Quantitative assessment model for gastric cancer screening.
(57/394)
AIM: To set up a mathematic model for gastric cancer screening and to evaluate its function in mass screening for gastric cancer. METHODS: A case control study was carried on in 66 patients and 198 normal people, then the risk and protective factors of gastric cancer were determined, including heavy manual work, foods such as small yellow-fin tuna, dried small shrimps, squills, crabs, mothers suffering from gastric diseases, spouse alive, use of refrigerators and hot food, etc. According to some principles and methods of probability and fuzzy mathematics, a quantitative assessment model was established as follows: first, we selected some factors significant in statistics, and calculated weight coefficient for each one by two different methods; second, population space was divided into gastric cancer fuzzy subset and non gastric cancer fuzzy subset, then a mathematic model for each subset was established, we got a mathematic expression of attribute degree (AD). RESULTS: Based on the data of 63 patients and 693 normal people, AD of each subject was calculated. Considering the sensitivity and specificity, the thresholds of AD values calculated were configured with 0.20 and 0.17, respectively. According to these thresholds, the sensitivity and specificity of the quantitative model were about 69% and 63%. Moreover, statistical test showed that the identification outcomes of these two different calculation methods were identical (P>0.05). CONCLUSION: The validity of this method is satisfactory. It is convenient, feasible, economic and can be used to determine individual and population risks of gastric cancer. (+info)
Small, fuzzy and interpretable gene expression based classifiers.
(58/394)
MOTIVATION: Interpretation of classification models derived from gene-expression data is usually not simple, yet it is an important aspect in the analytical process. We investigate the performance of small rule-based classifiers based on fuzzy logic in five datasets that are different in size, laboratory origin and biomedical domain. RESULTS: The classifiers resulted in rules that can be readily examined by biomedical researchers. The fuzzy-logic-based classifiers compare favorably with logistic regression in all datasets. AVAILABILITY: Prototype available upon request. (+info)
Novel genetic-neuro-fuzzy filter for speckle reduction from sonography images.
(59/394)
Edge-preserving speckle noise reduction is essential to computer-aided ultrasound image processing and understanding. A new class of genetic-neuro-fuzzy filter is proposed to optimize the trade-off between speckle noise removal and edge preservation. The proposed approach combines the advantages of the fuzzy, neural, and genetic paradigms. Neuro-fuzzy approaches are very promising for nonlinear filtering of noisy images. Fuzzy reasoning embedded into the network structure aims at reducing errors while fine details are being processed. The learning method based on the real-time genetic algorithms (GAs) performs an effective training of the network from a collection of training data and yields satisfactory results after a few generations. The performance of the proposed filter has been compared with that of the commonly used median and Wiener filters in reducing speckle noises on ultrasound images. We evaluate this filter by passing the filter's output to the edge detection algorithm and observing its ability to detect edge pixels.Experimental results show that the proposed genetic-neuro-fuzzy technique is very effective in speckle noise reduction as well as detail preserving even in the presence of highly noise corrupted data, and it works significantly better than other well-known conventional methods in the literature. (+info)
Fuzzy species among recombinogenic bacteria.
(60/394)
BACKGROUND: It is a matter of ongoing debate whether a universal species concept is possible for bacteria. Indeed, it is not clear whether closely related isolates of bacteria typically form discrete genotypic clusters that can be assigned as species. The most challenging test of whether species can be clearly delineated is provided by analysis of large populations of closely-related, highly recombinogenic, bacteria that colonise the same body site. We have used concatenated sequences of seven house-keeping loci from 770 strains of 11 named Neisseria species, and phylogenetic trees, to investigate whether genotypic clusters can be resolved among these recombinogenic bacteria and, if so, the extent to which they correspond to named species. RESULTS: Alleles at individual loci were widely distributed among the named species but this distorting effect of recombination was largely buffered by using concatenated sequences, which resolved clusters corresponding to the three species most numerous in the sample, N. meningitidis, N. lactamica and N. gonorrhoeae. A few isolates arose from the branch that separated N. meningitidis from N. lactamica leading us to describe these species as 'fuzzy'. CONCLUSION: A multilocus approach using large samples of closely related isolates delineates species even in the highly recombinogenic human Neisseria where individual loci are inadequate for the task. This approach should be applied by taxonomists to large samples of other groups of closely-related bacteria, and especially to those where species delineation has historically been difficult, to determine whether genotypic clusters can be delineated, and to guide the definition of species. (+info)
Prediction of protein solvent accessibility using fuzzy k-nearest neighbor method.
(61/394)
MOTIVATION: The solvent accessibility of amino acid residues plays an important role in tertiary structure prediction, especially in the absence of significant sequence similarity of a query protein to those with known structures. The prediction of solvent accessibility is less accurate than secondary structure prediction in spite of improvements in recent researches. The k-nearest neighbor method, a simple but powerful classification algorithm, has never been applied to the prediction of solvent accessibility, although it has been used frequently for the classification of biological and medical data. RESULTS: We applied the fuzzy k-nearest neighbor method to the solvent accessibility prediction, using PSI-BLAST profiles as feature vectors, and achieved high prediction accuracies. With leave-one-out cross-validation on the ASTRAL SCOP reference dataset constructed by sequence clustering, our method achieved 64.1% accuracy for a 3-state (buried/intermediate/exposed) prediction (thresholds of 9% for buried/intermediate and 36% for intermediate/exposed) and 86.7, 82.0, 79.0 and 78.5% accuracies for 2-state (buried/exposed) predictions (thresholds of each 0, 5, 16 and 25% for buried/exposed), respectively. Our method also showed slightly better accuracies than other methods by about 2-5% on the RS126 dataset and a benchmarking dataset with 229 proteins. AVAILABILITY: Program and datasets are available at http://biocom1.ssu.ac.kr/FKNNacc/ CONTACT: [email protected]. (+info)
FEDMA--a simple algorithm for theoretical modeling of linear metabolic pathways: from fuzzy data sets to prediction and experiment.
(62/394)
A theoretical model of a chain of irreversible Michaelis-Menten reactions proceeding inside a living cell, taking cell growth, division and subcellular compartmentation into account, was proposed. It became a basis for the construction of a "fuzzy" enzymatic data-modeling algorithm (FEDMA) - a procedure allowing the estimation of missing parameter values for the modeled system, in accordance both with the derived theoretical rules and the available experimental data. The obtained tool was tested to model the heme biosynthesis pathway in Saccharomyces cerevisiae, where about 40% of parameters remain unknown. The missing parameters estimated by means of FEDMA fall in the range of expected values. (+info)
Sequence signatures and the probabilistic identification of proteins in the Myc-Max-Mad network.
(63/394)
Accurate identification of specific groups of proteins by their amino acid sequence is an important goal in genome research. Here we combine information theory with fuzzy logic search procedures to identify sequence signatures or predictive motifs for members of the Myc-Max-Mad transcription factor network. Myc is a well known oncoprotein, and this family is involved in cell proliferation, apoptosis, and differentiation. We describe a small set of amino acid sites from the N-terminal portion of the basic helix-loop-helix (bHLH) domain that provide very accurate sequence signatures for the Myc-Max-Mad transcription factor network and three of its member proteins. A predictive motif involving 28 contiguous bHLH sequence elements found 337 network proteins in the GenBank NR database with no mismatches or misidentifications. This motif also identifies at least one previously unknown fungal protein with strong affinity to the Myc-Max-Mad network. Another motif found 96% of known Myc protein sequences with only a single mismatch, including sequences from genomes previously not thought to contain Myc proteins. The predictive motif for Myc is very similar to the ancestral sequence for the Myc group estimated from phylogenetic analyses. Based on available crystal structure studies, this motif is discussed in terms of its functional consequences. Our results provide insight into evolutionary diversification of DNA binding and dimerization in a well characterized family of regulatory proteins and provide a method of identifying signature motifs in protein families. (+info)
A dynamic neuro-fuzzy model providing bio-state estimation and prognosis prediction for wearable intelligent assistants.
(64/394)
BACKGROUND: Intelligent management of wearable applications in rehabilitation requires an understanding of the current context, which is constantly changing over the rehabilitation process because of changes in the person's status and environment. This paper presents a dynamic recurrent neuro-fuzzy system that implements expert-and evidence-based reasoning. It is intended to provide context-awareness for wearable intelligent agents/assistants (WIAs). METHODS: The model structure includes the following types of signals: inputs, states, outputs and outcomes. Inputs are facts or events which have effects on patients' physiological and rehabilitative states; different classes of inputs (e.g., facts, context, medication, therapy) have different nonlinear mappings to a fuzzy "effect." States are dimensionless linguistic fuzzy variables that change based on causal rules, as implemented by a fuzzy inference system (FIS). The FIS, with rules based on expertise and evidence, essentially defines the nonlinear state equations that are implemented by nuclei of dynamic neurons. Outputs, a function of weighing of states and effective inputs using conventional or fuzzy mapping, can perform actions, predict performance, or assist with decision-making. Outcomes are scalars to be extremized that are a function of outputs and states. RESULTS: The first example demonstrates setup and use for a large-scale stroke neurorehabilitation application (with 16 inputs, 12 states, 5 outputs and 3 outcomes), showing how this modelling tool can successfully capture causal dynamic change in context-relevant states (e.g., impairments, pain) as a function of input event patterns (e.g., medications). The second example demonstrates use of scientific evidence to develop rule-based dynamic models, here for predicting changes in muscle strength with short-term fatigue and long-term strength-training. CONCLUSION: A neuro-fuzzy modelling framework is developed for estimating rehabilitative change that can be applied in any field of rehabilitation if sufficient evidence and/or expert knowledge are available. It is intended to provide context-awareness of changing status through state estimation, which is critical information for WIA's to be effective. (+info)