Table 1 Summary of the structure–property relationship data sets from PoLyInfo and QM9 and their classification by use

From: Machine-learning-assisted discovery of polymers with high thermal conductivity using a molecular design algorithm

Use

Database

Property

Number of structures

Number of samples

Max σ of within-polymer fluctuation

Range of temperature

CMD, TLλ

PoLyInfo

T g

5917

17,001

30 °C

N/A

CMD, TLλ

PoLyInfo

T m

3234

12,374

30 °C

N/A

TLλ

PoLyInfo

ρ

1516

8613

0.50 g/cm3

10–35 °C

TLλ

QM9

C V

133,805

133,885

0.97 cal/molK

25 °C

Post-screening

PoLyInfo

λ

28

322

0.10 W/mK

10–35 °C

  1. For the PoLyInfo data sets, only homopolymers that have linearly connected structures with no additives or fillers were selected: CMD, used for forward modelling in the molecular design calculation; post-screening, used for transfer learning to obtain a screening model of λ; TLλ, used to obtain pre-trained source models for transfer learning; σ, standard deviation; Tg glass transition temperature, Tm melting temperature