---
title: "Triage a compound series"
description: Rank a series by drug-likeness and ADMET before committing chemistry time to it.
tags:
  - recipes
  - screening
tools:
  - rdkit-admet-triage
  - compound-safety-admet
  - drug-safety-profile
generated: true
---

> **Try it in a guest chat**

> Rank a series by drug-likeness and ADMET before committing chemistry time to it. Every prompt below is verbatim from the curated quick-action
> chips, so it runs the real routing. Open one in a guest chat (no account
> needed), edit the compound or target, and send.

**Best fit:** rank a series by drug-likeness and ADMET before committing chemistry time to it.

## Try it — rdkit admet triage

**Try this prompt** — [open in a guest chat](/chat/new?guest=true&prompt=Fetch%20palbociclib%2C%20ribociclib%2C%20and%20abemaciclib%20from%20PubChem%2C%20calculate%20RDKit%20descriptors%20(MW%2C%20cLogP%2C%20TPSA%2C%20HBD%2C%20HBA%2C%20Fsp3%2C%20aromatic%20rings%2C%20rotatable%20bonds)%20for%20all%20three%20approved%20CDK4%2F6%20inhibitors%2C%20apply%20Lipinski%2C%20Veber%2C%20and%20Pfizer%203%2F75%20filters%2C%20run%20ADMET-AI%20for%20hERG%2C%20CYP3A4%20inhibition%2C%20and%20metabolic%20stability%2C%20and%20rank%20by%20multiparameter%20optimization%20score%20-%20which%20approved%20CDK4%2F6%20inhibitor%20has%20the%20best%20overall%20ADMET%20profile%20and%20which%20structural%20features%20explain%20the%20differences%3F).

> Fetch palbociclib, ribociclib, and abemaciclib from PubChem, calculate RDKit descriptors (MW, cLogP, TPSA, HBD, HBA, Fsp3, aromatic rings, rotatable bonds) for all three approved CDK4/6 inhibitors, apply Lipinski, Veber, and Pfizer 3/75 filters, run ADMET-AI for hERG, CYP3A4 inhibition, and metabolic stability, and rank by multiparameter optimization score - which approved CDK4/6 inhibitor has the best overall ADMET profile and which structural features explain the differences?

_Seeded from the rdkit-admet-triage quick-action chip — open it in a guest chat, then change the compound or target._

## Try it — compound safety admet

**Try this prompt** — [open in a guest chat](/chat/new?guest=true&prompt=Fetch%20sorafenib%20from%20PubChem%2C%20run%20DeepPurpose%20to%20predict%20kinome-wide%20off-targets%2C%20then%20dock%20sorafenib%20against%20the%20top%203%20predicted%20off-target%20kinase%20structures%20with%20DiffDock%20and%20run%20ADMET-AI%20for%20full%20safety%20profiling%20-%20load%20all%20kinase%20binding%20predictions%20into%20the%20sandbox%20and%20use%20seaborn%20to%20generate%20a%20kinome-wide%20selectivity%20heatmap%20with%20DiffDock-validated%20hits%20highlighted%2C%20flagging%20the%20off-target%20with%20the%20highest%20combined%20DeepPurpose%20affinity%20%C3%97%20DiffDock%20confidence%20as%20a%20safety%20liability%20or%20repurposing%20opportunity%3F).

> Fetch sorafenib from PubChem, run DeepPurpose to predict kinome-wide off-targets, then dock sorafenib against the top 3 predicted off-target kinase structures with DiffDock and run ADMET-AI for full safety profiling - load all kinase binding predictions into the sandbox and use seaborn to generate a kinome-wide selectivity heatmap with DiffDock-validated hits highlighted, flagging the off-target with the highest combined DeepPurpose affinity × DiffDock confidence as a safety liability or repurposing opportunity?

_Seeded from the compound-safety-admet quick-action chip — open it in a guest chat, then change the compound or target._

## Try it — drug safety profile

**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?

_Seeded from the drug-safety-profile quick-action chip — open it in a guest chat, then change the compound or target._

## Read next

- [Workflows](/docs/workflows) — every workflow and recipe.
- [Which tool?](/docs/which-tool) — match a single goal to a tool.
- [How the orchestrator picks tools](/docs/how-orchestration-works) — the same chain from a plain-language goal.