A semi-supervised tensor regression model for siRNA efficacy prediction

From sequences to therapeutics: Using machine learning to predict chemically modified siRNA activity

Small interfering RNAs (siRNAs) exemplify the promise of genetic medicine in the discovery of novel therapeutic modalities. Their ability to selectively suppress gene expression makes them ideal candidates for the development of oligonucleotide pharmaceuticals. Recent advancements in machine learning (ML) have facilitated the design of unmodified siRNA and efficacy prediction. However, a model trained to predict the silencing activity of siRNAs with diverse chemical modification patterns is yet to be published despite the importance of such modifications in designing siRNAs with the potential to reach the level of clinical use. This study presents the first application of ML to efficiently classify chemically modified siRNAs on the basis of sequence and chemical modification patterns alone. Three algorithms were evaluated at three classification thresholds and compared according to sensitivity, specificity, consistency of feature weights with empirical knowledge, and performance using an external validation dataset. Finally, possible directions for future research were proposed.

Hepatitis A: Viral Structure, Classification, Life Cycle, Clinical Symptoms, Diagnosis Error, and Vaccination

Hepatitis A virus (HAV) is one of the well-known viruses that cause hepatitis all around the globe. Although this illness has decreased in developed countries due to extensive immunization, numerous developing and under-developed countries are struggling with this virus. HAV infection can be spread by oral-fecal contact, and there are frequent epidemics through nutrition. Improvements in socioeconomic and sanitary circumstances have caused a shift in the disease's prevalence worldwide. Younger children are usually asymptomatic, but as they become older, the infection symptoms begin to appear. Symptoms range from slight inflammation and jaundice to acute liver failure in older individuals. While an acute infection may be self-limiting, unrecognized persistent infections, and the misapplication of therapeutic methods based on clinical guidelines are linked to a higher incidence of cirrhosis, hepatocellular carcinoma, and mortality. Fortunately, most patients recover within two months of infection, though 10-15% of patients will relapse within the first six months. A virus seldom leads to persistent infection or liver damage. The mainstay of therapy is based on supportive care. All children from 12-23 months, as well as some susceptible populations, should receive routine vaccinations, according to the Centers for Disease Control and Prevention and the American Academy of Pediatrics. Laboratory diagnosis of HAV is based on antigen detection, checking liver enzyme levels, and antibody screening. Furthermore, polymerase chain reaction (PCR) technology has identified HAV in suspected nutrition sources; therefore, this technique is used for preventative measures and food-related laws.

The Use of Electronic Medical Records-Based Big-Data Informatics to Describe ALT Elevations Higher than 1000 IU/L in Patients with or without Hepatitis B Virus Infection

Hepatitis B virus (HBV) infection is one of the serious health problems in the world as HBV causes severe liver diseases. Moreover, HBV reactivation has occasionally been observed in patients with resolved HBV infection and patients using immunosuppression and anticancer drugs. Large-scale hospital data focused on HBV infection and severe liver function were analyzed at our hospital, located in an urban area adjacent to Tokyo, the capital city of Japan. A total of 99,932 individuals whose blood samples were taken at 7,170,240 opportunities were analyzed. The HBV surface antigen (HBsAg)-positive group had a more frequent prevalence of patients with higher transaminase elevations than the HBsAg-negative group. However, among the HBsAg-negative group, patients who were positive for anti-HBV surface antibody and/or anti-HBV core antibody, had more severe liver conditions and fatal outcomes. More careful attention should be paid to alanine transaminase (ALT) elevations higher than 1000 IU/L in patients who had current and previous HBV infection.

Therapeutic RNA interference: A novel approach to the treatment of primary hyperoxaluria

RNA interference (RNAi) is a natural biological pathway that inhibits gene expression by targeted degradation or translational inhibition of cytoplasmic mRNA by the RNA induced silencing complex. RNAi has long been exploited in laboratory research to study the biological consequences of the reduced expression of a gene of interest. More recently RNAi has been demonstrated as a therapeutic avenue for rare metabolic diseases. This review presents an overview of the cellular RNAi machinery as well as therapeutic RNAi design and delivery. As a clinical example we present primary hyperoxaluria, an ultrarare inherited disease of increased hepatic oxalate production which leads to recurrent calcium oxalate kidney stones. In the most common form of the disease (Type 1), end‐stage kidney disease occurs in childhood or young adulthood, often necessitating combined kidney and liver transplantation. In this context we discuss nedosiran (Dicerna Pharmaceuticals, Inc.) and lumasiran (Alnylam Pharmaceuticals), which are both novel RNAi therapies for primary hyperoxaluria that selectively reduce hepatic expression of lactate dehydrogenase and glycolate oxidase respectively, reducing hepatic oxalate production and urinary oxalate levels. Finally, we consider future optimizations advances in RNAi therapies.

FusionHub: A unified web platform for annotation and visualization of gene fusion events in human cancer

Gene fusion is a chromosomal rearrangement event which plays a significant role in cancer due to the oncogenic potential of the chimeric protein generated through fusions. At present many databases are available in public domain which provides detailed information about known gene fusion events and their functional role. Existing gene fusion detection tools, based on analysis of transcriptomics data usually report a large number of fusion genes as potential candidates, which could be either known or novel or false positives. Manual annotation of these putative genes is indeed time-consuming. We have developed a web platform FusionHub, which acts as integrated search engine interfacing various fusion gene databases and simplifies large scale annotation of fusion genes in a seamless way. In addition, FusionHub provides three ways of visualizing fusion events: circular view, domain architecture view and network view. Design of potential siRNA molecules through ensemble method is another utility integrated in FusionHub that could aid in siRNA-based targeted therapy. FusionHub is freely available at https://fusionhub.persistent.co.in.

Predicting siRNA efficacy based on multiple selective siRNA representations and their combination at score level

Small interfering RNAs (siRNAs) may induce to targeted gene knockdown, and the gene silencing effectiveness relies on the efficacy of the siRNA. Therefore, the task of this paper is to construct an effective siRNA prediction method. In our work, we try to describe siRNA from both quantitative and qualitative aspects. For quantitative analyses, we form four groups of effective features, including nucleotide frequencies, thermodynamic stability profile, thermodynamic of siRNA-mRNA interaction, and mRNA related features, as a new mixed representation, in which thermodynamic of siRNA-mRNA interaction is introduced to siRNA efficacy prediction for the first time to our best knowledge. And then an F-score based feature selection is employed to investigate the contribution of each feature and remove the weak relevant features. Meanwhile, we encode the siRNA sequence and existed empirical design rules as a qualitative siRNA representation. These two kinds of siRNA representations are combined to predict siRNA efficacy by supported Vector Regression (SVR) at score level. The experimental results indicate that our method may select the features with powerful discriminative ability and make the two kinds of siRNA representations work at full capacity. The prediction results also demonstrate that our method can outperform other popular siRNA efficacy prediction algorithms.

Utilizing Selected Di- and Trinucleotides of siRNA to Predict RNAi Activity

Small interfering RNAs (siRNAs) induce posttranscriptional gene silencing in various organisms. siRNAs targeted to different positions of the same gene show different effectiveness; hence, predicting siRNA activity is a crucial step. In this paper, we developed and evaluated a powerful tool named “siRNApred” with a new mixed feature set to predict siRNA activity. To improve the prediction accuracy, we proposed 2-3NTs as our new features. A Random Forest siRNA activity prediction model was constructed using the feature set selected by our proposed Binary Search Feature Selection (BSFS) algorithm. Experimental data demonstrated that the binding site of the Argonaute protein correlates with siRNA activity. “siRNApred” is effective for selecting active siRNAs, and the prediction results demonstrate that our method can outperform other current siRNA activity prediction methods in terms of prediction accuracy.

Direct-acting Antivirals and Host-targeting Agents against the Hepatitis A Virus

Hepatitis A virus (HAV) infection is a major cause of acute hepatitis and occasionally leads to acute liver failure in both developing and developed countries. Although effective vaccines for HAV are available, the development of new antivirals against HAV may be important for the control of HAV infection in developed countries where no universal vaccination program against HAV exists, such as Japan. There are two forms of antiviral agents against HAV: direct-acting antivirals (DAAs) and host-targeting agents (HTAs). Studies using small interfering ribonucleic acid (siRNA) have suggested that the HAV internal ribosomal entry site (IRES) is an attractive target for the control of HAV replication and infection. Among the HTAs, amantadine and interferon-lambda 1 (IL-29) inhibit HAV IRES-mediated translation and HAV replication. Janus kinase (JAK) inhibitors inhibit La protein expression, HAV IRES activity, and HAV replication. Based on this review, both DAAs and HTAs may be needed to control effectively HAV infection, and their use should continue to be explored.