Drug-drug interactions (DDIs) prediction is a challenging task in drug development and clinical application. Due to the extremely large complete set of all possible DDIs, computer-aided DDIs methods are getting lots attention pharmaceutical industry academia. However, most existing computational only use single perspective information few them conduct based on biomedical knowledge graph (BKG), which can provide more detailed comprehensive lateral side flow. To this end, deep learning...

Abstract Background Drug-target interaction (DTI) prediction has become a crucial prerequisite in drug design and discovery. However, the traditional biological experiment is time-consuming expensive, as there are abundant complex interactions present large size of genomic chemical spaces. For alleviating this phenomenon, plenty computational methods conducted to effectively complement experiments narrow search spaces into preferred candidate domain. Whereas, most previous approaches cannot...

The way of co-administration drugs is a sensible strategy for treating complex diseases efficiently. Because existing massive unknown interactions among drugs, predicting potential adverse drug-drug (DDIs) accurately promotive to prevent unanticipated interactions, which may cause significant harm patients. Currently, numerous computational studies are focusing on DDIs prediction account traditional experiments in wet lab being time-consuming, labor-consuming, costly and inaccurate. These...

Emerging evidence has revealed that circular RNA (circRNA) is widely distributed in mammalian cells and functions as microRNA (miRNA) sponges involved transcriptional posttranscriptional regulation of gene expression. Recognizing the circRNA–miRNA interaction provides a new perspective for detection treatment human complex diseases. Compared with traditional biological experimental methods used to predict association molecules, which are limited small-scale time-consuming laborious,...

Computational prediction of miRNAs, diseases, and genes associated with circRNAs has important implications for circRNA research, as well provides a reference wet experiments to save costs time. In this study, SGCNCMI, computational model combining multimodal information graph convolutional neural networks, combines node similarity form then predicts nodes using GCN distributive contribution mechanism. The can be used not only predict the molecular level circRNA-miRNA interactions but also...

Abstract According to the expression of miRNA in pathological processes, miRNAs can be divided into oncogenes or tumor suppressors. Prediction regulation relations between and small molecules (SMs) becomes a vital goal for miRNA-target therapy. But traditional biological approaches are laborious expensive. Thus, there is an urgent need develop computational model. In this study, we proposed model predict whether regulatory relationship SMs up-regulated down-regulated. Specifically, first use...

Abnormal microRNA (miRNA) functions play significant roles in various pathological processes. Thus, predicting drug-miRNA associations (DMA) may hold great promise for identifying the potential targets of drugs. However, discovering between drugs and miRNAs through wet experiments is time-consuming laborious. Therefore, it to develop computational prediction methods improve efficiency DMA on a large scale. In this paper, multiple features integration model (MFIDMA) proposed predict...

Vehicle detection based on machine vision is an important part of urban intelligent transportation, and vehicle technology combined with deep learning the mainstream method. In order to overcome low accuracy traditional YOLOv3 algorithm for small targets. this paper, we add a larger convolution layer basis three layers YOLOv3, use k-means++ clustering get 12 anchor frames again. method, newly added 104*104 feature scale more suitable target than original it easier global optimal point by...

LncRNA-protein interaction plays an important role in the development and treatment of many human diseases. As experimental approaches to determine lncRNA-protein interactions are expensive time-consuming, considering that there few calculation methods, therefore, it is urgent develop efficient accurate methods predict interactions. In this work, a model for heterogeneous network embedding based on meta-path, namely LPIH2V, proposed. The composed lncRNA similarity networks, protein known...

Non-coding RNAs (ncRNAs) take essential effects on biological processes, like gene regulation. One critical way of ncRNA executing functions is interactions between and RNA binding proteins (RBPs). Identifying proteins, involving ncRNA-protein interactions, can well understand the function ncRNA. Many high-throughput experiment have been applied to recognize interactions. As a consequence these approaches are time- labor-consuming, currently, great number computational methods developed...

Protein–protein interactions (PPIs) in plants play an essential role the regulation of biological processes. However, traditional experimental methods are expensive, time-consuming, and need sophisticated technical equipment. These drawbacks motivated development novel computational approaches to predict PPIs plants. In this article, a new deep learning framework, which combined discrete Hilbert transform (DHT) with neural networks (DNN), was presented To be more specific, plant protein...

During the development of drug and clinical applications, due to co-administration different drugs that have a high risk interfering with each other’s mechanisms action, correctly identifying potential drug–drug interactions (DDIs) is important avoid reduction in therapeutic activities serious injuries organism. Therefore, explore DDIs, we develop computational method integrating multi-level information. Firstly, information chemical sequence fully captured by Natural Language Processing...

As a novel target in pharmacy, microRNA (miRNA) can regulate gene expression under specific disease conditions to produce proteins. To date, many researchers leveraged miRNA reveal drug efficacy and pathogenesis at the molecular level. we all know that conventional wet experiments suffer from problems, including time-consuming, labor-intensity, high cost. Thus, there is an urgent need develop computational model facilitate identification of miRNA-drug interactions (MDIs). In this work,...

Oracle is the earliest known systematic writing in our country. It mostly originated from Shang Dynasty royal divination. The records cover a wide range of contents, including national politics, social atmosphere, and military wars. bone inscriptions are also source modem Chinese characters my country, they carry history civilization for thousands years. At present, oracle still rely on manual identification then handed over to experts decipher, level information low. Therefore, order...

Protein-protein interactions (PPIs) in plants are essential for understanding the regulation of biological processes. Although high-throughput technologies have been widely used to identify PPIs, they usually laborious, expensive, and suffer from high false-positive rates. Therefore, it is imperative develop novel computational approaches as a supplement tool detect PPIs plants. In this work, we presented method, namely DST-RoF, by combining an ensemble learning classifier-Rotation Forest...

Abstract According to the expression of miRNA in pathological processes, miRNAs can be divided into oncogenes or tumor suppressors. Prediction regulation relations between and small molecules (SMs) becomes a vital goal for miRNA-target therapy. But traditional biological approaches are laborious expensive. Thus, there is an urgent need develop computational model. In this study, we proposed model predict whether regulatory relationship SMs up-regulated down-regulated. Specifically, first use...