Preprint
Machine Learning
Featured

SwissADME: a free web tool to evaluate pharmacokinetics, drug-likeness and medicinal chemistry friendliness of small molecules

Antoine Daina(SIB Swiss Institute of Bioinformatics), Olivier Michielin(SIB Swiss Institute of Bioinformatics), Vincent Zoete(SIB Swiss Institute of Bioinformatics)
March 3, 2017Scientific Reports17,450 citations
PDFDOI

17k

Citations

561

Influential Citations

Scientific Reports

Venue

2017

Year

Abstract

To be effective as a drug, a potent molecule must reach its target in the body in sufficient concentration, and stay there in a bioactive form long enough for the expected biologic events to occur. Drug development involves assessment of absorption, distribution, metabolism and excretion (ADME) increasingly earlier in the discovery process, at a stage when considered compounds are numerous but access to the physical samples is limited. In that context, computer models constitute valid alternatives to experiments. Here, we present the new SwissADME web tool that gives free access to a pool of fast yet robust predictive models for physicochemical properties, pharmacokinetics, drug-likeness and medicinal chemistry friendliness, among which in-house proficient methods such as the BOILED-Egg, iLOGP and Bioavailability Radar. Easy efficient input and interpretation are ensured thanks to a user-friendly interface through the login-free website http://www.swissadme.ch. Specialists, but also nonexpert in cheminformatics or computational chemistry can predict rapidly key parameters for a collection of molecules to support their drug discovery endeavours.

Analysis

Why This Paper Matters

SwissADME addresses a critical bottleneck in drug discovery: the need for early assessment of absorption, distribution, metabolism, and excretion (ADME) properties when only computational models are feasible due to limited physical samples. By providing a free, user-friendly web tool, it democratizes access to sophisticated predictive models, enabling both specialists and non-experts to evaluate drug-likeness and pharmacokinetics rapidly. This has significant implications for reducing late-stage drug failures and accelerating the discovery pipeline.

The paper's high citation count (17,450) underscores its impact as a foundational resource in computational drug discovery. It bridges the gap between cheminformatics and practical drug development, making advanced predictions accessible to a broad audience.

Technical Contributions

  • BOILED-Egg: A method for predicting brain penetration and gastrointestinal absorption based on lipophilicity and polarity.
  • iLOGP: An in-house model for logP (lipophilicity) prediction, a key physicochemical property.
  • Bioavailability Radar: A visual tool for assessing drug-likeness across multiple parameters.
  • Integrated Platform: Combines multiple models into a single, efficient web interface with easy input and interpretation.
  • Free Access: No login required, lowering barriers for researchers worldwide.

Results

The abstract does not provide specific quantitative metrics, but the tool's widespread adoption (17,450 citations) and continued use in the drug discovery community serve as evidence of its practical utility. The models are described as "fast yet robust," suggesting validation against experimental data, though details are not in the abstract.

Significance

SwissADME has become a standard tool in computational drug discovery, enabling early-stage ADME screening for millions of compounds. Its impact extends beyond academia to pharmaceutical industry, where it supports lead optimization and reduces experimental costs. The tool's design philosophy—free, accessible, and user-friendly—has influenced subsequent web-based platforms in cheminformatics, promoting open science and reproducibility in drug development.

drug-discoveryadmepharmacokineticscheminformaticsweb-toolmachine-learningdrug-likeness

Related Papers