---
title: Head-to-head safety comparison
description: >-
  Compare two or three drugs on off-targets, real-world adverse-event signals,
  and pharmacogenomics in one pass.
tags:
  - recipes
  - admet
  - safety
tools:
  - admet_ai
  - deeppurpose
  - faers
  - pharmgkb
time: 2–5 min
---

**Best fit:** you have two or three compounds in the same class and want to know which has the cleaner safety profile — and whether the prediction explains the clinical difference.

**Try this prompt** — [open in a guest chat](/chat/new?guest=true&prompt=Look%20up%20methotrexate%20in%20FAERS%20for%20real-world%20adverse%20event%20signals%20(PRR%2FROR)%20and%20cross-reference%20OpenFDA%20adverse%20event%20counts%2C%20then%20fetch%20methotrexate%20from%20PubChem%20and%20run%20ADMET-AI%20%2B%20DeepPurpose%20to%20predict%20off-target%20binding%20that%20could%20explain%20the%20disproportionate%20signals%20-%20load%20FAERS%20signal%20data%20into%20the%20sandbox%20and%20use%20plotly%20to%20build%20an%20interactive%20volcano%20plot%20of%20PRR%20vs%20case%20count%20with%20predicted%20off-target%20annotations%2C%20flagging%20signals%20that%20exceed%20labeled%20warnings%20as%20candidates%20for%20safety%20label%20updates%3F).

> Look up methotrexate in FAERS for real-world adverse event signals (PRR/ROR) and cross-reference OpenFDA adverse event counts, then fetch methotrexate from PubChem and run ADMET-AI + DeepPurpose to predict off-target binding that could explain the disproportionate signals - load FAERS signal data into the sandbox and use plotly to build an interactive volcano plot of PRR vs case count with predicted off-target annotations, flagging signals that exceed labeled warnings as candidates for safety label updates?

_A real `drug-safety-profile` quick-action prompt — open it in a guest chat, then swap in your own compound or target._

## The prompt

```text
Compare gefitinib, erlotinib, and osimertinib head-to-head on safety — CYP
inhibition, hERG cardiotoxicity, oral bioavailability, the kinome-wide
off-target panel for each, and any real-world adverse-event signals when
patients are on these EGFR inhibitors. Pull the CYP-mediated pharmacogenomic
guidelines and tell me which compound has the cleanest safety profile, plus
whether the predicted ADMET explains the differential clinical toxicity we
actually see.
```

## What it does

The orchestrator runs each compound through the same safety panel and lines the results up side by side:

1. **[ADMET-AI](/docs/admet-ai)** predicts CYP inhibition, hERG liability, and oral bioavailability.
2. **[DeepPurpose](/docs/deeppurpose)** maps the kinome-wide off-target panel.
3. **FAERS** surfaces real-world adverse-event signals with disproportionality analysis.
4. **PharmGKB** pulls the CYP-mediated pharmacogenomic guidelines.

## Watch for

- **Prediction versus observation.** A predicted off-target is a hypothesis; the value is when it *explains* a real-world FAERS signal. Ask for that link explicitly, as the prompt does.
- **Class matters.** Head-to-head comparison is most informative within one mechanism (here, EGFR inhibitors) — cross-class comparisons need more care.
- **Signal ≠ causation.** FAERS disproportionality flags associations, not proven mechanisms.

## Read next

- [Safety assessment](/docs/workflows/safety-assessment) — the guided version: toxicity prediction and adverse-event analysis step by step.
- [Which tool?](/docs/which-tool#admet-and-safety) — solubility, toxicity, and safety alternatives.
- [What a passport is](/docs/passports-explained) — the [Safety passport](/docs/passports/safety) assembles this for a single drug.
- [How the orchestrator picks tools](/docs/how-orchestration-works) — the same chain from a plain-language safety question.