Biomedical subjects

S Draghici

Publications and source records attributed to S Draghici.

5 recordsLinked to original sources

PubMed2006

Transforming function of the LSM1 oncogene in human breast cancers with the 8p11-12 amplicon.

Amplification of the 8p11-12 region occurs in 15-20% of breast cancers, but the driving oncogene at this locus has yet to be definitively identified. We mapped the 8p11-12 amplicon in breast cancer cell lines and primary human breast cancers and identified the candidate oncogene human Sm-like protein (hLsm1, LSM1) based on increases in copy number and expression level relative to human mammary epithelial cells. To examine the oncogenic role of LSM1, we overexpressed this gene in MCF10A mammary epithelial cells and inhibited its production in the SUM44 breast cancer cell line, which has a natural amplification and overexpression of LSM1. Our data confirmed that LSM1 is an oncogene from the 8p11-12 amplicon by showing that hLsm1 overexpression induced growth factor-independent proliferation and soft agar colony formation in MCF10A cells, and hLsm1 inhibition in SUM44 cells dramatically reduced soft agar growth. Little is known about hLsm1 function other than its involvement in mRNA degradation; therefore, we used expression microarray analysis to investigate how hLsm1 affects cell transformation in MCF10A and SUM44 cells. We identified numerous genes altered following hLsm1 overexpression common to SUM44 breast cancer cells that play important roles in cell cycle regulation, cell proliferation and other cancer-promoting processes. Future work will continue to characterize these important changes to achieve a more complete understanding of the mechanism of hLsm1's effect on cancer progression.

Breast Neoplasms↗

PubMed2001

The constraint based decomposition (CBD) training architecture.

The Constraint Based Decomposition (CBD) is a constructive neural network technique that builds a three or four layer network, has guaranteed convergence and can deal with binary, n-ary, class labeled and real-value problems. CBD is shown to be able to solve complicated problems in a simple, fast and reliable manner. The technique is further enhanced by two modifications (locking detection and redundancy elimination) which address the training speed and the efficiency of the internal representation built by the network. The redundancy elimination aims at building more compact architectures while the locking detection aims at improving the training speed. The computational cost of the redundancy elimination is negligible and this enhancement can be used for any problem. However, the computational cost of the locking detection is exponential in the number of dimensions and should only be used in low dimensional spaces. The experimental results show the performance of the algorithm presented in a series of classical benchmark problems including the 2-spiral problem and the Iris, Wine, Glass, Lenses, Ionosphere, Lung cancer, Pima Indians, Bupa, TicTacToe, Balance and Zoo data sets from the UCI machine learning repository. CBD's generalization accuracy is compared with that of C4.5, C4.5 with rules, incremental decision trees, oblique classifiers, linear machine decision trees, CN2, learning vector quantization (LVQ), backpropagation, nearest neighbor, Q* and radial basis functions (RBFs). CBD provides the second best average accuracy on the problems tested as well as the best reliability (the lowest standard deviation).

Algorithms↗

PubMed2001

Experimental design, analysis of variance and slide quality assessment in gene expression arrays.

A microarray experiment is a sequence of complicated molecular biology procedures relying on various laboratory tools, instrumentation and experimenter's skills. This paper discusses statistical models for distinguishing small changes in gene expression from the noise in the system. It describes methods for assigning statistical confidence to gene expression values derived from a single array slide. Some of the theory is discussed in the context of practical applications via software usage.

Algorithms↗

PubMed2000

Neural networks in analog hardware--design and implementation issues.

This paper presents a brief review of some analog hardware implementations of neural networks. Several criteria for the classification of general neural networks implementations are discussed and a taxonomy induced by these criteria is presented. The paper also discusses some characteristics of analog implementations as well as some trade-offs and issues identified in the work reviewed. Parameters such as precision, chip area, power consumption, speed and noise susceptibility are discussed in the context of neural implementations. A unified review of various "VLSI friendly" algorithms is also presented. The paper concludes with some conclusions drawn from the analysis of the implementations presented.

Artificial Intelligence↗

PubMed1997

A neural network based artificial vision system for licence plate recognition.

This paper presents a neural network based artificial vision system able to analyze the image of a car given by a camera, locate the registration plate and recognize the registration number of the car. The paper describes in detail various practical problems encountered in implementing this particular application and the solutions used to solve them. The main features of the system presented are: controlled stability-plasticity behavior, controlled reliability threshold, both off-line and on-line learning, self assessment of the output reliability and high reliability based on high level multiple feedback. The system has been designed using a modular approach. Sub-modules can be upgraded and/or substituted independently, thus making the system potentially suitable in a large variety of vision applications. The OCR engine was designed as an interchangeable plug-in module. This allows the user to choose an OCR engine which is suited to the particular application and to upgrade it easily in the future. At present, there are several versions of this OCR engine. One of them is based on a fully connected feedforward artificial neural network with sigmoidal activation functions. This network can be trained with various training algorithms such as error backpropagation. An alternative OCR engine is based on the constraint based decomposition (CBD) training architecture. The system has showed the following performances (on average) on real-world data: successful plate location and segmentation about 99%, successful character recognition about 98% and successful recognition of complete registration plates about 80%.

Algorithms↗