OpenADMET AHR Induction: Aryl Hydrocarbon Receptor Reporter Assay Screen of 11,360 Compounds with Dose-Response Follow-Up

Provider
OpenADMET, Octant Bio
License
CC-BY-4.0 (source)
Size
5 files
Format
CSV (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/openadmet/ahr-induction)
Access
Free and public. No account with the data provider is needed.
Category
Drug Discovery
Source
https://huggingface.co/datasets/openadmet/ahr-induction

About this dataset

Experimental measurements of aryl hydrocarbon receptor (AHR) activation by small molecules, produced by OpenADMET from Octant Bio cell-based reporter assays. AHR is a ligand-activated transcription factor whose agonists induce CYP1A1, CYP1A2 and CYP1B1, so activation matters for drug-drug interactions and off-target toxicity. The release has three tiers from one screening campaign: a single-concentration primary screen (34,024 rows, 11,360 compounds at about 0.83, 8.25 and 33 uM, read out as log2 fold change in reporter signal with standard error, confidence interval, p-value, Benjamini-Hochberg FDR and Cohen's d), a nine-dose dose-response follow-up of 1,001 compounds with fitted pEC50, Emax, slope and their uncertainties, and a counter-screen of 974 compounds. Compounds are identified by OCNT ID and batch with SMILES, and the column layout matches the OpenADMET PXR challenge files so the same code reads both. Use it for AHR agonist prediction, nuclear receptor activation and ADMET toxicity modeling; load with pandas. License CC BY 4.0 (OpenADMET). Cite OpenADMET and Octant Bio.

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/openadmet/ahr-induction/ahr_counter_screen.csv")
df.head()

Data structure

File types in sampled files: CSV

Files

Example file: ahr_counter_screen.csv

Analyze this dataset without downloading it

On Scigantic, OpenADMET AHR Induction: Aryl Hydrocarbon Receptor Reporter Assay Screen of 11,360 Compounds with Dose-Response Follow-Up opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Drug Discovery datasets