TellWell
← Back to feed
Publications4h ago82% confidenceConfidence 82% — the share of independent, credible sources corroborating the core facts.

New Deep Learning Model SPLAIRE Improves Prediction of Splice Site Usage in Human Genes

Center 100%
1 source

Researchers developed SPLAIRE, a deep learning model trained on airway epithelial cell data that better predicts which splice sites are used in gene splicing, particularly for low-usage and tissue-specific sites. Alternative splicing affects over 95% of human protein-coding genes and is a major driver of disease, but existing models have gaps in identifying certain splice sites. The improved predictions could help identify genetic variants that cause disease by altering splicing patterns.

Scientists have created SPLAIRE, a dilated convolutional neural network trained on RNA and genotyping data from 100 human airway epithelial cell donors, to improve prediction of splice site usage. While existing deep learning models show near-perfect overall performance in identifying splice sites, they have substantial gaps—particularly in detecting low-usage splice sites and tissue-specific variants. The new model outperforms current state-of-the-art approaches on splice site identification and usage quantification, and demonstrates effectiveness across multiple tissues beyond those used in training. This work represents the most comprehensive evaluation of splicing prediction models to date and reveals both the strengths of current approaches and important directions for future development in understanding how genetic variants affect splicing and disease.

What's missing

The study's own limitations and caveats are not detailed in the provided abstract, such as: specific performance metrics (sensitivity, specificity, AUC values), the size of validation datasets, computational requirements, or availability of the model for public use. Additionally, the timeline for when this research will be published in a peer-reviewed journal is not specified.

What different sources said

  • bioRxivCenter

    Improving splice site usage prediction with SPLAIRE

Related

PublicationsConfidence 82% — the share of independent, credible sources corroborating the core facts.

Study finds cerebral blood vessel oscillations are self-generated, not driven by systemic blood pressure

Researchers observed that rhythmic oscillations in brain blood vessel diameter persist during cardiopulmonary bypass surgery when systemic blood pressure oscillations are absent, suggesting the brain generates these oscillations independently. The study involved 14 surgical patients and measured vaso-oscillations at approximately 0.1 Hz frequency. This finding challenges the understanding of how blood flow and fluid transport are regulated in the brain.

1 source1h ago
PublicationsConfidence 82% — the share of independent, credible sources corroborating the core facts.

New Framework Addresses Missing Data in Space Biology Research Using NASA RR9 Mission Data

Researchers have developed a systematic four-stage imputation framework to handle incomplete datasets from space biology experiments, demonstrated using retinal imaging and omics data from NASA's RR9 mission. Space biology studies are inherently limited by small sample sizes and logistical constraints, making missing data a significant obstacle to building reliable computational models of how the human body responds to spaceflight. The framework is important because it provides practical guidance for preserving biological signals while quantifying trade-offs, though it reveals that imputation can simultaneously improve predictive performance and obscure subtle biological patterns.

1 source1h ago
PublicationsConfidence 82% — the share of independent, credible sources corroborating the core facts.

OMIO: New Python Library Standardizes Microscopy Image Data Handling

Researchers have developed OMIO, a Python library that standardizes how microscopy images and their metadata are read and processed across different file formats and microscope systems. The tool addresses a longstanding problem in microscopy workflows where different file formats and reader software often introduce errors, metadata loss, or require custom workaround code. This standardization could improve reproducibility and reduce errors in microscopy-based research across biology, medicine, and materials science.

1 source1h ago