Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 8, 2026

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

DrugPTM-Bench: A Large-Scale Dataset for Predictive Modeling of Drug-Induced Cell Type-Specific Protein

Amitesh Badkul¹, Mohammadsadeq Mottaqi², Li Xie³

¹Computer Science, The Graduate Center, CUNY, 365 Fifth Avenue, New York City, New York, USA.

Biorxiv : the Preprint Server for Biology

|May 7, 2026

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Sequence-based Drug-Target Binding Site Pretraining Enables Cryptic Pocket Detection and Improves Binding Affinity and Kinetics Prediction.

bioRxiv : the preprint server for biology·2026

Same author

A Scalable Sign-Aware Multi-Omics Knowledge Graph Foundation Model for Mechanistic Drug Action and Clinical Response Predictions.

bioRxiv : the preprint server for biology·2026

Same author

Terazosin drives sex-dependent adrenergic-bioenergetic reprogramming to restore network function in Alzheimer's disease.

bioRxiv : the preprint server for biology·2026

Same author

Multimodal out-of-distribution individual uncertainty quantification enhances binding affinity prediction for polypharmacology.

Nature machine intelligence·2026

Same author

Integrating explainable artificial intelligence with multiomics systems biology and electronic health record data mining for personalized drug repurposing in Alzheimer's disease.

Briefings in bioinformatics·2025

Same author

Cross-level Cross-Scale Inference and Imputation of Single-cell Spatial Proteomics.

Research square·2025

This summary is machine-generated.

This study introduces DrugPTM-Bench, a new dataset for predicting drug-induced protein modifications. It highlights challenges in current models for understanding drug mechanisms of action (MoA) and target engagement.

Area of Science:

Biochemistry and Molecular Biology
Computational Biology and Bioinformatics
Pharmacology

Background:

Protein post-translational modifications (PTMs), especially phosphorylation, are crucial for cellular signaling and drug response.
Dysregulation of PTMs is linked to diseases like cancer and neurodegeneration.
Existing PTM datasets lack standardization and fail to capture context-dependent, drug-induced changes.

Purpose of the Study:

To develop DrugPTM-Bench, a large-scale, standardized benchmark dataset for drug-perturbed PTMs.
To enable the development of predictive models for context-aware PTM responses.
To facilitate deciphering drug Mechanism of Action (MoA) and target engagement.

Main Methods:

Curated a benchmark dataset from decryptM-derived PTM measurements across 7 cancer cell lines and 27 drugs.

Related Experiment Videos

Last Updated: May 8, 2026

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization

Published on: October 3, 2025

Included dose-dependent and time-resolved PTM data, encompassing 11,167 proteins.

Formulated a classification task to identify PTM site regulation (upregulated, downregulated, unchanged) and retained pEC50 values.

Main Results:

Baseline machine learning and deep learning models struggled with imbalanced PTM regulation classes in an out-of-distribution setting.
Standard rebalancing strategies improved recall but reduced precision and overall F1-score.
Current models lack robust decision boundaries for PTM event regulation.

Conclusions:

DrugPTM-Bench provides a critical phosphoproteomics resource for modeling drug-induced PTM regulation in complex biological contexts.
The dataset supports multi-task learning for drug potency regression and MoA prediction.
Establishes a framework for developing robust, context-aware models for PTM-centric drug discovery and elucidating drug MoA.