• BFIM
• MSCNN
• SFM
• Transformer
• drug-target interactions

• Neural Networks, Computer
• Humans
• Drug Repositioning
• Antineoplastic Agents/pharmacology
• Lung Neoplasms/drug therapy
• Algorithms
• Drug Discovery

• 2023xqxtsys01 Artificial Intelligence Industry-University-Research Joint Laboratory
• 2024kcjys05 Excellent AI Data Innovation Talent Cultivation Course Teaching and Research Section

• Artificial intelligence
• Conventional therapy
• Nanotechnology
• Pediatrics
• Theragnostics

• Humans
• Child
• Artificial Intelligence
• Gastrointestinal Diseases/drug therapy
• Gastrointestinal Diseases/therapy
• Cardiovascular Diseases/drug therapy
• Cardiovascular Diseases/therapy
• Nanotechnology
• Respiratory Tract Diseases/drug therapy
• Respiratory Tract Diseases/therapy
• Pediatrics
• Infant, Newborn
• Respiration Disorders/drug therapy
• Drug Delivery Systems
• Nanomedicine

• USE 23922-W Junta de Andalucía
• UIDP/04378/2020 AND UIDB/04378/2020 Fundação para a Ciência e a Tecnologia
• LA/P/0140/2020 ASSOCIATE LABORATORY INSTITUTE FOR HEALTH AND BIOECONOMY

• Computational Biology/methods
• Area Under Curve
• Algorithms
• Drug Discovery/methods
• Humans
• Pharmaceutical Preparations/metabolism
• Pharmaceutical Preparations/chemistry
• ROC Curve

• Acute myocardial infarction (AMI)
• eXtreme Gradient Boosting (XGBoost)
• machine learning
• major adverse cardiovascular events (MACEs)
• percutaneous coronary intervention (PCI)

• Drug Development/methods
• Neural Networks, Computer
• Drug Discovery/methods
• Databases, Factual
• Drug Interactions

• Machine learning
• chemoinformatics
• drug discovery
• drug-target interactions
• medications.
• prediction computational models

• Humans
• Drug Discovery/methods
• Machine Learning
• Molecular Docking Simulation
• Ligands
• Pharmaceutical Preparations/metabolism
• Pharmaceutical Preparations/chemistry
• Drug Repositioning/methods
• Proteins/metabolism

• Drug–target interactions
• Feature engineering
• Genomic space
• Molecular descriptors
• SMOTE

• Algorithms
• Drug Delivery Systems
• Drug Discovery
• Drug Interactions
• Machine Learning

• Drug repurposing
• Machine learning
• Proximal tubule on a chip
• Renal fibrosis
• UUO model

• Mice
• Animals
• Lubiprostone/pharmacology
• Artificial Intelligence
• Drug Repositioning
• Transforming Growth Factor beta1/metabolism
• Kidney Diseases
• Transforming Growth Factor beta/metabolism
• Fibrosis
• Biomarkers/metabolism
• Epithelial-Mesenchymal Transition
• Kidney/pathology

• NRF-2022R1A2C2004771 National Research Foundation of Korea (NRF)

• drug discovery
• diseases
• medical research
• engineering

• Pregnancy
• Female
• Humans
• Drug Delivery Systems
• Drug Development
• Forests
• Labor, Obstetric
• Protein Domains

• SMOTE
• class imbalance
• data resampling
• deep learning
• drug-target interaction
• machine learning

• artificial intelligence
• computational toxicology
• decision quality
• drug discovery
• lead-to-candidate
• machine learning

• anticancer
• antimicrobial
• benzoquinoline
• chemical space
• molecular database
• pharmacophore

• Molecular Docking Simulation
• Drug Design
• Anti-Bacterial Agents/pharmacology
• Antineoplastic Agents/pharmacology
• Antineoplastic Agents/chemistry
• Adenosine Triphosphate

• Drug Development
• Algorithms
• Drug Discovery/methods
• Drug Interactions
• ROC Curve

• COVID-19
• drug repositioning
• graph representation learning
• heterogeneous network
• variational graph autoencoders

• Drug-target interaction
• Graph attention network
• Line graph

• drug–target interaction prediction
• matrix factorization
• multiple similarity
• multiplex heterogeneous network
• random walks

• Algorithms
• Drug Development
• Drug Discovery/methods
• Drug Interactions
• Pharmaceutical Preparations
• Proteins

Accurate identification of potential targets for drugs to interact with can accelerate drug development. The identification of drug–target interactions can provide insights into hidden drug efficacy. This paper presents a prediction model based on feature similarity fusion that can identify crucial features of drugs and targets to help predict drug–target interactions.

The key to drug discovery is the identification of a target and a corresponding drug compound. Effective identification of drug–target interactions facilitates the development of drug discovery. In this paper, drug similarity and target similarity are considered, and graphical representations are used to extract internal structural information and intermolecular interaction information about drugs and targets. First, drug similarity and target similarity are fused using the similarity network fusion (SNF) method. Then, the graph isomorphic network (GIN) is used to extract the features with information about the internal structure of drug molecules. For target proteins, feature extraction is carried out using TextCNN to efficiently capture the features of target protein sequences. Three different divisions (CVD, CVP, CVT) are used on the standard dataset, and experiments are carried out separately to validate the performance of the model for drug–target interaction prediction. The experimental results show that our method achieves better results on AUC and AUPR. The docking results also show the superiority of the proposed model in predicting drug–target interactions.

• DS-3032B
• Molecular docking
• Mouse double minute 2 antagonist
• Tumor suppressor p53

Objective To explore the differential diagnostic efficiency of the residual network (ResNet)50, random forest (RF), and DS ensemble models for papillary thyroid carcinoma (PTC) and other pathological types of thyroid nodules.

Methods This study retrospectively analyzed 559 patients with thyroid nodules and collected thyroid pathological images and auxiliary examination results (laboratory and ultrasound results) to construct datasets. The pathological image dataset was used to train a ResNet50 model, the text dataset was used to train a random forest (RF) model, and a DS ensemble model was constructed from the results of the two models. The differential diagnostic values of the three models for PTC and other types of thyroid nodules were then compared.

Results The DS ensemble model had the highest sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (85.87%, 97.18%, 93.77%, and 0.982, respectively).

Conclusions Compared with Resnet50 and the RF models trained only on imaging data or text information, respectively, the DS ensemble model showed better diagnostic value for PTC.

• Deep neural network
• artificial intelligence
• diagnostics
• papillary carcinoma
• pathology
• thyroid tumor

• DTI prediction
• graph attention network
• graph neural network
• heterogeneous graph
• link prediction

• Drug repurposing
• Graph-embedding
• Link prediction
• Machine learning

• Algorithms
• Drug Interactions
• Drug Repositioning
• Molecular Docking Simulation
• Proteins/chemistry

• C10355/A15587 CRUK/NIHR in England/DoH Experimental Cancer Medicine Centre
• EP/V01479X/1 UKR
• MR/L023091/1 Medical Research Council
• IS-BRC-1215-20006 Health Research (NIHR) Biomedical Research Centre (BRC)
• C604/A25135 Cancer Research UK King's Health Partners CentreC604/A25135
• 147; KCL-BCN-Q3 Breast Cancer Now
• Cancer Research UK King’s Health Partners CentreC604/A25135

Drug discovery (DD) is a time-consuming and expensive process. Thus, the industry employs strategies such as drug repositioning and drug repurposing, which allows the application of already approved drugs to treat a different disease, as occurred in the first months of 2020, during the COVID-19 pandemic. The prediction of drug–target interactions is an essential part of the DD process because it can accelerate it and reduce the required costs. DTI prediction performed in silico have used approaches based on molecular docking simulations, including similarity-based and network- and graph-based ones. This paper presents MPS2IT-DTI, a DTI prediction model obtained from research conducted in the following steps: the definition of a new method for encoding molecule and protein sequences onto images; the definition of a deep-learning approach based on a convolutional neural network in order to create a new method for DTI prediction. Training results conducted with the Davis and KIBA datasets show that MPS2IT-DTI is viable compared to other state-of-the-art (SOTA) approaches in terms of performance and complexity of the neural network model. With the Davis dataset, we obtained 0.876 for the concordance index and 0.276 for the MSE; with the KIBA dataset, we obtained 0.836 and 0.226 for the concordance index and the MSE, respectively. Moreover, the MPS2IT-DTI model represents molecule and protein sequences as images, instead of treating them as an NLP task, and as such, does not employ an embedding layer, which is present in other models.

• artificial intelligence
• blackbox models
• deep learning
• drug discovery
• high-quality data acquisition
• machine learning

• DTI networks
• DTIs
• Drug-target interactions
• Network-based approaches

• Drug-target interaction prediction
• Feature fusion
• Graph mining
• Heterogeneous network embedding

• Drug Development
• Drug Interactions
• Drug Repositioning
• Machine Learning
• Pharmaceutical Preparations

• Business strategy in drug development
• Drug therapy

• BB/M017702/1 Biotechnology and Biological Sciences Research Council
• BBS/E/J/000PR9790 Biotechnology and Biological Sciences Research Council
• MR/P007570/1 Medical Research Council

Combining drugs, a phenomenon often referred to as polypharmacy, can induce additional adverse effects. The identification of adverse combinations is a key task in pharmacovigilance. In this context, in silico approaches based on machine learning are promising as they can learn from a limited number of combinations to predict for all. In this work, we identify various subtasks in predicting effects caused by drug–drug interaction. Predicting drug–drug interaction effects for drugs that already exist is very different from predicting outcomes for newly developed drugs, commonly called a cold-start problem. We propose suitable validation schemes for the different subtasks that emerge. These validation schemes are critical to correctly assess the performance. We develop a new model that obtains AUC-ROC =0.843 for the hardest cold-start task up to AUC-ROC =0.957 for the easiest one on the benchmark dataset of Zitnik et al. Finally, we illustrate how our predictions can be used to improve post-market surveillance systems or detect drug–drug interaction effects earlier during drug development.

• cold-start problems
• cross-validation
• drug–drug interaction
• machine learning
• polypharmacy
• prediction

• Alzheimer's
• CNS
• Parkinson's
• anesthesia
• artificial intelligence
• blood-brain barrier
• depression
• disease subtyping
• drug design
• drug discovery
• machine learning
• neurological diseases
• pain treatment
• schizophrenia
• target identification

• Algorithms
• Artificial Intelligence
• Central Nervous System Diseases/drug therapy
• Drug Discovery
• Humans
• Machine Learning

• R01 AG072562 NIA NIH HHS
• RF1 AG057440 NIA NIH HHS
• U01 AG052411 NIA NIH HHS
• R35 GM133504 NIGMS NIH HHS
• RF1 AG059319 NIA NIH HHS
• R01 AG068030 NIA NIH HHS
• U01 AG058635 NIA NIH HHS
• R01 AG062355 NIA NIH HHS
• R01 AI124465 NIAID NIH HHS
• RF1 AG054014 NIA NIH HHS
• U01 AG046170 NIA NIH HHS
• R01 AG057907 NIA NIH HHS

Identifying the interactions of the drug-target is central to the cognate areas including drug discovery and drug reposition. Although the high-throughput biotechnologies have made tremendous progress, the indispensable clinical trials remain to be expensive, laborious, and intricate. Therefore, a convenient and reliable computer-aided method has become the focus on inferring drug-target interactions (DTIs). In this research, we propose a novel computational model integrating a pyramid histogram of oriented gradients (PHOG), Position-Specific Scoring Matrix (PSSM), and rotation forest (RF) classifier for identifying DTIs. Specifically, protein primary sequences are first converted into PSSMs to describe the potential biological evolution information. After that, PHOG is employed to mine the highly representative features of PSSM from multiple pyramid levels, and the complete describers of drug-target pairs are generated by combining the molecular substructure fingerprints and PHOG features. Finally, we feed the complete describers into the RF classifier for effective prediction. The experiments of 5-fold Cross-Validations (CV) yield mean accuracies of 88.96%, 86.37%, 82.88%, and 76.92% on four golden standard data sets (enzyme, ion channel, G protein-coupled receptors (GPCRs), and nuclear receptor, respectively). Moreover, the paper also conducts the state-of-art light gradient boosting machine (LGBM) and support vector machine (SVM) to further verify the performance of the proposed model. The experimental outcomes substantiate that the established model is feasible and reliable to predict DTIs. There is an excellent prospect that our model is capable of predicting DTIs as an efficient tool on a large scale.