Magdalena Tkacz

Familial or Sporadic Idiopathic Scoliosis – classification based on artificial neural network and GAPDH and ACTB transcription profile

BackgroundImportance of hereditary factors in the etiology of Idiopathic Scoliosis is widely accepted. In clinical practice some of the IS patients present with positive familial history of the deformity and some do not. Traditionally about 90% of patients have been considered as sporadic cases without familial recurrence. However the exact proportion of Familial and Sporadic Idiopathic Scoliosis is still unknown. Housekeeping genes encode proteins that are usually essential for the maintenance of basic cellular functions. ACTB and GAPDH are two housekeeping genes encoding respectively a cytoskeletal protein β-actin, and glyceraldehyde-3-phosphate dehydrogenase, an enzyme of glycolysis. Although their expression levels can fluctuate between different tissues and persons, human housekeeping genes seem to exhibit a preserved tissue-wide expression ranking order. It was hypothesized that expression ranking order of two representative housekeeping genes ACTB and GAPDH might be disturbed in the tissues of patients with Familial Idiopathic Scoliosis (with positive family history of idiopathic scoliosis) opposed to the patients with no family members affected (Sporadic Idiopathic Scoliosis). An artificial neural network (ANN) was developed that could serve to differentiate between familial and sporadic cases of idiopathic scoliosis based on the expression levels of ACTB and GAPDH in different tissues of scoliotic patients. The aim of the study was to investigate whether the expression levels of ACTB and GAPDH in different tissues of idiopathic scoliosis patients could be used as a source of data for specially developed artificial neural network in order to predict the positive family history of index patient.ResultsThe comparison of developed models showed, that the most satisfactory classification accuracy was achieved for ANN model with 18 nodes in the first hidden layer and 16 nodes in the second hidden layer. The classification accuracy for positive Idiopathic Scoliosis anamnesis only with the expression measurements of ACTB and GAPDH with the use of ANN based on 6-18-16-1 architecture was 8 of 9 (88%). Only in one case the prediction was ambiguous.ConclusionsSpecially designed artificial neural network model proved possible association between expression level of ACTB, GAPDH and positive familial history of Idiopathic Scoliosis.

Artificial Neural Networks in Incomplete Data Sets Processing

This paper presents some results obtained in experiments with artificial neural networks trained with different learning algorithms in case of lack of some data in training and testing sets.

Transforming Growth Factor-Beta (TGF-β) Signaling in Paravertebral Muscles in Juvenile and Adolescent Idiopathic Scoliosis

Most researchers agree that idiopathic scoliosis (IS) is a multifactorial disease influenced by complex genetic and environmental factors. The onset of the spinal deformity that determines the natural course of the disease, usually occurs in the juvenile or adolescent period. Transforming growth factors β (TGF-βs) and their receptors, TGFBRs, may be considered as candidate genes related to IS susceptibility and natural history. This study explores the transcriptional profile of TGF-βs, TGFBRs, and TGF-β responsive genes in the paravertebral muscles of patients with juvenile and adolescent idiopathic scoliosis (JIS and AIS, resp.). Muscle specimens were harvested intraoperatively and grouped according to the side of the curve and the age of scoliosis onset. The results of microarray and qRT-PCR analysis confirmed significantly higher transcript abundances of TGF-β2, TGF-β3, and TGFBR2 in samples from the curve concavity of AIS patients, suggesting a difference in TGF-β signaling in the pathogenesis of juvenile and adolescent curves. Analysis of TGF-β responsive genes in the transcriptomes of patients with AIS suggested overrepresentation of the genes localized in the extracellular region of curve concavity: LTBP3, LTBP4, ITGB4, and ITGB5. This finding suggests the extracellular region of paravertebral muscles as an interesting target for future molecular research into AIS pathogenesis.

Chromosome Territory Modeller and Viewer

This paper presents ChroTeMo, a tool for chromosome territory modelling, accompanied by ChroTeVi–a chromosome territory visualisation software that uses the data obtained by ChroTeMo. These tools have been developed in order to complement the molecular cytogenetic research of interphase nucleus structure in a model grass Brachypodium distachyon. Although the modelling tool has been initially created for one particular species, it has universal application. The proposed version of ChroTeMo allows for generating a model of chromosome territory distribution in any given plant or animal species after setting the initial, species-specific parameters. ChroTeMo has been developed as a fully probabilistic modeller. Due to this feature, the comparison between the experimental data on the structure of a nucleus and the results obtained from ChroTeMo can indicate whether the distribution of chromosomes inside a nucleus is also fully probabilistic or is subjected to certain non-random patterns. The presented tools have been written in Python, so they are multiplatform, portable and easy to read. Moreover, if necessary they can be further developed by users writing their portions of code. The source code, documentation, and wiki, as well as the issue tracker and the list of related articles that use ChroTeMo and ChroTeVi, are accessible in a public repository at Github under GPL 3.0 license.

Artificial Neural Network Resistance to Incomplete Data

This paper presents results obtained in experiments related to artificial neural networks. Artificial neural networks have been trained with delta-bar-delta and conjugate gradient algorithms in case of removing some data from dataset and fulfilling empty places with mean. The goal of the experiment was to observe how long will neural network (trained with specific algorithm) be able to learn when dataset will be consistently less and less exact - the number of incomplete data is increased.

Transforming Growth Factor beta in basal cell carcinoma (BCC), squamous cell carcinoma (SCC) and keratoacanthoma (KA)

1School of Medicine in Katowice, Medical University of Silesia in Katowice, Department of Dermatology Head of Department: prof. Ligia Brzezinska-Wcislo, MD, PhD 2School of Pharmacy with the Division of Laboratory Medicine in Sosnowiec, Medical University of Silesia in Katowice, Department of Molecular Biology Head of Department: prof. Urszula Mazurek, PhD 3School of Pharmacy with the Division of Laboratory Medicine in Sosnowiec, Medical University of Silesia in Katowice, Department of Skin Structural Studies Head of Department: Associate Professor of Biology Krzysztof Jasik, PhD 4School of Computer Science and Material Science, University of Silesia in Katowice, Institute of Computer Science, Division of Information Systems Head of Department: prof. Mariusz Boryczka, PhD

Rough Sets in Oligonucleotide Microarray Data Analysis

This paper shows attempts of the rough set theory application to the oligonucleotide microarrays data analysis.