Ribopeaks: a web tool for bacterial classification through m/z data from ribosomal proteins.

Summary: MALDI-TOF MS is a rapid, sensitive and economic tool for bacterial identification. Highly abundant bacterial proteins are detected by this technique, including ribosomal proteins (r-protein), and the generated mass spectra are compared with a MALDI-TOF MS spectra database. Currently, it allows mainly the classification of clinical bacteria due to the limited number of environmental bacteria included in the spectra database. We present a wide-ranging bacterium classifier tool, called Ribopeaks, which was created based on r-protein data from the Genbank. The Ribopeaks database has more than 28 500 bacterial taxonomic records. It compares the incoming m/z data from MALDI-TOF MS analysis with models stored in the Ribopeaks database created by machine learning and then taxonomically classifies the bacteria. Availability and implementation: The software is available at http://www.ribopeaks.com. Supplementary information: Supplementary data are available at Bioinformatics online.

Previsão do Índice de Desenvolvimento Humano e da expectativa de vida nos países da América Latina por meio de técnicas de mineração de dados / Forecasting the human development index and life expectancy in Latin American countries using data mining techniques

Resumo A previsibilidade de indicadores epidemiológicos pode contribuir na projeção de variáveis dependentes, auxiliar em tomadas de decisões para sustentar ou não políticas públicas e justificar o cenário vivido pelos países e o mundo. O artigo tem por objetivo predizer o Índice de Desenvolvimento Humano e a expectativa de vida nos países latino-americanos no período de 2015 a 2020, utilizando técnicas de mineração de dados. Foram percorridas as etapas do processo Descoberta de Conhecimento em Base Dados. Adotaram-se para previsões modelos desenvolvidos com séries multivariadas através do algoritmo de mineração de dados SMOReg, que apresentaram melhor desempenho em testes desenvolvidos durante o experimento. As médias do Índice de Desenvolvimento Humano e da expectativa de vida nos países latino-americanos tendem a aumentar no período analisado, respectivamente, 4,99 ± 3,90 % e 2,65 ± 0,06 anos. Experiências multivariadas possibilitam maior aprendizagem dos algoritmos, aumentando sua precisão. As técnicas de mineração de dados apresentaram melhor qualidade nas previsões em relação à técnica mais popular, ARIMA. As previsões sugerem média de crescimento do IDH e EV dos países latino-americanos maiores que a mundial.

Abstract The predictability of epidemiological indicators can help estimate dependent variables, assist in decision-making to support public policies, and explain the scenarios experienced by different countries worldwide. This study aimed to forecast the Human Development Index (HDI) and life expectancy (LE) for Latin American countries for the period of 2015-2020 using data mining techniques. All stages of the process of knowledge discovery in databases were covered. The SMOReg data mining algorithm was used in the models with multivariate time series to make predictions; this algorithm performed the best in the tests developed during the evaluation period. The average HDI and LE for Latin American countries showed an increasing trend in the period evaluated, corresponding to 4.99 ± 3.90% and 2.65 ± 0.06 years, respectively. Multivariate models allow for a greater evaluation of algorithms, thus increasing their accuracy. Data mining techniques have a better predictive quality relative to the most popular technique, Autoregressive Integrated Moving Average (ARIMA). In addition, the predictions suggest that there will be a higher increase in the mean HDI and LE for Latin American countries compared to the mean values for the rest of the world.