Bayesian network ensemble as a multivariate strategy to predict radiation pneumonitis risk.

PURPOSE: Prediction of radiation pneumonitis (RP) has been shown to be challenging due to the involvement of a variety of factors including dose-volume metrics and radiosensitivity biomarkers. Some of these factors are highly correlated and might affect prediction results when combined. Bayesian network (BN) provides a probabilistic framework to represent variable dependencies in a directed acyclic graph. The aim of this study is to integrate the BN framework and a systems' biology approach to detect possible interactions among RP risk factors and exploit these relationships to enhance both the understanding and prediction of RP. METHODS: The authors studied 54 nonsmall-cell lung cancer patients who received curative 3D-conformal radiotherapy. Nineteen RP events were observed (common toxicity criteria for adverse events grade 2 or higher). Serum concentration of the following four candidate biomarkers were measured at baseline and midtreatment: alpha-2-macroglobulin, angiotensin converting enzyme (ACE), transforming growth factor, interleukin-6. Dose-volumetric and clinical parameters were also included as covariates. Feature selection was performed using a Markov blanket approach based on the Koller-Sahami filter. The Markov chain Monte Carlo technique estimated the posterior distribution of BN graphs built from the observed data of the selected variables and causality constraints. RP probability was estimated using a limited number of high posterior graphs (ensemble) and was averaged for the final RP estimate using Bayes' rule. A resampling method based on bootstrapping was applied to model training and validation in order to control under- and overfit pitfalls. RESULTS: RP prediction power of the BN ensemble approach reached its optimum at a size of 200. The optimized performance of the BN model recorded an area under the receiver operating characteristic curve (AUC) of 0.83, which was significantly higher than multivariate logistic regression (0.77), mean heart dose (0.69), and a pre-to-midtreatment change in ACE (0.66). When RP prediction was made only with pretreatment information, the AUC ranged from 0.76 to 0.81 depending on the ensemble size. Bootstrap validation of graph features in the ensemble quantified confidence of association between variables in the graphs where ten interactions were statistically significant. CONCLUSIONS: The presented BN methodology provides the flexibility to model hierarchical interactions between RP covariates, which is applied to probabilistic inference on RP. The authors' preliminary results demonstrate that such framework combined with an ensemble method can possibly improve prediction of RP under real-life clinical circumstances such as missing data or treatment plan adaptation.

Assessment of DNA extraction methods for detection of arbuscular mycorrhizal fungi in plant roots by nested-PCR / Avaliação de métodos de extração de ADN para detecção de fungos micorrízicos arbusculares em raízes de plantas por nested-PCR

DNA extraction methods were evaluated for the yield and purity of DNA recovered from mycorrhized roots and whether the recovered DNA is suitable for amplification of arbuscular mycorrhizal (AM) fungal SSU rDNA. The DNeasy Plant Mini Kit and three extraction buffers were used alone or in combination with either polyvinylpyrrolidone (PVP), polyvinylpolypyrrolidone (PVPP) and/or activated charcoal (AC). Among the extraction methods tested, those based on the CTAB buffers yielded more DNA than those based on the TE buffer and the DNeasy Plant Mini Kit. Moreover, the use of AC alone or in combination with PVPP reduced DNA yield, while it significantly improved the purity of recovered DNA, whatever the extraction buffer. On the other hand, the success of nested-PCR amplification was negatively correlated with the amount of template DNA and positively correlated with the purity of recovered DNA. Three methods based on the TE buffer, two on the CTAB-ßM buffer and one on the DNeasy Plant Mini Kit produced high-quality DNA in terms of purity and PCR performance. However, the TE buffer-based methods are less time consuming than the CTAB-ßM buffer-based methods, and cheaper than the method based on the DNeasy Plant Mini Kit.

Diferentes métodos de extração de ADN, a partir de amostras de raízes, foram testados e o ADN obtido foi avaliado para a amplificação de genes ribossomais de fungos micorrízicos arbusculares (AM). Três tampões de extração foram utilizados isoladamente ou em combinação com polivinilpirrolidona (PVP), polivinipolipirrolidona (PVPP) e/ou carvão ativado (CA), além do DNeasy Plant Mini Kit. Entre os métodos de extração testados, aqueles com base no tampão CTAB renderam mais ADN do que os baseados no tampão TE e o DNeasy Plant Mini Kit. A utilização de CA ou PVPP nos diferentes tampões reduziram o rendimento de ADN, contudo, melhoraram significativamente a pureza do ADN recuperado, independentemente do tampão de extração. Por outro lado, o sucesso da amplificação por Nested-PCR foi negativamente correlacionado com a quantidade de DNA molde, e positivamente correlacionada com a pureza do ADN. Três métodos baseados no tampão TE, dois no tampão CTAB-ßM e o DNeasy Plant Mini Kit produziram ADN de alta qualidade, em termos de pureza e rendimento da PCR. No entanto, os métodos baseados em tampão TE demandam menos tempo do que os métodos baseados em tampão CTAB-ßM e são mais baratos do que o uso do DNeasy Plant Mini Kit.