scholarly journals DPDDI: a deep predictor for drug-drug interactions

2020 ◽  
Vol 21 (1) ◽  
Author(s):  
Yue-Hua Feng ◽  
Shao-Wu Zhang ◽  
Jian-Yu Shi
Keyword(s):  
Drug Interactions ◽  
Computational Methods ◽  
Biological Properties ◽  
Inner Product ◽  
Network Information ◽  
Feature Representations ◽  
Feature Aggregation ◽  
Latent Features ◽  
Low Dimensional ◽  
Multiple Drugs

Abstract Background The treatment of complex diseases by taking multiple drugs becomes increasingly popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly to obtain and not available in many cases. Results In this work, we presented a novel method (namely DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN), and the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs by capturing the topological relationship of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. Experiment results show that, the newly proposed DPDDI method outperforms four other state-of-the-art methods; the GCN-derived latent features include more DDI information than other features derived from chemical, biological or anatomical properties of drugs; and the concatenation feature aggregation operator is better than two other feature aggregation operators (i.e., inner product and summation). The results in case studies confirm that DPDDI achieves reasonable performance in predicting new DDIs. Conclusion We proposed an effective and robust method DPDDI to predict the potential DDIs by utilizing the DDI network information without considering the drug properties (i.e., drug chemical and biological properties). The method should also be useful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.

scholarly journals DPDDI:a Deep Predictor for Drug-Drug Interactions

2020 ◽  
Author(s):  
Yue-Hua Feng ◽  
Shao-Wu Zhang ◽  
Jian-Yu Shi
Keyword(s):  
Drug Interactions ◽  
Computational Methods ◽  
Biological Properties ◽  
Inner Product ◽  
Network Information ◽  
Feature Representations ◽  
Feature Aggregation ◽  
Latent Features ◽  
Low Dimensional ◽  
Multiple Drugs

Abstract Background: The treatment of complex diseases taking multiple drugs becomes popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity. DDI detection in the wet lab is expensive and time-consuming. Thus, it is highly desired to develop the computational methods for predicting DDIs. Generally, most of the existing computational methods predict DDIs by extracting the chemical and biological features of drugs from diverse drug-related properties, however some drug properties are costly obtained and not available in many cases. Results: In this work, we present a novel method (called DPDDI) to predict DDIs by extracting the network structure features of drugs from DDI network with graph convolution network (GCN) and constructing the deep neural network (DNN) model as a predictor. GCN learns the low-dimensional feature representations of drugs for capturing the topological relationship to their neighborhood of drugs in DDI network. DNN predictor concatenates the latent feature vectors of any two drugs as the feature vector of the corresponding drug pairs to train a DNN for predicting the potential drug-drug interactions. The experiment results show that our DPDDI outperforms other four state-of-the-art methods; the GCN-derived latent features greatly outperform other features derived from chemical, biological or anatomical properties of drugs; the concatenation feature aggregation operator is better than other two feature aggregation operators (i.e., inner product and summation). The results in case studies indicates that DPDDI has the good capability for predicting the new DDIs. Conclusion—We propose an effective and robust method of DPDDI to predict the potential DDIs, which just utilizes the DDI network information, working well without drug properties (i.e., drug chemical and biological properties). It can be expected that DPDDI can be helpful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.

scholarly journals DPDDI: a Deep Predictor for Drug-Drug Interactions

2020 ◽  
Author(s):  
Feng Yue-Hua ◽  
Zhang Shao-Wu ◽  
Shi Jian-Yu
Keyword(s):  
Drug Interactions ◽  
Feature Vector ◽  
Low Cost ◽  
Inner Product ◽  
Wet Lab ◽  
Low Dimensional ◽  
Multiple Drugs ◽  
Potential Interactions ◽  
Fold Cross Validation ◽  
Significant Superiority

Abstract Background— The treatment of complex diseases taking multiple drugs becomes popular. However, drug-drug interactions (DDIs) may give rise to the risk of unanticipated adverse effects and even unknown toxicity.As DDI detection in the wet lab is expensive and time-consuming, computational DDIs prediction based on machine learning becomes a promising approach due to its low cost and fast running.Generally, most of the existing computational approaches construct drug features from diverse drug properties, which are costly obtained and not available in many cases. Result— To address this issue, by organizing DDIs a network, we propose a novel predicting approach, which can without drug property.It consists of a feature extractor based on graph convolution network(GCN) as well as a predictor based on deep neural network (DNN). The formercharacterizes drugs in a graph embedding space, where each drugwasrepresented as a low-dimensional latent feature vector capturing the topological relationship to its neighborhood drugs by GCN. The latter concatenates latent feature vectors of any two drugsas the feature vector of the corresponding drug pairs and trains a DNN to predict potential interactions. In the experiments, we first demonstrate that our DNN-based predictor greatly outperforms the inner product-based predictor in the original GCN, and our network-derived latent feature greatly outperforms other features derived from chemical, biological or anatomicalproperties of drugs. Then, we indicate the over-optimistic prediction caused by down-sampling unlabeled drug pairs and validate the robustness of our approach to different datasets w.r.t. drug number, DDI number, and network sparsity. Moreover, the comparison with four state-of-the-art approaches using drug properties demonstrates the significant superiority of our approach under 5-fold cross-validation. Finally, a novel prediction validates its potentials in a real predicting scenario with finding 13 verified DDI out of the top 20 unlabeled candidates. Conclusion — We propose a simple but robust method DPDDI to predicting novel DDIs, which canwork without drug property. It can be expected that DPDDI can be helpful in other DDI-related scenarios, such as the detection of unexpected side effects, and the guidance of drug combination.

scholarly journals POTENTIAL DRUG INTERACTIONS IN HYPERTENSIVE PATIENTS IN LIWA DISTRICT HOSPITAL, LAMPUNG BARAT, INDONESIA

2017 ◽  
Vol 9 (6) ◽  
pp. 134
Author(s):  
Erna Yanti ◽  
Erna - Kristin ◽  
Alfi Yasmina
Keyword(s):  
Drug Interactions ◽  
District Hospital ◽  
Antihypertensive Agents ◽  
Potential Interaction ◽  
Multiple Drug ◽  
Potential Drug ◽  
Cross Sectional ◽  
Hypertensive Patients ◽  
Multiple Drugs ◽  
Potential Interactions

Objective: Patients with hypertension often suffer from other comorbidities, resulting in prescriptions of multiple drugs to treat the conditions. Multiple drug treatment is potentially associated with drug interactions. This aim of the study was to assess potential drug interactions in hypertensive patients in Liwa District Hospital.Methods: The design of the study was cross-sectional. The prescriptions for in-patients with essential hypertension in the Internal Medicine Unit in Liwa District Hospital during April-December 2012 were collected. Potential drug interactions were analyzed with the Drug Interaction Facts version 4.0, and classified into minor, significant, and serious.Results: A total of 60 hypertensive patients were included. They were prescribed 265 prescriptions, with a median total of 6 (range 1-21) drugs prescribed per prescription. There were 1616 potential drug interactions, with 6 (1-31) potential interactions per prescription. Most interactions (75.6%) were classified as significant. Serious potential interactions were most common in the combinations of diltiazem-amlodipine and spironolactone-potassium chloride, while significant potential interaction may occur most often with the combinations of calcium chloride-amlodipine and bisoprolol-amlodipine.Conclusion: Numerous potential drug interactions might occur in hypertensive patients, and most interactions were significant in severity. The largest proportion of the interactions occurred between antihypertensive agents and other drugs. 

scholarly journals A multicentered pharmacoepidemiological approach to evaluate clinically significant potential drug–drug interactions in medical intensive care settings in Pakistan

2018 ◽  
Vol 25 (4) ◽  
pp. 190-195 ◽  
Author(s):  
Faisal Shakeel ◽  
Jamshaid Ali Khan ◽  
Muhammad Aamir ◽  
Syed Muhammad Asim ◽  
Irfan Ullah
Keyword(s):  
Intensive Care ◽  
Drug Interactions ◽  
Intensive Care Units ◽  
Potential Drug ◽  
Significant Potential ◽  
Significant Difference ◽  
Tertiary Hospitals ◽  
Medical Intensive Care ◽  
Clinically Significant ◽  
Multiple Drugs

Background: Iatrogenic injuries due to drug–drug interactions are particularly significant in critical care units because of the severely compromised state of the patient. The risk further increases with the use of multiple drugs, increasing age, and stay of the patient. Objective: The aim was to assess potential drug–drug interactions, evaluate clinically significant potential drug–drug interactions and their predictors in medical intensive care units of tertiary hospitals in Pakistan. Methods: Analysis of patient data collected from medical intensive care units of tertiary hospitals in Pakistan were carried out using Micromedex DrugReax. Various statistical tools were applied to identify the significance of associated predictors. Results: In a total of 830 patients, prevalence of potential drug–drug interactions was found to be 39%. These attributed to 190 drug combinations, of which 15.4% were clinically significant. A significant association of potential drug–drug interactions was present with number of prescribed drugs, age, and gender. In terms of clinically significant potential drug–drug interactions, the association was significant with increasing age. Moreover, one-way analysis of variance revealed a significant difference in the means of potential drug–drug interactions among the four hospitals. Conclusion: A prevalence of 39% potential drug–drug interactions was observed in patients of medical intensive care unit, with 22.8% being clinically significant. These attributed to nine drug pairs and could easily be avoided to reduce the risk of adverse effects from potential drug–drug interactions.

scholarly journals Prediction of Side Effects Using Comprehensive Similarity Measures

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Sukyung Seo ◽  
Taekeon Lee ◽  
Mi-hyun Kim ◽  
Youngmi Yoon
Keyword(s):  
Side Effects ◽  
Drug Interactions ◽  
Side Effect ◽  
Drug Repositioning ◽  
Phenotypic Expression ◽  
Area Under The Curve ◽  
Similarity Measures ◽  
Biological Properties ◽  
Nucleotide Polymorphisms ◽  
Chemical Structures

Identifying the potential side effects of drugs is crucial in clinical trials in the pharmaceutical industry. The existing side effect prediction methods mainly focus on the chemical and biological properties of drugs. This study proposes a method that uses diverse information such as drug-drug interactions from DrugBank, drug-drug interactions from network, single nucleotide polymorphisms, and side effect anatomical hierarchy as well as chemical structures, indications, and targets. The proposed method is based on the assumption that properties used in drug repositioning studies could be utilized to predict side effects because the phenotypic expression of a side effect is similar to that of the disease. The prediction results using the proposed method showed a 3.5% improvement in the area under the curve (AUC) over that obtained when only chemical, indication, and target features were used. The random forest model delivered outstanding results for all combinations of feature types. Finally, after identifying candidate side effects of drugs using the proposed method, the following four popular drugs were discussed: (1) dasatinib, (2) sitagliptin, (3) vorinostat, and (4) clonidine.

scholarly journals Adverse Event Circumstances and the Case of Drug Interactions

Healthcare ◽  
2019 ◽  
Vol 7 (1) ◽  
pp. 45 ◽  
Author(s):  
Theodoros G. Soldatos ◽  
David B. Jackson
Keyword(s):  
Adverse Event ◽  
Adverse Events ◽  
Drug Interactions ◽  
Drug Targets ◽  
Drug Induced ◽  
Related Factors ◽  
Human Phenotype ◽  
Potential Applications ◽  
Patient Responses ◽  
Multiple Drugs

Adverse events are a common and for the most part unavoidable consequence of therapeutic intervention. Nevertheless, available tomes of such data now provide us with an invaluable opportunity to study the relationship between human phenotype and drug-induced protein perturbations within a patient system. Deciphering the molecular basis of such adverse responses is not only paramount to the development of safer drugs but also presents a unique opportunity to dissect disease systems in search of novel response biomarkers, drug targets, and efficacious combination therapies. Inspired by the potential applications of this approach, we first examined adverse event circumstances reported in FAERS and then performed a molecular level interrogation of cancer patient adverse events to investigate the prevalence of drug-drug interactions in the context of patient responses. We discuss avoidable and/or preventable cases and how molecular analytics can help optimize therapeutic use of co-medications. While up to one out of three adverse events in this dataset might be explicable by iatrogenic, patient, and product/device related factors, almost half of the patients in FAERS received multiple drugs and one in four may have experienced effects attributable to drug interactions.

High Confidence Predictions of Drug−Drug Interactions: Predicting Affinities for Cytochrome P450 2C9 with Multiple Computational Methods

2008 ◽  
Vol 51 (3) ◽  
pp. 648-654 ◽  
Author(s):  
Matthew G. Hudelson ◽  
Nikhil S. Ketkar ◽  
Lawrence B. Holder ◽  
Timothy J. Carlson ◽  
Chi-Chi Peng ◽  
...  
Keyword(s):  
Cytochrome P450 ◽  
Drug Interactions ◽  
Computational Methods ◽  
Cytochrome P450 2C9 ◽  
High Confidence

scholarly journals Artificial intelligence based computational framework for drug-target prioritization and inference of novel repositionable drugs for Alzheimer’s disease

2020 ◽  
Author(s):  
Shingo Tsuji ◽  
Takeshi Hase ◽  
Ayako Yachie ◽  
Taiko Nishino ◽  
Samik Ghosh ◽  
...  
Keyword(s):  
Target Genes ◽  
Therapeutic Targets ◽  
Computational Framework ◽  
Computational Tools ◽  
Therapeutic Drugs ◽  
Latent Space ◽  
Latent Features ◽  
Low Dimensional ◽  
Network Metrics ◽  
Novel Therapeutic

AbstractBackgroundIdentification of novel therapeutic targets is a key for successful drug development. However, the cost to experimentally identify therapeutic targets is huge and only 400 genes are targets for FDA-approved drugs. Therefore, it is inevitable to develop powerful computational tools to identify potential novel therapeutic targets. Because proteins make their functions together with their interacting partners, a protein-protein interaction network (PIN) in human could be a useful resource to build computational tools to investigate potential targets for therapeutic drugs. Network embedding methods, especially deep-learning based methods would be useful tools to extract an informative low-dimensional latent space that contains enough information required to fully represent original high-dimensional non-linear data of PINs.ResultsIn this study, we developed a deep learning based computational framework that extracts low-dimensional latent space embedded in high-dimensional data of the human PIN and uses the features in the latent space (latent features) to infer potential novel targets for therapeutic drugs. We examined the relationships between the latent features and the representative network metrics and found that the network metrics can explain a large number of the latent features, while several latent features do not correlate with all the network metrics. The results indicate that the features are likely to capture information that the representative network metrics can not capture, while the latent features also can capture information obtained from the network metrics. Our computational framework uses the latent features together with state-of-the-art machine learning techniques to infer potential drug target genes. We applied our computational framework to prioritized novel putative target genes for Alzheimer’s disease and successfully identified key genes for potential novel therapeutic targets (e.g., DLG4, EGFR, RAC1, SYK, PTK2B, SOCS1). Furthermore, based on these putative targets, we inferred repositionable candidate-compounds for the disease (e.g., Tamoxifen, Bosutinib, and Dasatinib)DiscussionsOur computational framework could be powerful computational tools to efficiently prioritize new therapeutic targets and drug repositioning. It is pertinent to note here that our computational platform is easily applicable to investigate novel potential targets and repositionable compounds for any diseases, especially for rare diseases.

scholarly journals EVALUATING UNIFORM MANIFOLD APPROXIMATION AND PROJECTION FOR DIMENSION REDUCTION AND VISUALIZATION OF POLINSAR FEATURES

2021 ◽  
Vol V-1-2021 ◽  
pp. 39-46
Author(s):  
S. Schmitz ◽  
U. Weidner ◽  
H. Hammer ◽  
A. Thiele
Keyword(s):  
Dimension Reduction ◽  
Visual Analysis ◽  
Principal Component ◽  
Feature Space ◽  
Decomposition Methods ◽  
High Dimensional ◽  
Feature Representations ◽  
Wide Range ◽  
Nonlinear Dimension ◽  
Low Dimensional

Abstract. In this paper, the nonlinear dimension reduction algorithm Uniform Manifold Approximation and Projection (UMAP) is investigated to visualize information contained in high dimensional feature representations of Polarimetric Interferometric Synthetic Aperture Radar (PolInSAR) data. Based on polarimetric parameters, target decomposition methods and interferometric coherences a wide range of features is extracted that spans the high dimensional feature space. UMAP is applied to determine a representation of the data in 2D and 3D euclidean space, preserving local and global structures of the data and still suited for classification. The performance of UMAP in terms of generating expressive visualizations is evaluated on PolInSAR data acquired by the F-SAR sensor and compared to that of Principal Component Analysis (PCA), Laplacian Eigenmaps (LE) and t-distributed Stochastic Neighbor embedding (t-SNE). For this purpose, a visual analysis of 2D embeddings is performed. In addition, a quantitative analysis is provided for evaluating the preservation of information in low dimensional representations with respect to separability of different land cover classes. The results show that UMAP exceeds the capability of PCA and LE in these regards and is competitive with t-SNE.

scholarly journals Convolutional Neural Networks with Deep Supervised Feature Learning for Remote Sensing Scene Classification

2020 ◽  
Author(s):  
Grigorios Tsagkatakis ◽  
Panagiotis Tsakalides
Keyword(s):  
Remote Sensing ◽  
Feature Learning ◽  
Ground Truth ◽  
Classification Performance ◽  
Cross Entropy ◽  
Scene Classification ◽  
Feature Representations ◽  
Benchmark Datasets ◽  
Low Dimensional ◽  
Fully Connected

State-of-the-art remote sensing scene classification methods employ different Convolutional Neural Network architectures for achieving very high classification performance. A trait shared by the majority of these methods is that the class associated with each example is ascertained by examining the activations of the last fully connected layer, and the networks are trained to minimize the cross-entropy between predictions extracted from this layer and ground-truth annotations. In this work, we extend this paradigm by introducing an additional output branch which maps the inputs to low dimensional representations, effectively extracting additional feature representations of the inputs. The proposed model imposes additional distance constrains on these representations with respect to identified class representatives, in addition to the traditional categorical cross-entropy between predictions and ground-truth. By extending the typical cross-entropy loss function with a distance learning function, our proposed approach achieves significant gains across a wide set of benchmark datasets in terms of classification, while providing additional evidence related to class membership and classification confidence.

Sign in / Sign up

Export Citation Format

Share Document