Scleroderma Genes: New Insights from Exome Sequencing & AI
- A new study has identified novel genetic contributors to systemic sclerosis (SSc), also known as scleroderma, using advanced machine learning techniques.
- The team's findings were validated by collaborators in Spain, who replicated the results using European genome-wide association study (GWAS) data from nearly 10,000 cases.This replication underscores the importance...
- Olivier Lichtarge's lab at Baylor employed an evolutionary action-machine learning (EAML) framework to analyze exome sequencing data.
Groundbreaking research uses machine learning to uncover new genes linked to systemic sclerosis, a perilous form of scleroderma.Baylor College of Medicine’s study spotlights MICB and interferon pathway genes as potential therapeutic targets, validated by European GWAS data. Scientists leveraged evolutionary action-machine learning to analyze exome sequencing, identifying critical genetic variants. These scleroderma genes are expressed in cells central to fibrosis. The implications could reshape treatment approaches for this challenging autoimmune disease.News Directory 3 is following the progress. Discover what’s next in the ongoing quest to understand and combat scleroderma.
Machine Learning Pinpoints New Genes Contributing to Systemic Sclerosis Risk
Updated June 16, 2025
A new study has identified novel genetic contributors to systemic sclerosis (SSc), also known as scleroderma, using advanced machine learning techniques. The research, led by Baylor College of Medicine, highlights MICB and interferon pathway genes as potential therapeutic targets for this complex autoimmune disease.
The team’s findings were validated by collaborators in Spain, who replicated the results using European genome-wide association study (GWAS) data from nearly 10,000 cases.This replication underscores the importance of the initial discoveries.
Dr. Olivier Lichtarge’s lab at Baylor employed an evolutionary action-machine learning (EAML) framework to analyze exome sequencing data. This approach prioritized genes with high-impact variants predictive of SSc, revealing MICB, NOTCH4, and rare missense variants in interferon signaling genes such as IFI44L and IFIT5.
“With our machine learning framework, we are not only identifying whether a variant occurs frequently, but also, using evolutionary data across all species, we are weighing the likelihood the variant is functionally disruptive to the protein and eventually to the patient,” said Lichtarge, Cullen Chair and professor of molecular and human genetics, biochemistry and molecular biology and pharmacology.
Researchers integrated single-cell RNA sequencing data from SSc skin biopsies to understand the functional impact of the identified genetic variants.This allowed them to resolve cell type-specific expression patterns of risk genes. They also performed expression quantitative trait locus (eQTL) analysis using whole blood datasets to establish regulatory links between disease-associated variants and transcriptomic changes.
The study revealed that MICB and NOTCH4 are expressed in fibroblasts and endothelial cells, both of which play key roles in fibrosis and vasculopathy, which are central clinical features of SSc. These analyses confirmed the functional regulatory effects of the identified risk genes.
According to Dr.Shamika Ketkar, assistant professor of molecular and human genetics at Baylor, the identification of MICB represents a novel genetic contributor and a potential therapeutic target for systemic sclerosis.
“To solve complex diseases like SSc,we need to combine different approaches and machine learning to the analysis of large DNA,RNA and protein data sets to discover or else hidden targets for treatment,” said corresponding author Dr. Brendan lee, professor, chair and Robert and Janice McNair Endowed Chair of molecular and human genetics at Baylor.
What’s next
Further research will focus on validating MICB as a therapeutic target and exploring the potential of interferon pathway genes in treating systemic sclerosis.