Identifying the tumor location-associated candidate genes in development of new drugs for colorectal cancer using machine-learning-based approach.

Numerous studies have been conducted to elucidate the relation of tumor proximity to cancer prognosis and treatment efficacy in colorectal cancer. However, the molecular pathways and prognoses of left- and right-sided colorectal cancers are different, and this difference has not been fully investigated at the genomic level. In this study, a set of data science approaches, including six feature selection methods and three classification models, were used in predicting tumor location from gene expression profiles. Specificity, sensitivity, accuracy, and Mathew's correlation coefficient (MCC) evaluation metrics were used to evaluate the classification ability. Gene ontology enrichment analysis was applied by the Gene Ontology PANTHER Classification System. For the most significant 50 genes, protein-protein interactions and drug-gene interactions were analyzed using the GeneMANIA, CytoScape, CytoHubba, MCODE, and DGIdb databases. The highest classification accuracy (90%) is achieved with the most significant 200 genes when the ensemble-decision tree classification model is used with the ReliefF feature selection method. Molecular pathways and drug interactions are investigated for the most significant 50 genes. It is concluded that a machine-learning-based approach could be useful to discover the significant genes that may have an important role in the development of new therapies and drugs for colorectal cancer.

What Will Be the Economic Impact of the New Medical Device Regulation? An Interrupted Time-Series Analysis of Foreign Trade Data.

OBJECTIVES: To date, the economic effects of medical device directives compared with the clinical and regulatory effects have not been sufficiently studied. We believe that the financial obligations and responsibilities imposed on the stakeholders by the legal regulations have a corresponding economic indicator in the medical device market. METHODS: In this study, we selected 2 crucial legal regulations on medical devices in Turkey: the Medical Device Directive that has been harmonized from the European Union and the Medical Device Sales, Advertising, and Promotion Directive. The impacts of these regulations on foreign trade were investigated using interrupted time-series analysis. Turkey's monthly medical device export and import data from 2008 to 2019 were obtained under 56 6-digit custom codes. RESULTS: The results show that the selected directives have significantly affected the foreign trade trend level, and they may be breakpoints in the Turkey's foreign trade trend curve. We also reported the significant differences between the Medical Device Directive and the European Union's new medical device regulation (MDR) (2017/745 MDR). CONCLUSIONS: We concluded that the MDR, which has more strict requirements, will result in increased costs for economic operators in comparison with the current directive and would further increase the import of medical devices by the importing countries. To prevent this, Turkey should aim to have a manufacturer's position by improving their clinical trial capabilities and manufacturing infrastructures with innovation-based approaches.

Modeling and Forecasting Foreign Trade Values in Medical Devices.

OBJECTIVES: Forecasting foreign trade values can be a good guidance to enable policymakers to introduce efficient instruments to regulate the medical device market. The purpose of this study is to forecast Turkey's medical device export and import values for the next 5 years. METHODS: To that end, we identified the universal HS-6 commodity codes associated with medical devices, and then retrieved foreign trade data from the ITC Trademap database. We proposed Box-Jenkins autoregressive integrated moving average model in forecasting foreign trade values for upcoming years. RESULTS: Turkey's foreign trade analysis has shown there is a 14% decrease in import and 21% increase in export in past 5 years. The Asian region is the main target market in medical device export with the rate of 42.8%, and most importers of Turkey are located in Europe region. The results show that the total value of imports is expected to reach $1.78 billion, and the total value of exports is expected to reach $720 million by 2023. CONCLUSIONS: It is concluded that Turkey may have a larger medical device market in the next 5 years, which provides an appropriate environment for investment. We believe that the results are promising and our approach can be adopted in other countries.

Predicted SARS-CoV-2 miRNAs Associated with Epigenetic Viral Pathogenesis and the Detection of New Possible Drugs for Covid-19.

OBJECTIVE: The outbreak of COVID-19 caused by SARS-CoV-2 has promptly spread worldwide. This study aimed to predict mature miRNA sequences in the SARS-CoV-2 genome, their effects on protein-protein interactions in the affected cells, and gene-drug relationships to detect possible drug candidates. METHODS: Viral hairpin structure prediction, classification of hairpins, mutational examination of precursor miRNA candidate sequences, Minimum Free Energy (MFE) and regional entropy analysis, mature miRNA sequences, target gene prediction, gene ontology enrichment, and Protein-Protein Interaction (PPI) analysis, and gene-drug interactions were performed. RESULTS: A total of 62 candidate hairpins were detected by VMir analysis. Three hairpin structures were classified as true precursor miRNAs by miRBoost. Five different mutations were detected in precursor miRNA sequences in 100 SARS-CoV-2 viral genomes. Mutations slightly elevated MFE values and entropy in precursor miRNAs. Gene ontology terms associated with fibrotic pathways and immune system were found to be enriched in PANTHER, KEGG and Wiki pathway analysis. PPI analysis showed a network between 60 genes. CytoHubba analysis showed SMAD1 as a hub gene in the network. The targets of the predicted miRNAs, FAM214A, PPM1E, NUFIP2 and FAT4, were downregulated in SARS-CoV-2 infected A549 cells. CONCLUSION: miRNAs in the SARS-CoV-2 virus genome may contribute to the emergence of the Covid-19 infection by activating pathways associated with fibrosis in the cells infected by the virus and modulating the innate immune system. The hub protein between these pathways may be the SMAD1, which has an effective role in TGF signal transduction.

Eliminating rib shadows in chest radiographic images providing diagnostic assistance.

A major difficulty with chest radiographic analysis is the invisibility of abnormalities caused by the superimposition of normal anatomical structures, such as ribs, over the main tissue to be examined. Suppressing the ribs with no information loss about the original tissue would therefore be helpful during manual identification or computer-aided detection of nodules on a chest radiographic image. In this study, we introduce a two-step algorithm for eliminating rib shadows in chest radiographic images. The algorithm first delineates the ribs using a novel hybrid self-template approach and then suppresses these delineated ribs using an unsupervised regression model that takes into account the change in proximal thickness (depth) of bone in the vertical axis. The performance of the system is evaluated using a benchmark set of real chest radiographic images. The experimental results determine that proposed method for rib delineation can provide higher accuracy than existing methods. The knowledge of rib delineation can remarkably improve the nodule detection performance of a current computer-aided diagnosis (CAD) system. It is also shown that the rib suppression algorithm can increase the nodule visibility by eliminating rib shadows while mostly preserving the nodule intensity.