Response to Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”

Jesús G. Estrada; Derek T. Ahneman; Robert P. Sheridan; Spencer D. Dreher; Abigail G. Doyle

doi:10.1126/science.aat8763

Response to Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”

Jesús G. Estrada, Derek T. Ahneman, Robert P. Sheridan, Spencer D. Dreher, Abigail G. Doyle

Research output: Contribution to journal › Article › peer-review

48 Scopus citations

Abstract

We demonstrate that the chemical-feature model described in our original paper is distinguishable from the nongeneralizable models introduced by Chuang and Keiser. Furthermore, the chemical-feature model significantly outperforms these models in out-of-sample predictions, justifying the use of chemical featurization from which machine learning models can extract meaningful patterns in the dataset, as originally described.

Original language	English (US)
Article number	eaat8763
Journal	Science
Volume	362
Issue number	6416
DOIs	https://doi.org/10.1126/science.aat8763
State	Published - Nov 16 2018

All Science Journal Classification (ASJC) codes

General

Access to Document

10.1126/science.aat8763

Cite this

@article{bd96d0670a344f0a92e7425f003c4fdc,

title = "Response to Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”",

abstract = "We demonstrate that the chemical-feature model described in our original paper is distinguishable from the nongeneralizable models introduced by Chuang and Keiser. Furthermore, the chemical-feature model significantly outperforms these models in out-of-sample predictions, justifying the use of chemical featurization from which machine learning models can extract meaningful patterns in the dataset, as originally described.",

author = "Estrada, {Jes{\'u}s G.} and Ahneman, {Derek T.} and Sheridan, {Robert P.} and Dreher, {Spencer D.} and Doyle, {Abigail G.}",

note = "Publisher Copyright: {\textcopyright} 2017 The Authors.",

year = "2018",

month = nov,

day = "16",

doi = "10.1126/science.aat8763",

language = "English (US)",

volume = "362",

journal = "Science",

issn = "0036-8075",

publisher = "American Association for the Advancement of Science",

number = "6416",

}

TY - JOUR

T1 - Response to Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”

AU - Estrada, Jesús G.

AU - Ahneman, Derek T.

AU - Sheridan, Robert P.

AU - Dreher, Spencer D.

AU - Doyle, Abigail G.

PY - 2018/11/16

Y1 - 2018/11/16

N2 - We demonstrate that the chemical-feature model described in our original paper is distinguishable from the nongeneralizable models introduced by Chuang and Keiser. Furthermore, the chemical-feature model significantly outperforms these models in out-of-sample predictions, justifying the use of chemical featurization from which machine learning models can extract meaningful patterns in the dataset, as originally described.

AB - We demonstrate that the chemical-feature model described in our original paper is distinguishable from the nongeneralizable models introduced by Chuang and Keiser. Furthermore, the chemical-feature model significantly outperforms these models in out-of-sample predictions, justifying the use of chemical featurization from which machine learning models can extract meaningful patterns in the dataset, as originally described.

UR - http://www.scopus.com/inward/record.url?scp=85056574032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056574032&partnerID=8YFLogxK

U2 - 10.1126/science.aat8763

DO - 10.1126/science.aat8763

M3 - Article

C2 - 30442777

AN - SCOPUS:85056574032

SN - 0036-8075

VL - 362

JO - Science

JF - Science

IS - 6416

M1 - eaat8763

ER -

Response to Comment on “Predicting reaction performance in C–N cross-coupling using machine learning”

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this