Jornal de Ciência da Computação e Biologia de Sistemas

Due to rapid growth of computing resources over the past years, cloud computing has been treated as a prominent research field and this technology appeared as a new solution in the IT field. Many businesses including small, medium and enterprise are migrating to this technology for so many reasons such as computing resources, reduced total cost of ownership, on demand services, increased revenue and many more. Cloud Computing offers number of advantages of cloud migration that motivated the business enterprises to adopt this change. There are so many challenges for the companies adopting cloud computing like interoperability, portability, organizational aspects and the most important challenge is the security and privacy of the information. There are different solutions or suggestions that a company should follow to overcome various challenges and issues.

To reduce the effect of noise in raw Electrocardiogram (ECG) data for faster detection of cardiac arrhythmia, Heart Rate Variability (HRV) features represent good choices. This work extracted 34 popular Heart Rate Variability (HRV) features based on the MIT-BIH Arrhythmia Database. Combinations of 11 feature selection algorithms and 2 classification algorithms are used to discover the effective features of the abnormal ECG signal detection. The systematic comparisons show that the combination of 34 original features has a stable classification performance for 3 different time windows, i.e., 32 RR-intervals, 5 minutes, and 30 minutes of raw ECG records. It has been discovered that a 10-feature combination (RMSSD, SDNN, CV, TINN, HF, SampEn, SD1/SD2, VAI, ED, and DC) can rapidly classify the arrhythmia and normal state, based on the shortest ECG records (32 RR-intervals). The future work will utilize this combination of features to implement in a portable ECG equipment and clinical Arrhythmia on-line detection.

Objective: Determine if machine learning programs coupled with standard statistical methods can accurately predict rates of bark coverage and death of saguaro cactus plants.

Methods: Data of twelve surfaces of 1,149 saguaro cacti with four samplings over 23 years that provided more than 55,000 data points were analyzed to predict rates of bark coverage on cactus surfaces and cactus death with three machine learning programs, Validate Model, WEKA 3.8 decision trees, and Random Forest.

Results: Saguaro cacti (Carnegiea gigantea) show extensive bark coverage and cacti with extensive bark coverage die prematurely. Over the 23-year period of study, bark coverage on all surfaces was relatively constant. Decision trees are able to predict cactus death up to 96%. Three machine learning programs used similar surface coverages to make similar predictions of future bark coverage and cactus death accurately (approximately 92%), for cacti that had overall bark coverage less than 80% on south-facing surfaces. Higher prediction accuracies were obtained for cacti with were low bark percentages. While bark coverage rates and cactus death were less accurate for cacti with higher bark percentages because cacti can remain with high bark percentages with many years prior to death. Cacti with more than 80% coverage on south-facing surfaces were accurately predicted (p<0.05) to be alive and dead of the 23-year period with a tracking method.

Conclusions: The combined machine learning programs coupled with standard statistical procedures accurately predicted bark coverages and cactus death with greater than 95%.

Over the years, methods capable of integrating data from omics, such as transcriptomics, proteomics and metabolomics have emerged in Systems Biology, principally the use of networks to integrate omics information. In particular, the role of each biological pathway aims to understand the intermolecular interactions. While there are theoretical and experimental strategies to investigate biological pathways involved in cellular metabolism, computational modeling methods allow for a better understanding of them. Here we propose a new method to connect transcriptomic data with simulation approach using stochastic Petri Net (PN) metabolic networks. This new approach was developed based on well-studied theoretical gene expression modeling while trying to assimilate dynamic ordinary systems to a stochastic model function. The developed method was used to perform stochastic PN simulations of ethanol fermentation by Saccharomyces cerevisiae considering glucose and xylose as carbon sources. Lastly, we developed the PeNTIOS software, which is capable of converting Saccharomyces cerevisiae metabolic pathways and transcriptomic data into SBML format. The generated files can be readily imported into PN simulation programs. Our results show that the reconstruction of stochastic PN systems with transcriptomics data is a promising method that can generate new insights about biological experiments, as shown through our case study with the xylose-fermenting yeast.