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.

We defined gender-specific phenotypes for men and women diagnosed with obstructive sleep apnea syndrome (OSAS) based on easy-to-measure anthropometric parameters, using a network science approach. We collected data from 2796 consecutive patients since 2005, from 4 sleep laboratories in Western Romania, recording sleep, breathing, and anthropometric measurements. For both genders, we created specific apnea patient networks defined by patient compatibility relationships in terms of age, body mass index (BMI), neck circumference (NC), blood pressure (BP), and Epworth sleepiness score (ESS). We classified the patients with clustering algorithms, then statistically analyzed the groups/clusters. Our study uncovered eight phenotypes for each gender. We found that all males with OSAS have a large NC, followed by daytime sleepiness and high BP or obesity. Furthermore, all unique female phenotypes have high BP, followed by obesity and sleepiness. We uncovered gender-related differences in terms of associated OSAS parameters. In males, we defined the pattern large NC–sleepiness–high BP as an OSAS predictor, while in women, we found the pattern of high BP–obesity–sleepiness. These insights are useful for increasing awareness, improving diagnosis, and treatment response.

Complex networks are often characterized by their underlying graph metrics, yet there is no unified computational method for comparing networks to each other. Given that complex networks are entities characterized by a set of known properties, our problem is reduced to quantifying the similarity between the multi-variable entities. To address this issue, we introduce the new statistical fidelity metric, which can compare any types of entities, characterized by specific individual metrics, in order to gauge the similarity of the entities under the form of a single number between 0 and 1. To test the efficiency of statistical fidelity, we apply our composite metric in the field of complex networks, by assessing topological similarity and realism of social networks and urban road networks. Pinned against other statistical methods, such as the cosine similarity, Pearson correlation, Mahalanobis distance and fractal dimension, we highlight the superior analytic power of statistical fidelity.

Computational models for large, resurgent epidemics are recognized as a crucial tool for predicting the spread of infectious diseases. It is widely agreed, that such models can be augmented with realistic multiscale population models and by incorporating human mobility patterns. Nevertheless, a large proportion of recent studies, aimed at better understanding global epidemics, like influenza, measles, H1N1, SARS, and COVID-19, underestimate the role of heterogeneous mixing in populations, characterized by strong social structures and geography. Motivated by the reduced tractability of studies employing homogeneous mixing, which make conclusions hard to deduce, we propose a new, very fine-grained model incorporating the spatial distribution of population into geographical settlements, with a hierarchical organization down to the level of households (inside which we assume homogeneous mixing). In addition, population is organized heterogeneously outside households, and we model the movement of individuals using travel distance and frequency parameters for inter- and intra-settlement movement. Discrete event simulation, employing an adapted SIR model with relapse, reproduces important qualitative characteristics of real epidemics, like high variation in size and temporal heterogeneity (e.g., waves), that are challenging to reproduce and to quantify with existing measures. Our results pinpoint an important aspect, that epidemic size is more sensitive to the increase in distance of travel, rather that the frequency of travel. Finally, we discuss implications for the control of epidemics by integrating human mobility restrictions, as well as progressive vaccination of individuals.

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 ($D_1$, $D_2$, $D_3$) with 1046 patients from four sleep laboratories in Western Romania, including 145 subjects ($D_1$) with one-night CPAP therapy. Using $D_1$ 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 $D_2$ (OSA-diagnosed) and $D_3$ (control), using the area under the curve. As such, we confirmed the correlation between NC and AHI ($\rho =0.35$, $p<0.001$) 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 $D_1$ 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.