Feature extraction through local learning

Large Margin Gaussian Mixture Classifier With a Gabriel Graph Geometric Representation of Data Set Structure

This brief presents a geometrical approach for obtaining large margin classifiers. The method aims at exploring the geometrical properties of the data set from the structure of a Gabriel graph, which represents pattern relations according to a given distance metric, such as the Euclidean distance. Once the graph is generated, geometrical support vectors (SVs) (analogous to support vector machines (SVMs) SVs) are obtained in order to yield the final large margin solution from a Gaussian mixture model. Experiments with 20 data sets have shown that the solutions obtained with the proposed method are statistically equivalent to those obtained with SVMs. However, the present method does not require optimization and can also be extended to large data sets using the cascade SVM concept.

Why Deep Learning Works: A Manifold Disentanglement Perspective

Deep hierarchical representations of the data have been found out to provide better informative features for several machine learning applications. In addition, multilayer neural networks surprisingly tend to achieve better performance when they are subject to an unsupervised pretraining. The booming of deep learning motivates researchers to identify the factors that contribute to its success. One possible reason identified is the flattening of manifold-shaped data in higher layers of neural networks. However, it is not clear how to measure the flattening of such manifold-shaped data and what amount of flattening a deep neural network can achieve. For the first time, this paper provides quantitative evidence to validate the flattening hypothesis. To achieve this, we propose a few quantities for measuring manifold entanglement under certain assumptions and conduct experiments with both synthetic and real-world data. Our experimental results validate the proposition and lead to new insights on deep learning.

Derivation of cancer diagnostic and prognostic signatures from gene expression data

The ability to compare genome-wide expression profiles in human tissue samples has the potential to add an invaluable molecular pathology aspect to the detection and evaluation of multiple diseases. Applications include initial diagnosis, evaluation of disease subtype, monitoring of response to therapy and the prediction of disease recurrence. The derivation of molecular signatures that can predict tumor recurrence in breast cancer has been a particularly intense area of investigation and a number of studies have shown that molecular signatures can outperform currently used clinicopathologic factors in predicting relapse in this disease. However, many of these predictive models have been derived using relatively simple computational algorithms and whether these models are at a stage of development worthy of large-cohort clinical trial validation is currently a subject of debate. In this review, we focus on the derivation of optimal molecular signatures from high-dimensional data and discuss some of the expected future developments in the field.

Optimizing molecular signatures for predicting prostate cancer recurrence

BACKGROUND

The derivation of molecular signatures indicative of disease status and predictive of subsequent behavior could facilitate the optimal choice of treatment for prostate cancer patients.

METHODS

In this study, we conducted a computational analysis of gene expression profile data obtained from 79 cases, 39 of which were classified as having disease recurrence, to investigate whether advanced computational algorithms can derive more accurate prognostic signatures for prostate cancer.

RESULTS

At the 90% sensitivity level, a newly derived prognostic genetic signature achieved 85% specificity. This is the first reported genetic signature to outperform a clinically used postoperative nomogram. Furthermore, a hybrid prognostic signature derived by combination of the nomogram and gene expression data significantly outperformed both genetic and clinical signatures, and achieved a specificity of 95%.

CONCLUSIONS

Our study demonstrates the feasibility of utilizing gene expression information for highly accurate prostate cancer prognosis beyond the current clinical systems, and shows that more advanced computational modeling of tissue-derived microarray data is warranted before clinical application of molecular signatures is considered.

Derivation of molecular signatures for breast cancer recurrence prediction using a two-way validation approach

Previous studies have demonstrated the potential value of gene expression signatures in assessing the risk of post-surgical breast cancer recurrence, however, many of these predictive models have been derived using simple computational algorithms and validated internally or using one-way validation on a single dataset. We have recently developed a new feature selection algorithm that overcomes some limitations inherent to high-dimensional data analysis. In this study, we applied this algorithm to two publicly available gene expression datasets obtained from over 400 patients with breast cancer to investigate whether we could derive more accurate prognostic signatures and reveal common predictive factors across independent datasets. We compared the performance of three advanced computational algorithms using a robust two-way validation method, where one dataset was used for training and to establish a prediction model that was then blindly tested on the other dataset. The experiment was then repeated in the reverse direction. Analyses identified prognostic signatures that while comprised of only 10-13 genes, significantly outperformed previously reported signatures for breast cancer evaluation. The cross-validation approach revealed CEGP1 and PRAME as major candidates for breast cancer biomarker development.