ICI - C4 | Centro de Competências em Cloud Computing | Documentos por Auto-Depósito
Permanent URI for this collection
O C4 - Centro de Competências em Cloud Computing conta com o contributo de investigadores afetos à Universidade da Beira Interior (UBI) e aos institutos politécnicos de Castelo Branco e da Guarda.
Website C4Browse
Recent Submissions
- Irrigation optimization with a deep reinforcement learning model: Case study on a site in PortugalPublication . Alibabaei, Khadijeh; Gaspar, Pedro Dinis; Assunção, Eduardo Timóteo; Alirezazadeh, Saeid; Lima, Tânia M.In the field of agriculture, the water used for irrigation should be given special treatment, as it is responsible for a large proportion of total water consumption. Irrigation scheduling is critical to food production because it guarantees producers a consistent harvest and minimizes the risk of losses due to water shortages. Therefore, the creation of an automatic irrigation method using new technologies is essential. New methods such as deep learning algorithms have attracted a lot of attention in agriculture and are already being used successfully. In this work, a Deep Q-Network was trained for irrigation scheduling. The agent was trained to schedule irrigation for a tomato field in Portugal. Two Long Short Term Memory models were used as the agent environment. One predicts the total water in the soil profile on the next day. The other one was employed to estimate the yield based on the environmental condition during a season and then measure the net return. The agent uses this information to decide the following irrigation amount. An Artificial Neural Network, a Long Short Term Memory, and a Convolutional Neural Network were used to estimating the Q-table during training. Unlike the Long-Short Terms Memory model, the Artificial Neural Network and the Convolutional Neural Network could not estimate the Q-table, and the agent’s reward decreased during training. The comparison of the performance of the model was done with fixed base irrigation and threshold based irrigation. The trained model increased productivity by 11% and decreased water consumption by 20–30% compared to the fixed method.
- Natural Transformation as a Mechanism of Horizontal Gene Transfer in Aliarcobacter butzleriPublication . Bonifácio, Marina; Mateus, Cristiana; Alves, Ana R.; Maldonado, Emanuel; Duarte, Ana Paula; Domingues, Fernanda; Oleastro, Mónica; Ferreira, SusanaAliarcobacter butzleri is an emergent enteropathogen, showing high genetic diversity, which likely contributes to its adaptive capacity to different environments. Whether natural transformation can be a mechanism that generates genetic diversity in A. butzleri is still unknown. In the present study, we aimed to establish if A. butzleri is naturally competent for transformation and to investigate the factors influencing this process. Two different transformation procedures were tested using exogenous and isogenic DNA containing antibiotic resistance markers, and different external conditions influencing the process were evaluated. The highest number of transformable A. butzleri strains were obtained with the agar transformation method when compared to the biphasic system (65% versus 47%). A. butzleri was able to uptake isogenic chromosomal DNA at different growth phases, and the competence state was maintained from the exponential to the stationary phases. Overall, the optimal conditions for transformation with the biphasic system were the use of 1 µg of isogenic DNA and incubation at 30 ◦C under a microaerobic atmosphere, resulting in a transformation frequency ~8 × 10−6 transformants/CFU. We also observed that A. butzleri favored the transformation with the genetic material of its own strain/species, with the DNA incorporation process occurring promptly after the addition of genomic material. In addition, we observed that A. butzleri strains could exchange genetic material in co-culture assays. The presence of homologs of well-known genes involved in the competence in the A. butzleri genome corroborates the natural competence of this species. In conclusion, our results show that A. butzleri is a naturally transformable species, suggesting that horizontal gene transfer mediated by natural transformation is one of the processes contributing to its genetic diversity. In addition, natural transformation can be used as a tool for genetic studies of this species.
- On the stability of point cloud machine learning based codingPublication . Prazeres, João; Rodrigues, Rafael; Pereira, Manuela; Pinheiro, Antonio M. G.This paper analyses the performance of two of the most well known deep learning-based point cloud coding solutions, considering the training conditions. Several works have recently been published on point cloud machine learning-based coding, following the recent tendency on image coding. These codecs are typically seen as a set of predefined trained machines. However, the performance of such models is usually very dependent of their training, and little work has been considered on the stability of the codecs’ performance, as well as the possible influence of the loss function parameters, and the increasing number of training epochs. The evaluation experiments are supported in a generic test set with point clouds representing objects and also more complex scenes, using the point to point metric (PSNR D1), as several studies revealed the good quality representation of this geometry-only point cloud metric.
- Prediction of the Arbutus unedo colonization time via an agent-based distribution modelPublication . Bioco, João; Prata, Paula; Canovas, Fernando; Fazendeiro, PauloSpecies distribution models (SDMs) have been used to predict the distribution of species in an environment. Usually, this prediction is based on previous species occurrence data. Nowadays, several species are facing climatic changes that impact the way species behave. Global warming has implicated species displacement from their natural habitat to new suitable places. SDMs can be used to anticipate possible impacts of the climatic changes in species distribution, preventing species extinction scenarios. New SDMs approaches are needed to give valuable information that better approximates these models to reality. This paper presents a novel approach to the prediction of species distribution. It starts by using an agent-based model (ABM) to establish an approximate mapping between the geological and the computational times. Afterwards, the implemented ABM can be used to predict the species distribution at different time intervals. The presented case study concerns the distribution of the Arbutus unedo in the Iberian peninsula, a species with relevant socio-economic impact in Portugal. The results show that the measurement of the geological time, supported by the approximate correspondence to the number of epochs of an ABM, can be a valuable tool for the prediction of the species distribution in a changing environmental scenario.
- The Effectiveness of Therapeutic Vaccines for the Treatment of Cervical Intraepithelial Neoplasia 3: A Systematic Review and Meta-AnalysisPublication . Ventura, Cathy; Luís, Ângelo; Soares, Christiane P.; Venuti, Aldo; Paolini, Francesca; Pereira, L.; Sousa, ÂngelaCervical cancer (CC) is a disease that affects many women worldwide, especially in low-income countries. The human papilloma virus (HPV) is the main causative agent of this disease, with the E6 and E7 oncoproteins being responsible for the development and maintenance of transformed status. In addition, HPV is also responsible for the appearance of cervical intraepithelial neoplasia (CIN), a pre-neoplastic condition burdened by very high costs for its screening and therapy. So far, only prophylactic vaccines have been approved by regulatory agencies as a means of CC prevention. However, these vaccines cannot treat HPV-positive women. A search was conducted in several databases (PubMed, Scopus, Web of Science, and ClinicalTrials.gov) to systematically identify clinical trials involving therapeutic vaccines against CIN 3. Histopathological regression data, immunological parameters, safety, DNA clearance, and vaccine efficacy were considered from each selected study, and from the 102 articles found, 8 were selected based on the defined inclusion criteria. Histopathological regression from CIN 3 to CIN < 1 was 22.1% (95% CI: 0.627–0.967; p-value = 0.024), showing a vaccine efficacy of 23.6% (95% CI; 0.666–0.876; p-value < 0.001). DNA clearance was assessed, and the risk of persistent HPV DNA was 23.2% (95% CI: 0.667–0.885; p-value < 0.001). Regarding immunological parameters, immune responses by specific T-HPV cells were more likely in vaccinated women (95% CI: 1.245–9.162; p-value = 0.017). In short, these studies favored the vaccine group over the placebo group. This work indicated that therapeutic vaccines are efficient in the treatment of CIN 3, even after accounting for publication bias.
- The Prevalence of Arcobacteraceae in Aquatic Environments: A Systematic Review and Meta-AnalysisPublication . Venâncio, Igor Miguel Antunes; Luís, Ângelo; Domingues, F.C.; Oleastro, Mónica; Pereira, L.; Ferreira, SusanaMembers of the family Arcobacteraceae are distributed widely in aquatic environments, and some of its species have been associated with human and animal illness. However, information about the diversity and distribution of Arcobacteraceae in different water bodies is still limited. In order to better characterize the health risk posed by members in the family Arcobacteraceae, a systematic review and meta-analysis-based method was used to investigate the prevalence of Arcobacteraceae species in aquatic environments based on available data published worldwide. The database search was performed using related keywords and considering studies up to February 2021. The pooled prevalence in aquatic environments was 69.2%, ranging from 0.6 to 99.9%. These bacteria have a wide geographical distribution, being found in diverse aquatic environments with the highest prevalence found in raw sewage and wastewater treatment plants (WWTP), followed by seawater, surface water, ground water, processing water from food processing plants and water for human consumption. Assessing the effectiveness of treatments in WWTP in eliminating this contamination, it was found that the wastewater treatment may not be efficient in the removal of Arcobacteraceae. Among the analyzed Arcobacteraceae species, Al. butzleri was the most frequently found species. These results highlight the high prevalence and distribution of Arcobacteraceae in different aquatic environments, suggesting a risk to human health. Further, it exposes the importance of identifying and managing the sources of contamination and taking preventive actions to reduce the burden of members of the Arcobacteraceae family.
- Utility-driven assessment of anonymized data via clusteringPublication . Ferrão, Maria Eugénia; Prata, Paula; Fazendeiro, PauloIn this study, clustering is conceived as an auxiliary tool to identify groups of special interest. This approach was applied to a real dataset concerning an entire Portuguese cohort of higher education Law students. Several anonymized clustering scenarios were compared against the original cluster solution. The clustering techniques were explored as data utility models in the context of data anonymization, using k-anonymity and (ε, δ)-differential as privacy models. The purpose was to assess anonymized data utility by standard metrics, by the characteristics of the groups obtained, and the relative risk (a relevant metric in social sciences research). For a matter of self-containment, we present an overview of anonymization and clustering methods. We used a partitional clustering algorithm and analyzed several clustering validity indices to understand to what extent the data structure is preserved, or not, after data anonymization. The results suggest that for low dimensionality/cardinality datasets the anonymization procedure easily jeopardizes the clustering endeavor. In addition, there is evidence that relevant field-of-study estimates obtained from anonymized data are biased.
- On the Modelling of Species Distribution: Logistic Regression Versus Density Probability FunctionPublication . Bioco, João; Prata, Paula; Canovas, Fernando; Fazendeiro, PauloThe concerns related to climate changes have been gaining attention in the last few years due to the negative impacts on the environment, economy, and society. To better understand and anticipate the effects of climate changes in the distribution of species, several techniques have been adopted comprising models of different complexity. In general, these models apply algorithms and statistical methods capable of predicting in a particular study area, the locations considered suitable for a species to survive and reproduce, given a set of eco-geographical variables that influence species behavior. Logistic regression algorithm and Probability density function are two common methods that can be used to model the species suitability. The former is a representative of a class of models that requires the availability (or imputation) of presence-absence data whereas the latter represents the models that only require presence data. Both approaches are compared regarding the capability to accurately predict the environmental suitability for species. On a different way, the behaviour of the species in the projected environments are analysed by simulating its potential distribution in the projected environment. A case study reporting results from two types of species with economical interest is presented: the strawberry tree (Arbutus unedo) in mainland Portugal, and the Apis mellifera (African Lineage) in the Iberian Peninsula.
- Promoter Demethylation Upregulates STEAP1 Gene Expression in Human Prostate Cancer: In Vitro and In Silico AnalysisPublication . Rocha, Sandra; Sousa, Inês; Gomes, Inês M.; Arinto, Patrícia; Pinheiro, Pedro Costa; Coutinho, Eduarda; Santos, Cecilia; Jerónimo, Carmen; Lemos, Manuel C.; Passarinha, L A; Socorro, Sílvia; Baptista, Cláudio MaiaThe Six Transmembrane Epithelial Antigen of the Prostate (STEAP1) is an oncogene overexpressed in several human tumors, particularly in prostate cancer (PCa). However, the mechanisms involved in its overexpression remain unknown. It is well known that epigenetic modifications may result in abnormal gene expression patterns, contributing to tumor initiation and progression. Therefore, this study aimed to analyze the methylation pattern of the STEAP1 gene in PCa versus non-neoplastic cells. Bisulfite amplicon sequencing of the CpG island at the STEAP1 gene promoter showed a higher methylation level in non-neoplastic PNT1A prostate cells than in human PCa samples. Bioinformatic analysis of the GEO datasets also showed the STEAP1 gene promoter as being demethylated in human PCa, and a negative association with STEAP1 mRNA expression was observed. These results are supported by the treatment of non-neoplastic PNT1A cells with DNMT and HDAC inhibitors, which induced a significant increase in STEAP1 mRNA expression. In addition, the involvement of HDAC in the regulation of STEAP1 mRNA expression was corroborated by a negative association between STEAP1 mRNA expression and HDAC4,5,7 and 9 in human PCa. In conclusion, our work indicates that STEAP1 overexpression in PCa can be driven by the hypomethylation of STEAP1 gene promoter.
- Molecular Beacon Assay Development for Severe Acute Respiratory Syndrome Coronavirus 2 DetectionPublication . Carvalho, Josué; Nunes, J. Lopes; Figueiredo, Joana; Santos, Tiago; Miranda, André; Riscado, Micaela; Sousa, Fani; Duarte, A. P.; Socorro, Sílvia; Tomaz, Cândida; Felgueiras, Mafalda; Teixeira, Rui; Faria, Conceição; Cruz, CarlaThe fast spread of SARS-CoV-2 has led to a global pandemic, calling for fast and accurate assays to allow infection diagnosis and prevention of transmission. We aimed to develop a molecular beacon (MB)-based detection assay for SARS-CoV-2, designed to detect the ORF1ab and S genes, proposing a two-stage COVID-19 testing strategy. The novelty of this work lies in the design and optimization of two MBs for detection of SARS-CoV-2, namely, concentration, fluorescence plateaus of hybridization, reaction temperature and real-time results. We also identify putative G-quadruplex (G4) regions in the genome of SARS-CoV-2. A total of 458 nasopharyngeal and throat swab samples (426 positive and 32 negative) were tested with the MB assay and the fluorescence levels compared with the cycle threshold (Ct) values obtained from a commercial RT-PCR test in terms of test duration, sensitivity, and specificity. Our results show that the samples with higher fluorescence levels correspond to those with low Ct values, suggesting a correlation between viral load and increased MB fluorescence. The proposed assay represents a fast (total duration of 2 h 20 min including amplification and fluorescence reading stages) and simple way of detecting SARS-CoV-2 in clinical samples from the upper respiratory tract.