The Evolution of Data-Driven Modeling in Organic Chemistry

Abstract

Organic chemistry is replete with complex relationships: for example, how a reactant’s structure relates to the resulting product formed; how reaction conditions relate to yield; how a catalyst’s structure relates to enantioselectivity. Questions like these are at the foundation of understanding reactivity and developing novel and improved reactions. An approach to probing these questions that is both longstanding and contemporary is data-driven modeling. Here, we provide a synopsis of the history of data-driven modeling in organic chemistry and the terms used to describe these endeavors. We include a timeline of the steps that led to its current state. The case studies included highlight how, as a community, we have advanced physical organic chemistry tools with the aid of computers and data to augment the intuition of expert chemists and to facilitate the prediction of structure–activity and structure–property relationships.

Harvesting the fragment-based nature of bifunctional organocatalysts to enhance their activity

“…9,10 Computational approaches help in identifying structural aspects pertinent to reactivity and inform the design of improved catalysts. [11][12][13][14][15][16] A strategy popularized by Sigman and co-workers is to correlate physical organic descriptors to experimental activity or selectivity outcomes via multivariate regression analysis. [17][18][19][20][21][22][23][24][25] not fully exploit the fragment-based nature of organocatalysts and has limited transferability because, when even small modifications on part of the catalyst are made, its entire structure must be re-optimized and the parameters collected.…”

“…9,10 Computational approaches help in identifying structural aspects pertinent to reactivity and inform the design of improved catalysts. 11–16 A strategy popularized by Sigman and co-workers is to correlate physical organic descriptors to experimental activity or selectivity outcomes via multivariate regression analysis. 17–25 When applied to organocatalysts, the descriptors are typically evaluated on the catalyst structure as a whole or, occasionally, from truncated versions of it.…”

Guidelines for Machine Learning Yield Prediction from Small-Size Literature Dataset

“…3B, while HTE data cover a narrow and homogeneous chemical space (Fig. 2A and 1A-B) and are devoid of experimental and reporting bias 13,24,31,32 . Unlike published reaction data, HTE systematically reports yields for all reactions including low yields, and is comprised of reactions performed in the same experimental settings.…”

Molecular field analysis for data-driven molecular design in asymmetric catalysis

“…Machine learning-based data-driven approaches have attracted tremendous interest recently due to their potential to change the conventional reaction development processes. 1 Although classification 2 and clustering 3 techniques have been applied to analyze molecular catalysis/reactivities of transition metal complexes, regression analysis between reaction outcomes ( e.g. , enantioselectivity) and molecular descriptors is one of the central foci in data-driven approaches for the design and optimization of molecular catalysis.…”