Abstract Motivation An essential part of drug discovery is the accurate prediction binding affinity new compound–protein pairs. Most standard computational methods assume that compounds or proteins test data are observed during training phase. However, in real-world situations, and sampled from different domains with distributions. To cope this challenge, we propose a deep learning-based approach consists three steps. In first step, encoder network learns novel representation proteins. end,...

Abstract Background The Drug–Target Interaction (DTI) prediction uses a drug molecule and protein sequence as inputs to predict the binding affinity value. In recent years, deep learning-based models have gotten more attention. These methods two modules: feature extraction module task module. most approaches, simple loss (i.e., categorical cross entropy for classification mean squared error regression task) is used learn model. machine learning, contrastive-based functions are developed...

Drug synergy prediction plays a vital role in cancer treatment. Because experimental approaches are labor-intensive and expensive, computational-based get more attention. There two types of computational methods for drug prediction: feature-based similarity-based. In methods, the main focus is to extract discriminative features from pairs cell lines pass task predictor. similarity-based similarities among all drugs utilized as fed into this work, novel approach, called CFSSynergy, that...

Abstract Motivation Drug repurposing is a viable solution for reducing the time and cost associated with drug development. However, thus far, proposed approaches still need to meet expectations. Therefore, it crucial offer systematic approach achieve savings enhance human lives. In recent years, using biological network-based methods has generated promising results. Nevertheless, these have limitations. Primarily, scope of generally limited concerning size variety data they can effectively...

Screening bioactive compounds in cancer cell lines receive more attention. Multidisciplinary drugs or drug combinations have a effective role treatments and selectively inhibit the growth of cells.Hence, we propose new deep learning-based approach for combination synergy prediction called DeepTraSynergy. Our proposed utilizes multimodal input including drug-target interaction, protein-protein cell-target interaction to predict synergy. To learn feature representation drugs, utilized...

Virtual screening has emerged as a valuable computational tool for predicting compound-protein interactions, offering cost-effective and rapid approach to identifying potential candidate drug molecules. Current machine learning-based methods rely on molecular structures their relationship in the network. The former utilizes information such amino acid sequences chemical structures, while latter leverages interaction network data, protein-protein drug-disease protein-disease interactions....

The main problem of small molecule-based drug discovery is to find a candidate molecule with increased pharmacological activity, proper ADME, and low toxicity. Recently, machine learning has driven significant contribution discovery. However, many methods, such as deep learning-based approaches, require large amount training data form accurate predictions for unseen data. In lead optimization step, the available biological on compounds low, which makes it challenging apply methods. goal this...

Precise prognostic classification of patients and identifying survival subgroups their associated genes can be important clinical references when designing treatment strategies for cancer patients. Multi-omics data integration techniques are powerful tools to achieve this goal. This study aimed introduce a machine learning method integrate three types biological data, investigate the performance two other methods, in dependency The included TCGA RNA-seq gene expression, DNA methylation, from...

Drug-target interaction (DTI) plays a vital role in drug discovery. Identifying drug-target interactions related to wet-lab experiments are costly, laborious, and time-consuming. Therefore, computational methods predict an essential task the discovery process. Meanwhile, can reduce search space by proposing potential drugs already validated on experiments. Recently, deep learning-based prediction have gotten more attention. Traditionally, DTI methods' performance heavily depends additional...

Cancer treatment has become one of the biggest challenges in world today. Different treatments are used against cancer; drug-based have shown better results. On other hand, designing new drugs for cancer is costly and time-consuming. Some computational methods, such as machine learning deep learning, been suggested to solve these using drug repurposing. Despite promise classical machine-learning methods repurposing predicting responses, deep-learning performed better. This study aims develop...

Bentham Science - STM publisher of online and print journals, related print/online book series. answers the information needs scientists in fields pharmaceutical, biomedical, medical, engineering, technology, computer social sciences.

The protein-ligand binding affinity (PLA) prediction goal is to predict whether or not the ligand could bind a protein sequence. Recently, in PLA prediction, deep learning has received much attention. Two steps are involved learning-based approaches: feature extraction and task step. Many approaches concentrate on introducing new networks integrating auxiliary knowledge like protein-protein interaction gene ontology knowledge. Then, network designed simply using some fully connected layers....

Motivation: Drug repurposing is a viable solution for reducing the time and cost associated with drug development. However, thus far, proposed approaches still need to meet expectations. Therefore, it crucial offer systematic approach achieve savings enhance human lives. In recent years, using biological network-based methods has generated promising results. Nevertheless, these have limitations. Primarily, scope of generally limited concerning size variety data they can effectively handle....

Abstract Background In drug discovery, drug-target interaction (DTI) plays a crucial role. Identifying DTI in wet-lab experiment is time-consuming, labor-intensive, and costly. Using reliable computational methods to predict mitigates the enormous costs time of discovery. Deep learning-based for predicting have recently gained more attention. Results this paper, new multimodal approach proposed. It shown that discriminative feature representation pair main role prediction. To achieve goal,...