Modeling and Predicting the Activities of Trans-Acting Splicing Factors with Machine Learning

Identification of two short peptide motifs from serine/arginine-rich protein ribonucleic acid recognition motif-1 domain acting as splicing regulators

Background

Serine/arginine-rich (SR) proteins regulate pre-mRNA splicing. However, structurally similar proteins often behave differently in splicing regulation and the underlying mechanisms are largely unknown. Here, using SMN1/2 minigenes we extensively analyzed four SR proteins, SRSF1/5/6/9.

Methods

In this study, the effects of these proteins on SMN1/2 exon 7 splicing when tethered at either intron 6 or 7 were evaluated using an MS2-tethering assay. Deletion analysis in four SR proteins and co-overexpression analysis were performed.

Results

Splicing outcomes varied among all four SR proteins, SRSF1 and SRSF5 function the same at the two sites, acting as repressor and stimulator, respectively; while SRSF6 and SRSF9 promote exon 7 inclusion at only one site. Further, the key domains of each SR proteins were investigated, which identified a potent inhibitory nonapeptide in the C-terminus of SRSF1/9 ribonucleic acid recognition motif-1 (RRM1) and a potent stimulatory heptapeptide at the N-terminus of SRSF5/6 RRM1.

Conclusion

The insight of the four SR proteins and their domains in affecting SMN gene splicing brings a new perspective on the modes of action of SR proteins; and the functional peptides obtained here offers new ideas for developing splice switching-related therapies.

Study on Black Spot Disease Detection and Pathogenic Process Visualization on Winter Jujubes Using Hyperspectral Imaging System

In this work, the potential of a hyperspectral imaging (HSI) system for the detection of black spot disease on winter jujubes infected by Alternaria alternata during postharvest storage was investigated. The HSI images were acquired using two systems in the visible and near-infrared (Vis-NIR, 400-1000 nm) and short-wave infrared (SWIR, 1000-2000 nm) spectral regions. Meanwhile, the change of physical (peel color, weight loss) and chemical parameters (soluble solids content, chlorophyll) and the microstructure of winter jujubes during the pathogenic process were measured. The results showed the spectral reflectance of jujubes in both the Vis-NIR and SWIR wavelength ranges presented an overall downtrend during the infection. Partial least squares discriminant models (PLS-DA) based on the HSI spectra in Vis-NIR and SWIR regions of jujubes both gave satisfactory discrimination accuracy for the disease detection, with classification rates of over 92.31% and 91.03%, respectively. Principal component analysis (PCA) was carried out on the HSI images of jujubes to visualize their infected areas during the pathogenic process. The first principal component of the HSI spectra in the Vis-NIR region could highlight the diseased areas of the infected jujubes. Consequently, Vis-NIR HSI and NIR HSI techniques had the potential to detect the black spot disease on winter jujubes during the postharvest storage, and the Vis-NIR HSI spectral information could visualize the diseased areas of jujubes during the pathogenic process.

Emerging roles of alternative RNA splicing in oral squamous cell carcinoma

Alternative RNA splicing (ARS) is an essential and tightly regulated cellular process of post-transcriptional regulation of pre-mRNA. It produces multiple isoforms and may encode proteins with different or even opposite functions. The dysregulated ARS of pre-mRNA contributes to the development of many cancer types, including oral squamous cell carcinoma (OSCC), and may serve as a biomarker for the diagnosis and prognosis of OSCC and an attractive therapeutic target. ARS is mainly regulated by splicing factors, whose expression is also often dysregulated in OSCC and involved in tumorigenesis. This review focuses on the expression and roles of splicing factors in OSCC, the alternative RNA splicing events associated with OSCC, and recent advances in therapeutic approaches that target ARS.

A widespread length-dependent splicing dysregulation in cancer

Dysregulation of alternative splicing is a key molecular hallmark of cancer. However, the common features and underlying mechanisms remain unclear. Here, we report an intriguing length-dependent splicing regulation in cancers. By systematically analyzing the transcriptome of thousands of cancer patients, we found that short exons are more likely to be mis-spliced and preferentially excluded in cancers. Compared to other exons, cancer-associated short exons (CASEs) are more conserved and likely to encode in-frame low-complexity peptides, with functional enrichment in GTPase regulators and cell adhesion. We developed a CASE-based panel as reliable cancer stratification markers and strong predictors for survival, which is clinically useful because the detection of short exon splicing is practical. Mechanistically, mis-splicing of CASEs is regulated by elevated transcription and alteration of certain RNA binding proteins in cancers. Our findings uncover a common feature of cancer-specific splicing dysregulation with important clinical implications in cancer diagnosis and therapies.

Roles of Physicochemical and Structural Properties of RNA-Binding Proteins in Predicting the Activities of Trans-Acting Splicing Factors with Machine Learning

Trans-acting splicing factors play a pivotal role in modulating alternative splicing by specifically binding to cis-elements in pre-mRNAs. There are approximately 1500 RNA-binding proteins (RBPs) in the human genome, but the activities of these RBPs in alternative splicing are unknown. Since determining RBP activities through experimental methods is expensive and time consuming, the development of an efficient computational method for predicting the activities of RBPs in alternative splicing from their sequences is of great practical importance. Recently, a machine learning model for predicting the activities of splicing factors was built based on features of single and dual amino acid compositions. Here, we explored the role of physicochemical and structural properties in predicting their activities in alternative splicing using machine learning approaches and found that the prediction performance is significantly improved by including these properties. By combining the minimum redundancy–maximum relevance (mRMR) method and forward feature searching strategy, a promising feature subset with 24 features was obtained to predict the activities of RBPs. The feature subset consists of 16 dual amino acid compositions, 5 physicochemical features, and 3 structural features. The physicochemical and structural properties were as important as the sequence composition features for an accurate prediction of the activities of splicing factors. The hydrophobicity and distribution of coil are suggested to be the key physicochemical and structural features, respectively.

Recent Advances in the Prediction of Protein Structural Classes: Feature Descriptors and Machine Learning Algorithms

In the postgenomic age, rapid growth in the number of sequence-known proteins has been accompanied by much slower growth in the number of structure-known proteins (as a result of experimental limitations), and a widening gap between the two is evident. Because protein function is linked to protein structure, successful prediction of protein structure is of significant importance in protein function identification. Foreknowledge of protein structural class can help improve protein structure prediction with significant medical and pharmaceutical implications. Thus, a fast, suitable, reliable, and reasonable computational method for protein structural class prediction has become pivotal in bioinformatics. Here, we review recent efforts in protein structural class prediction from protein sequence, with particular attention paid to new feature descriptors, which extract information from protein sequence, and the use of machine learning algorithms in both feature selection and the construction of new classification models. These new feature descriptors include amino acid composition, sequence order, physicochemical properties, multiprofile Bayes, and secondary structure-based features. Machine learning methods, such as artificial neural networks (ANNs), support vector machine (SVM), K-nearest neighbor (KNN), random forest, deep learning, and examples of their application are discussed in detail. We also present our view on possible future directions, challenges, and opportunities for the applications of machine learning algorithms for prediction of protein structural classes.

Insights Into the Role of CircRNAs: Biogenesis, Characterization, Functional, and Clinical Impact in Human Malignancies

Circular RNAs (circRNAs) are an evolutionarily conserved novel class of non-coding endogenous RNAs (ncRNAs) found in the eukaryotic transcriptome, originally believed to be aberrant RNA splicing by-products with decreased functionality. However, recent advances in high-throughput genomic technology have allowed circRNAs to be characterized in detail and revealed their role in controlling various biological and molecular processes, the most essential being gene regulation. Because of the structural stability, high expression, availability of microRNA (miRNA) binding sites and tissue-specific expression, circRNAs have become hot topic of research in RNA biology. Compared to the linear RNA, circRNAs are produced differentially by backsplicing exons or lariat introns from a pre-messenger RNA (mRNA) forming a covalently closed loop structure missing 3′ poly-(A) tail or 5′ cap, rendering them immune to exonuclease-mediated degradation. Emerging research has identified multifaceted roles of circRNAs as miRNA and RNA binding protein (RBP) sponges and transcription, translation, and splicing event regulators. CircRNAs have been involved in many human illnesses, including cancer and neurodegenerative disorders such as Alzheimer’s and Parkinson’s disease, due to their aberrant expression in different pathological conditions. The functional versatility exhibited by circRNAs enables them to serve as potential diagnostic or predictive biomarkers for various diseases. This review discusses the properties, characterization, profiling, and the diverse molecular mechanisms of circRNAs and their use as potential therapeutic targets in different human malignancies.