---

Background: Based on the severity and prognostic condition of respective cancers caused by them, papilloma viruses are classified into high, medium, and low risk groups using E6 and E7 viral proteins. Nowadays, different methods of modeling in clinical medicine are used for diagnosis of diseases and evaluation of their molecular characteristics. Among the new methods of modeling, fuzzy systems are of particular importance in various fields of science. The aim of this study was to use a new intelligent Adaptive Nero Fuzzy Inference System (ANFIS) for predicting human papilloma virus oncogenicity based on a number of biochemical properties of E7 protein. Materials and Methods: In this study, using ANFIS model, a new model was developed for predicting oncogenicity of papilloma virus isolated from patients. The process of training and testing was performed using a set of available published filed data and several statistical and graphical criteria. Accordingly, through provision of needed biochemical and biophysical data on E7 gens from the existing data, this model was developed. The results of this model were, then, validated by the authentic published data. Results: Based on the results, the developed model is capable of predicting papilloma virus oncogenicity efficiently. R2 and RMSE values in training stage were 0.99 and 101.18, respectively. In the testing stage, however, they stood at 0.94 and 173.8, respectively. Conclusion: Based on the findings, the use of ANFIS model significantly improves the accuracy of estimating virus oncogenicity phenomenon. The methodology presented in this study is a new approach in estimating viral oncogenicity and can successfully be combined with other mathematical models for model updating in real conditions.

---

Background: In 1970, human papillomavirus (HPV) was introduced as the main etiologic factor of cervical carcinoma. Since there is no possibility of detecting the virus and its subtypes using serological methods and cell culture, the molecular methods such as PCR have particular importance in accurate, early and definite diagnosis of the virus. So, in this research, our goal is to use a proprietary PCR assay based on L1 gene of human papillomavirus for molecular recognition of HPV and to evaluate its prevalence in patient samples.

Materials and Methods: In this experimental study, after collecting of samples from malignant cervical lesions, the viral DNA was extracted from paraffin blocks of 50 clinical samples and PCR was done by specific primers for L1 gene of human papillomavirus in all samples. After the analysis of PCR products by 2% agarose gel electrophoresis, sensitivity and specificity of the test were also evaluated.

Results: Among 50 patient samples, 33 cases were confirmed to be positive for HPV infection and 17 cases were negative, showing high frequency of HPV in this patient population (about 66%). The results of specificity assay were positive for papilloma samples and sensitivity of the assay was 20 copies of recombinant construct containing L1 per reaction.

Conclusion: This study showed that PCR by specific primers for L1 gene of human papilloma virus is a proper and accurate method for detection of this virus and the results confirm the previous reports of correlation between HPV and cervical carcinoma.