Classification of News Articles using Supervised Machine Learning Approach

Today the big challenge for NEWS organization to well organize the news and well categorize the news in automatically no need the data entry people to enter and select the category and then based on the category and its sub-category they will be manually selected and enter the details and then after this the analysis will later on used for different aspects. The news is almost every second used in different sources of media in soft and hard. We use the both sources of the Pakistan News in dual languages English and Urdu both and process them and prepare them for machine learning and based on the Machine learning trained data we build a very effective and efficient model that can predict the title category of the news and category of description of the news. We use different machine learning algorithms and different features extraction finally we build the model using the machine learning algorithm with 89% accuracy with logistic regression.

Studies on Deregulation of Base Excision Repair Pathway Genes and Micrornas in Head and Neck Cancer

Base excision repair system plays an indispensable role in maintaining genomic integrity, and its ability to mediate and repair carcinogen-induced DNA lesion is a key determinant of susceptibility to carcinogenesis. Increasing evidence has demonstrated that reduced DNA repair capacity might play a central role in cancer development. This study is divided in two parts, first part was aimed to investigate the BER pathway gene expression at DNA, RNA and proteins levels and to correlate these parameters with head and neck cancer risk and disease progression in Pakistani population. Second part of this study was identification of a panel of deregulated microRNAs and contribution of deregulated miR- 99 family in tumorigenesis of HNSCC. In first part of the study, PCR-single-strand conformation polymorphism and DNA sequencing were used to analyze the whole exonic region of OGG1, APEX1 and XRCC1 in 450 head and neck cancer patients and 300 controls. Sequence analysis of OGG1 gene revealed eight novel mutations (six missense and two frame shift mutations). Among these eight mutations, frequencies of missense mutations, Asp267Asn, Ser279Gly and Ile253Phe were 0.12 (12%), 0.13 (13%) and 0.06 (6%) respectively. Frequencies of other missense mutations, 1578A>T, 1582C>T and Ala399Glu were 0.13 (13%), 0.13 (13%) and 0.16 (16%), whereas values for the frame shift mutations 1582insG and 1543_1544delCT were 0.13 (13%) and 0.16 (16%). In addition to these mutations, two silent (Gln718Gln, His699-700His) and four missense (Ala597Val, Thr608-610Pro, Glu707Lys and 1578G<A) mutations of OGG1 gene were observed specifically in laryngeal cancer patients. DNA sequences for APEX1 gene exhibited three novel muatations such as 13T>G, Ser129Arg and Val131Gly in HNC patients. Frequency of 13T>G, Ser129Arg and Val131Gly was calculated as 0.17 (17%), 0.24 (24%) and 0.22 (22%) respectively. Germline screening of XRCC1 gene revealed two silent and two missense mutations. Frequency of silent mutations; Pro206Pro and Gln632Gln was calculated as 0.16 (16 %) and 0.30 (30 %) respectively. Whereas, the frequency of missense mutations; Arg399Gln and Tyr576Asn was calculated as 0.27 (27 %) and 0.28 (28 %) respectively. xThe mRNA level and protein levels of base excision repair pathway genes (OGG1, APEX1 and XRCC1) and a proliferation marker, Ki-67, was studied in a cohort of 50 HNSCC patients and controls, using real-time PCR and Immunohistochemistry in order to determine the potential prognostic significance of these factors. Using real-time PCR, statistically significant down-regulation of XRCC1 (p<0.01) and OGG1 (p<0.04) was observed in HNC tumor samples compared to control samples. Ki-67 (p<0.03) and APEX1 (p<0.02) was over-expressed in HNC tumor samples versus control samples. Immunohistochemical analysis of OGG1, APEX1, XRCC1 and Ki-67 showed that among 50 HNC samples that we examined, 78% of OGG1 cases exhibited down-regulated expression, 65% of APEX1cases exhibited up-regulated level, 64% of XRCC1cases showed down-regulation and 75% of Ki-67 cases exhibited up-regulation. From the current study, OGG1, APEX1 and XRCC1 were found to be one of the factors responsible for systematic progression of HNC. Our data suggests that germline mutations in base excision repair and down-regulation of base excision repair pathway genes, such as OGG1 and XRCC1, combined with over-expression of APEX1 and Ki-67 (a marker for excessive proliferation) may contribute to the initiation and progression of HNSCC in Pakistani population. MicroRNA deregulation is a critical event in head and neck squamous cell carcinoma (HNSCC). Several microRNA profiling studies aimed at deciphering the microRNA signatures of HNSCC have been reported, but there tends to be poor agreement among these studies. The second part of this study was to survey the published microRNA profiling studies on HNSCC, and to assess the commonly deregulated microRNAs in an independent sample set. We identified 67 commonly deregulated microRNAs in current study. The up-regulation of miR-21, miR-155, miR-130b, miR-223 and miR-31, and down-regulation of miR-100, miR-99a and miR-375 were further validated in an independent set of HNSCC cases with quantitative RT-PCR. Among these validated microRNAs, miR-100 and miR-99a belong to miR-99 family. Our in vitro study demonstrated that restoration of miR-100 to HNSCC cell lines suppressed cell proliferation and migration, and enhanced apoptosis. Furthermore, ectopic transfection of miR-99 family members down-regulated the expression of insulin-like growth factor 1 xireceptor (IGF1R) and mechanistic target of rapamycin (mTOR) genes. In current study, we identified a panel of frequently deregulated microRNAs in HNSCC, including members of miR-99 family. The deregulation of miR-99 family contributes to the tumorigenesis of HNSCC, in part by targeting IGF1R and mTOR signaling pathways.