Saltar al contenido
TakoAPI
Volver a skills

admet-prediction

por huifer

Browser & Automation
494Descargas según clawskills.sh
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) prediction for drug candidates.

Descripción

Qué hace esta skill

Predicts ADMET properties (Absorption, Distribution, Metabolism, Excretion, Toxicity) for drug candidates using ML/QSAR models. Takes molecular structures as SMILES or SDF files and returns property estimates with confidence scores. Covers drug-likeness rules, PK parameters, CYP interactions, and toxicity alerts including hERG and DILI.

Running predictions computationally before synthesis lets teams deprioritize compounds with poor PK or toxicity flags without spending lab resources on in vitro assays.

Cuándo usarla

  • Screening a compound library for hERG cardiotoxicity risk before synthesis
  • Checking oral bioavailability and Caco-2 permeability of a lead molecule
  • Identifying CYP3A4 inhibition liability in a clinical candidate
  • Filtering virtual compounds by Lipinski Ro5 and Veber rules
  • Predicting BBB permeability for CNS-targeted drug candidates

Flujo de trabajo de ejemplo

ENTRADA

User asks: /admet "CC1=CC=C(C=C1)CNC" --full

AGENTE
  1. 1

    Parse SMILES input and validate molecular structure

  2. 2

    Run ML/QSAR models across all ADMET property categories

  3. 3

    Apply drug-likeness filters (Lipinski Ro5, Veber, PAINS, Brenk)

  4. 4

    Score toxicity endpoints including hERG, DILI, and Ames mutagenicity

  5. 5

    Compile property table with confidence levels and flag concerns

SALIDA

Full ADMET profile table with absorption, distribution, metabolism, excretion, and toxicity predictions, plus a recommendations section listing strengths, concerns, and a go/no-go suggestion.

Instalación

clawhub install huifer/admet-prediction

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces