using Variational Autoencoder and Genetic Algorithm

Journal of Bioinformatics and Computational Biology, Journal Year: 2024, Volume and Issue: 22(04)

Published: July 5, 2024

Circular RNAs (circRNAs) are endogenous non-coding with a covalently closed loop structure. They have many biological functions, mainly regulatory ones. been proven to modulate protein-coding genes in the human genome. CircRNAs linked various diseases like Alzheimer's disease, diabetes, atherosclerosis, Parkinson's disease and cancer. Identifying associations between circular is essential for diagnosis, prevention, treatment. The proposed model, based on variational autoencoder genetic algorithm RNA association (VAGA-CDA), predicts novel circRNA-disease associations. First, experimentally verified augmented synthetic minority oversampling technique (SMOTE) regenerated using autoencoder, feature selection applied these vectors by (GA). effectively extracts features from samples. optimized of carried out dimensionality reduction. sophisticated extracted then given Random Forest classifier predict new model yields an AUC value 0.9644 0.9628 under 5-fold 10-fold cross-validations, respectively. results case studies indicate robustness model.

Language: Английский

---