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

Genome Annotation and Assembly

Genome Annotation and Assembly

The genome refers to all of the genetic material in an organism. It can range from a few million base pairs in microbial cells to several billion base pairs in many eukaryotic organisms. Genome assembly refers to the process of taking the DNA sequencing data and putting it all back together in a correct order to create a close representation of the original genome. This is followed by the identification of functional elements on the newly assembled genome, a process called genome annotation.

You might also read

Related Articles

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

Sort by

Same author

Multiple instance fine-mapping: Predicting causal regulatory variants with a deep sequence model.

PLoS genetics·2026

Same author

Expanding the human proteome with microproteins and peptideins.

Nature·2026

Same author

Prediction and risk evaluation of delirium after surgery in older patients: development and internal validation of an algorithm from the prospective BioCog cohort study.

British journal of anaesthesia·2026

Same author

Large language models improve transferability of electronic health record-based predictions across countries and coding systems.

NPJ digital medicine·2026

Same author

A Pre-Trained Model Customization Framework for Accelerated PET/MR Segmentation of Abdominal Fat in Obstructive Sleep Apnea.

Diagnostics (Basel, Switzerland)·2025

Same author

The AIR·MS data platform for artificial intelligence in healthcare.

JAMIA open·2025

Same journal

Cross-Domain Transfer Learning from Peptides to Metabolites Using a Multi-Property Fine-Tuned LLM.

Bioinformatics (Oxford, England)·2026

Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026

Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026

Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026

Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026

Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 14, 2025

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA

Published on: August 21, 2016

Metadata-guided feature disentanglement for functional genomics.

Alexander Rakowski¹, Remo Monti^1,2, Viktoriia Huryn²

¹Digital Health Machine Learning, Hasso Plattner Institute for Digital Engineering, Digital Engineering, University of Potsdam, Campus III Building G2, Rudolf-Breitscheid-Strasse 187, Potsdam, Brandenburg, 14482, Germany.

Bioinformatics (Oxford, England)

|September 4, 2024

Summary

This summary is machine-generated.

Metadata-guided Feature Disentanglement (MFD) separates biological signals from technical biases in large functional genomics datasets. This approach improves model interpretability and performance in tasks like enhancer prediction.

More Related Videos

High-throughput Identification of Gene Regulatory Sequences Using Next-generation Sequencing of Circular Chromosome Conformation Capture 4C-seq

High-throughput Identification of Gene Regulatory Sequences Using Next-generation Sequencing of Circular Chromosome Conformation Capture 4C-seq

Published on: October 5, 2018

Identification of Functionally-Relevant Lentivirus Integration Sites in an Insertional Mutagenesis Cell Library

Identification of Functionally-Relevant Lentivirus Integration Sites in an Insertional Mutagenesis Cell Library

Published on: January 10, 2025

Related Experiment Videos

Last Updated: Jun 14, 2025

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA

Screening for Functional Non-coding Genetic Variants Using Electrophoretic Mobility Shift Assay EMSA and DNA-affinity Precipitation Assay DAPA

Published on: August 21, 2016

High-throughput Identification of Gene Regulatory Sequences Using Next-generation Sequencing of Circular Chromosome Conformation Capture 4C-seq

High-throughput Identification of Gene Regulatory Sequences Using Next-generation Sequencing of Circular Chromosome Conformation Capture 4C-seq

Published on: October 5, 2018

Identification of Functionally-Relevant Lentivirus Integration Sites in an Insertional Mutagenesis Cell Library

Identification of Functionally-Relevant Lentivirus Integration Sites in an Insertional Mutagenesis Cell Library

Published on: January 10, 2025

Area of Science:

Genomics
Computational Biology
Machine Learning

Background:

High-throughput technologies generate large functional genomics datasets, enabling Deep Learning (DL) models for predicting epigenetic readouts from genome sequences.
Large datasets, often aggregated from diverse studies, can introduce technical biases due to varying experimental conditions, confounding biological insights.
Existing methods struggle to effectively isolate biological signals from experimental noise in large-scale genomics data.

Purpose of the Study:

To introduce Metadata-guided Feature Disentanglement (MFD), a novel approach for disentangling biologically relevant features from technical biases in functional genomics data.
To enable better model introspection by connecting latent features to specific experimental factors.
To maintain or enhance DL model performance on downstream tasks despite bias mitigation.

Main Methods:

MFD incorporates experimental metadata into DL model training by conditioning output layer weights on different factors.
The approach separates experimental factors into distinct groups and enforces feature subspace independence using an adversarial penalty.
This method facilitates the disentanglement of biological signals from confounding technical variations.

Main Results:

MFD successfully disentangles biological features from technical biases in functional genomics data.
The approach enhances model introspection, allowing clear connections between latent features and experimental metadata.
Downstream task performance, including enhancer prediction and genetic variant discovery, was maintained or improved.

Conclusions:

Metadata-guided Feature Disentanglement (MFD) is an effective strategy for addressing biases in large-scale functional genomics datasets.
MFD enhances the interpretability of Deep Learning models in genomics without sacrificing predictive accuracy.
This method offers a robust framework for leveraging large, heterogeneous genomics data for biological discovery.