Predicting transcriptional changes induced by molecules with MiTCP.
Kaiyuan Yang1, Jiabei Cheng1, Shenghao Cao1
1Department of Automation, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang District, Shanghai 200240, China.
Briefings in Bioinformatics
|January 23, 2025
Summary
Researchers developed a deep learning method, Molecule-induced Transcriptional Change Predictor (MiTCP), to predict cellular transcriptional changes caused by molecules. This approach aids drug discovery by accurately forecasting gene expression alterations, outperforming existing methods.
Area of Science:
- Computational Biology
- Genomics
- Drug Discovery
Background:
- Understanding cellular responses to small molecules is vital for drug discovery.
- Experimental methods for profiling transcriptional changes are time-consuming and costly.
Purpose of the Study:
- To develop a deep learning model, MiTCP, for predicting molecule-induced transcriptional changes.
- To accurately forecast changes in transcriptional profiles (CTPs) of 978 landmark genes.
Main Methods:
- Utilized graph neural networks to model molecular structure and gene co-expression.
- Trained the MiTCP model on the L1000 dataset.
- Integrated molecular structure and gene relationships for CTP prediction.
Main Results:
- Achieved an average Pearson correlation coefficient (PCC) of 0.482 on the test set.
- Demonstrated high accuracy in predicting top differentially expressed genes (PCC of 0.801).
- Outperformed existing methods in CTP prediction.
Conclusions:
- MiTCP shows potential in accelerating drug development by predicting drug-induced gene expression changes.
- Enrichment analysis of predicted CTPs for cancer drugs revealed disease-relevant pathways.
- The method offers a faster and potentially more cost-effective alternative to experimental profiling.
Related Concept Videos
02:23Master Transcription Regulators
6.9K
Master transcription regulators are regulatory proteins that are predominantly responsible for regulating the expression of multiple genes. Often these genes work in concert to drive a complex process. Activation of a master transcription regulator can lead to a cascade of transcriptional activation necessary for that outcome. These regulators can directly bind to the regulatory sequences of the various genes involved, or they can indirectly regulate transcription by binding to regulatory...
6.9K
02:36Chromatin Immunoprecipitation- ChIP
11.0K
Chromatin immunoprecipitation, or ChIP, is an antibody-based technique used to identify sites on DNA that bind to transcription factors of interest or histone proteins. It also helps determine the type of histone modifications such as acetylation, phosphorylation, or methylation.
Types of ChIP
ChIP can be divided into two types - X-ChIP and N-ChIP. X-ChIP involves in vivo cross-linking of histones and regulatory proteins to DNA, fragmenting the DNA by sonication, and isolating the protein-DNA...
Types of ChIP
ChIP can be divided into two types - X-ChIP and N-ChIP. X-ChIP involves in vivo cross-linking of histones and regulatory proteins to DNA, fragmenting the DNA by sonication, and isolating the protein-DNA...
11.0K
02:33Combinatorial Gene Control
8.3K
Combinatorial gene control is the synergistic action of several transcriptional factors to regulate the expression of a single gene. The absence of one or more of these factors may lead to a significant difference in the level of gene expression or repression.
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
8.3K