DeepRF: A deep learning method for predicting metabolic pathways in organisms based on annotated genomes
Abstract
The rapid increase of metabolomics has led to an increasing focus on metabolic pathway modeling and reconstruction. In particular, reconstructing an organism's metabolic network based on its genome sequence is a key challenge in systems biology. The method used to address this problem predicts the presence or absence of metabolic pathways from known pathways in a reference database. However, this method is based on manual metabolic pathway construction and cannot be used for large genome sequencing data. To address such problems, we apply a supervised machine learning approach consisting of deep neural networks to learn feature representations of metabolic pathways and feed these representations into random forests to predict metabolic pathways. The supervised learning model, DeepRF, predicts all known and unknown metabolic pathways in an organism. Evaluation of DeepRF on over 318,016 instances shows that the model can predict metabolic pathways with high-performance metrics accuracy (>97%), recall (>95%), and precision (>99%). Comparing DeepRF with other methods in the literature shows that DeepRF produces more reliable results than other methods.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
ML methods have increasingly been applied to MetS prediction based on clinical and biochemical data, with encouraging outcomes across various populations.
“In recent years, ML methods have increasingly been applied to MetS prediction based on clinical and biochemical data, with encouraging outcomes across various populations [46–50].”
From Machine learning with the body roundness index and associated indicators: a new approach to predicting metabolic syndrome (2025) · cites this paper as [50]
Cites
1 retracted
A deep learning architecture for metabolic pathway prediction
Baranwal, M., Magner, A., Elvati, P., Saldinger, J. C., Violi, A., & Hero, A. O. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz954 · Cited by 108 · see citing works
RetractedSMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · see citing works
KEGG: Kyoto Encyclopedia of Genes and Genomes
Ogata, H., Goto, S., Sato, K., Fujibuchi, W., Bono, H., & Kanehisa, M. (1999) · Nucleic Acids Research · doi:10.1093/nar/27.1.29 · Cited by 31,232 · see citing works
Pathway Tools version 13.0: integrated software for pathway/genome informatics and systems biology
Karp, P. D., Paley, S. M., Krummenacker, M., Latendresse, M., Dale, J. M., Lee, T. J., Kaipa, P., Gilham, F., Spaulding, A., Popescu, L., et al. (2010) · Briefings in Bioinformatics · doi:10.1093/bib/bbp043 · Cited by 694 · see citing works
A Parsimony Approach to Biological Pathway Reconstruction/Inference for Genomes and Metagenomes
Ye, Y., & Doak, T. G. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000465 · Cited by 680 · see citing works
Binary cross entropy with deep learning technique for Image classification
Ruby, A. U. (2020) · International Journal of Advanced Trends in Computer Science and Engineering · doi:10.30534/ijatcse/2020/175942020 · Cited by 637 · see citing works
MetaCyc: a multiorganism database of metabolic pathways and enzymes
Caspi, R. R. (2005) · Nucleic Acids Research · doi:10.1093/nar/gkj128 · Cited by 620 · see citing works
Expansion of the BioCyc collection of pathway/genome databases to 160 genomes
Karp, P. D. (2005) · Nucleic Acids Research · doi:10.1093/nar/gki892 · Cited by 611 · see citing works
Artificial Intelligence and COVID-19: Deep Learning Approaches for Diagnosis and Treatment
Jamshidi, M., Lalbakhsh, A., Talla, J., Peroutka, Z., Hadjilooei, F., Lalbakhsh, P., Jamshidi, M., Spada, L. L., Mirmozafari, M., Dehghani, M., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3001973 · Cited by 551 · see citing works
KEGG Atlas mapping for global analysis of metabolic pathways
Okuda, S., Yamada, T., Hamajima, M., Itoh, M., Katayama, T., Peer Bork, B., Goto, S., & Kanehisa, M. I. (2008) · Nucleic Acids Research · doi:10.1093/nar/gkn282 · Cited by 515 · see citing works
Caspi, R., Altman, T., Dale, J. M., Dreher, K. A., Fulcher, C. A., Gilham, F., Kaipa, P., Karthikeyan, A. S., Kothari, A., Krummenacker, M., et al. (2009) · Nucleic Acids Research · doi:10.1093/nar/gkp875 · Cited by 483 · see citing works
Karp, P. D. (2002) · Nucleic Acids Research · doi:10.1093/nar/30.1.59 · Cited by 414 · see citing works
A Proof of Local Convergence for the Adam Optimizer
Bock, S., & Weis, M. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852239 · Cited by 364 · see citing works
Exploring the diversity of complex metabolic networks
Vassily Hatzimanikatis, A., Li, C.-C., Ionita, J. A., Henry, C. S., Jankowski, M. D., & Broadbelt, L. J. (2004) · Computer applications in the biosciences · doi:10.1093/bioinformatics/bti213 · Cited by 349 · see citing works
Types of minority class examples and their influence on learning classifiers from imbalanced data
Napierała, K., & Stefanowski, J. (2015) · Journal of Intelligent Information Systems · doi:10.1007/s10844-015-0368-1 · Cited by 296 · see citing works
Extremely Randomized Trees-Based Scheme for Stealthy Cyber-Attack Detection in Smart Grid Networks
Camana, M. R., Ahmed, S., García, C. E., & Koo, I. (2020) · IEEE Access · doi:10.1109/access.2020.2968934 · Cited by 177 · see citing works
Machine learning methods for metabolic pathway prediction
Dale, J. M., Popescu, L., & Karp, P. D. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-15 · Cited by 168 · see citing works
Vani, S., & Rao, T. (2019) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei.2019.8862686 · Cited by 107 · see citing works
Application of deep learning and machine learning models to detect COVID-19 face masks - A review
Mbunge, E., Simelane, S., Fashoto, S. G., Akinnuwesi, B. A., & Metfula, A. S. (2021) · Sustainable Operations and Computers · doi:10.1016/j.susoc.2021.08.001 · Cited by 93 · see citing works
Pathway discovery in metabolic networks by subgraph extraction
Faust, K., Dupont, P., Callut, J., & van Helden, J. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq105 · Cited by 92 · see citing works
Trimmed categorical cross‐entropy for deep learning with label noise
Rusiecki, A. (2019) · Electronics Letters · doi:10.1049/el.2018.7980 · Cited by 92 · see citing works
A Novel Boundary Oversampling Algorithm Based on Neighborhood Rough Set Model: NRSBoundary-SMOTE
Hu, F., & Li, H. (2013) · Mathematical Problems in Engineering · doi:10.1155/2013/694809 · Cited by 70 · see citing works
Deep learning for computational structural optimization
Nguyen, L. C., & Nguyen‐Xuan, H. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.03.033 · Cited by 66 · see citing works
Orlenko, A., Kofink, D., Lyytikäinen, L., Nikus, K. C., Mishra, P. P., Kuukasjärvi, P., Karhunen, P. J., Kähönen, M. A. P., Laurikka, J. O., Lehtimäki, T. J., et al. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz796 · Cited by 59 · see citing works
Human metabolic network reconstruction and its impact on drug discovery and development
Ma, H., & Goryanin, I. (2008) · Drug Discovery Today · doi:10.1016/j.drudis.2008.02.002 · Cited by 59 · see citing works
Review of Machine Learning Methods for the Prediction and Reconstruction of Metabolic Pathways
Shah, H. A., Liu, J., Yang, Z., & Feng, J. Q. (2021) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2021.634141 · Cited by 54 · see citing works
Self-citationKhalaj, O., Jamshidi, M. B., Saebnoori, E., Mašek, B., Štádler, C., & Svoboda, J. (2021) · IEEE Access · doi:10.1109/access.2021.3129454 · Cited by 29 · see citing works
A Conceptual Deep Learning Framework for COVID-19 Drug Discovery
Jamshidi, M. B., Talla, J., Lalbakhsh, A., Sharifi-Atashgah, M. S., Sabet, A., & Peroutka, Z. (2021) · IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) · doi:10.1109/uemcon53757.2021.9666715 · Cited by 26 · see citing works
Construction and Analysis of Human Diseases and Metabolites Network
Mi, K., Jiang, Y., Chen, J., Lv, D., Qian, Z., Sun, H., & Shang, D. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00398 · Cited by 21 · see citing works
Deep Learning Techniques for Model Reference Adaptive Control and Identification of Complex Systems
Jamshidi, M. B., Talla, J., & Peroutka, Z. (2020) · International Conference on Mechatronics - Mechatronika · doi:10.1109/me49197.2020.9286698 · Cited by 9 · see citing works
Determining the Presence of Metabolic Pathways using Machine Learning Approach
Aljarbou, Y. S., & Haron, F. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110845 · Cited by 2 · see citing works
Flagged first, then by citations
1 of the 32 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Metabolomics‐driven approaches for identifying therapeutic targets in drug discovery
Pan, S., Yin, L., Liu, J., Tong, J., Wang, Z., Zhao, J., Liu, X., Chen, Y., Miao, J., Zhou, Y., et al. (2024) · MedComm · doi:10.1002/mco2.792 · Cited by 46 · see citing works
Self-citationAhmad, Z., Shareen, Ganie, I. B., Firdaus, F., Ramakrishnan, M., Shahzad, A., & Ding, Y. (2024) · Plants · doi:10.3390/plants13152171 · Cited by 25 · see citing works
Multi-label classification with XGBoost for metabolic pathway prediction
Joe, H., & Kim, H. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05666-0 · Cited by 23 · see citing works
Metabolic Connectome and Its Role in the Prediction, Diagnosis, and Treatment of Complex Diseases
Meng, W., Pan, H., Sha, Y., Zhai, X., Xing, A., Lingampelly, S. S., Sripathi, S. R., Wang, Y., & Li, K. (2024) · Metabolites · doi:10.3390/metabo14020093 · Cited by 17 · see citing works
Advances in AI-based strategies and tools to facilitate natural product and drug development
Basnet, B. B., Zhou, Z., Wei, B., & Wang, H. (2025) · Critical Reviews in Biotechnology · doi:10.1080/07388551.2025.2478094 · Cited by 17 · see citing works
Artificial intelligence in systems biology
Dasgupta, A., & De, R. K. (2023) · Handbook of statistics · doi:10.1016/bs.host.2023.06.004 · Cited by 10 · see citing works
Metabolic syndrome predictive modelling in Bangladesh applying machine learning approach
Hossain, M. F., Hossain, S., Akter, M. N., Nahar, A., Liu, B., & Faruque, M. O. (2024) · PLoS ONE · doi:10.1371/journal.pone.0309869 · Cited by 7 · see citing works
Arici, M. K., & Tunçbağ, N. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae399 · Cited by 6 · see citing works
Shah, H. A., Yasmin, S., & Ansari, M. Y. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108423 · Cited by 6 · see citing works
Self-citationHe, Y., Chen, Z., Tang, Z., Qin, Y., & Wang, F. (2025) · BMC Public Health · doi:10.1186/s12889-025-23858-y · Cited by 5 · see citing works
Moozhippurath, B., & Jayapandian, N. (2025) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v21i10.55539 · Cited by 3 · see citing works
Artificial intelligence revolutionizes cellular metabolic pathway reconstruction
Zheng, J., Xu, X., Yang, Q., Dong, N., & Li, S. Z. (2026) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2026.01.003 · Cited by 2 · see citing works
Oulia, F., Charton, P., Lo-Thong-Viramoutou, O., Acevedo‐Rocha, C. G., Liu, W., Huynh, D. Q., Damour, C., Wang, J. B., & Cadet, F. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms252413390 · Cited by 2 · see citing works
Characterization of microbial primary and secondary metabolism in the marine realm
Geller‐McGrath, D. (2024) · doi:10.1575/1912/70396 · Cited by 1 · see citing works
Predicting enzyme-compound associations for enzyme-catalysed reactions
Brydon, L., Dobbie, G., Taškova, K., & Wicker, J. S. (2026) · Journal of Cheminformatics · doi:10.1186/s13321-026-01190-w
Ali, A., Wang, Y., & Shah, H. A. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02437-0
Self-citationWill predictive AI make discovery research in metabolism obsolete
Sun, J., Baker, S. M., Montgomery, M. K., & Zhou, H. (2026) · npj Metabolic Health and Disease · doi:10.1038/s44324-026-00117-1
- Authors
- Shah, H. A., Liu, J., Yang, Z., Zhang, X., & Feng, J.
- Affiliations
- Wuhan University (CN)
- Corresponding author
- Liu, Juan
- Venue
- Computers in Biology and Medicine
- Publisher
- Elsevier BV
- Published
- 2022-08
- Volume
- 147
- Pages
- 105756
- ISSN
- 0010-4825 (ISSN-L)
- OpenAlex
- W4283155576
- Cited by
- 17
- References
- 32
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 8 · 2023: 1
- FWCI
- 1.06
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Computers in Biology and Medicine (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Hubei Technological Innovation Special Fund (2019010701011381, 2019AEA170)
- Wuhan University
- National Key Research and Development Program of China (2019YFA0904303)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Microbial Metabolic Engineering and Bioproduction
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Keywords
- metabolic pathway prediction, metabolic pathway reconstruction, genome annotation, annotated genome, deep neural network, random forest, metabolic network reconstruction, metabolomics, systems biology
- MeSH terms
- Deep Learning, Databases, Factual, Neural Networks, Computer, Genome, Metabolic Networks and 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
