CPA-Perturb-seq: Multiplexed single-cell characterization of alternative polyadenylation regulators

Abstract

Most mammalian genes have multiple polyA sites, representing a substantial source of transcript diversity that is governed by the cleavage and polyadenylation (CPA) regulatory machinery. To better understand how these proteins govern polyA site choice we introduce CPA-Perturb-seq, a multiplexed perturbation screen dataset of 42 known CPA regulators with a 3' scRNA-seq readout that enables transcriptome-wide inference of polyA site usage. We develop a statistical framework to specifically identify perturbation-dependent changes in intronic and tandem polyadenylation, and discover modules of co-regulated polyA sites exhibiting distinct functional properties. By training a multi-task deep neural network (APARENT-Perturb) on our dataset, we delineate a cis-regulatory code that predicts responsiveness to perturbation and reveals interactions between distinct regulatory complexes. Finally, we leverage our framework to re-analyze published scRNA-seq datasets, identifying new regulators that affect the relative abundance of alternatively polyadenylated transcripts, and characterizing extensive cellular heterogeneity in 3' UTR length amongst antibody-producing cells. Our work highlights the potential for multiplexed single-cell perturbation screens to further our understanding of post-transcriptional regulation in vitro and in vivo.

Single-nucleus multiomic atlas of frontal cortex in amyotrophic lateral sclerosis with a deep learning-based decoding of alternative polyadenylation mechanisms

“…In C9-ALS, Module 1 (Fig. 6a) highlights interactions with RBPs like MBNL1 and SRSF7, both involved in transcript shortening 99,101 . This module also features other APA-related factors such as HNRNPA1, as well as TDP-43 ( TARDBP ).…”

Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation

“…We hypothesize that adding such training data will generally improve learning the sequence basis of these regulatory processes, but also positively influence challenging cell type specific predictions like alternative splicing. Similarly, we anticipate training on experiments in which regulatory proteins have been perturbed will improve model performance generally and enable causal inference tying particular regulators to the sequence patterns mediating their functions [95, 96]. Data quantity is a critical factor in successful machine learning and we believe that adding RNA-seq, as well as other biochemical readouts, from more mammals is a viable path to increasing training data and model quality [97].…”

From words to complete phrases: insight into single-cell isoforms using short and long reads

“…In this respect, technologies like PERTURB-Seq [ 72–74 ], which apply scRNA-seq to CRISPR screens could add important insights to the field. Although the original publications of these techniques investigated immune response in the brain, T-cell receptor induction, as well as unfolded protein stress response, some recent work has focused on RNA variables, notably looking at polyA site usage and polyadenylation regulation [ 75 ]. Paired with long-read sequencing, such techniques would gain isoform resolution and could answer questions such as (i) which splicing factors control which exons?…”