Signatures of Life Detected in Images of Rocks Using Neural Network Analysis Demonstrate New Potential for Searching for Biosignatures on the Surface of Mars.

Microorganisms play a role in the construction or modulation of various types of landforms. They are especially notable for forming microbially induced sedimentary structures (MISS). Such microbial structures have been considered to be among the most likely biosignatures that might be encountered on the martian surface. Twenty-nine algorithms have been tested with images taken during a laboratory experiment for testing their performance in discriminating mat cracks (MISS) from abiotic mud cracks. Among the algorithms, neural network types produced excellent predictions with similar precision of 0.99. Following that step, a convolutional neural network (CNN) approach has been tested to see whether it can conclusively detect MISS in images of rocks and sediment surfaces taken at different natural sites where present and ancient (fossil) microbial mat cracks and abiotic desiccation cracks were observed. The CNN approach showed excellent prediction of biotic and abiotic structures from the images (global precision, sensitivity, and specificity, respectively, 0.99, 0.99, and 0.97). The key areas of interest of the machine matched well with human expertise for distinguishing biotic and abiotic forms (in their geomorphological meaning). The images indicated clear differences between the abiotic and biotic situations expressed at three embedded scales: texture (size, shape, and arrangement of the grains constituting the surface of one form), form (outer shape of one form), and pattern of form arrangement (arrangement of the forms over a few square meters). The most discriminative components for biogenicity were the border of the mat cracks with their tortuous enlarged and blistered morphology more or less curved upward, sometimes with thin laminations. To apply this innovative biogeomorphological approach to the images obtained by rovers on Mars, the main physical and biological sources of variation in abiotic and biotic outcomes must now be further considered.

An artificial neural network-based model to predict chronic kidney disease in aged cats.

BACKGROUND: Chronic kidney disease (CKD) frequently causes death in older cats; its early detection is challenging. OBJECTIVES: To build a sensitive and specific model for early prediction of CKD in cats using artificial neural network (ANN) techniques applied to routine health screening data. ANIMALS: Data from 218 healthy cats ≥7 years of age screened at the Royal Veterinary College (RVC) were used for model building. Performance was tested using data from 3546 cats in the Banfield Pet Hospital records and an additional 60 RCV cats-all initially without a CKD diagnosis. METHODS: Artificial neural network (ANN) modeling used a multilayer feed-forward neural network incorporating a back-propagation algorithm. Clinical variables from single cat visits were selected using factorial discriminant analysis. Independent submodels were built for different prediction time frames. Two decision threshold strategies were investigated. RESULTS: Input variables retained were plasma creatinine and blood urea concentrations, and urine specific gravity. For prediction of CKD within 12 months, the model had accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 88%, 87%, 70%, 53%, and 92%, respectively. An alternative decision threshold increased specificity and PPV to 98% and 87%, but decreased sensitivity and NPV to 42% and 79%, respectively. CONCLUSIONS AND CLINICAL IMPORTANCE: A model was generated that identified cats in the general population ≥7 years of age that are at risk of developing CKD within 12 months. These individuals can be recommended for further investigation and monitoring more frequently than annually. Predictions were based on single visits using common clinical variables.

Seasonal variation in the voluntary food intake of domesticated cats (Felis catus).

There are numerous reports about seasonal cycles on food intake in animals but information is limited in dogs and cats. A 4-year prospective, observational, cohort study was conducted to assess differences in food intake in 38 ad-libitum-fed adult colony cats, of various breeds, ages and genders. Individual food intake was recorded on a daily basis, and the mean daily intake for each calendar month was calculated. These data were compared with climatic data (temperature and daylight length) for the region in the South of France where the study was performed. Data were analysed using both conventional statistical methods and by modelling using artificial neural networks (ANN). Irrespective of year, an effect of month was evident on food intake (P<0.001), with three periods of broadly differing intake. Food intake was least in the summer months (e.g. June, to August), and greatest during the months of late autumn and winter (e.g. October to February), with intermediate intake in the spring (e.g. March to May) and early autumn (e.g. September). A seasonal effect on bodyweight was not recorded. Periods of peak and trough food intake coincided with peaks and troughs in both temperature and daylight length. In conclusion, average food intake in summer is approximately 15% less than food intake during the winter months, and is likely to be due to the effects of outside temperatures and differences in daylight length. This seasonal effect in food intake should be properly considered when estimating daily maintenance energy requirements in cats.

Influence of in situ biological activity on the vertical profile of pre-emergence herbicides in sediment.

The in situ effect of biological activity on herbicide degradation was studied in sediment. Early diagenesis indicators of organic matter (OM) was selected to provide information on the presence and the kinetics of the various biotic and abiotic processes involved in the degradation of fresh organic matter, the vector of herbicides in sediment. Two tandem-coring samples were taken in the Malause reservoir, one in the hyperoxic zone (Tarn confluence, MT core) and the other in the central part, under the exclusive influence of the Garonne River (MG core), after having crossed a zone where the high intensity of abiotic processes is proven. At each site, analysis of the vertical profile of the herbicides was coupled with compounds associated with early diagenesis of OM. The MT core proved nearly seven times more contaminated than the MG core. DEA played a minor role in sediment contamination. Biological activity only seems to influence herbicide degradation indirectly. Neither oxygen concentration nor the level of labile carbon indicated any correlation between the consumption of fresh organic matter and substrate degradation. Herbicide transformation thus does not seem to depend on the consortia studied but on physicochemical parameters such as hydrolysis, leading to the long half-life of herbicides in sediment and hence their long-term presence in the aquatic environment.