Classification of crossed immunoelectrophoretic patterns using digital image processing and artificial neural networks

Marker-Trait Association Analysis of Seed Traits in Accessions of Common Bean (Phaseolus vulgaris L.) in China

Seed weight and seed size are the key agronomic traits that determine yield in common bean. To investigate the genetic architecture of four seed traits (100-seed weight, seed length, seed width, and seed height) of common bean in China, marker-trait association analysis of these seed traits was performed in a nationwide population of 395 common bean accessions using 116 polymorphic SSR markers. The four seed traits were evaluated in six trials across three environments. Seed size varied among the environments. Population structure was evaluated based on SSR markers and phaseolin, which divided the accessions into two main subpopulations representing the two known gene pools. Seed weight and seed size had a strong relationship with population clustering. In addition, in a Genome-wide association studies (GWAS), 21 significantly associated markers were identified for the four seed traits with two models, namely, general linear model (GLM) and mixed linear model (MLM). Some markers had pleiotropic effects, i.e., controlled more than one trait. The significant quantitative trait loci identified in this study could be used in marker-assisted breeding to accelerate the genetic improvement of yield in common bean.

Adaptive classification of two-dimensional gel electrophoretic spot patterns by neural networks and cluster analysis

The interpretation of two-dimensional gel electrophoresis spot profiles can be facilitated by statistical and machine learning programs. Two different approaches to classification of spot profiles - cluster analysis and neural networks - are discussed. Neural networks for two different model patterns were designed and an algorithm for training of the net for the classification was developed. It was shown that the performance of neural networks is higher compared to cluster and principal component analysis. The possibility of combining both approaches into one process can increase reliability and speed of classification. Artificially created training sets with added random noise can be used for network training. The analysis was applied on the Streptomyces coelicolor developmental two-dimensional (2-D) gel database.

From image processing to classification: IV. Classification of electrophoretic patterns by neural networks and statistical methods enable quality assessment of wheat varieties for breadmaking

The end-use quality of products made from doughs consisting of wheat flour and water is often dependent upon the storage (gluten) proteins of the grain endosperm. Today the electrophoretic patterns of the high molecular weight (HMW) glutenin subunits are used for quality selections in wheat breeding programs in several countries. In this study, we used two multivariate techniques to classify digitized patterns from isoelectric focusing of gliadins and glutenins: a two-layered neural network architecture consisting of a self-organizing feature map and a feed-forward classifier [1], and discriminant analysis [2,3]. Three groups of seven wheat varieties (Triticum aestivum L.), associated with poor, medium or good properties in relation to bread-making quality, were used. The best classification results were obtained by the neural network model, based on data from the gliadin fraction: it was possible to classify varieties associated with poor or good quality, with recognition rates of 70 and 69%, respectively. The statistical method was better suited to solve the classification problem when the data was based on the glutenin fraction: if a specific variety was already known to be non-poor, this method enabled us to classify the medium- and good-quality classes with recognition rates of 90 and 88%, respectively. The results obtained were confirmed by correlation coefficients.

Artificial neural networks for decision support in clinical medicine

Connectionist models such as neural networks are alternatives to linear, parametric statistical methods. Neural networks are computer-based pattern recognition methods with loose similarities with the nervous system. Individual variables of the network, usually called 'neurones', can receive inhibitory and excitatory inputs from other neurones. The networks can define relationships among input data that are not apparent when using other approaches, and they can use these relationships to improve accuracy. Thus, neural nets have substantial power to recognize patterns even in complex datasets. Neural network methodology has outperformed classical statistical methods in cases where the input variables are interrelated. Because clinical measurements usually derive from multiple interrelated systems it is evident that neural networks might be more accurate than classical methods in multivariate analysis of clinical data. This paper reviews the use of neural networks in medical decision support. A short introduction to the basics of neural networks is given, and some practical issues in applying the networks are highlighted. The current use of neural networks in image analysis, signal processing and laboratory medicine is reviewed. It is concluded that neural networks have an important role in image analysis and in signal processing. However, further studies are needed to determine the value of neural networks in the analysis of laboratory data.

From image processing to classification: II. Classification of electrophoretic patterns using self-organizing feature maps and feed-forward neural networks

In a recent study, isoelectric focusing patterns were classified with a neural network using the back-propagation algorithm [1]. In order to further study the classification process and to generalize the presentation of electrophoretic patterns, Kohonen's self-organizing feature maps [2] were applied in this study. Although these feature maps are very efficient in many pattern recognition tasks, our data proved to be too complex for classification with an unsupervised system. Therefore, a second supervised network on top of the feature map was necessary. As in [3], a feed-forward network trained by the back-propagation algorithm was used. The final system allows us to correctly classify 90% of all wheat varieties. Moreover, the system proved to be reliable, reasonable in training time and shows the same accuracy in different experimental setups.

The development of a decision support system for the pathological diagnosis of human cerebral tumours based on a neural network classifier

This study describes the use of a topological mapping system in the classification of cerebral tumours and the development of a decision support system based upon that classifier. Fourteen pathological parameters from two hundred primary cerebral tumours are presented as vectors to a topological map. The map, consisting of a grid of neurones, learns the features of each tumour by means of a shortest Euclidean distance algorithm, after which self adaptation of the neurons occurs. An LVQ algorithm performs the final classification. Study of the map reveals that it can correctly classify tumors following their malignancy potential and their cytogenesis. The decision support system uses the network at its core and helps not only in reaching a diagnosis but also in finding the optimal way to reach that diagnosis. The usefulness of such a mapping system lies in the field of education, clinical research and medically acceptable cost reduction.

Classification of wheat varieties by isoelectric focusing patterns of gliadins and neural network

Classification of wheat varieties, using isoelectric focusing patterns of the gliadins, image processing and neural networks, is described. The method was compared to a statistical classification method, discriminant analysis. The isoelectric point and the area of each band were calculated by image processing. Different methods of presenting the electrophoretic patterns to the neural network were studied. The most effective method was transformation of the electrophoretic pattern to a small (11 x 47 pixels) representation of the original digitized image, which was presented to the neural network as a vector. The neural network was trained with a number of patterns and tested with new patterns from different electrophoretic runs of the same wheat varieties. In this study we used ten different wheat varieties and the neural network was able to classify 95.5% of the patterns correctly. The statistical classification method classified the same data set 91.8% correctly. We conclude that both the neural network and discriminant analysis were able to classify the patterns correctly with a high degree of certainty. The patterns that were misclassified were indistinguishable by visual inspection.

Artificial neural networks for cancer research: outcome prediction

The use of artificial neural networks in biological and medical research has increased tremendously in the last few years. Artificial neural networks are being used in cancer research for image processing, the analysis of laboratory data for breast cancer diagnosis, the discovery of chemotherapeutic agents, and for cancer outcome prediction. A neural network generalizes from the input data to patterns inherent in the data, and its uses these patterns to make predictions or to classify. This paper explains how neural networks work, and it shows that a neural network is more accurate at predicting breast cancer patient outcome than the current staging system.