Background: Cytokines are the key regulator molecules that modulate immune response. Tumor necrosis factor (TNF-α-308 G/A and TNF-β +252 A/G) are inflammatory cytokine that control the progression of several types of cancer. They play a vital role in both tumor progression and destruction based on their concentrations. The role of TNF-α-308 G/A and TNF-β +252 A/G gene polymorphism in the etiology of breast cancer (BC) is not clearly understood. Therefore, present study investigates the association of TNF-α-308 G/A and TNF-β +252 A/G and the clinical features with Breast cancer patients. Methods: In a case-control study, we have investigated 150 breast cancer patients and 300 age and ethnically matched healthy controls for duration of 3 years from North India. Promoter polymorphisms of tumor necrosis factor gene (TNF-α-308 G/A and TNF-β +252 A/G) were genotyped using allele specific oligonucleotide polymerase chain reaction ASO and restriction fragment length polymorphism (PCR-RFLP). The associations were evaluated by calculating the pooled odds ratio (OR) with 95% confidence interval (95% CI) using SPSS. Results: Patients with different clinico-pathological variables and healthy controls were analyzed. Significant association was observed in A allele of TNF-α-308 G/A in breast cancer patients as compared to healthy controls (p<0.0001). However, no association was seen in TNF-β +252 A/G both at genotypic and allelic level. The GG genotype of TNF-β +252A/G is higher in grades III (p<0.01) patients. Conclusion: Our results suggest that TNF-α-308G/A polymorphism showed significant association with breast cancer patients.

In our paper we present Deep Learning models with a layer differentiated training method which were used for the SHARED TASK @ CONSTRAINT 2021 sub-tasks COVID19 Fake News Detection in English and Hostile Post Detection in Hindi. We propose a Layer Differentiated training procedure for training a pre-trained ULMFiT [8] model. We used special tokens to annotate specific parts of the tweets to improve language understanding and gain insights on the model making the tweets more interpretable. The other two submissions included a modified RoBERTa model and a simple Random Forest Classifier. The proposed approach scored a precision and f1-score of 0.96728972 and 0.967324832 respectively for sub-task COVID19 Fake News Detection in English. Also, Coarse Grained Hostility f1 Score and Weighted Fine Grained f1 score of 0.908648 and 0.533907 respectively for sub-task Hostile Post Detection in Hindi. The proposed approach ranked 61st out of 164 in the sub-task "COVID19 Fake News Detection in English" and 18th out of 45 in the sub-task "Hostile Post Detection in Hindi".

No abstract