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

lncRNA - Long Non-coding RNAs

lncRNA - Long Non-coding RNAs

In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA (lncRNA)...

You might also read

Related Articles

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

Sort by

Same author

An innovative 2D optical navigation workflow for percutaneous pedicle screw fixation in thoracolumbar fractures: comparison with O-arm 3D navigation.

Frontiers in surgery·2026

Same author

Site-specific neoepitope induction by RNA editing reprograms tumor immunogenicity.

Frontiers in immunology·2026

Same author

Features predicting data exclusion in imaging studies of Alzheimer's disease.

Alzheimer's & dementia (Amsterdam, Netherlands)·2026

Same author

No cognitive or psychological impact from returning research Alzheimer disease biomarkers: A delayed-start, noninferiority, randomized clinical trial.

medRxiv : the preprint server for health sciences·2026

Same author

Subgroup identification via Interaction Tree and Mixed Model for Repeated Measures with application to Alzheimer's disease.

Biometrics·2026

Same author

Evaluating the accuracy and reliability of telephone-derived Clinical Dementia Rating scores: A comparative analysis with in-person assessments.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026

Search research articles

Related Experiment Video

Updated: Jul 12, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Decoding cancer circulating transcriptomic signatures with language models.

Siwei Deng^1,2,3,4, Lei Sha^5,6,7,8, Yongcheng Jin^9,10

¹Division of Gastrointestinal Surgery, Peking University First Hospital, Peking University, Beijing, China.

Nature Communications

|July 9, 2026

Summary

GeneLLM, a novel AI model, analyzes RNA sequences in blood for multi-cancer detection. This approach captures more signals than traditional methods, enabling cost-efficient and scalable cancer screening.

More Related Videos

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Related Experiment Videos

Last Updated: Jul 12, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Published on: March 1, 2024

Area of Science:

Genomics
Bioinformatics
Artificial Intelligence

Background:

Liquid biopsy using plasma cell-free RNA (cfRNA) is promising for multi-cancer detection.
Current methods often rely on gene annotations, potentially missing signals from unannotated genomic regions.

Purpose of the Study:

To develop a novel method for multi-cancer detection using plasma cfRNA that bypasses gene annotations.
To leverage sequence-level information in cfRNA for improved cancer detection.

Main Methods:

Developed GeneLLM, a Transformer-based model processing nucleotide sequences of cfRNA reads.
The model learns latent pseudo-biomarkers from cfRNA embeddings for classification.
Evaluated performance across a multi-centre cohort.

Main Results:

GeneLLM achieved high ROC-AUC values (0.9250–0.9962) across multiple cancers.
The model maintained comparable performance at one-sixth of the typical sequencing depth.
Sequence-level modeling captured diagnostically relevant information beyond annotation-dependent approaches.

Conclusions:

Plasma cfRNA sequence-level modeling offers a powerful alternative to annotation-dependent methods.
GeneLLM enables more cost-efficient and scalable cancer screening.
This approach unlocks signals from the 'transcriptomic dark matter'.