CoChat
Sign Up
Cited by 551Computational Drug Discovery MethodsMicrobial Natural Products and BiosynthesisMachine Learning in Materials Science

The DOI matches its Crossref record; 69 of the 70 references it cites were found in a registry or an index.

NPClassifier: A Deep Neural Network-Based Structural Classification Tool for Natural Products

Open access
Kim, Hyun Woo, Wang, Mingxun, Leber, Christopher A., Nothias, Louis-Félix, Reher, Raphael, Kang, Kyo Bin, van der Hooft, Justin J. J., Dorrestein, Pieter C., Gerwick, William H., Cottrell, Garrison W.·2021·Journal of Natural Products
DOI 10.1021/acs.jnatprod.1c00399PMC PMC8631337

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Computational approaches such as genome and metabolome mining are becoming essential to natural products (NPs) research. Consequently, a need exists for an automated structure-type classification system to handle the massive amounts of data appearing for NP structures. An ideal semantic ontology for the classification of NPs should go beyond the simple presence/absence of chemical substructures, but also include the taxonomy of the producing organism, the nature of the biosynthetic pathway, and/or their biological properties. Thus, a holistic and automatic NP classification framework could have considerable value to comprehensively navigate the relatedness of NPs, and especially so when analyzing large numbers of NPs. Here, we introduce NPClassifier, a deep-learning tool for the automated structural classification of NPs from their counted Morgan fingerprints. NPClassifier is expected to accelerate and enhance NP discovery by linking NP structures to their underlying properties.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1021/acs.jnatprod.1c00399

Cites

69 of 69 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Structures of typical (cedrone) and highly modified (cipadonoid B and quivisianone) limonoids.
Figure 1 Structures of typical (cedrone) and highly modified (cipadonoid B and quivisianone) limonoids.CC BY-NC-ND · PubMed Central
Figure 2 Overview of NPClassifier. (A) In the data preparation stage, compound names and their class information were collected from the literature. The compound names were converted to chemical fingerprints, and class information was assigned based on the NPClassifier ontology. During the training phase, molecular fingerprints were input to a deep neural network. Binary cross-entropy loss was calculated by comparison between the prediction result from the sigmoid outputs and the ground truth and back-propagated to adjust the model parameters. In classification, a submitted chemical structure is classified by NPClassifier at three levels, including Pathway, Superclass, and Class. (B) Classification result of a highly modified limonoid, cipadonoid B, by NPClassifier and ClassyFire. NPClassifier returns the classification result with three category levels including Pathway, Superclass, and Class, which are based on the semantic knowledge of natural product research.
Figure 2 Overview of NPClassifier. (A) In the data preparation stage, compound names and their class information were collected from the literature. The compound names were converted to chemical fingerprints, and class information was assigned based on the NPClassifier ontology. During the training phase, molecular fingerprints were input to a deep neural network. Binary cross-entropy loss was calculated by comparison between the prediction result from the sigmoid outputs and the ground truth and back-propagated to adjust the model parameters. In classification, a submitted chemical structure is classified by NPClassifier at three levels, including Pathway, Superclass, and Class. (B) Classification result of a highly modified limonoid, cipadonoid B, by NPClassifier and ClassyFire. NPClassifier returns the classification result with three category levels including Pathway, Superclass, and Class, which are based on the semantic knowledge of natural product research.CC BY-NC-ND · PubMed Central
Figure 3 Example of the classification ontology of NPClassifier. (A) Amino acids–peptides Pathway and its Superclasses and Classes in the NPClassifier classification system. This Pathway contains 12 Superclasses and 51 Classes. (B) The macrolides Superclass is involved in both polyketides and amino acids–peptides Pathways. (C) The peptide alkaloids Superclass and its Classes belong to both alkaloids and amino acids–peptides Pathways.
Figure 3 Example of the classification ontology of NPClassifier. (A) Amino acids–peptides Pathway and its Superclasses and Classes in the NPClassifier classification system. This Pathway contains 12 Superclasses and 51 Classes. (B) The macrolides Superclass is involved in both polyketides and amino acids–peptides Pathways. (C) The peptide alkaloids Superclass and its Classes belong to both alkaloids and amino acids–peptides Pathways.CC BY-NC-ND · PubMed Central
Figure 4 Chemical descriptor and the deep learning architecture of NPClassifier. (A) Illustration of the difference between Morgan fingerprints and counted Morgan fingerprints; the latter was used in this application. Morgan fingerprints are generally presented in a binary data format over all radii. Alternatively, the counted Morgan fingerprints have an integer format reflecting the count of atomic substructures. (B) Illustration of the structure of the neural network used for NPClassifier. Three different networks were trained: one for each level of classification in NPClassifier. The same structure was used for all three networks with just the top layers differing as a result of the number of alternatives for each level, as indicated in the legend.
Figure 4 Chemical descriptor and the deep learning architecture of NPClassifier. (A) Illustration of the difference between Morgan fingerprints and counted Morgan fingerprints; the latter was used in this application. Morgan fingerprints are generally presented in a binary data format over all radii. Alternatively, the counted Morgan fingerprints have an integer format reflecting the count of atomic substructures. (B) Illustration of the structure of the neural network used for NPClassifier. Three different networks were trained: one for each level of classification in NPClassifier. The same structure was used for all three networks with just the top layers differing as a result of the number of alternatives for each level, as indicated in the legend.CC BY-NC-ND · PubMed Central
Figure 5 Comparison of the classification results from NPClassifier (blue) and ClassyFire (orange); overlap is shown in brown. Chemical entities (n = 6200, 100 chemical entities for each of 62 classes) were analyzed by NPClassifier and ClassyFire, and the classification accuracy was measured. Classes are numbered around the circumference of the circle, while the ratio of correct predictions to total predictions ranging from 0 to 100 is denoted by the scale across the radius. NPClassifier showed better results for 47 classes and equal or slightly worse results for 15 classes compared with ClassyFire.
Figure 5 Comparison of the classification results from NPClassifier (blue) and ClassyFire (orange); overlap is shown in brown. Chemical entities (n = 6200, 100 chemical entities for each of 62 classes) were analyzed by NPClassifier and ClassyFire, and the classification accuracy was measured. Classes are numbered around the circumference of the circle, while the ratio of correct predictions to total predictions ranging from 0 to 100 is denoted by the scale across the radius. NPClassifier showed better results for 47 classes and equal or slightly worse results for 15 classes compared with ClassyFire.CC BY-NC-ND · PubMed Central
Figure 6 Examples of the correlations between structural modifications and classification results. (A) Ester bonds of a cyclic depsipeptide were sequentially replaced with amide bonds, and the classification result changed from cyclic peptide and depsipeptides to cyclic peptides. (B) Correlations between the modification of the C-ring substituents in flavonoids and the resulting classifications.
Figure 6 Examples of the correlations between structural modifications and classification results. (A) Ester bonds of a cyclic depsipeptide were sequentially replaced with amide bonds, and the classification result changed from cyclic peptide and depsipeptides to cyclic peptides. (B) Correlations between the modification of the C-ring substituents in flavonoids and the resulting classifications.CC BY-NC-ND · PubMed Central
Figure 7 Incorrectly classified structures and five categories with low F1 scores in the test set.
Figure 7 Incorrectly classified structures and five categories with low F1 scores in the test set.CC BY-NC-ND · PubMed Central
Figure 8 Application of NPClassifier to natural products research and drug discovery. (A) NPClassifier analysis of the diversity of metabolites and BGCs from bacteria and fungi (see text for more details). (B) Distribution of PKS-derived metabolites from bacteria and fungi. (C) The results of in silico antimalarial screening of NP Atlas using the MAIP tool (upper) and the analysis of these results using NPClassifier (lower). The level of predicted antimalarial activity is colored red for active and blue for inactive. (D) Spirotetronate macrolides with high (decalin containing) and low (non-decalin containing) MAIP scores present in the NP Atlas database.
Figure 8 Application of NPClassifier to natural products research and drug discovery. (A) NPClassifier analysis of the diversity of metabolites and BGCs from bacteria and fungi (see text for more details). (B) Distribution of PKS-derived metabolites from bacteria and fungi. (C) The results of in silico antimalarial screening of NP Atlas using the MAIP tool (upper) and the analysis of these results using NPClassifier (lower). The level of predicted antimalarial activity is colored red for active and blue for inactive. (D) Spirotetronate macrolides with high (decalin containing) and low (non-decalin containing) MAIP scores present in the NP Atlas database.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 70 references

Research works printed but not linked: 5

  1. Rogers F. B., 1963, Bull. Med. Libr. Assoc., 51, 114
  2. Rutz A., 2021, bioRxiv
  3. Hoffmann M. A., 2021, bioRxiv
  4. Landrum G., 2019, Abstr. Pap. Am. Chem. Soc., 258
  5. Shaffer J. P., 2021, bioRxiv

Cited by

Sorted by citations

Related

See all

Metadata

Authors
Kim, H. W., Wang, M., Leber, C. A., Nothias, L.-F., Reher, R., Kang, K. B., van der Hooft, J. J. J., Dorrestein, P. C., Gerwick, W. H., & Cottrell, G. W.
Affiliations
  • Scripps Institution of Oceanography (US)
  • University of California San Diego (US)
  • Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, California 92093, United States
  • Sookmyung Women's University (KR)
  • Bioinformatics Group, Wageningen University, Wageningen 6700, The Netherlands
Corresponding author
  • Gerwick, William H.
  • Cottrell, Garrison W.
ORCID
Venue
Journal of Natural Products
Publisher
American Chemical Society (ACS)
Published
2021-10-18
Volume
84
Issue
11
Pages
2795-2807
ISSN
  • 0163-3864 (ISSN-L)
  • 1520-6025
DOI
10.1021/acs.jnatprod.1c00399
PMC
PMC8631337
OpenAlex
W3206742358
Cited by
551
References
70
Citations by year
2026: 140 · 2025: 165 · 2024: 115 · 2023: 83 · 2022: 30 · 2021: 18
FWCI
32.17
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Natural Products (publishedVersion, cc-by-nc-nd)
  • ChemRxiv (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • Socio-Environmental Systems Modeling (acceptedVersion, cc-by-nc-nd)
  • eScholarship (California Digital Library) (submittedVersion, cc-by-nc-nd)
  • Figshare (submittedVersion)
  • Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, cc-by)
  • Data Archiving and Networked Services (DANS) (submittedVersion, cc-by-nc-nd)
Funders
  • Gordon and Betty Moore Foundation (GBMF7622)
  • National Research Foundation of Korea (NRF-2020R1C1C1004046)
  • Netherlands eScience Center (ASDI.2017.030)
  • National Institute of General Medical Sciences (R01 GM107550)
Topics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Immunology and Microbiology › Applied Microbiology and Biotechnology › Microbial Natural Products and Biosynthesis
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
Keywords
natural products, structural classification, Morgan fingerprints, deep neural network, natural product discovery, biosynthetic pathway, chemical substructures
MeSH terms
Biological Products, Neural Networks, Computer, Biosynthetic Pathways

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review