Recurrent Neural Network Model for Constructive Peptide Design
The DOI matches its Crossref record; 47 of the 50 references it cites were found in a registry or an index.
Abstract
We present a generative long short-term memory (LSTM) recurrent neural network (RNN) for combinatorial de novo peptide design. RNN models capture patterns in sequential data and generate new data instances from the learned context. Amino acid sequences represent a suitable input for these machine-learning models. Generative models trained on peptide sequences could therefore facilitate the design of bespoke peptide libraries. We trained RNNs with LSTM units on pattern recognition of helical antimicrobial peptides and used the resulting model for de novo sequence generation. Of these sequences, 82% were predicted to be active antimicrobial peptides compared to 65% of randomly sampled sequences with the same amino acid distribution as the training set. The generated sequences also lie closer to the training data than manually designed amphipathic helices. The results of this study showcase the ability of LSTM RNNs to construct new amino acid sequences within the applicability domain of the model and motivate their prospective application to peptide and protein design without the need for the exhaustive enumeration of sequence libraries.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“In previous studies, it has been verified that LSTM-based neural networks could learn AMP’s amino-acid grammar and create new potential AMP sequences32,33.”
From Experimental demonstration of highly reliable dynamic memristor for artificial neuron and neuromorphic computing (2022) · cites this paper as [32]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
(2014) · Cited by 33,419
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893
Learning to forget: Continual prediction with LSTM
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000) · Neural Computation · doi:10.1162/089976600300015015 · Cited by 4,823
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076
Statistical Inference for Probabilistic Functions of Finite State Markov Chains
Baum, L. E., & Petrie, T. (1966) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177699147 · Cited by 2,775
APD3: the antimicrobial peptide database as a tool for research and education
Wang, G., Li, X., & Wang, Z. (2016) · Nucleic Acids Research · doi:10.1093/nar/gkv1278 · Cited by 2,388
Designing antimicrobial peptides: form follows function
Fjell, C. D., Hiss, J. A., Hancock, R. E. W., & Schneider, G. (2012) · Nature Reviews Drug Discovery · doi:10.1038/nrd3591 · Cited by 2,035
Self-citation
Research works printed but not linked: 16
- Lipton, Z. C.; Berkowitz, J.; Elkan, C.A Critical Review of Recurrent Neural Networks for Sequence Learning.arXiv:1506.00019, 2015.
- Brown P. F., 1992, Comput. Linquistics, 18, 467
- Boulanger-Lewandowski N., 2012, Proc. 29th Int. Conf. Mach. Learn., 1159
- Sutskever I., 2011, Proc. 28th Int. Conf. Mach. Learn., 1017
- Segler M. H. S., 2017, ACS Cent. Sci.
- Baldi P., 2003, J. Mach. Learn. Res., 4, 575
- Sønderby S. K., 2015, Algorithms for Computational Biology. AlCoB 2015. Lecture Notes in Computer Science, 9199, 68
- Jozefowicz R., 2015, Proc. 32nd Int. Conf. Mach. Learn. Lille, Fr., 37
- Srivastava N., 2014, J. Mach. Learn. Res., 15, 1929
- Gal Y., 2016, Adv. Neural Inf. Process. Syst., 1019
- Kingma, D. P.; Ba, J.Adam: A Method for Stochastic Optimization.arXiv:1412.6980, 2014.
- Chollet F., 2015, Keras
- Abadi, M.; Agarwal, A.; Barham, P.; Brevdo, E.; Chen, Z.; Citro, C.; Corrado, G. S.; Davis, A.; Dean, J.; Devin, M.TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems.arXiv:1603.04467, 2016.
- Graves, A.Generating Sequences With Recurrent Neural Networks.arXiv:1308.0850, 2013.
- McKinney W., 2010, Proc. 9th Python Sci. Conf., 51
- Goodfellow I. J., 2014, Adv. Neural Inf. Process. Syst., 2, 2672
Cited by
Items 101–200 of 277
The Scent of Change: Sustainable Fragrances Through Industrial Biotechnology
Michailidou, F. (2023) · ChemBioChem · doi:10.1002/cbic.202300309 · Cited by 32
Integrated computational approaches for advancing antimicrobial peptide development
Fang, Y., Ma, Y., Yu, K., Dong, J. N., & Zeng, W. (2024) · Trends in Pharmacological Sciences · doi:10.1016/j.tips.2024.09.011 · Cited by 27
Moretta, A., Scieuzo, C., Salvia, R., Popović, Ž. D., Sgambato, A., & Falabella, P. (2022) · Current Pharmaceutical Design · doi:10.2174/1381612828666220817163339 · Cited by 28
Bolatchiev, A., Baturin, V., Shchetinin, E., & Bolatchieva, E. (2022) · Antibiotics · doi:10.3390/antibiotics11030411 · Cited by 26
“fasta” in the Supplementary Information) [16] (Figure 1).”
BackgroundInfluentialAhmad, S. B., Achek, A., Farooq, M., & Choi, S. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.09.038 · Cited by 26
“Several groups have used the LSTM or generative autoencoder architecture for de novo peptide design [8, 36, 62].”
MethodZhao, W., Hou, K., Shen, Y., & Hu, X. T. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf069 · Cited by 25
“To address the challenge, various deep learning methods for AMP discovery have been proposed, including RNN-based (Muller et al. 2018, Shaon et al. 2024), LSTM-based (Mao et al. 2023), GAN-based (Tucs et al. 2020, Surana et al. 2023), and VAE-based (Dean et al. 2021, Pandi et al. 2023, Renaud and…”
Molecular hybridization strategy for tuning bioactive peptide function
Pedron, C. N., Torres, M. D. T., Oliveira, C. S., da Silva, A. F., Andrade, G. P., Wang, Y., Pinhal, M. A. D. S., Cerchiaro, G., da Silva, P. I., da Silva, F. D., et al. (2023) · Communications Biology · doi:10.1038/s42003-023-05254-7 · Cited by 23
Arras, P., Yoo, H. B., Pekar, L., Clarke, T., Friedrich, L., Schröter, C., Schanz, J., Tonillo, J., Siegmund, V., Doerner, A., et al. (2023) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2023.1249247 · Cited by 24
“, 2021), but also for peptides (Müller et al., 2018) and small molecules (Gupta et al.”
BackgroundMethodInfluentialComputational and data-driven modelling of solid polymer electrolytes
Wang, K., Shi, H., Li, T., Zhao, L., Zhai, H., Korani, D., & Yeo, J. (2023) · Digital Discovery · doi:10.1039/d3dd00078h · Cited by 24
Villalobos-Alva, J., Ochoa-Toledo, L., Villalobos-Alva, M. J., Aliseda, A., Escamirosa, F. P., Altamirano-Bustamante, N. F., Ochoa-Fernández, F., Zamora-Solís, R., Villalobos-Alva, S., Revilla, M., et al. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2022.788300 · Cited by 27
“, 2017, Switzerland (Müller et al., 2018) ADAM, APD DADP Antimicrobial peptide Amino acid sequences Design of new peptide combinatorial de novo peptide design RNN, LSTM modlAMP Python package https:// github.”
MethodInfluentialCao, J., Zhang, J., Yu, Q., Ji, J., Li, J., He, S., & Zhu, Z. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae644 · Cited by 21
Vendrell, R. C., Ajagekar, A., Bergman, M. T., Hall, C. K., & You, F. (2024) · Science Advances · doi:10.1126/sciadv.adq8492 · Cited by 24
“Long-short term memory (LSTM) networks ( 22 , 23 ) and variational autoencoder (VAE) ( 24 , 25 ) models have been developed for generating bioactive peptides with antimicrobial and therapeutic properties ( 26 ).”
Chang, D. H., Lee, M., Wang, N., Lynn, D. M., & Palecek, S. P. (2023) · ACS Infectious Diseases · doi:10.1021/acsinfecdis.3c00468 · Cited by 20
Can large language models predict antimicrobial peptide activity and toxicity?
Orsi, M., & Reymond, J. (2024) · RSC Medicinal Chemistry · doi:10.1039/d4md00159a · Cited by 20
Wang, Q., Hu, X., Wei, Z., Lu, H., & Liu, H. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae444 · Cited by 24
“RNN networks have been successfully applied to generate peptide sequences by learning patterns from known sequences [16–19].”
MethoddsAMP and dsAMPGAN: Deep Learning Networks for Antimicrobial Peptides Recognition and Generation
Zhao, M., Zhang, Y., Wang, M., & Luyan, Z. (2024) · Antibiotics · doi:10.3390/antibiotics13100948 · Cited by 22
CPL‐Diff: A Diffusion Model for De Novo Design of Functional Peptide Sequences with Fixed Length
Luo, Z., Geng, A., Wei, L., Zou, Q., Cui, F., & Zhang, Z. (2025) · Advanced Science · doi:10.1002/advs.202412926 · Cited by 19
Wang, L., Fu, X., Yang, J., Zhang, X., Ye, X., Sakurai, T., Zeng, X., & Liu, Y. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf376 · Cited by 19
“…model architectures have been explored to enhance AMP discovery, with significant attention de voted to foundational models including variational autoen-coders (VAEs) [5–12], generative adversarial networks (GANs) [13– 17], recurrent neural networks (RNNs) [18, 19], and graph neural networks [20].”
Zhang, B., Zhao, M., Tian, J., Lei, L., & Huang, R. (2022) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2022.1065235 · Cited by 23
“…in computational-resources have facilitated the discovery and synthesis of novel AMPs (Porto et al., 2017; De La Fuente-Nunez, 2019), including structure-activity relationships (SAR) study (Abdel Monaim et al., 2018), neural networks (Müller et al., 2018), deep learning (Hamid and Friedberg, 2019).”
BackgroundImpact of Data Preparation in Freezing of Gait Detection Using Feature-Less Recurrent Neural Network
Esfahani, A. H., Dyka, Z., Ortmann, S., & Langendörfer, P. (2021) · IEEE Access · doi:10.1109/access.2021.3117543 · Cited by 20
A Multi‐Property Optimizing Generative Adversarial Network for de novo Antimicrobial Peptide Design
Liu, J., Cui, T., Wang, T., Lin, L., Zeng, X., Lu, D., Jiao, S., Wang, J., Li, X., Xiao, S., et al. (2025) · Advanced Science · doi:10.1002/advs.202503443 · Cited by 24
EBAMP: An efficient de novo broad-spectrum antimicrobial peptide discovery framework
Zhao, Y., Li, Q., Sun, M., Su, Y., Su, X., Jiang, L., Zhang, X., Hu, Y., Wang, B., Yu, H., et al. (2025) · Cell Reports · doi:10.1016/j.celrep.2025.116215 · Cited by 18
Jibril, M. M., Malami, S. I., Jibrin, H. B., Muhammad, U. J., Duhu, M. A., Usman, A. G., Ibrahim, A. G., Ozsahin, D. U., Lawal, Z. K., & Abba, S. I. (2024) · Asian Journal of Civil Engineering · doi:10.1007/s42107-023-00908-7 · Cited by 18
“RNNs are a subset of ANN that are created specifically for the processing of sequential data (Kaveh et al., 2023; Rofooei et al., 2011), such as time series or data from natural languages, where the order of the parts is crucial (Müller et al., 2018).”
De novo Molecular Design with Generative Long Short-term Memory
Grisoni, F., & Schneider, G. (2019) · CHIMIA International Journal for Chemistry · doi:10.2533/chimia.2019.1006 · Cited by 21
Self-citationSaleem, N., Kumar, N., El-Omar, E. M., Willcox, M. D. P., & Jiang, X. (2025) · Antibiotics · doi:10.3390/antibiotics14121263 · Cited by 17
“…peptide databases and in vitro and in vivo experimental validations, can make it possible to explore and identify a rich landscape of antimicrobial peptides, heralding a promising alternative novel therapeutic strategy for combating resistance, particularly against Gram-negative pathogens.”
Feedback-AVPGAN: Feedback-guided generative adversarial network for generating antiviral peptides
Hasegawa, K., Moriwaki, Y., Terada, T., Wei, C., & Shimizu, K. (2022) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720022500263 · Cited by 17
Erjavac, I., Kalafatović, D., & Mauša, G. (2022) · Artificial Intelligence in the Life Sciences · doi:10.1016/j.ailsci.2022.100034 · Cited by 17
Tian, C., Hao, Y., Fu, H., Shao, X., & Cai, W. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00892 · Cited by 17
Zhao, H., & Song, G. (2024) · Viruses · doi:10.3390/v16111673 · Cited by 16
“To address these limitations, machine learning models have gained traction for high-throughput peptide design and antiviral activity identification [4,5].”
Campoccia, D., Bottau, G., Donno, A. D., Bua, G., Ravaioli, S., Capponi, E., Sotgiu, G., Bellotti, C., Costantini, S., & Arciola, C. R. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms252413241 · Cited by 16
Fine, J. A., Liu, J. K., Beck, A. G., Alzarieni, K. Z., Ma, X., Boulos, V. M., Kenttämaa, H. I., & Chopra, G. (2020) · Chemical Science · doi:10.1039/d0sc02530e · Cited by 18
How Deep Learning Tools Can Help Protein Engineers Find Good Sequences
Osadchy, M., & Kolodny, R. (2021) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.1c02449 · Cited by 16
“12,35b,39 Energy-Based Models.”
BackgroundMethodInfluentialMesa, A., Orrego, A., Branch, J. W., Mera, C., & Ordúz, S. (2025) · Current Microbiology · doi:10.1007/s00284-025-04346-3 · Cited by 15
Exploring machine learning strategies for single-cell transcriptomic analysis in wound healing
Cui, J., Wang, M., Lin, C., Xu, X., & Zhang, Z. (2025) · Burns & Trauma · doi:10.1093/burnst/tkaf032 · Cited by 15
“RNNs have excelled in analyzing sequential biological data, such as protein sequences for engineering novel peptides, capturing temporal or positional dependencies critical to understanding molecular functions [71].”
Hard Turning on JIS S45C Structural Steel: An Experimental, Modelling and Optimisation Approach
Kumar, R., Modi, A., Panda, A., Sahoo, A. K., Deep, A., Behra, P. K., & Tiwari, R. (2019) · International Journal of Automotive and Mechanical Engineering · doi:10.15282/ijame.16.4.2019.10.0544 · Cited by 15
“RNN is a combining form of feedforward and back forward structure [37-38].”
BackgroundCheung, A., Liu, Y., Chenoweth, A. M., Montaseri, H., Esapa, B., Chudasama, V., Baker, J. R., Thurston, D. E., & Karagiannis, S. N. (2026) · Physiological Reviews · doi:10.1152/physrev.00039.2025 · Cited by 15
Chen, J., Yang, R., Zhang, C., Zhang, L., & Zhang, Q. (2019) · IEEE Access · doi:10.1109/access.2019.2944411 · Cited by 14
“Thus, LSTM RNNs [31] will be designed in this study to generate peptide chains with lysines.”
Atz, K., Nippa, D. F., Müller, A. T., Jost, V., Anelli, A., Reutlinger, M., Krämer, C., Martin, R. E., Grether, U., Schneider, G., et al. (2024) · RSC Medicinal Chemistry · doi:10.1039/d4md00196f · Cited by 15
Self-citationLu, Z., Cheng, Z., & Yang, T.-Y. (2020) · Computational Intelligence and Neuroscience · doi:10.1155/2020/8882279 · Cited by 13
(2022) · doi:10.1038/s41598-022-13227-9 · Cited by 12
“Peptides can then be sampled from such distribution to generate novel peptides that are similar, but different to those in the training set [5,8].”
BackgroundWu-Mo, C., Flores-González, A., Meléndez-Delgado, J., Ortiz-Gómez, V., Meléndez-González, H., & Maldonado‐Hernández, R. (2026) · Microorganisms · doi:10.3390/microorganisms14030591 · Cited by 12
GM-Pep: A High Efficiency Strategy to De Novo Design Functional Peptide Sequences
Chen, Q., Yang, C., Xie, Y., Wang, Y., Li, X., Wang, K., Huang, J., & Yan, W. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00089 · Cited by 12
Autonome Entdeckung in den chemischen Wissenschaften, Teil I: Fortschritt
Coley, C. W., Eyke, N. S., & Jensen, K. F. (2019) · Angewandte Chemie · doi:10.1002/ange.201909987 · Cited by 12
Deep learning approaches for conformational flexibility and switching properties in protein design
Rudden, L. S. P., Hijazi, M., & Barth, P. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.928534 · Cited by 14
“Recurrent neural networks, a subclass architecture of autoregressive models, have been used to design antimicrobial and membranolytic anticancer peptides (Grisoni et al., 2018; Müller et al., 2018).”
MethodFukunaga, I., Sawada, R., Shibata, T., Kaitoh, K., Sakai, Y., & Yamanishi, Y. (2019) · Molecular Informatics · doi:10.1002/minf.201900134 · Cited by 12
Benchmarking protein structure predictors to assist machine learning-guided peptide discovery
Aldas-Bulos, V. D., & Plisson, F. (2023) · Digital Discovery · doi:10.1039/d3dd00045a · Cited by 11
Can C-Reactive Protein (CRP) Time Series Forecasting be Achieved via Deep Learning?
Dorraki, M., Fouladzadeh, A., Salamon, S. J., Allison, A., Coventry, B. J., & Abbott, D. (2019) · IEEE Access · doi:10.1109/access.2019.2914473 · Cited by 12
“Moreover, recurrent neural networks with long short-term memory (LSTM) have been widely employed for biomedical time series [46]–[51].”
Li, S., Lu, P., Chen, L., Que, L., Kang, W., Hu, X., Ma, J., Di, Z., & Liu, Y. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01006 · Cited by 15
Advanced Artificial Intelligence Technologies Transforming Contemporary Pharmaceutical Research
Kumar, P., Chaudhary, B., Arya, P., Chauhan, R., Devi, S., Parejiya, P. B., & Gupta, M. M. (2025) · Bioengineering · doi:10.3390/bioengineering12040363 · Cited by 14
“Since the target compounds may be computationally iterated, the realm of chemicals provides a platform for novel discovery [43].”
Deeply learning molecular structure-property relationships using graph attention neural network.Preprint
Ryu, S., Lim, J., & Kim, W. Y. (2018) · arXiv (Cornell University) · Cited by 11
Sinha, K., Parwez, S., Shahana, M. V., Yadav, A., Siddiqi, M. I., & Banerjee, D. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2240416 · Cited by 9
“…processes of discovery of novel drugs, like determining physiochemical activities (H. Chen et al., 2018; Kadurin et al., 2017; Lusci et al., 2013; M € uller et al., 2018; Olivecrona et al., 2017; Tetko et al., 2005) toxicity prediction (V. K. Gupta & Rana, 2019; Mayr et al., 2016; Z. Wang et…”
Peptides in plant–microbe interactions: Functional diversity and pharmacological applications
Song, M., Zhou, Y., Li, G., Barashkova, A. S., Rogozhin, E. A., & Chang, W. (2025) · The Cell Surface · doi:10.1016/j.tcsw.2025.100145 · Cited by 9
“Deep learning architectures, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), have recently demonstrated superior accuracy over traditional scoring methods by autonomously extracting high-order sequence patterns (Junet and Daura, 2021; Müller et al., 2018).”
GEU-AMP50: Enhanced antimicrobial peptide prediction using a machine learning approach
Panwar, S., Thapliyal, M., Kuriyal, V., Tripathi, V., & Thapliyal, A. (2022) · Materials Today Proceedings · doi:10.1016/j.matpr.2022.09.326 · Cited by 9
Machine Learning Approaches to Improve Prediction of Target‐Drug Interactions
Balatti, G. E., Barletta, P. G., D. Perez, A., Giudicessi, S. L., & Martínez‐Ceron, M. C. (2022) · Wiley eBooks · doi:10.1002/9781394167258.ch2 · Cited by 10
Nájera, G. S., Narganes-Carlón, D., & Crowther, D. J. (2021) · Scientific Reports · doi:10.1038/s41598-021-94897-9 · Cited by 13
Cruz-Victoria, J. C., Netzahuatl-Muñoz, A. R., & Cristiani‐Urbina, E. (2024) · Sustainability · doi:10.3390/su16072874 · Cited by 11
Yu-liang, D., Lu, Z., Zhang, H., Zhan, T., Lu, J., & Wang, P. (2019) · Earth and Space Science · doi:10.1029/2019ea000641 · Cited by 9
Tracking the Chemical Evolution of Iodine Species Using Recurrent Neural Networks
Bilbrey, J. A., Marrero, C. O., Sassi, M. J., Ritzmann, A. M., Henson, N. J., & Schram, M. (2020) · ACS Omega · doi:10.1021/acsomega.9b04104 · Cited by 9
Machine learning in protein engineeringPreprint
Yang, K., Wu, Z., & Arnold, F. H. (2018) · arXiv (Cornell University) · Cited by 9
Wang, Y., Li, M., Huang, F., Qiu, M., & Zhang, W. (2025) · Advanced Science · doi:10.1002/advs.202507457 · Cited by 8
AI-driven discovery and design of antimicrobial peptides
Shen, X., Wang, Y., Zhang, P., & Ji, J. (2025) · Science China Technological Sciences · doi:10.1007/s11431-025-3100-9 · Cited by 9
“Müller et al. utilized an LSTM-based RNN to learn the sequence distribution of helical AMPs, enabling de novo generation [116].”
Saraswat, A., Sharma, U., Gandotra, A., Wasan, L., Artham, S., Maitra, A., & Singh, B. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00900 · Cited by 8
ANTIPSEUDOBASE: Database of Antimicrobial Peptides and Essential Oils Against Pseudomonas
Zouhir, A., Souiaï, O., Harigua‐Souiai, E., Cherif, A., Chaalia, A. B., & Sebei, K. (2023) · International Journal of Peptide Research and Therapeutics · doi:10.1007/s10989-023-10511-8 · Cited by 8
“…the principles of the highly conserved signal peptide subclasses related to AMPs (Abdel Monaim et al. 2018; Juretić et al. 2011), neural networks (Müller et al. 2018), deep learning and machine learning such as a method by Matlab is proposed based on the concept of scoring the contribution of…”
MethodZhao, H., & Song, G. (2024) · Viruses · doi:10.3390/v17010014 · Cited by 8
“Previous peptide generation models like LSTM [21] can suffer from the vanishing gradient problem, limiting their ability to capture long-term dependencies.”
Review of Deep Learning Algorithms in Computational biochemistry
Sino, N. I., Farhan, R. N., & Seno, M. E. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1804/1/012135 · Cited by 7
“In [13], generative long-term memory (LSTM) was used by the Researchers as one form of RNN architectures for computational de novo peptide architecture.”
MethodWang, Y. (2023) · PLoS ONE · doi:10.1371/journal.pone.0285496 · Cited by 7
Empowering Protein Engineering through Recombination of Beneficial Substitutions
Wang, X., Li, A., Li, X., & Cui, H. (2024) · Chemistry - A European Journal · doi:10.1002/chem.202303889 · Cited by 8
Reinforcement learning with low-rank adaptation for targeted antimicrobial peptide design
Park, J., Bae, D., Bae, B., & Nam, H. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf641 · Cited by 9
“Muller used an LSTM-based model [12] to generate new sequences by learning the structural patterns of helical AMPs [13].”
Qayyum, N., Seo, H., Khan, N., Manan, A., Ramachandran, R., Haseeb, M., Kim, E., & Choi, S. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.144652 · Cited by 6
AMPGP: Discovering Highly Effective Antimicrobial Peptides via Deep Learning
Wang, J., Wu, R., Zhang, X., Jiang, C., Zhao, S., Li, Q., & Zhang, N. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00647 · Cited by 6
Mishra, V. K., & Banerjee, A. G. (2025) · Artificial Intelligence Evolution · doi:10.37256/aie.6120255553 · Cited by 6
Talluri, S. (2022) · Advances in protein chemistry and structural biology · doi:10.1016/bs.apcsb.2022.01.003 · Cited by 6
SeqNovo: De Novo Peptide Sequencing Prediction in IoMT via Seq2Seq
Wang, K., Zhu, M., Boulila, W., Driss, M., Gadekallu, T. R., Chen, C., Wang, L., Kumari, S., & Yiu, S. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3321780 · Cited by 6
Controllable Protein Design by Prefix-Tuning Protein Language Models
Luo, J., Li, J., Liu, X., Zhang, Y., Chen, Q., & Chen, J. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c03186 · Cited by 9
Artificial intelligence in drug discovery and clinical practice
Karalis, V. D. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-91111-5.00006-8 · Cited by 7
Hamre, J. R., & Jafri, M. S. (2022) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2022.100886 · Cited by 6
Multiscale profiling of enzyme activity in cancerPreprint
Amini, A. P., Kirkpatrick, J. D., Wang, C. S., Jaeger, A. M., Su, S., Naranjo, S., Zhong, Q., Cabana, C. M., Jacks, T., & Bhatia, S. N. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.11.11.468288 · Cited by 6
Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian OptimizationPreprint
Feng, L., Nouri, P., Muni, A., Bengio, Y., & Bacon, P. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.06259 · Cited by 7
“We can divide existing methods for biological sequence design into three categories [2] : directed evolution [38], optimization using discriminative models (e.g. Bayesian Optimization), and optimization using generative model [33, 23].”
MethodArtificial intelligence in drug design: why a ‘one-size-fits-all’ approach remains out of reach
Almeida, R. L., Campera, G. M., Pöhner, I., & Maltarollo, V. G. (2025) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2025.2543802 · Cited by 5
“RNNs have been successfully employed in tasks such as molecular generation, property prediction, and analysis of time-series biological data [56,57].”
Transforming modern drug discovery with machine learning – applications in ligand-based drug design
Pore, S., & Roy, K. (2025) · Annual reports in medicinal chemistry · doi:10.1016/bs.armc.2025.08.001 · Cited by 5
Contemporary data-driven innovations in peptide-based therapeutic design
Priyadarsinee, L., Kungurtsev, V., Kumar, V., Chatterjee, B., Sastry, G. N., & Murugan, N. A. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag220 · Cited by 5
“First, the model architecture is built for sequence generation using Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTMs) due to their ability to capture temporal dependencies in biological sequences [83].”
AmpClass: an Antimicrobial Peptide Predictor Based on Supervised Machine Learning
Mera, C., Ordúz, S., Cardona, P., Orrego, A., Muñoz‐Pérez, J. M., & Branch, J. W. (2024) · Anais da Academia Brasileira de Ciências · doi:10.1590/0001-3765202420230756 · Cited by 6
Configurable soft computing-based generative model: The search for catalytic peptides
Mauša, G., Njirjak, M., Otović, E., & Kalafatovic, D. (2023) · MRS Advances · doi:10.1557/s43580-023-00629-8 · Cited by 5
“The application of algorithms such as recurrent neural networks (RNN) [6], variational autoencoders (VAE) [7, 8], and generative adversarial networks (GAN) [9] accelerated antimicrobial discovery [10, 11] and the design of functional protein variants [12, 13], peptide-based drugs [6, 14], and small…”
BackgroundMethodFukunaga, I., Matsukiyo, Y., Kaitoh, K., & Yamanishi, Y. (2024) · Molecular Informatics · doi:10.1002/minf.202300148 · Cited by 6
Yan, J., Chen, Z., Cai, J., Xian, W., Wei, X., Qin, Y., & Li, Y. (2025) · Applied Sciences · doi:10.3390/app15137363 · Cited by 5
Machine learning classifiers aid virtual screening for efficient design of mini-protein therapeutics
Gaur, N., Goyal, V. D., Kulkarni, K. A., & Makde, R. D. (2021) · Bioorganic & Medicinal Chemistry Letters · doi:10.1016/j.bmcl.2021.127852 · Cited by 5
Thakur, V., Gupta, V., Sharma, P., Gupta, A., & Capalash, N. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.23.568446 · Cited by 6
“Recurrent Neural Networks, Generative Adversarial Networks, and Variational Autoencoders have been used to de novo design AMP sequences of varying lengths ( ean and alper, 2020 upta and ou, 2019 ller et al., 2018).”
MethodPhysicochemical Property-guided Conditional VAE for Antimicrobial Peptides Generation
Hou, K., Zhao, W., & He, T. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822555 · Cited by 4
Drug Delivery Applications of Peptide Materials
Hamsici, S., Gunay, G., Kirit, H. A., Kamatar, A., Loving, K., & Acar, H. (2020) · Royal Society of Chemistry eBooks · doi:10.1039/9781839161148-00291 · Cited by 4
DeepRCI: predicting RNA‐chromatin interactions via deep learning with multi‐omics data
Xiong, Y., He, X., Zhao, D. Y., Jiang, T., & Zeng, J. (2023) · Quantitative Biology · doi:10.15302/j-qb-022-0316 · Cited by 4
Generación de péptidos antimicrobianos mediante redes neuronales recurrentes
Echeverry, A. V., Mera, C., Ordúz, S., & Branch, J. W. (2021) · DYNA · doi:10.15446/dyna.v88n216.88799 · Cited by 4
Antimicrobial Bioceramics for Biomedical Applications
Riccio, P., Zare, M., Gomes, D., Green, D. W., & Stamboulis, A. G. (2022) · Springer series in biomaterials science and engineering · doi:10.1007/978-981-16-7435-8_5 · Cited by 4
Research Advance in the Development of Antimicrobial Peptides Using Deep Learning
Hu, Y., Zhou, J., Gao, Y., Chen, B., Su, J., Li, H., & Wu, W. (2025) · Journal of Computational Chemistry · doi:10.1002/jcc.70203 · Cited by 3
“AALF refers to the sequence-based textual features of peptides, which can be utilized as input for RNN [70, 71], LSTM [72, 73], CNN [74, 75], and similar architectures.”
Zhaxi, Y., Xiang, Y., Zou, J., & Zhang, F. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.804447 · Cited by 3
“This section elaborates on the DL model, such as the popular recurrent neural network (RNN) (Bueno et al., 2018; Müller and Hiss, 2018; Pang et al., 2020).”
MethodApplication of artificial intelligence in pharmaceutical development
Mourelatou, E. A., Iosif, E., Galatou, E., Sarigiannis, Y. M., Vlasiou, M. C., Zacharia, L. C., & Petrou, C. C. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-91816-9.00009-6 · Cited by 4
Nie, Z., Li, D., Liu, Y., Xu, F., Zhang, H., Huang, X., Liu, X., Wang, Z., Ma, Y., Ye, Y., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00623 · Cited by 3
Chen, S., & Kim, H. U. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006253 · Cited by 3
“In terms of the pseudo-probability, our method outperformed the previously developed LSTM RNN [2] and CVAE [3] models for generating AMPs; the best P (AMP) values of our method, LSTM RNN and CVAE were 0.96 (at T = 0.3), 0.83 and 0.84, respectively.”
MethodInfluentialQuality evaluation of preschool video games based on RNN
Tian, J. (2023) · Entertainment Computing · doi:10.1016/j.entcom.2023.100581 · Cited by 3
Generative models for antimicrobial peptide design: auto-encoders and beyond
Beierle, L., Hahnfeld, J. M., Goesmann, A., Mostolizadeh, R., & Cemič, F. (2026) · BioData Mining · doi:10.1186/s13040-026-00558-w · Cited by 2
“Conversely, the recurrent neural network demonstrated notable efficacy, as previously reported [17].”
InfluentialLipopeptide Engineering: From Natural Origins to Rational Design Against Antimicrobial Resistance
Xie, S.-Y., He, F.-J., Yang, Y.-Y., Tao, Y., & Wang, X. (2026) · Antibiotics · doi:10.3390/antibiotics15010100 · Cited by 2
Metadata
- Authors
- Müller, A. T., Hiss, J. A., & Schneider, G.
- Affiliations
- ETH Zurich (CH)
- Corresponding author
- Schneider, Gisbert
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2018-01-22
- Volume
- 58
- Issue
- 2
- Pages
- 472-479
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2784920021
- Cited by
- 270
- References
- 50
- Citations by year
- 2026: 31 · 2025: 40 · 2024: 39 · 2023: 33 · 2022: 31 · 2021: 37 · 2020: 17 · 2019: 29 · 2018: 13
- FWCI
- 17.95
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Chemical Information and Modeling (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Schweizerischer Nationalfonds zur F?rderung der Wissenschaftlichen Forschung (200021_157190)
- Topics
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Life Sciences › Immunology and Microbiology › Microbiology › Antimicrobial Peptides and Activities
- Physical Sciences › Chemistry › Organic Chemistry › Chemical Synthesis and Analysis
- Keywords
- de novo peptide design, long short-term memory, antimicrobial peptides, helical peptides, sequence generation, peptide libraries, amphipathic helix, applicability domain, protein design
- MeSH terms
- Machine Learning, Amino Acid Sequence, Anti-Infective Agents, Models, Chemical, Peptides, Neural Networks, Computer
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.