Machine learning approach for predicting the antifungal effect of gilaburu (Viburnum opulus) fruit extracts on Fusarium spp. isolated from diseased potato tubers.

This work addresses the mathematical model building to detect the diameter of the inhibition zone of gilaburu (Viburnum opulus L.) extract against eight different Fusarium strains isolated from diseased potato tubers. Gilaburu extracts were obtained with acetone, ethanol or methanol. The isolated Fusarium strains were: F. solani, F. oxysporum, F. sambucinum, F. graminearum, F. coeruleum, F. sulphureum, F. auneaceum and F. culmorum. In general, it was observed that ethanolic extracts showed highest antifungal activity. The antifungal activity of extracts was evaluated with machine learning (ML) methods. Several ML methods (classification and regression trees (CART), support vector machines (SVM), k-Nearest Neighbors (k-NN), artificial neural network (ANN), ensemble algorithms (EA), AdaBoost (AB) algorithm, gradient boosting (GBM) algorithm, random forests (RF) bagging algorithm and extra trees (ET)) were applied and compared for modeling fungal growth. From this research, it is clear that ML methods have the lowest error level. As a result, ML methods are reliable, fast, and cheap tools for predicting the antifungal activity of gilaburu extracts. These encouraging results will attract more research efforts to implement ML into the field of food microbiology instead of traditional methods.

Prediction of the antimicrobial activity of walnut (Juglans regia L.) kernel aqueous extracts using artificial neural network and multiple linear regression.

The mathematical model was established to determine the diameter of inhibition zone of the walnut extract on the twelve bacterial species. Type of extraction, concentration, and pathogens were taken as input variables. Two models were used with the aim of designing this system. One of them was developed with artificial neural networks (ANN), and the other was formed with multiple linear regression (MLR). Four common training algorithms were used. Levenberg-Marquardt (LM), Bayesian regulation (BR), scaled conjugate gradient (SCG) and resilient back propagation (RP) were investigated, and the algorithms were compared. Root mean squared error and correlation coefficient were evaluated as performance criteria. When these criteria were analyzed, ANN showed high prediction performance, while MLR showed low prediction performance. As a result, it is seen that when the different input values are provided to the system developed with ANN, the most accurate inhibition zone (IZ) estimates were obtained. The results of this study could offer new perspectives, particularly in the field of microbiology, because these could be applied to other type of extraction, concentrations, and pathogens, without resorting to experiments.

Relationships between skin cancers and blood groups--link between non-melanomas and ABO/Rh factors.

BACKGROUND: This investigation focused on possible relationships between skin cancers and ABO/Rh blood groups. MATERIALS AND METHODS: Between January 2005 and December 2012, medical data of 255 patients with skin cancers who were admitted to Kayseri Training and Research Hospital, Radiation Oncology and Plastic Surgery Outpatient Clinics were retrospectively analyzed. Blood groups of these patients were recorded. The control group consisted of 25701 healthy volunteers who were admitted to Kayseri Training and Research Hospital, Blood Donation Center between January 2010 and December 2011. The distribution of the blood groups of the patients with skin cancers was compared to the distribution of ABO/Rh blood groups of healthy controls. The association of the histopathological subtypes of skin cancer with the blood groups was also investigated. RESULTS: Of the patients, 50.2% had A type, 26.3% had O type, 16.1% had B type, and 7.5% had AB blood group with a positive Rh (+) in 77.3%. Of the controls, 44.3% had A type, 31.5% had 0 type, 16.1% had B type, and 8.1% had AB blood group with a positive Rh (+) in 87.8%. There was a statistically significant difference in the distribution of blood groups and Rh factors (A Rh (-) and 0 Rh positive) between the patients and controls. A total of 36.8% and 20.4% of the patients with basal cell carcinoma (BCC) had A Rh (+) and B Rh (+), respectively, while 39.2% and 27.6% of the controls had A Rh (+) and B Rh (+), respectively. A significant relationship was observed between the patients with BCC and controls in terms of A Rh (-) (p=0.001). CONCLUSION: Our study results demonstrated that there is a significant relationship between non-melanoma skin cancer and ABO/Rh factors.