Review for: Assessing Conformer Energies using Electronic Structure and Machine Learning Methods
This is a follow-on paper from the Hutchison group, expanding on some previous work looking at correlations of molecular energy from a variety of levels of theory with results from high-level ab initio calculations. A new addition in this paper is a small set of ML methods, a welcome addition to the forcefield and electronic structure methods usually used in comparisons of this kind.
The paper presents some interesting results, but is riddled with missing or misattributed data, typos, grammatical errors (particularly agreements for single and plural nouns) and errors in the references. The paper should be carefully corrected before resubmission.
The key omission in the paper is any attempt to provide confidence in the deductions made about the differences in accuracy between the methods compared. Confidence intervals on each of the estimators, estimates of success rates and their errors, and pairwise hypothesis tests, at a minimum, must be added before publication. With this data in hand the new version can make quantitative estimates of the differences between the methods.