Drug Prediction and Molecular Docking Profiling for Idiopathic Pulmonary Fibrosis

A 9.5 KB dataset by Yongbin Wang, last updated April 23, 2026, containing results from a multi-omics study of idiopathic pulmonary fibrosis (IPF). The research integrated bulk and single-cell transcriptomic data from the Gene Expression Omnibus (GEO) with machine learning to identify candidate biomarkers CD247, IL7R, and RETN related to mitochondrial dynamics.

Use Cases

• Training diagnostic models based on the identified candidate biomarkers CD247, IL7R, and RETN.
• Predicting molecular docking interactions with selected compounds as suggested in the study.
• Analyzing immune infiltration profiles and regulatory networks involving transcription factors and non-coding RNAs.
• Validating single-cell expression patterns and pseudotime trajectories in monocyte-associated compartments.

Strengths

• Results are validated by RT-qPCR in an independent clinical cohort.
• Analysis employed 101 machine-learning model combinations, including random forest, LASSO, and SVM.
• The artificial neural network model achieved a training AUC of 0.91 and validation AUC of 0.82.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 9.5 KB, indicating limited scope.

Provenance

Source

figshare, with data derived from the Gene Expression Omnibus (GEO).

Collection Method

Integrated analysis of bulk transcriptomics, single-cell RNA sequencing, and literature-derived gene sets.

Time Range

null

Freshness

Last updated 2026-04-23 17:24:39; freshness should be verified.

Geography

null