Prediction of RNA-interacting residues in a protein using CNN and evolutionary profile.

This paper describes a method Pprint2, which is an improved version of Pprint developed for predicting RNA-interacting residues in a protein. Training and independent/validation datasets used in this study comprises of 545 and 161 non-redundant RNA-binding proteins, respectively. All models were trained on training dataset and evaluated on the validation dataset. The preliminary analysis reveals that positively charged amino acids such as H, R and K, are more prominent in the RNA-interacting residues. Initially, machine learning based models have been developed using binary profile and obtain maximum area under curve (AUC) 0.68 on validation dataset. The performance of this model improved significantly from AUC 0.68 to 0.76, when evolutionary profile is used instead of binary profile. The performance of our evolutionary profile-based model improved further from AUC 0.76 to 0.82, when convolutional neural network has been used for developing model. Our final model based on convolutional neural network using evolutionary information achieved AUC 0.82 with Matthews correlation coefficient of 0.49 on the validation dataset. Our best model outperforms existing methods when evaluated on the independent/validation dataset. A user-friendly standalone software and web-based server named 'Pprint2' has been developed for predicting RNA-interacting residues (https://webs.iiitd.edu.in/raghava/pprint2 and https://github.com/raghavagps/pprint2).

Endometrial Histopathology in Abnormal Uterine Bleeding and Its Relation With Thyroid Profile and Endometrial Thickness.

INTRODUCTION: Abnormal uterine bleeding (AUB) is a common complaint in postmenopausal and perimenopausal women, caused by a range of disorders, including structural and systemic diseases. The evaluation of endometrial thickness (ET) via radiological methods, followed by a histopathological examination of the endometrium, is useful for proper diagnosis. Among systemic diseases, thyroid dysfunction, specifically hypothyroidism and hyperthyroidism, contribute significantly to AUB cases. MATERIALS AND METHODS: This descriptive cross-sectional study was conducted at Sri Aurobindo Medical College, Indore, Madhya Pradesh, India, over a period of 16 months, from May 2021 to September 2022. Patients presenting with abnormal uterine bleeding and undergoing thyroid function tests (TFTs), ultrasonography, and endometrial biopsy/hysterectomy at the gynecological outpatient department were included. Hospital records were used to obtain clinical details and investigation results. Endometrial thickness and thyroid status were recorded, and descriptive statistics were used to analyze the collected data. RESULTS: This study included 150 patients with abnormal uterine bleeding, with a mean age of 44 years and 80.6% of patients in the premenopausal age group. A total of 48% of patients had a deranged thyroid profile, with hypothyroidism being more common (91.6%). Structural causes of AUB were identified in 81.3% of cases, with adenomyosis (33.65%), concomitant adenomyosis and leiomyoma (31.5%), and leiomyoma (14.8%) being the most common. Endometrial polyps (4.6%) and endometrial carcinoma (0.6%) were also observed and were consistent with the final histopathology. The remaining 18 patients had no structural causes and were categorized as cases of dysfunctional uterine bleeding (DUB). Increased ET was more commonly observed in postmenopausal patients (4.3%) compared to premenopausal patients (0.7%) among those with AUB, while the reverse was true for patients with DUB. Increased ET was commonly associated with hypothyroidism in both groups. Histopathological examination of endometrial biopsies/hysterectomy specimens revealed additional findings in some patients, including hyperplasia of the endometrium with (0.7%) and without atypia (4%), leading to a more accurate diagnosis. CONCLUSION: AUB is a prevalent condition affecting women in both pre-menopausal and postmenopausal stages, frequently caused by structural anomalies. However, thyroid dysfunction, especially hypothyroidism, is also a significant contributing factor. As such, thyroid function tests (TFTs) are an effective and economical means of identifying potential underlying causes of AUB. Hypothyroidism is frequently associated with increased endometrial thickness, and histopathological examination remains the gold standard for determining the precise cause of AUB.