Breast cancer risk estimation with intelligent algorithms and risk factors for Cuban women.

Breast cancer is the most common malignant neoplasm and the leading cause of cancer mortality among women globally. Current prediction models based on risk factors are inefficient in specific populations, so an appropriate and calibrated breast cancer prediction model for Cuban women is essential. This article proposes a conceptual model for breast cancer risk estimation for Cuban women using machine learning algorithms and risk factors. The model has three main components: knowledge representation, risk estimation modeling, and risk predictor evaluation. Nine of the most common machine learning algorithms were used to generate risk predictors using the proposed model. Two data sources served as case studies: the first comprised data collected from Cuban women, and the second included data from US Hispanic women obtained from the Breast Cancer Surveillance Consortium dataset. The results show that the model effectively estimates breast cancer risk and could be a valuable tool for early detection of breast cancer and identification of patients at risk. According to the first experiment results, the best predictor of breast cancer risk for the Cuban female population corresponds to the Random Forest algorithm with a weighted score of 5.981, a training accuracy of 0.996 and a training AUC of 0.997. In a second experiment, it was demonstrated that the risk predictors generated by the proposed model using data from Cuban women obtained better AUC and accuracy values compared to the predictors generated by using the US Hispanic population, potentially generalizable to other Hispanic populations. Implementing this model could be an economically viable alternative to reduce the mortality rate of this type of cancer in Latin American countries such as Cuba.

Epidemiological overview of snakebites in the Baja California peninsula, Mexico (2003-2018).

INTRODUCTION: Ophidian accident is a global public health problem. In Mexico, there is a high incidence of snakebites, which cause medical complications that can leave severe sequelae. OBJECTIVE: To analyze the epidemiological overview of snake venom poisoning in the Baja California (BC) peninsula within the 2003-2018 period. METHOD: A descriptive, retrospective analysis of reported cases was carried out, based on data collection and interpretation. RESULTS: A total of 541 records were obtained, out of which 273 occurred in BC and 268 in Baja California Sur (BCS), with an annual average of 17.06 and 16.75, respectively. The incidence rate for BC was 7.62, while for BCS it was 33.09. The highest annual incidence rate in the state of BC corresponded to southern Ensenada, with a value of 42.3, while in BCS it corresponded to the municipality of Comondú, with a value of 54.04. CONCLUSIONS: Epidemiological analyses allow a better local, state and regional understanding of the problem, in order to develop efficient action protocols to face an ophidian accident, as well as to determine the training requirements of medical personnel and establish a support network for the treatment of cases.

INTRODUCCIÓN: El accidente ofídico es un problema de salud pública mundial. En México existe una alta incidencia de mordeduras por serpientes, que provocan complicaciones médicas que pueden dejar secuelas severas. OBJETIVO: Analizar el panorama epidemiológico del ofidismo en la península de Baja California (BC) en los años 2003-2018. MÉTODO: Se hizo un análisis de tipo descriptivo y retrospectivo de los casos presentados, a partir de la recopilación e interpretación de la información. RESULTADOS: Se obtuvieron 541 registros, de los cuales 273 se presentaron en BC y 268 en Baja California Sur (BCS), con un promedio anual de 17.06 y 16.75 respectivamente. La tasa de incidencia para BC fue de 7.62 y para BCS de 33.09. La tasa de incidencia anual más alta en el Estado de BC correspondió al sur de Ensenada, con un valor de 42.3, mientras que en BCS fue en Comondú, con un valor de 54.04. CONCLUSIONES: Los análisis epidemiológicos permiten tener un mejor entendimiento local, estatal y regional de la problemática, para poder desarrollar protocolos de acción eficientes para enfrentar un accidente ofídico, así como para determinar las necesidades de capacitación del personal médico y establecer una red de ayuda para el tratamiento de casos.

An agent-based model of the fission yeast cell cycle.

The objective of this paper is to develop a computational model of the fission yeast (Schizosaccharomyces pombe) cell cycle using agent-based modeling (ABM), to study the sequence of states of the proteins and time of the cell cycle phases, under the action of proteins that regulate its cell cycle. The model relies only on the conceptual model of the yeast cell cycle regulatory network, where each protein has been represented as an agent with a property called activity that represents its biological function and a stochastic Brownian movement. The results indicate that the simulated phase time did have similar results in comparison with other models using mathematical approaches. Similarly, the correct sequence of states was achieved, and the model was run under different initial states to understand its emergent behaviors. The cell reached the G1 stationary state 94% of the times when running the model under biological initial conditions and 87% of the times when running the model through all the different combinations of initial states. Such results imply that the cell was capable to fix toward the biological expected phenomena. These results show that ABM is a suitable technique to study protein-protein interactions without using, often unavailable, kinetic parameters, or differential equations. This model sets as a base for further studies that involve the cell cycle of the fission yeast, with a special attention to studies and development of drug treatments for specific types of cancer.

Model based on GA and DNN for prediction of mRNA-Smad7 expression regulated by miRNAs in breast cancer.

BACKGROUND: The Smad7 protein is negative regulator of the TGF-ß signaling pathway, which is upregulated in patients with breast cancer. miRNAs regulate proteins expressions by arresting or degrading the mRNAs. The purpose of this work is to identify a miRNAs profile that regulates the expression of the mRNA coding for Smad7 in breast cancer using the data from patients with breast cancer obtained from the Cancer Genome Atlas Project. METHODS: We develop an automatic search method based on genetic algorithms to find a predictive model based on deep neural networks (DNN) which fit the set of biological data and apply the Olden algorithm to identify the relative importance of each miRNAs. RESULTS: A computational model of non-linear regression is shown, based on deep neural networks that predict the regulation given by the miRNA target transcripts mRNA coding for Smad7 protein in patients with breast cancer, with R2 of 0.99 is shown and MSE of 0.00001. In addition, the model is validated with the results in vivo and in vitro experiments reported in the literature. The set of miRNAs hsa-mir-146a, hsa-mir-93, hsa-mir-375, hsa-mir-205, hsa-mir-15a, hsa-mir-21, hsa-mir-20a, hsa-mir-503, hsa-mir-29c, hsa-mir-497, hsa-mir-107, hsa-mir-125a, hsa-mir-200c, hsa-mir-212, hsa-mir-429, hsa-mir-34a, hsa-let-7c, hsa-mir-92b, hsa-mir-33a, hsa-mir-15b, hsa-mir-224, hsa-mir-185 and hsa-mir-10b integrate a profile that critically regulates the expression of the mRNA coding for Smad7 in breast cancer. CONCLUSIONS: We developed a genetic algorithm to select best features as DNN inputs (miRNAs). The genetic algorithm also builds the best DNN architecture by optimizing the parameters. Although the confirmation of the results by laboratory experiments has not occurred, the results allow suggesting that miRNAs profile could be used as biomarkers or targets in targeted therapies.