Jacek Tabor, Agnieszka Pocha, Tomasz Danel, Sabina Podlewska, Łukasz Maziarka
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing new model architectures, and the importance of atom featurisation is oftentimes belittled. When contrasting two graph neural networks, the use of different atom features possibly leads to the incorrect attribution of the results to the network architecture. To provide a better understanding of this issue, we compare multiple atom representations for graph models and evaluate them on the prediction of free energy, solubility, and metabolic stability. To the best of our knowledge, this is the first methodological study that focuses on the relevance of atom representation to the predictive performance of graph neural networks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.04444")
get_code_for_paper("2012.04444")
have("2012.04444")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.04444.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.04444)
Connect an agent — have() is free.