Alternative polyadenylation (APA) plays important roles in modulating mRNA stability, translation, and subcellular localization, and contributes extensively to shaping eukaryotic transcriptome complexity and proteome diversity. Identification of poly(A) sites (pAs) on a genome-wide scale is a critical step toward understanding the underlying mechanism of APA-mediated gene regulation. A number of established computational tools have been proposed to predict pAs from diverse genomic data. Here we provided an exhaustive overview of computational approaches for predicting pAs from DNA sequences, bulk RNA sequencing (RNA-seq) data, and single-cell RNA sequencing (scRNA-seq) data. Particularly, we examined several representative tools using bulk RNA-seq and scRNA-seq data from peripheral blood mononuclear cells and put forward operable suggestions on how to assess the reliability of pAs predicted by different tools. We also proposed practical guidelines on choosing appropriate methods applicable to diverse scenarios. Moreover, we discussed in depth the challenges in improving the performance of pA prediction and benchmarking different methods. Additionally, we highlighted outstanding challenges and opportunities using new machine learning and integrative multi-omics techniques, and provided our perspective on how computational methodologies might evolve in the future for non-3′ untranslated region, tissue-specific, cross-species, and single-cell pA prediction.

Alternative polyadenylation (APA) is a widespread regulatory mechanism of transcript diversification in eukaryotes, which is increasingly recognized as an important layer for eukaryotic gene expression. Recent studies based on single-cell RNA-seq (scRNA-seq) have revealed cell-to-cell heterogeneity in APA usage and APA dynamics across different cell types in various tissues, biological processes and diseases. However, currently available APA databases were all collected from bulk 3′-seq and/or RNA-seq data, and no existing database has provided APA information at single-cell resolution. Here, we present a user-friendly database called scAPAdb (http://www.bmibig.cn/scAPAdb), which provides a comprehensive and manually curated atlas of poly(A) sites, APA events and poly(A) signals at the single-cell level. Currently, scAPAdb collects APA information from > 360 scRNA-seq experiments, covering six species including human, mouse and several other plant species. scAPAdb also provides batch download of data, and users can query the database through a variety of keywords such as gene identifier, gene function and accession number. scAPAdb would be a valuable and extendable resource for the study of cell-to-cell heterogeneity in APA isoform usages and APA-mediated gene regulation at the single-cell level under diverse cell types, tissues and species.

Gene set scoring (GSS) has been routinely conducted for gene expression analysis of bulk or single-cell RNA-seq data, which helps to decipher single-cell heterogeneity and cell-type-specific variability by incorporating prior knowledge from functional gene sets. Single-cell assay for transposase accessible chromatin using sequencing (scATAC-seq) is a powerful technique for interrogating single-cell chromatin-based gene regulation, and genes or gene sets with dynamic regulatory potentials can be regarded as cell-type specific markers as if in scRNA-seq. However, there are few GSS tools specifically designed for scATAC-seq, and the applicability and performance of RNA-seq GSS tools on scATAC-seq data remain to be investigated. We systematically benchmarked ten GSS tools, including four bulk RNA-seq tools, five single-cell RNA-seq (scRNA-seq) tools, and one scATAC-seq method. First, using matched scATAC-seq and scRNA-seq datasets, we find that the performance of GSS tools on scATAC-seq data is comparable to that on scRNA-seq, suggesting their applicability to scATAC-seq. Then the performance of different GSS tools were extensively evaluated using up to ten scATAC-seq datasets. Moreover, we evaluated the impact of gene activity conversion, dropout imputation, and gene set collections on the results of GSS. Results show that dropout imputation can significantly promote the performance of almost all GSS tools, while the impact of gene activity conversion methods or gene set collections on GSS performance is more GSS tool or dataset dependent. Finally, we provided practical guidelines for choosing appropriate pre-processing methods and GSS tools in different scenarios.

Alternative polyadenylation (APA) plays important roles in modulating mRNA stability, translation, and subcellular localization, and contributes extensively to shaping eukaryotic transcriptome complexity and proteome diversity. Identification of poly(A) sites (pAs) on a genome-wide scale is a critical step toward understanding the underlying mechanism of APA-mediated gene regulation. A number of established computational tools have been proposed to predict pAs from diverse genomic data. Here we provided an exhaustive overview of computational approaches for predicting pAs from DNA sequences, bulk RNA-seq data, and single-cell RNA-seq (scRNA-seq) data. Particularly, we examined several representative tools using RNA-seq and scRNA-seq data from peripheral blood mononuclear cells and put forward operable suggestions on how to assess the reliability of pAs predicted by different tools. We also proposed practical guidelines on choosing appropriate methods applicable to diverse scenarios. Moreover, we discussed in depth the challenges in improving the performance of pA prediction and benchmarking different methods. Additionally, we highlighted outstanding challenges and opportunities using new machine learning and integrative multi-omics techniques and provided our perspective on how computational methodologies might evolve in the future for non-3’ UTR, tissue-specific, cross-species, and single-cell pA prediction.

Reinforcement learning and deep reinforcement learning, as a research hotspot in the field of machine learning, have been widely used in our daily life. In this field, game is playing an extremely important role in the developing of reinforcement learning algorithms. Based on the Tennis environment built by Unity ML Agents, this paper used three algorithms, Proximal Policy Optimization (PPO), Multi-Agent Deep Deterministic Policy Gradients (MADDPG) and Soft Actor-Critic (SAC), combined with PyTorch framework, solved the continuous control problem of this environment. Meanwhile, a group of optimal parameters are obtained through multiple trainings, so that Agents can achieve a perfect effect of solving the continuous control problem in Tennis environment. At the end, this paper compared and analyzed the difference among these three algorithms, summarized the application and properties of each algorithm. For different parameters of the algorithm, this paper also maked a comparison and explained the reasons for some special cases as well which can be used for the future work.