Effectiveness of molecular fingerprints for exploring the chemical space of natural products (2024)

Boldini, D., Ballabio, D., Consonni, V., Todeschini, R., Grisoni, F. (2024). Effectiveness of molecular fingerprints for exploring the chemical space of natural products. Journal of Cheminformatics, 16(1), Article 35. https://doi.org/10.1186/s13321-024-00830-3

Boldini, Davide ; Ballabio, Davide ; Consonni, Viviana et al. / Effectiveness of molecular fingerprints for exploring the chemical space of natural products. In: Journal of Cheminformatics. 2024 ; Vol. 16, No. 1.

@article{8e087b4079704ecc8adcda77698cd1e9,

title = "Effectiveness of molecular fingerprints for exploring the chemical space of natural products",

abstract = "Natural products are a diverse class of compounds with promising biological properties, such as high potency and excellent selectivity. However, they have different structural motifs than typical drug-like compounds, e.g., a wider range of molecular weight, multiple stereocenters and higher fraction of sp3-hybridized carbons. This makes the encoding of natural products via molecular fingerprints difficult, thus restricting their use in cheminformatics studies. To tackle this issue, we explored over 30years of research to systematically evaluate which molecular fingerprint provides the best performance on the natural product chemical space. We considered 20 molecular fingerprints from four different sources, which we then benchmarked on over 100,000 unique natural products from the COCONUT (COlleCtion of Open Natural prodUcTs) and CMNPD (Comprehensive Marine Natural Products Database) databases. Our analysis focused on the correlation between different fingerprints and their classification performance on 12 bioactivity prediction datasets. Our results show that different encodings can provide fundamentally different views of the natural product chemical space, leading to substantial differences in pairwise similarity and performance. While Extended Connectivity Fingerprints are the de-facto option to encoding drug-like compounds, other fingerprints resulted to match or outperform them for bioactivity prediction of natural products. These results highlight the need to evaluate multiple fingerprinting algorithms for optimal performance and suggest new areas of research. Finally, we provide an open-source Python package for computing all molecular fingerprints considered in the study, as well as data and scripts necessary to reproduce the results, at https://github.com/dahvida/NP_Fingerprints.",

keywords = "Fingerprint, Natural products, Similarity, Supervised classification, Virtual screening",

author = "Davide Boldini and Davide Ballabio and Viviana Consonni and Roberto Todeschini and Francesca Grisoni and Sieber, {Stephan A.}",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = dec,

doi = "10.1186/s13321-024-00830-3",

language = "English",

volume = "16",

journal = "Journal of Cheminformatics",

issn = "1758-2946",

publisher = "Chemistry Central",

number = "1",

}

Boldini, D, Ballabio, D, Consonni, V, Todeschini, R, Grisoni, F 2024, 'Effectiveness of molecular fingerprints for exploring the chemical space of natural products', Journal of Cheminformatics, vol. 16, no. 1, 35. https://doi.org/10.1186/s13321-024-00830-3

Effectiveness of molecular fingerprints for exploring the chemical space of natural products. / Boldini, Davide; Ballabio, Davide; Consonni, Viviana et al.
In: Journal of Cheminformatics, Vol. 16, No. 1, 35, 12.2024.

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

TY - JOUR

T1 - Effectiveness of molecular fingerprints for exploring the chemical space of natural products

AU - Boldini, Davide

AU - Ballabio, Davide

AU - Consonni, Viviana

AU - Todeschini, Roberto

AU - Grisoni, Francesca

AU - Sieber, Stephan A.

N1 - Publisher Copyright:© The Author(s) 2024.

PY - 2024/12

Y1 - 2024/12

N2 - Natural products are a diverse class of compounds with promising biological properties, such as high potency and excellent selectivity. However, they have different structural motifs than typical drug-like compounds, e.g., a wider range of molecular weight, multiple stereocenters and higher fraction of sp3-hybridized carbons. This makes the encoding of natural products via molecular fingerprints difficult, thus restricting their use in cheminformatics studies. To tackle this issue, we explored over 30years of research to systematically evaluate which molecular fingerprint provides the best performance on the natural product chemical space. We considered 20 molecular fingerprints from four different sources, which we then benchmarked on over 100,000 unique natural products from the COCONUT (COlleCtion of Open Natural prodUcTs) and CMNPD (Comprehensive Marine Natural Products Database) databases. Our analysis focused on the correlation between different fingerprints and their classification performance on 12 bioactivity prediction datasets. Our results show that different encodings can provide fundamentally different views of the natural product chemical space, leading to substantial differences in pairwise similarity and performance. While Extended Connectivity Fingerprints are the de-facto option to encoding drug-like compounds, other fingerprints resulted to match or outperform them for bioactivity prediction of natural products. These results highlight the need to evaluate multiple fingerprinting algorithms for optimal performance and suggest new areas of research. Finally, we provide an open-source Python package for computing all molecular fingerprints considered in the study, as well as data and scripts necessary to reproduce the results, at https://github.com/dahvida/NP_Fingerprints.

AB - Natural products are a diverse class of compounds with promising biological properties, such as high potency and excellent selectivity. However, they have different structural motifs than typical drug-like compounds, e.g., a wider range of molecular weight, multiple stereocenters and higher fraction of sp3-hybridized carbons. This makes the encoding of natural products via molecular fingerprints difficult, thus restricting their use in cheminformatics studies. To tackle this issue, we explored over 30years of research to systematically evaluate which molecular fingerprint provides the best performance on the natural product chemical space. We considered 20 molecular fingerprints from four different sources, which we then benchmarked on over 100,000 unique natural products from the COCONUT (COlleCtion of Open Natural prodUcTs) and CMNPD (Comprehensive Marine Natural Products Database) databases. Our analysis focused on the correlation between different fingerprints and their classification performance on 12 bioactivity prediction datasets. Our results show that different encodings can provide fundamentally different views of the natural product chemical space, leading to substantial differences in pairwise similarity and performance. While Extended Connectivity Fingerprints are the de-facto option to encoding drug-like compounds, other fingerprints resulted to match or outperform them for bioactivity prediction of natural products. These results highlight the need to evaluate multiple fingerprinting algorithms for optimal performance and suggest new areas of research. Finally, we provide an open-source Python package for computing all molecular fingerprints considered in the study, as well as data and scripts necessary to reproduce the results, at https://github.com/dahvida/NP_Fingerprints.

KW - Fingerprint

KW - Natural products

KW - Similarity

KW - Supervised classification

KW - Virtual screening

UR - http://www.scopus.com/inward/record.url?scp=85188535382&partnerID=8YFLogxK

U2 - 10.1186/s13321-024-00830-3

DO - 10.1186/s13321-024-00830-3

M3 - Article

AN - SCOPUS:85188535382

SN - 1758-2946

VL - 16

JO - Journal of Cheminformatics

JF - Journal of Cheminformatics

IS - 1

M1 - 35

ER -

Boldini D, Ballabio D, Consonni V, Todeschini R, Grisoni F, Sieber SA. Effectiveness of molecular fingerprints for exploring the chemical space of natural products. Journal of Cheminformatics. 2024 Dec;16(1):35. doi: 10.1186/s13321-024-00830-3