Analyzing drug-drug interactions may unravel previously unknown drug action patterns, leading to the development of new drug discovery tools. We present a new approach to analyzing drug-drug interaction networks, based on clustering and topological community detection techniques that are specific to complex network science. Our methodology uncovers functional drug categories along with the intricate relationships between them. Using modularity-based and energy-model layout community detection algorithms, we link the network clusters to 9 relevant pharmacological properties. Out of the 1141 drugs from the DrugBank 4.1 database, our extensive literature survey and cross-checking with other databases such as Drugs.com, RxList, and DrugBank 4.3 confirm the predicted properties for 85% of the drugs. As such, we argue that network analysis offers a high-level grasp on a wide area of pharmacological aspects, indicating possible unaccounted interactions and missing pharmacological properties that can lead to drug repositioning for the 15% drugs which seem to be inconsistent with the predicted property. Also, by using network centralities, we can rank drugs according to their interaction potential for both simple and complex multi-pathology therapies. Moreover, our clustering approach can be extended for applications such as analyzing drug-target interactions or phenotyping patients in personalized medicine applications.

Obstructive sleep apnea syndrome (OSAS) is a common clinical condition. The way that OSAS risk factors associate and converge is not a random process. As such, defining OSAS phenotypes fosters personalized patient management and population screening. In this paper, we present a network-based observational, retrospective study on a cohort of 1,371 consecutive OSAS patients and 611 non-OSAS control patients in order to explore the risk factor associations and their correlation with OSAS comorbidities. To this end, we construct the Apnea Patients Network (APN) using patient compatibility relationships according to six objective parameters: age, gender, body mass index (BMI), blood pressure (BP), neck circumference (NC) and the Epworth sleepiness score (ESS). By running targeted network clustering algorithms, we identify eight patient phenotypes and corroborate them with the co-morbidity types. Also, by employing machine learning on the uncovered phenotypes, we derive a classification tree and introduce a computational framework which render the Sleep Apnea Syndrome Score (SAS Score ); our OSAS score is implemented as an easy-to-use, web-based computer program which requires less than one minute for processing one individual. Our evaluation, performed on a distinct validation database with 231 consecutive patients, reveals that OSAS prediction with SAS Score has a significant specificity improvement (an increase of 234%) for only 8.2% sensitivity decrease in comparison with the stateof-the-art score STOP-BANG. The fact that SAS Score has bigger specificity makes it appropriate for OSAS screening and risk prediction in big, general populations.

Despite recent advances in bioinformatics, systems biology, and machine learning, the accurate prediction of drug properties remains an open problem. Indeed, because the biological environment is a complex system, the traditional approach—based on knowledge about the chemical structures—can not fully explain the nature of interactions between drugs and biological targets. Consequently, in this paper, we propose an unsupervised machine learning approach that uses the information we know about drug–target interactions to infer drug properties. To this end, we define drug similarity based on drug–target interactions and build a weighted Drug–Drug Similarity Network according to the drug–drug similarity relationships. Using an energy-model network layout, we generate drug communities associated with specific, dominant drug properties. DrugBank confirms the properties of 59.52% of the drugs in these communities, and 26.98% are existing drug repositioning hints we reconstruct with our DDSN approach. The remaining 13.49% of the drugs seem not to match the dominant pharmacologic property; thus, we consider them potential drug repurposing hints. The resources required to test all these repurposing hints are considerable. Therefore we introduce a mechanism of prioritization based on the betweenness/degree node centrality. Using betweenness/degree as an indicator of drug repurposing potential, we select Azelaic acid and Meprobamate as a possible antineoplastic and antifungal, respectively. Finally, we use a test procedure based on molecular docking to analyze Azelaic acid and Meprobamate’s repurposing.

ProposalThis paper investigates a novel screening tool for Obstructive Sleep Apnea Syndrome (OSAS), which aims at efficient population-wide monitoring. To this end, we introduce SASscore which provides better OSAS prediction specificity while maintaining a high sensitivity.MethodsWe process a cohort of 2595 patients from 4 sleep laboratories in Western Romania, by recording over 100 sleep, breathing, and anthropometric measurements per patient; using this data, we compare our SASscore with state of the art scores STOP-Bang and NoSAS through area under curve (AUC), sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). We also evaluate the performance of SASscore by considering different Apnea–Hypopnea Index (AHI) diagnosis cut-off points and show that custom refinements are possible by changing the score’s threshold.ResultsSASscore takes decimal values within the interval (2, 7) and varies linearly with AHI; it is based on standardized measures for BMI, neck circumference, systolic blood pressure and Epworth score. By applying the STOP-Bang and NoSAS questionnaires, as well as the SASscore on the patient cohort, we respectively obtain the AUC values of 0.69 (95% CI 0.66-0.73, p < 0.001), 0.66 (95% CI 0.63-0.68, p < 0.001), and 0.73 (95% CI 0.71-0.75, p < 0.001), with sensitivities values of 0.968, 0.901, 0.829, and specificity values of 0.149, 0.294, 0.359, respectively. Additionally, we cross-validate our score with a second independent cohort of 231 patients confirming the high specificity and good sensitivity of our score. When raising SASscore’s diagnosis cut-off point from 3 to 3.7, both sensitivity and specificity become roughly 0.6.ConclusionsIn comparison with the existing scores, SASscore is a more appropriate screening tool for monitoring large populations, due to its improved specificity. Our score can be tailored to increase either sensitivity or specificity, while balancing the AUC value.

No abstract

No abstract

We explored the relationship between obstructive sleep apnea (OSA) patients’ anthropometric measures and the CPAP treatment response. To that end, we processed three non-overlapping cohorts (D1, D2, D3) with 1046 patients from four sleep laboratories in Western Romania, including 145 subjects (D1) with one-night CPAP therapy. Using D1 data, we created a CPAP-response network of patients, and found neck circumference (NC) as the most significant qualitative indicator for apnea–hypopnea index (AHI) improvement. We also investigated a quantitative NC cutoff value for OSA screening on cohorts D2 (OSA-diagnosed) and D3 (control), using the area under the curve. As such, we confirmed the correlation between NC and AHI (ρ=0.35, p<0.001) and showed that 71% of diagnosed male subjects had bigger NC values than subjects with no OSA (area under the curve is 0.71, with 95% CI 0.63–0.79, p<0.001); the optimal NC cutoff is 41 cm, with a sensitivity of 0.8099, a specificity of 0.5185, positive predicted value (PPV) = 0.9588, negative predicted value (NPV) = 0.1647, and positive likelihood ratio (LR+) = 1.68. Our NC =41 cm threshold classified the D1 patients’ CPAP responses—measured as the difference in AHI prior to and after the one-night use of CPAP—with a sensitivity of 0.913 and a specificity of 0.859.

No abstract