Naoto Yukinawa

A multi-class predictor based on a probabilistic model: application to gene expression profiling-based diagnosis of thyroid tumors

BackgroundAlthough microscopic diagnosis has been playing the decisive role in cancer diagnostics, there have been cases in which it does not satisfy the clinical need. Differential diagnosis of malignant and benign thyroid tissues is one such case, and supplementary diagnosis such as that by gene expression profile is expected.ResultsWith four thyroid tissue types, i.e., papillary carcinoma, follicular carcinoma, follicular adenoma, and normal thyroid, we performed gene expression profiling with adaptor-tagged competitive PCR, a high-throughput RT-PCR technique. For differential diagnosis, we applied a novel multi-class predictor, introducing probabilistic outputs. Multi-class predictors were constructed using various combinations of binary classifiers. The learning set included 119 samples, and the predictors were evaluated by strict leave-one-out cross validation. Trials included classical combinations, i.e., one-to-one, one-to-the-rest, but the predictor using more combination exhibited the better prediction accuracy. This characteristic was consistent with other gene expression data sets. The performance of the selected predictor was then tested with an independent set consisting of 49 samples. The resulting test prediction accuracy was 85.7%.ConclusionMolecular diagnosis of thyroid tissues is feasible by gene expression profiling, and the current level is promising towards the automatic diagnostic tool to complement the present medical procedures. A multi-class predictor with an exhaustive combination of binary classifiers could achieve a higher prediction accuracy than those with classical combinations and other predictors such as multi-class SVM. The probabilistic outputs of the predictor offer more detailed information for each sample, which enables visualization of each sample in low-dimensional classification spaces. These new concepts should help to improve the multi-class classification including that of cancer tissues.

Optimal Aggregation of Binary Classifiers for Multiclass Cancer Diagnosis Using Gene Expression Profiles

Multiclass classification is one of the fundamental tasks in bioinformatics and typically arises in cancer diagnosis studies by gene expression profiling. There have been many studies of aggregating binary classifiers to construct a multiclass classifier based on one-versus-the-rest (1R), one-versus-one (11), or other coding strategies, as well as some comparison studies between them. However, the studies found that the best coding depends on each situation. Therefore, a new problem, which we call the “optimal coding problem,” has arisen: how can we determine which coding is the optimal one in each situation? To approach this optimal coding problem, we propose a novel framework for constructing a multiclass classifier, in which each binary classifier to be aggregated has a weight value to be optimally tuned based on the observed data. Although there is no a priori answer to the optimal coding problem, our weight tuning method can be a consistent answer to the problem. We apply this method to various classification problems including a synthesized data set and some cancer diagnosis data sets from gene expression profiling. The results demonstrate that, in most situations, our method can improve classification accuracy over simple voting heuristics and is better than or comparable to state-of-the-art multiclass predictors.

High‐Speed Multineuron Calcium Imaging Using Nipkow‐Type Confocal Microscopy

Conventional confocal and two‐photon microscopy scan the field of view sequentially with single‐point laser illumination. This raster‐scanning method constrains video speeds to tens of frames per second, which are too slow to capture the temporal patterns of fast electrical events initiated by neurons. Nipkow‐type spinning‐disk confocal microscopy resolves this problem by the use of multiple laser beams. We describe experimental procedures for functional multineuron calcium imaging (fMCI) based on Nipkow‐disk confocal microscopy, which enables us to monitor the activities of hundreds of neurons en masse at a cellular resolution at up to 2000 fps. Curr. Protoc. Neurosci. 57:2.14.1‐2.14.10.

Multi-class pattern classification based on a probabilistic model of combining binary classifiers

We propose a novel probabilistic model for constructing a multi-class pattern classifier by weighted aggregation of general binary classifiers including one-versus-the-rest, one-versus-one, and others. Our model has a latent variable that represents class membership probabilities, and it is estimated by fitting it to probability estimate outputs of binary classfiers. We apply our method to classification problems of synthetic datasets and a real world dataset of gene expression profiles. We show that our method achieves comparable performance to conventional voting heuristics.

Learning spatio-temporal visual features by a large scale neural network model

iments. Thus, if data can be made readily available, it can have a profound effect on advancing our understanding of the brain, since more researchers will be able to build and test algorithms with empirical data. Towards this end, we created a web portal and search engine to facilitate data sharing. Our system allows users to search for, upload, and download data. To advance BMI research by combining behavioral and neurophysiological data, we allow users to upload files and videos describing their experiments, and we use a uniform file format for neurophysiological data, which allows us to develop software that can be used to process and extract important features. We are currently working on a time-alignment tool to combine behavioral information with neurophysiological data, which is a feature that other neuroscience databases do not have. Additionally, we have a web-based data previewer that allows users to preview data before they download it. Taken together, these features are made to connect data with the people that need it. Through licensing the data with a Creative Commons license, we allow users who upload data to specify required citations of their work, while also allowing people who download data to freely use it. In future work we will provide a data-driven search tool that will allow users to search for data by inputting some of their own data.

Combining multiple decisions: applications to bioinformatics

Multi-class classification is one of the fundamental tasks in bioinformatics and typically arises in cancer diagnosis studies by gene expression profiling. This article reviews two recent approaches to multi-class classification by combining multiple binary classifiers, which are formulated based on a unified framework of error-correcting output coding (ECOC). The first approach is to construct a multi-class classifier in which each binary classifier to be aggregated has a weight value to be optimally tuned based on the observed data. In the second approach, misclassification of each binary classifier is formulated as a bit inversion error with a probabilistic model by making an analogy to the context of information transmission theory. Experimental studies using various real-world datasets including cancer classification problems reveal that both of the new methods are superior or comparable to other multi-class classification methods.