# Draft Solution

Uploading my notebook and relevant files. I will try to write something up more fully when I get the time. Summary:
I've made two categories of models basic (only using SMILES given) and basic-plus (using SMILES plus Id number). Basic-plus (in my mind) has a fairly similar architecture to basic and
should
have performed similarly, if Id wasn't a significant factor. However, the best (and latest) basic model got a score of 0.08981 and the best (and the one on leaderboard #6) got a score of 0.11536--a fairly wide delta.
Basic-plus:
Leaderboard submission is basic-plus (notebook attached, relevant file
[https://drive.google.com/file/d/1rBCAxlrbaWF983gBckcPQW2BMtzel1jS/view?usp=sharing)](https://drive.google.com/file/d/1rBCAxlrbaWF983gBckcPQW2BMtzel1jS/view?usp=sharing))
.
Basic
The best basic model (0.08981) is a slight modification of the approach presented in the discussion post (
[https://www.kaggle.com/code/davidoloren/getting-score-0-11353-multi-representation-model/notebook](https://www.kaggle.com/code/davidoloren/getting-score-0-11353-multi-representation-model/notebook)
) which ended with a private score of 0.07443.
… I think the situation is very much complicated by noise in the underlying, and I would further share that to my knowledge the basic models are fairly representative of high-quality molecular property predictors, and similar models have scored very highly on the therapeutic data commons dataset