Predicting ...

Welcome to Co.PolymerGenome.org

Your ultra-fast copolymer property predictor on the web

We use three multitask deep neural networks to predict the thermal, mechanical, and gas permeability properties of polymers. Polymer structures are represented as SMILES strings that use two stars to indicate the two endpoints of the repetitive unit of the polymers, but otherwise follow the SMILES syntax. See PolymerGenome Guide and OpenSmiles for more information. The shaded bands represent $1\sigma$ uncertainty estimates using Monte Carlo dropouts.

Thermal Properties

$T_\text{g}$
Glass transition temperature
$T_\text{m}$
Melting temperature
$T_\text{d}$

Mechanical Properties

$E$
Young's modulus
$\sigma_\text{y}$
Tensile strength at yield
$\sigma_\text{b}$
Tensile strength at break
$\epsilon_\text{b}$
Elongation at break

Gas Permeabilities

$\mu_{\text{O}_2}$
O$_2$
$\mu_{\text{N}_2}$
N$_2$
$\mu_{\text{He}}$
He
$\mu_{\text{CO}_2}$
CO$_2$
$\mu_{\text{H}_2}$
H$_2$
$\mu_{\text{CH}_4}$
CH$_4$