Journal article · 2023 · Open access

Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets

Ganesh Chandan Kanakala, Rishal Aggarwal, Divya Nayar, U. Deva Priyakumar

ACS Omega, 8(2), 2389–2397 · Published 5 January 2023 · DOI 10.1021/acsomega.2c06781

Open PDFView at the publisherCite this paper

In brief

“Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets” is a 2023 journal article by Ganesh Chandan Kanakala and 3 co-authors, published in ACS Omega. OpenAlex counts 44 citations as of 20 November 2026, which puts it in the top 3% of works published in 2023 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at ACS Omega.

Citations
44
Most cited in
2026 (20)
Field-weighted impact
3.41
References
38
Authors
4

Abstract

Drug design involves the process of identifying and designing molecules that bind well to a given receptor. A vital computational component of this process is the protein-ligand interaction scoring functions that evaluate the binding ability of various molecules or ligands with a given protein receptor binding pocket reasonably accurately. With the publicly available protein-ligand binding affinity data sets in both sequential and structural forms, machine learning methods have gained traction as a top choice for developing such scoring functions. While the performance shown by these models is optimistic, there are several hidden biases present in these data sets themselves that affect the utility of such models for practical purposes such as virtual screening. In this work, we use published methods to systematically investigate several such factors or biases present in these data sets. In our analysis, we highlight the importance of considering sequence, protein-ligand interaction, and pocket structure similarity while constructing data splits and provide an explanation for good protein-only and ligand-only performances in some data sets. Through this study, we provide to the community several pointers for the design of binding affinity predictors and data sets for reliable applicability.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Kanakala, G. C., Aggarwal, R., Nayar, D., & Priyakumar, U. D. (2023). Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets. ACS Omega, 8(2), 2389–2397. https://doi.org/10.1021/acsomega.2c06781

MLA 9

Kanakala, Ganesh Chandan, et al. “Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets.” ACS Omega, vol. 8, no. 2, 2023, pp. 2389–2397. https://doi.org/10.1021/acsomega.2c06781.

Chicago

Kanakala, Ganesh Chandan, Rishal Aggarwal, Divya Nayar, and U. Deva Priyakumar. 2023. “Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets.” ACS Omega 8 (2): 2389–2397. https://doi.org/10.1021/acsomega.2c06781.

Harvard

Kanakala, G. C. et al. (2023) ‘Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets’, ACS Omega, 8(2), pp. 2389–2397. doi:10.1021/acsomega.2c06781.

IEEE

G. C. Kanakala, R. Aggarwal, D. Nayar, and U. D. Priyakumar, “Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets,” ACS Omega, vol. 8, no. 2, pp. 2389–2397, 2023, doi: 10.1021/acsomega.2c06781.

BibTeX

@article{kanakala2023latent,
  title     = {{Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets}},
  author    = {Kanakala, Ganesh Chandan and Aggarwal, Rishal and Nayar, Divya and Priyakumar, U. Deva},
  journal   = {ACS Omega},
  year      = {2023},
  volume    = {8},
  number    = {2},
  pages     = {2389--2397},
  doi       = {10.1021/acsomega.2c06781},
  url       = {https://doi.org/10.1021/acsomega.2c06781}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202355
20241212
202577
20262020

Its field-weighted citation impact is 3.41: it has been cited 3.41 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods

  • protein-ligand binding affinity prediction
  • virtual screening
  • data splits
  • sequence similarity
  • drug design

Work with this paper

Most-cited papers in Pharmacology, Toxicology and Pharmaceutics

All highly cited Pharmacology, Toxicology and Pharmaceutics papers

Questions about this paper

How do I cite this paper in APA style?

Kanakala, G. C., Aggarwal, R., Nayar, D., & Priyakumar, U. D. (2023). Latent Biases in Machine Learning Models for Predicting Binding Affinities Using Popular Data Sets. ACS Omega, 8(2), 2389–2397. https://doi.org/10.1021/acsomega.2c06781

How many times has this paper been cited?

44 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at ACS Omega: sign in and open the PDF from this page.

Who wrote this paper?

Ganesh Chandan Kanakala, Rishal Aggarwal, Divya Nayar, U. Deva Priyakumar.

What is the DOI of this paper?

10.1021/acsomega.2c06781, permanently at https://doi.org/10.1021/acsomega.2c06781. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.