Table 2_Integrated machine learning, molecular dynamics, and density functional theory app

3576 antibacterial compounds were evaluated for drug-like properties to find inhibitors for TEM beta-lactamase enzymes in E. coli. Aditi Roy published the results on figshare in May 2026, identifying a lead compound with high binding affinity. The dataset likely contains the shortlisted 55 compounds and their associated computational analysis scores.

Use Cases

• Training ML models for virtual screening based on described drug-likeness and toxicity criteria
• Benchmarking molecular docking scores based on the reported binding affinities for TEM-1 and TEM-235
• Analyzing structure-activity relationships based on the H-bonding and intermolecular interactions mentioned
• Prioritizing lead compounds for experimental validation based on the described molecular dynamics and DFT analysis results

Strengths

• Includes results from a multi-method computational pipeline (machine learning, molecular docking, MD simulations, DFT) as described
• Focuses on a specific, high-impact biological target (TEM beta-lactamase in E. coli)
• Applies clear filtering criteria, starting from 3576 compounds and shortlisting 55 based on drug-likeness and non-toxicity

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• The 36.2 KB file size suggests a very limited scope, likely containing summary results rather than raw screening data

Provenance

Source

figshare

Collection Method

Computational screening and analysis of compound libraries as described in the study summary.

Freshness

Last updated 2026-05-20 05:47:56; freshness should be verified