Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Protein Networks

Protein Networks

An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...

Alternative RNA Splicing

Alternative RNA Splicing

Alternative RNA splicing is the regulated splicing of exons and introns to produce different mature mRNAs from a single pre-mRNA. Unlike in constitutive splicing where a single gene produces a single type of mRNA, alternative splicing allows an organism to produce multiple proteins from a single gene and plays an important role in protein diversity.
There are five types of alternative RNA splicing that vary in the ways the pre-mRNA segments are removed or retained in the mature mRNA. The first...

Alternative RNA Splicing

Alternative RNA Splicing

Predicting Molecular Geometry

Predicting Molecular Geometry

VSEPR Theory for Determination of Electron Pair Geometries

Network Covalent Solids

Network Covalent Solids

Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...

Null and Alternative Hypotheses

Null and Alternative Hypotheses

The actual hypothesis testing begins by considering two hypotheses. They are termed the null hypothesis and the alternative hypothesis. These hypotheses contain opposing viewpoints.
The null hypothesis, denoted by H0 is a statement of no difference between the variables—they are not related. This can often be considered the status quo. As a result if you cannot accept the null, it requires some action.
The alternative hypothesis, denoted by H1 or Ha, is a claim about the...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Teaching an old dog new cells.

Nature methods·2026

Same author

Transforming the cytokine literature into a resource for experimental analysis and discovery.

bioRxiv : the preprint server for biology·2026

Same author

Dynamics of phage-host interactions in Bacteroides fragilis resolved by single-cell transcriptomics.

Nature communications·2026

Same author

The Next Generation of Protein Sequencing and Analysis Methods.

Annual review of analytical chemistry (Palo Alto, Calif.)·2026

Same author

Parameter-efficient fine-tuning enables scalable transfer of regulatory sequence models to novel contexts.

Genome biology·2026

Same author

A single-cell cytokine dictionary of human peripheral blood.

Research square·2026

Search research articles

Related Experiment Video

Updated: Jan 23, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

A Deep Neural Network for Predicting and Engineering Alternative Polyadenylation.

Nicholas Bogard¹, Johannes Linder², Alexander B Rosenberg¹

¹Department of Electrical & Computer Engineering, University of Washington, Seattle, WA 98195, USA.

|June 11, 2019

Summary

This summary is machine-generated.

Deep learning model APARENT predicts alternative polyadenylation (APA) from DNA sequence. This tool identifies sequence motifs regulating APA and quantifies genetic variant impacts on disease.

Keywords:

MPRA SNV alternative polyadenylation cis-regulation deep learning generative model mRNA processing machine learning massively parallel reporter assay single nucleotide variant synthetic biology

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data

Published on: June 24, 2021

Related Experiment Videos

Last Updated: Jan 23, 2026

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data

Identification of Alternative Splicing and Polyadenylation in RNA-seq Data

Published on: June 24, 2021

Area of Science:

Genomics and Bioinformatics
Molecular Biology
Computational Biology

Background:

Alternative polyadenylation (APA) significantly contributes to transcriptome diversity in human cells.
Understanding the DNA sequence determinants of APA is crucial for deciphering gene regulation.
Current methods for predicting APA often require experimental data or are limited in scope.

Purpose of the Study:

To develop a deep learning model (APARENT) capable of predicting APA solely from DNA sequence.
To identify novel sequence motifs and regulatory elements governing APA.
To apply the model for engineering polyadenylation signals and assessing the impact of genetic variants on APA.

Main Methods:

Trained a deep learning model, APARENT (APA REgression NeT), on a large dataset of over 3 million APA reporters and their isoform expression data.
Utilized visualization techniques to interpret the sequence features learned by the neural network.
Experimentally validated the model's predictions for engineered polyadenylation signals and genetic variant effects.

Main Results:

APARENT demonstrates high accuracy in predicting APA in both synthetic and human 3' untranslated regions (3'UTRs).
The model successfully identified known and discovered novel sequence motifs involved in recruiting APA regulators.
APARENT effectively quantified the impact of genetic variants on APA, identifying pathogenic variants associated with various diseases.

Conclusions:

Deep learning can accurately predict alternative polyadenylation from DNA sequence alone, providing a powerful tool for genomic analysis.
APARENT reveals a complex cis-regulatory code governing 3' end processing and offers insights into gene expression regulation.
The model has significant implications for understanding the genetic basis of diseases by identifying pathogenic variants affecting APA.