RFLMDA: A Novel Reinforcement Learning-Based Computational Model for Human MicroRNA-Disease Association Prediction

Numerous studies have confirmed that microRNAs play a crucial role in the research of complex human diseases. Identifying the relationship between miRNAs and diseases is important for improving the treatment of complex diseases. However, traditional biological experiments are not without restrictions. It is an urgent necessity for computational simulation to predict unknown miRNA-disease associations. In this work, we combine Q-learning algorithm of reinforcement learning to propose a RFLMDA model, three submodels CMF, NRLMF, and LapRLS are fused via Q-learning algorithm to obtain the optimal weight S. The performance of RFLMDA was evaluated through five-fold cross-validation and local validation. As a result, the optimal weight is obtained as S (0.1735, 0.2913, 0.5352), and the AUC is 0.9416. By comparing the experiments with other methods, it is proved that RFLMDA model has better performance. For better validate the predictive performance of RFLMDA, we use eight diseases for local verification and carry out case study on three common human diseases. Consequently, all the top 50 miRNAs related to Colorectal Neoplasms and Breast Neoplasms have been confirmed. Among the top 50 miRNAs related to Colon Neoplasms, Gastric Neoplasms, Pancreatic Neoplasms, Kidney Neoplasms, Esophageal Neoplasms, and Lymphoma, we confirm 47, 41, 49, 46, 46 and 48 miRNAs respectively.

P-OGC92 Esophagogastric Lymphomas; Lymphomas outside Lymphoid tissue

Background Primary gastric lymphomas are rare tumours and account for 5% of all gastric neoplasms. Esophaphageal lymphomas are even rarer, accounting for 1% of all oesophageal tumours. Incidence of these tumours have been increasing over time and there is increasing need to understand this tumour subtype. This is a single centre study of esophagogastric lymphomas over a period of 15 years. Methods Between 2005 to 2020; patients who were diagnosed of having esophagogastric lymphomas, were retrospectively studied. Their clinical records were assessed for age, gender, clinical signs and symptoms, histological type, association with H pylori, LDH levels, stage at diagnosis, treatment type, Endoscopy and clinical follow up and survival. Results 66 patients were diagnosed of having lymphoma, out of which 4 (6%) were oesophageal and 62 (93.93%) were gastric. Median age was 77 years (Range 41-102 years), 39 were male (59%) and 27(41%) were female. Anaemia was the commonest sign (53%), followed by nausea/vomiting (45%), weight loss (44.5%), abdominal pain (40.6%) and dysphagia (24%). 15.6% patients were found to have H pylori and 10% of patients had Barrett’s. Diffuse Large B Cell Lymphomas were commonest tumours (28.33%) followed by MALToma’s (26.6%). 60% patients were T3/4 at the time of diagnosis and 9.7% had other OG malignancies. 53% patients received antibiotics, 61% received chemotherapy, 16% received chemoradiotherapy and 16% received surgical resection. Median survival was 3 years (range 0-14). Conclusions Esophagogastric lymphomas are successfully treated with chemotherapy with promising survival. The stage at diagnosis and presence of comorbidities are limiting factors in overall disease prognosis.