Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets
March 1st, 2024
Here, we introduce a protocol for converting transcriptomic data into a mqTrans view, enabling the identification of dark biomarkers. While not differentially expressed in conventional transcriptomic analyses, these biomarkers exhibit differential expression in the mqTrans view. The approach serves as a complementary technique to traditional methods, unveiling previously overlooked biomarkers.
Our research focuses on the intergenetic interactions of disease. We found that many genes have complex intertwined relationships with each other. By exploring these relationships, we aim in making more precise diagnosis in disease treatment and management.
We found that many dark biomarkers with traditional combinational methods ignored, are supported by many medical literatures. This indicates that approach can further assist biologists in reducing time cycle for biomarker screening. The biggest challenge during the experiment was addressing the issue of small sample sizes of different disease types.
To overcome this difficulty, we collected as many healthy samples as possible to train a reference model, which we called Health Model. To begin, create a new virtual environment named Health Model with Python version 3.7. in the Slurm Cluster supercomputing platform, execute the module load anaconda command.
Once the command is executed, a confirmation prompt appears on the screen. Enter Y to proceed and wait for the process to complete. Then activate the virtual environment following platform specific instructions.
Next, run the command to install PyTorch 1.13.1. Install additional packages for torch geometric, such as torch underscore scatter, torch underscore sparse, torch underscore cluster, and torch underscore spline underscore convulsion, following the installation guidelines. Then install the torch geometric package version 2.2.0.
Download the code and the pre-trained Health Model from the Health Informatics Lab website. Decompress the file to a desired path. Then change the working directory in the command line to the Health Model MQ trans folder.
Execute the command to generate MQ trans features and obtain the outputs. The MQ trans features will be generated as output MQ targets CSV, and the label file will be received as output label CSV. Additionally, original expression values of the MRNA genes will be extracted as file output test targets CSV.
Next, use the feature selection algorithm for selecting MQ trans features. If selecting MQ trans features or original features without combining them, set combine to false. Select 800 original features and split the dataset into 0.8 to 0.2 for training and testing.
To combine MQ trans features with the original expression values for feature selection, set combine to true. Dark biomarkers with differential MQ trans values, but undifferential mRNA expression were identified. Among 3, 062 features, 221 dark biomarkers were detected.
A general scarcity of dark biomarkers was observed in comparison to traditional biomarkers across most cancer types except BRCA, MESO, and TGCT.
Overview
This study addresses the intricate interactions among genes related to disease, focusing on the identification of dark biomarkers often overlooked by traditional methods. The proposed mqTrans view allows for a new understanding of these biomarkers, which exhibit differential expression compared to conventional transcriptomic analyses.
Key Study Components
Research Area
- Genetic interactions related to disease.
- Identification and analysis of biomarkers.
- Improvement of diagnostic approaches.
Background
- Genes show complex interdependencies in disease contexts.
- Conventional methods often miss dark biomarkers.
- Existing medical literature supports the prevalence of these biomarkers.
Methods Used
- Creation of a virtual environment named Health Model in Python.
- Utilization of a reference model trained on healthy samples.
- Implementation of feature selection algorithms for mqTrans features.
Main Results
- Identification of 221 dark biomarkers from 3,062 features.
- Dark biomarkers showed differential mqTrans values but not differential mRNA expression.
- The approach successfully highlighted shortcomings in traditional biomarker detection.
Conclusions
- The study provides a novel methodology for unraveling dark biomarkers.
- This approach could enhance biomarker screening efficiency and accuracy.
Frequently Asked Questions
Executive Industry Relevance
Integrating multitask graph-attention networks with transcriptomic data enables detection of regulatory features and dark biomarkers that traditional differential expression analyses overlook. This approach enhances predictive confidence in early discovery by revealing hidden regulatory signals, supporting more robust target validation and risk-adjusted portfolio decisions. The HealthModel framework addresses small dataset challenges, expanding the utility of transcriptomic profiling in biopharma R&D pipelines.
Strategic Applications in Biopharma R&D
Early Discovery & Target Validation
- Enables interrogation of complex inter-genic regulatory networks for functional target validation.
- Supports biological de-risking by uncovering dark biomarkers missed by standard analyses.
- Improves predictive confidence for target selection and triage in small-sample contexts.
Screening & Assay Development
- Generates quantitative mqTrans features for standardized downstream screening workflows.
- Facilitates reproducible feature selection and assay readiness by combining regulatory and expression data.
- Enables scalable identification of novel biomarker candidates for compound evaluation.
Translational & Preclinical Research
- Aligns transcriptomic regulatory features with disease-relevant systems for translational continuity.
- Supports risk-adjusted advancement by integrating dark biomarker detection into preclinical models.
- Provides mechanistic de-risking through regulatory network analysis.
Pipeline & Workflow Integration
The HealthModel and mqTrans workflow bridges early discovery, target validation, and preclinical research by generating regulatory feature views from transcriptomic data.
- Discovery Biology: Supports hypothesis testing and pathway clarification via regulatory network modeling.
- Screening: Delivers reproducible, quantitative mqTrans outputs for robust assay development.
- Analytics: Provides statistical outputs and feature selection for comparing regulatory and expression-based biomarkers.
- Translational Research: Enables continuity from discovery to preclinical validation by identifying disease-relevant regulatory features.
- Enterprise Reuse: Offers a reusable computational pipeline adaptable to diverse transcriptomic datasets.
Operational & Enterprise Impact
- Scientific Value: Increases predictive confidence and reduces mechanistic ambiguity in biomarker discovery.
- Operational Value: Standardizes regulatory feature extraction and supports reproducibility across datasets.
- Strategic Value: Improves go/no-go decisions and capital efficiency by revealing hidden regulatory signals.
- Portfolio Impact: Enables risk-adjusted prioritization by integrating dark biomarker detection into pipeline decisions.
Implementation Considerations
- Requires expertise in computational biology and transcriptomic data analysis.
- Needs access to Python, PyTorch, and torch geometric infrastructure for model execution.
- Demands cross-team standardization for feature selection and data preprocessing.
- Adaptable to various disease models but dependent on healthy reference sample availability.
- Limited by small sample sizes and the need for robust computational resources.
