Journal of Cheminformatics 2019

7 papers
The 2019 edition of the Journal of Cheminformatics emphasized the application of machine learning to molecular discovery and chemical space exploration. A primary research theme involved Bayesian optimization, with studies focusing on accelerating discovery through expert priors and scaling optimization techniques beyond Gaussian processes. These methods were applied to tasks such as conformer generation and sample-efficient scientific discovery. Another prominent trend was the refinement of generative models for molecular design. Research explored the use of randomized SMILES strings to improve model quality and the application of deep generative models, including generative adversarial networks (GANs), to navigate the GDB-13 chemical space. Additionally, the journal featured work on molecular representation, such as combining structural and bioactivity-based fingerprints to enhance scaffold hopping capabilities. Automated tools also saw development, notably in rule-based functional group detection using the Chemistry Development Kit. Key contributors to these themes included Hongming Chen, Josep Arús‐Pous, and Esben Jannik Bjerrum.

Top Research Directions

The 11 research directions with Journal of Cheminformatics 2019 papers, ranked by paper count, next to 2017. Share is the fraction of the edition’s papers in the direction.

#Direction20192017Share 2019Share 20172017 rank
1Navigating the Combinatorial Complexity of Chemical Space3142.9%25.0%4
2Chemical Language Modeling for Molecular Discovery1014.3%0.0%—
3Classifier-Free Guidance for Steerable Molecular Design1014.3%0.0%—
4Equivalent String Augmentation for Chemical Language Models1014.3%0.0%—
5Fusing Graphs and Sequences for Molecular Representation1014.3%0.0%—
6Guiding Bayesian Optimization with Expert Priors1014.3%0.0%—
7Optimizing Expensive Black Box Functions with Probabilistic Surrogates1014.3%0.0%—
8Predicting Activity Cliffs in Chemical Property Landscapes1014.3%0.0%—
9Sample Efficient Optimization for High Cost Objectives1014.3%0.0%—
10Scaling Gaussian Processes Beyond Cubic Complexity1014.3%0.0%—
11Stabilizing Adversarial Networks with Wasserstein Distance and Gradient Penalties1014.3%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Journal of Cheminformatics 2019 papers: a paper credits every institution named in its affiliations, once. 4 institutions share 6 credited papers.

#InstitutionPapersShare20172017 rank
1AstraZeneca (United Kingdom) 350.0%21
2University of Bern 233.3%0—
3University of Pittsburgh 116.7%0—
4Westfälische Hochschule 116.7%0—

Download all institutions as CSV

About this data

Papers. Journal of Cheminformatics 2019 lists 7 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. Comparisons with 2017 use shares, since the edition went from 4 to 7 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 6 of 7 papers (85.7%) 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 2026-11-21 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Journal of Cheminformatics 2019”, https://lacuna.tiptreesystems.com/venue/journal-of-cheminformatics/2019.

Impactful Papers

Papers from Journal of Cheminformatics 2019 that shaped research clusters.

Foundational

Influential

Papers

Title
A de novo molecular generation method using latent vector based generative adversarial network
Bayesian optimization for conformer generation
Combining structural and bioactivity-based fingerprints improves prediction performance and scaffold hopping capability
Combining structural and bioactivity-based fingerprints improves prediction performance and scaffold hopping capability
ErtlFunctionalGroupsFinder: automated rule-based functional group detection with the Chemistry Development Kit (CDK)
Exploring the GDB-13 chemical space using deep generative models
Randomized SMILES strings improve the quality of molecular generative models