Predicting Drug-Drug Interactions Through Large-Scale Similarity-Based Link Prediction

AbstractThe entities of real-world networks are connected via different types of connections (i.e., layers). The task of link prediction in multiplex networks is about finding missing connections based on both intra-layer and inter-layer correlations. Our observations confirm that in a wide range of real-world multiplex networks, from social to biological and technological, a positive correlation exists between connection probability in one layer and similarity in other layers. Accordingly, a similarity-based automatic general-purpose multiplex link prediction method—SimBins—is devised that quantifies the amount of connection uncertainty based on observed inter-layer correlations in a multiplex network. Moreover, SimBins enhances the prediction quality in the target layer by incorporating the effect of link overlap across layers. Applying SimBins to various datasets from diverse domains, our findings indicate that SimBins outperforms the compared methods (both baseline and state-of-the-art methods) in most instances when predicting links. Furthermore, it is discussed that SimBins imposes minor computational overhead to the base similarity measures making it a potentially fast method, suitable for large-scale multiplex networks.

Download Full-text

Pharmacokinetic and safety study of co-administration of albendazole, diethylcarbamazine, Ivermectin and azithromycin for the integrated treatment of Neglected Tropical Diseases

Clinical Infectious Diseases ◽

10.1093/cid/ciaa1202 ◽

2020 ◽

Author(s):

Lucy N John ◽

Catherine Bjerum ◽

Pere Millat Martinez ◽

Rhoda Likia ◽

Linda Silus ◽

...

Keyword(s):

Drug Interactions ◽

Large Scale ◽

Neglected Tropical Diseases ◽

Pharmacokinetic Interaction ◽

Integrated Treatment ◽

Secondary Outcome ◽

Pharmacokinetic Data ◽

Tropical Diseases ◽

Open Label ◽

Significant Difference

Abstract Background Pharmacokinetic data are a pre-requisite to integrated implementation of large-scale mass drug administration (MDA) for neglected tropical diseases (NTDs). We investigated the safety and drug interactions of a combination of azithromycin (AZI) targeting yaws and trachoma, with the newly approved ivermectin, albendazole, diethylcarbamazine (IDA) regime for Lymphatic Filariasis. Methodology An open-label, randomized, 3-arm pharmacokinetic interaction study in adult volunteers was carried out in Lihir Island, Papua New Guinea. Healthy adult participants were recruited and randomized to (I) IDA alone, (II) IDA combined with AZI, (III) AZI alone. The primary outcome was lack of a clinically relevant drug interaction. The secondary outcome was the overall difference in the proportion of AEs between treatment arms. Results Thirty-seven participants, eighteen men and nineteen women, were randomized and completed the study. There were no significant drug-drug interactions between the study arms. The GMR of Cmax, AUC0–t, and AUC0–∞ for IVM, DEC, ALB-SOX, and AZI were within the range of 80–125% (GMR for AUC0–∞ for IVM, 87.9; DEC, 92.9; ALB-SOX, 100.0; and AZI, 100.1). There was no significant difference in the frequency of AEs across study arms (AZI and IDA alone arms 9/12 (75%), co-administration arm 12/13 (92%); p = 0.44). All AEs were grade 1 and self-limiting. Conclusions Co-administration of AZI with IDA did not show evidence of significant drug-interactions. There were no serious AEs in any of the study arms. Our data support further evaluation of the safety of integrated MDA for NTDs. Clinical Trials Registration. NCT03664063

Download Full-text

Large-Scale Similarity Join with Edit-Distance Constraints

Database Systems for Advanced Applications - Lecture Notes in Computer Science ◽

10.1007/978-3-319-05813-9_22 ◽

2014 ◽

pp. 328-342 ◽

Cited By ~ 7

Author(s):

Chen Lin ◽

Haiyang Yu ◽

Wei Weng ◽

Xianmang He

Keyword(s):

Large Scale ◽

Edit Distance ◽

Distance Constraints ◽

Similarity Join ◽

Scale Similarity

Download Full-text

OpenBioLink: a benchmarking framework for large-scale biomedical link prediction

Bioinformatics ◽

10.1093/bioinformatics/btaa274 ◽

2020 ◽

Vol 36 (13) ◽

pp. 4097-4098 ◽

Cited By ~ 3

Author(s):

Anna Breit ◽

Simon Ott ◽

Asan Agibetov ◽

Matthias Samwald

Keyword(s):

Link Prediction ◽

Large Scale ◽

Source Code ◽

Machine Learning Algorithms ◽

Knowledge Networks ◽

Supplementary Information ◽

Supplementary Data ◽

Biomedical Knowledge ◽

High Quality ◽

Baseline Evaluation

Abstract Summary Recently, novel machine-learning algorithms have shown potential for predicting undiscovered links in biomedical knowledge networks. However, dedicated benchmarks for measuring algorithmic progress have not yet emerged. With OpenBioLink, we introduce a large-scale, high-quality and highly challenging biomedical link prediction benchmark to transparently and reproducibly evaluate such algorithms. Furthermore, we present preliminary baseline evaluation results. Availability and implementation Source code and data are openly available at https://github.com/OpenBioLink/OpenBioLink. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

A Modified Skip-Gram Algorithm for Extracting Drug-Drug Interactions from AERS Reports

Computational and Mathematical Methods in Medicine ◽

10.1155/2020/1747413 ◽

2020 ◽

Vol 2020 ◽

pp. 1-9

Author(s):

Li Wang ◽

Wenjie Pan ◽

QingHua Wang ◽

Heming Bai ◽

Wei Liu ◽

...

Keyword(s):

Adverse Event ◽

Drug Interactions ◽

Large Scale ◽

Characteristic Curve ◽

Language Model ◽

Adverse Event Reporting System ◽

Adverse Event Reporting ◽

Concept Representation ◽

Average Accuracy ◽

Tenfold Cross Validation

Drug-drug interactions (DDIs) are one of the indispensable factors leading to adverse event reactions. Considering the unique structure of AERS (Food and Drug Administration Adverse Event Reporting System (FDA AERS)) reports, we changed the scope of the window value in the original skip-gram algorithm, then propose a language concept representation model and extract features of drug name and reaction information from large-scale AERS reports. The validation of our scheme was tested and verified by comparing with vectors originated from the cooccurrence matrix in tenfold cross-validation. In the verification of description enrichment of the DrugBank DDI database, accuracy was calculated for measurement. The average area under the receiver operating characteristic curve of logistic regression classifiers based on the proposed language model is 6% higher than that of the cooccurrence matrix. At the same time, the average accuracy in five severe adverse event classes is 88%. These results indicate that our language model can be useful for extracting drug and reaction features from large-scale AERS reports.

Download Full-text