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

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

You might also read

Related Articles

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

Sort by

Same author

Random-with-constraints: Constructing minimal models for high-dimensional biology.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

Factors Affecting Chronic Subdural Hematoma Recurrence after Middle Meningeal Artery Embolization.

Asian journal of neurosurgery·2026

Same author

Emergent frequency-dependent selection predicts mutation outcomes in complex ecological communities.

ArXiv·2026

Same author

Emergent frequency-dependent selection predicts mutation outcomes in complex ecological communities.

bioRxiv : the preprint server for biology·2026

Same author

Ecology of metagenomes: incorporating genotype-to-phenotype maps into ecological models.

bioRxiv : the preprint server for biology·2026

Same author

From genes to collective modes: biological constraints shape metabolic evolution.

bioRxiv : the preprint server for biology·2026

Same journal

Poisoning the Genome: Targeted Backdoor Attacks on DNA Foundation Models.

ArXiv·2026

Same journal

Mechanistic mathematical model of the in vitro infection dynamics of Bunyamwera and Batai viruses including MOI-dependent shortening of the eclipse phase.

ArXiv·2026

Same journal

AI-Driven Lumped-Element Modeling of Human Respiratory System for Studying Voice Mechanics.

ArXiv·2026

Same journal

Beyond Algorithms: Conceptual Innovation in Medical Imaging AI.

ArXiv·2026

Same journal

Feynman Kac Reweighted Schrödinger Bridge Matching for Surface-Based Tau PET Harmonization.

ArXiv·2026

Same journal

Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3.

ArXiv·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Feb 28, 2026

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

Parameter-free representations outperform single-cell foundation models on downstream benchmarks.

Huan Souza¹, Pankaj Mehta^1,2

¹Department of Physics, Boston University, Boston, MA, 02215, USA.

|February 27, 2026

Summary

This summary is machine-generated.

Simple linear methods achieve state-of-the-art performance on single-cell RNA sequencing (scRNA-seq) data, rivaling complex foundation models. This suggests that interpretable representations can effectively capture cell identity, challenging the necessity of computationally intensive deep learning.

More Related Videos

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Related Experiment Videos

Last Updated: Feb 28, 2026

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Droplet Barcoding-Based Single Cell Transcriptomics of Adult Mammalian Tissues

Published on: January 10, 2019

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Area of Science:

Computational Biology
Genomics
Machine Learning

Background:

Single-cell RNA sequencing (scRNA-seq) generates complex gene expression data with inherent statistical structure.
Foundation models, like TranscriptFormer, leverage transformer architectures to create gene embeddings for various downstream tasks.
These deep learning approaches have achieved state-of-the-art (SOTA) results in cell-type classification, disease prediction, and cross-species analysis.

Purpose of the Study:

To investigate if SOTA performance can be achieved using computationally simpler methods than deep learning-based foundation models.
To evaluate the efficacy of interpretable pipelines based on normalization and linear methods for scRNA-seq data analysis.
To compare the performance of linear methods against foundation models, particularly on out-of-distribution tasks.

Main Methods:

Development of interpretable pipelines utilizing careful data normalization techniques.
Application of linear methods for analyzing gene expression data and generating representations.
Benchmarking against established single-cell foundation models across multiple datasets and tasks.

Main Results:

Simple, interpretable pipelines achieved SOTA or near-SOTA performance on common benchmarks for single-cell foundation models.
These linear methods outperformed foundation models on out-of-distribution tasks, including novel cell types and organisms.
The findings indicate that gene expression data can be effectively represented using linear models.

Conclusions:

Computationally intensive deep learning models may not be strictly necessary for achieving high performance in scRNA-seq data analysis.
Interpretable linear representations can capture significant biological information, including cell identity.
Rigorous benchmarking is crucial for evaluating the true capabilities and necessity of complex models in bioinformatics.