Machine Learning Approaches on High Throughput NGS Data to Unveil Mechanisms of Function in Biology and Disease.

In this review, the fundamental basis of machine learning (ML) and data mining (DM) are summarized together with the techniques for distilling knowledge from state-of-the-art omics experiments. This includes an introduction to the basic mathematical principles of unsupervised/supervised learning methods, dimensionality reduction techniques, deep neural networks architectures and the applications of these in bioinformatics. Several case studies under evaluation mainly involve next generation sequencing (NGS) experiments, like deciphering gene expression from total and single cell (scRNA-seq) analysis; for the latter, a description of all recent artificial intelligence (AI) methods for the investigation of cell sub-types, biomarkers and imputation techniques are described. Other areas of interest where various ML schemes have been investigated are for providing information regarding transcription factors (TF) binding sites, chromatin organization patterns and RNA binding proteins (RBPs), while analyses on RNA sequence and structure as well as 3D dimensional protein structure predictions with the use of ML are described. Furthermore, we summarize the recent methods of using ML in clinical oncology, when taking into consideration the current omics data with pharmacogenomics to determine personalized treatments. With this review we wish to provide the scientific community with a thorough investigation of main novel ML applications which take into consideration the latest achievements in genomics, thus, unraveling the fundamental mechanisms of biology towards the understanding and cure of diseases.

Short-term adoption rates for a web-based portal within the intranet of a hospital information system.

OBJECTIVE: An intranet portal that combines cost-free, open-source software technology with easy set-up features can be beneficial for daily hospital processes. We describe the short-term adoption rates of a costless content management system (CMS) in the intranet of a tertiary Greek hospital. DESIGN: Dashboard statistics of our CMS platform were the implementation assessment of our system. RESULTS: In a period of 10 months of running the software, the results indicate the employees overcame 'Resistance to Change' status. The average growth rate of end users who exploit the portal services is calculated as 2.73 every 3.3 months. CONCLUSION: We found our intranet web-based portal to be acceptable and helpful so far. Exploitation of an open-source CMS within the hospital intranet can influence healthcare management and the employees' way of working as well.

Metaplastic breast carcinoma in a patient with Von Recklinghausen's disease.

Metaplastic carcinomas of the breast are uncommon lesions and account for < 5% of all breast malignancies. A type of metaplastic carcinoma is carcinosarcoma, an even more rare lesion. We present a case of carcinosarcoma in association with Von Recklinghausen's disease in a 60-year-old woman. Von Recklinghausen's disease is an autosomal dominant disorder that is localized at the long arm of chromosome 17 and affects 1 in 4000 individuals. There are few reports on breast tumor development and incidence in patients with Von Recklinghausen's disease. To our knowledge, there has been no report of breast carcinosarcoma associated with Von Recklinghausen's disease. We comment on the difficulties of diagnosis and treatment and the possibility of breast tumors occurring more frequently in patients with Von Recklinghausen's disease.

Nutrient dynamics in shallow lakes of Northern Greece.

UNLABELLED: GOAL, SCOPE, BACKGROUND: Shallow lakes display a number of features that set them apart from the more frequently studied deeper systems. The majority of lakes in Northern Greece are small to moderate in size with a relatively low depth and are considered as sites of high value of the wetland habitat. However, the water quality of these lakes has only been evaluated segmentally and occasionally. OBJECTIVE: The objectives of this study were to thoroughly investigate nitrogen and phosphorus speciation in lakes of a high ecological significance located in N. Greece, in order to evaluate their eutrophication status and possible nutrient limitation factors, and to investigate the main factors/sources that affect the water quality of these systems. METHODS: An extensive survey was carried out during the period from 1998-1999. Water samples were collected on a monthly basis from lakes Koronia, Volvi, Doirani, Mikri Prespa and Megali Prespa located in N. Greece. Water quality parameters (temperature, dissolved oxygen, pH and conductivity), organic indices (COD, BOD5), and N- and P-species (NO3(-), NO2(-), NH4(+), and PO4(3-), Kieldahl nitrogen and acid-hydrolysable phosphorus) were determined according to standard methods for surface water. Statistical treatment of the data was employed. RESULTS AND CONCLUSIONS: The physicochemical parameters determined in the lakes studied revealed a high temporal variation. The trophic state of the lakes ranged from meso- to hypertrophic. The nutrient limiting factor varied among lakes suggesting either P-limitation conditions or mixed conditions changing from P- to N-limitation throughout the year. Urban/industrial activities and agricultural runoff are the major factors affecting all lakes, although with a varying contribution. RECOMMENDATION AND OUTLOOK: This lake-specific research offers valuable information about water quality and nutrient dynamics in lakes of significant ecological value located in N. Greece that can be useful for an effective pollution control/management of these systems. Due to the large intra-annual variability of certain physicochemical parameters, a properly designed monitoring program of lake water is recommended.