PandaOmics

PandaOmics performs integrative AI-driven analysis of multi-omics and literature data to identify biomarkers and prioritize therapeutic targets in disease contexts.

Key Features:

• AI-Driven Analysis: Employs advanced artificial intelligence algorithms to analyze gene expression changes across multiple datasets.
• Biomarker Identification: Identifies molecular biomarkers that stratify cancer patients by survival outcomes using gene expression data.
• Target Discovery: Discovers and prioritizes novel therapeutic targets supported by computational analyses and experimental validation.
• Data Integration: Integrates diverse omics datasets with existing scientific literature for comprehensive analyses.
• Expression Analysis: Performs differential gene expression analysis to identify genes altered in specific conditions or diseases.
• Survival Correlation: Correlates gene expression levels with patient survival outcomes across multiple cancer types.
• Target-ID Algorithm: Applies a target-ID algorithm to propose and rank candidate therapeutic targets.

Scientific Applications:

• Analysis of DNA repair-deficient disorders: Applied to rare DNA repair-deficient disorders to identify cancer predisposition markers, including downregulation of CEP135.
• CEP135 characterization: Identified CEP135, a protein linked to centriole biogenesis, as downregulated in high cancer-risk conditions and associated with prognosis.
• TCGA survival analysis: Evaluated CEP135 expression across 33 cancer types in the TCGA database and found low CEP135 levels associated with poor survival in sarcoma patients.
• Sarcoma target nomination: Used the platform to nominate polo-like kinase 1 (PLK1) as a therapeutic candidate for sarcoma patients with high CEP135 and poor survival.
• Oncology biomarker and target characterization: Supports rapid in silico discovery and characterization of biomarkers and targets in oncology.

Methodology:

Computational methods include AI-driven analysis of gene expression, integration of diverse omics datasets with scientific literature, differential expression analysis, correlation of gene expression with patient survival across cancer types, and use of the target-ID algorithm for target prioritization.