Abstract
BackgroundRNA velocity is a novel and powerful concept which enables the inference of dynamical cell state changes from seemingly static single-cell RNA sequencing (scRNA-seq) data. However, accurate estimation of RNA velocity is still a challenging problem, and the underlying kinetic mechanisms of transcriptional and splicing regulations are not fully clear. Moreover, scRNA-seq data tend to be sparse compared with possible cell states, and a given dataset of estimated RNA velocities needs imputation for some cell states not yet covered.ResultsWe formulate RNA velocity prediction as a supervised learning problem of classification for the first time, where a cell state space is divided into equal-sized segments by directions as classes, and the estimated RNA velocity vectors are considered as ground truth. We propose Velo-Predictor, an ensemble learning pipeline for predicting RNA velocities from scRNA-seq data. We test different models on two real datasets, Velo-Predictor exhibits good performance, especially when XGBoost was used as the base predictor. Parameter analysis and visualization also show that the method is robust and able to make biologically meaningful predictions.ConclusionThe accurate result shows that Velo-Predictor can effectively simplify the procedure by learning a predictive model from gene expression data, which could help to construct a continous landscape and give biologists an intuitive picture about the trend of cellular dynamics.
Highlights
RNA velocity is a novel and powerful concept which enables the inference of dynamical cell state changes from seemingly static single-cell RNA sequencing data
There are various approaches to trajectory reconstrcution, e.g. SCUBA [5] is based on bifurcation analysis, SCENT [6] and scEpath [7] use a measurement of entropy of cell states
=β · U (t) − γ · S(t), dt where S(t) represents mature mRNA abundance over time, U(t) represents pre-mRNA abundance over time, α is the rate of transcription, β is the rate of splicing, and γ is the rate of degradation. k and t are cell-specific latent variables, where k represents discrete transcriptional state, and t represents latent time
Summary
RNA velocity is a novel and powerful concept which enables the inference of dynamical cell state changes from seemingly static single-cell RNA sequencing (scRNA-seq) data. Accurate estimation of RNA velocity is still a challenging problem, and the underlying kinetic mechanisms of transcriptional and splicing regulations are not fully clear. ScRNA-seq data tend to be sparse compared with possible cell states, and a given dataset of estimated RNA velocities needs imputation for some cell states not yet covered. Recent advances in high-throughput RNA sequencing technologies [1] have enabled analysis of transcription at single-cell level [2], which has provided immense opportunities to unravel the underlying mechanisms of gene expression regulation. Trajectory inference (including pseudotime analysis) is a primary task to identify cells in various states of differentiation [4]. HopLand [8] and Topslam [9] project cells to a landscape with optimized parameters
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
