Long non-coding RNA (lncRNA) play critical roles in the occurrence and development of various diseases. The determination lncRNA-disease associations thus would contribute to provide new insights into pathogenesis disease, diagnosis, gene treatments. Considering that traditional experimental approaches are difficult detect potential human from vast amount biological data, developing computational method could be significant value. In this paper, we proposed a novel named LDASR identify...

Found in recent research, tumor cell invasion, proliferation, or other biological processes are controlled by circular RNA. Understanding the association between circRNAs and diseases is an important way to explore pathogenesis of complex promote disease-targeted therapy. Most methods, such as k-mer PSSM, based on analysis high-throughput expression data have tendency think functionally similar nucleic acid lack direct linear homology regardless positional information only quantify nonlinear...

Predicting drug-target interactions (DTIs) is crucial in innovative drug discovery, repositioning and other fields. However, there are many shortcomings for predicting DTIs using traditional biological experimental methods, such as the high-cost, time-consumption, low efficiency, so on, which make these methods difficult to widely apply. As a supplement, silico method can provide helpful information predictions of timely manner. In this work, deep walk embedding developed from...

Abstract Background The interactions between non-coding RNAs (ncRNA) and proteins play an essential role in many biological processes. Several high-throughput experimental methods have been applied to detect ncRNA-protein interactions. However, these are time-consuming expensive. Accurate efficient computational can assist accelerate the study of Results In this work, we develop a stacking ensemble framework, RPI-SE, for effectively predicting More specifically, fully exploit protein RNA...

Abstract Effectively representing Medical Subject Headings (MeSH) headings (terms) such as disease and drug discriminative vectors could greatly improve the performance of downstream computational prediction models. However, these terms are often abstract difficult to quantify. In this paper, we converted MeSH tree structure into a relationship network applied several graph embedding algorithms on it represent terms. Specifically, consisting nodes (MeSH headings) edges (relationships), which...

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with time-consuming and labor-intensive vivo experimental methods, computational models can provide high-quality DTI candidates an instant. In this study, we propose novel method called LGDTI to predict DTIs based on large-scale graph representation learning. capture local global structural information graph. Specifically, first-order neighbor nodes be aggregated...

Single-cell RNA-seq (scRNA-seq) data from multiple species present remarkable opportunities to explore cellular origins and evolution. However, integrating annotating scRNA-seq across different remains challenging due the variations in sequencing techniques, ambiguity of homologous relationships, limited biological knowledge. To tackle above challenges, we introduce CAMEX, a heterogeneous Graph Neural Network (GNN) tool that leverages many-to-many relationships for multi-species integration,...

One key issue in the post-genomic era is how to systematically describe associations between small molecule transcripts or translations inside cells. With rapid development of high-throughput "omics" technologies, achieved ability detect and characterize molecules with other targets opens possibility investigating relationships different from a global perspective. In this article, molecular association network (MAN) constructed comprehensively analyzed by integrating among miRNA, lncRNA,...

The prediction of potential drug-target interactions (DTIs) not only provides a better comprehension biological processes but also is critical for identifying new drugs. However, due to the disadvantages expensive and high time-consuming traditional experiments, small section between drugs targets in database were verified experimentally. Therefore, it meaningful important develop computational methods with good performance DTIs prediction. At present, many existing utilize single type...

A key aim of post-genomic biomedical research is to systematically understand molecules and their interactions in human cells. Multiple biomolecules coordinate sustain life activities, between various are interconnected. However, existing studies usually only focusing on associations two or very limited types molecules. In this study, we propose a network representation learning based computational framework MAN-SDNE predict any intermolecular associations. More specifically, constructed...

Abstract Abundant life activities are maintained by various biomolecule relationships in human cells. However, many previous computational models only focus on isolated objects, without considering that cell is a complete entity with ample functions. Inspired holism, we constructed Molecular Associations Network (MAN) including 9 kinds of among 5 types biomolecules, and prediction model called MAN-GF. More specifically, biomolecules can be represented as vectors the algorithm biomarker2vec...

Molecular components that are functionally interdependent in human cells constitute molecular association networks. Disease can be caused by disturbance of multiple interactions. New biomolecular regulatory mechanisms revealed discovering new To this end, a heterogeneous network is formed systematically integrating comprehensive associations between miRNAs, lncRNAs, circRNAs, mRNAs, proteins, drugs, microbes, and complex diseases. We propose machine learning method for predicting...

Analysis of miRNA-target mRNA interaction (MTI) is crucial significance in discovering new target candidates for miRNAs. However, the biological experiments identifying MTIs have a high false positive rate and are high-priced, time-consuming, arduous. It an urgent task to develop effective computational approaches enhance investigation relationships. In this study, novel method called MIPDH developed miRNA-mRNA prediction by using DeepWalk on heterogeneous network. More specifically,...

Identifying proteins that interact with drug compounds has been recognized as an important part in the process of discovery. Despite extensive efforts have invested predicting compound-protein interactions (CPIs), existing traditional methods still face several challenges. The computer-aided can identify high-quality CPI candidates instantaneously. In this research, a novel model is named GraphCPIs, proposed to improve prediction accuracy. First, we establish adjacent matrix entities...

A key aim of post-genomic biomedical research is to systematically understand and model complex biomolecular activities based on a systematic perspective. Biomolecular interactions are widespread interrelated, multiple biomolecules coordinate sustain life activities, any disturbance these connections can lead abnormal or diseases. However, many existing researches usually only focus individual intermolecular interactions. In this work, we revealed, constructed, analyzed large-scale molecular...

Detecting whether a pair of biomolecules associate is great significance in the study molecular biology. Hence, computational methods are urgently needed as guidance for practice. However, most previous prediction models influenced by reductionism focused on isolated research objects, which have their own inherent defects. Inspired holism, machine-learning-based framework called MAN-node2vec proposed to predict multi-type relationships associations network (MAN). Specifically, we constructed...

Benefiting from advances in high-throughput experimental techniques, important regulatory roles of miRNAs, lncRNAs, and proteins, as well biological property information, are gradually being complemented. As the key data support to promote biomedical research, domain knowledge such intermolecular relationships that increasingly revealed by molecular genome-wide analysis is often used guide discovery potential associations. However, method performing network representation learning...

URLs play a crucial role in understanding and categorizing web content, particularly tasks related to security control online recommendations. While pre-trained models are currently dominating various fields, the domain of URL analysis still lacks specialized models. To address this gap, paper introduces URLBERT, first representation learning model applied variety classification or detection tasks. We train tokenizer on corpus billions data tokenization. Additionally, we propose two novel...

Abstract Background The explosive growth of genomic, chemical, and pathological data provides new opportunities challenges for humans to thoroughly understand life activities in cells. However, there exist few computational models that aggregate various bioentities comprehensively reveal the physical functional landscape biological systems. Results We constructed a molecular association network, which contains 18 edges (relationships) between 8 nodes (bioentities). Based on this, we propose...