Nature Reviews Chemistry 2022

5 papers
In 2022, Nature Reviews Chemistry featured research centered on the integration and standardization of machine learning within the chemical sciences. A primary theme was the expansion of machine learning applications beyond interatomic potentials to predict a broader range of molecular properties. This shift was supported by the introduction of formal evaluation guidelines for machine learning tools and the CACHE (Critical Assessment of Computational Hit-finding Experiments) initiative, a public–private partnership designed to benchmark computational hit-finding methods. Research also addressed systemic challenges in computational modeling, including the mitigation of reporting bias in discovery models and the use of unified benchmarking to isolate neural architectural gains. Prolific contributors such as Sergei Tretiak, Alexander I. Boldyrev, and Justin S. Smith published work emphasizing the necessity of rigorous testing and transparency. These efforts, alongside studies on molecular properties and hit-finding, reflect a trend toward refining computational frameworks to enhance the accuracy and reproducibility of chemical discovery models.

Top Research Directions

The 3 research directions with Nature Reviews Chemistry 2022 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Inference Time Self Correction Loops in Language Models120.0%
2Learning from Failed Experiments in Scientific Machine Learning120.0%
3Unified Evaluation Frameworks for Reproducible Machine Learning120.0%

Download all directions as CSV

Institutions

Institutions credited by Nature Reviews Chemistry 2022 papers: a paper credits every institution named in its affiliations, once. 2 institutions share 1 credited papers.

#InstitutionPapersShare
1Bayer (Germany) 1100.0%
2University of Toronto 1100.0%

Download all institutions as CSV

About this data

Papers. Nature Reviews Chemistry 2022 lists 5 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 1 of 5 papers (20.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Nature Reviews Chemistry 2022”, https://lacuna.tiptreesystems.com/venue/nature-reviews-chemistry/2022.

Top Authors

AuthorPapers
Ben Nebgen2
Robert A. Batey1
Takeharu Nagai1

Papers

Title
CACHE (Critical Assessment of Computational Hit-finding Experiments): A public–private partnership benchmarking initiative to enable the development of computational methods for hit-finding
Evaluation guidelines for machine learning tools in the chemical sciences
Extending machine learning beyond interatomic potentials for predicting molecular properties
Publisher Correction: Extending machine learning beyond interatomic potentials for predicting molecular properties
Tiny but bright