Sequence and Physicochemical Associations with Antimicrobial Peptide Activity against Acinetobacter baumannii: A Homology-Aware Regression and Explainable Machine-Learning Study

Aziza Omari 1 * , Nurlan Sadykov 1, Bakhytzhan Seksenbayev 2, Yerlan Suleimenov 2 3, Assylkhan Bekbayev 2
More Detail
1 School of Pharmacy, Astana Medical University, Astana, Kazakhstan.
2 OLYMP Clinical Diagnostic Laboratories LLP, Astana, Kazakhstan
3 QazGene LLP, Astana, Kazakhstan
* Corresponding Author
J CLIN MED KAZ, Volume 23, Issue 5, pp. 65-75. https://doi.org/10.23950/jcmk/19488
OPEN ACCESS 408 Views 173 Downloads
Download Full Text (PDF)
Author Contributions: Conceptualization, B.S. and A.O.; methodology, B.S., Y.S. and N.S.; validation, Y.S. and N.S.; formal analysis, B.S. and Y.S.; investigation, B.S.; resources, A.B.; data curation, B.S.; writing – original draft preparation, B.S.; writing – review and editing, Y.S., A.B., N.S. and A.O.; visualization, B.S. and Y.S.; supervision, A.B. and A.O.; project administration, A.B. and A.O.; funding acquisition, not applicable. All authors have read and agreed to the submitted version of the manuscript.

Data availability statement: The analysis-ready data, executable code, sensitivity outputs, and fitted model are available at  Zenodo: https://doi.org/10.5281/zenodo.22170145.

Artificial Intelligence (AI) Disclosure Statement: During preparation of this work, the authors used OpenAI ChatGPT to assist with manuscript organization, language refinement, and drafting and debugging of analytical code. All methodological decisions, statistical analyses, references, numerical results, and interpretations were independently reviewed and verified by the authors. The figures were generated deterministically from analysis outputs using Matplotlib; no generative image model was used. The authors take full responsibility for the content.

ABSTRACT

Background: Carbapenem-resistant Acinetobacter baumannii is a critical-priority pathogen, but the available database records were predominantly not annotated for carbapenem resistance. We evaluated associations between interpretable peptide features and A. baumannii minimum inhibitory concentration (MIC), and tested transfer across sequence-disjoint clusters.
Methods: From 1,740 raw records, 809 exact or reported-mean MIC observations were eligible and were aggregated into 525 conservative chemical entities. The outcome was entity-level median log2 MIC in micromolar units. Twelve prespecified sequence and physicochemical features were analyzed by multiple regression with HC3 and 80%-sequence-cluster-robust uncertainty estimates. Peptides sharing at least 80% normalized global identity were kept within the same development or test partition. A median baseline, Elastic Net, Random Forest, and Extra Trees were compared by nested grouped cross-validation; the locked Extra Trees model was evaluated in 104 test entities. Descriptor, assay-metadata, structural, censoring, alignment, homology-threshold, and similarity-domain sensitivities were examined.
Results: Only 19 of 809 observations (2.3%; 14 entities) were explicitly labeled carbapenem-resistant, and 578 (71.4%) lacked a resistance label. Seven features had nominal HC3 P values below 0.05, including negative associations of MIC with charge, mean hydrophobicity, beta-strand hydrophobic moment, cysteine fraction, and C-terminal amidation. Cluster-robust and leave-one-cluster-out analyses reduced precision and showed that the cysteine and N-terminal acetylation findings were concentrated in particular sequence families. Extra Trees showed weak development-set transfer (pooled out-of-fold R²=0.054; mean outer-fold RMSE=2.174, versus 2.236 for the median baseline). In the test set, RMSE was 1.775 log2 units, R² was 0.381 (95% cluster-bootstrap CI -0.024 to 0.543), and Spearman rho was 0.579. Performance weakened when more remote families were separated and in the named-strain-only subset.
Conclusions: The data support hypothesis-generating associations rather than causal feature effects. Predictive transfer to unseen peptide clusters was weak during grouped cross-validation, and the more favorable single test estimate was uncertain. The model is not validated as a stand-alone prioritization method and does not support carbapenem-resistant-specific inference; standardized prospective MIC testing, toxicity and stability assessment, and external validation remain necessary.
Keywords: Acinetobacter baumannii, antimicrobial peptides, minimum inhibitory concentration, homology-aware validation, machine learning, sequence clustering.

CITATION

Omari A, Sadykov N, Seksenbayev B, Suleimenov Y, Bekbayev A. Sequence and Physicochemical Associations with Antimicrobial Peptide Activity against Acinetobacter baumannii: A Homology-Aware Regression and Explainable Machine-Learning Study. J CLIN MED KAZ. 2026;23(5):65-75. https://doi.org/10.23950/jcmk/19488

REFERENCES

  • Antimicrobial Resistance Collaborators. Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis. Lancet. 2022;399(10325):629-655. https://doi.org/10.1016/S0140-6736(21)02724-0
  • GBD 2021 Antimicrobial Resistance Collaborators. Global burden of bacterial antimicrobial resistance 1990-2021: a systematic analysis with forecasts to 2050. Lancet. 2024;404(10459):1199-1226. https://doi.org/10.1016/S0140-6736(24)01867-1
  • World Health Organization. WHO bacterial priority pathogens list, 2024: bacterial pathogens of public health importance to guide research, development and strategies to prevent and control antimicrobial resistance. Geneva: World Health Organization; 2024. ISBN 978-92-4-009346-1.
  • Harding CM, Hennon SW, Feldman MF. Uncovering the mechanisms of Acinetobacter baumannii virulence. Nat Rev Microbiol. 2018;16(2):91-102. https://doi.org/10.1038/nrmicro.2017.148
  • Peleg AY, Seifert H, Paterson DL. Acinetobacter baumannii: emergence of a successful pathogen. Clin Microbiol Rev. 2008;21(3):538-582. https://doi.org/10.1128/CMR.00058-07
  • Mookherjee N, Anderson MA, Haagsman HP, Davidson DJ. Antimicrobial host defence peptides: functions and clinical potential. Nat Rev Drug Discov. 2020;19(5):311-332. https://doi.org/10.1038/s41573-019-0058-8
  • Hancock REW, Sahl HG. Antimicrobial and host-defense peptides as new anti-infective therapeutic strategies. Nat Biotechnol. 2006;24(12):1551-1557. https://doi.org/10.1038/nbt1267
  • Fjell CD, Hiss JA, Hancock REW, Schneider G. Designing antimicrobial peptides: form follows function. Nat Rev Drug Discov. 2012;11(1):37-51. https://doi.org/10.1038/nrd3591
  • Pirtskhalava M, Amstrong AA, Grigolava M, Chubinidze M, Alimbarashvili E, Vishnepolsky B, Gabrielian A, Rosenthal A, Hurt DE, Tartakovsky M. DBAASP v3: database of antimicrobial/cytotoxic activity and structure of peptides as a resource for development of new therapeutics. Nucleic Acids Res. 2021;49(D1):D288-D297. https://doi.org/10.1093/nar/gkaa991
  • Anwer F, Navid A, Faiz F, Haider U, Nasir S, Farooq M, Zahra M, Bano A, Bashir HH, Ahmad M, Abbas SA, Room SE, Saeed MT, Ali A. AbAMPdb: a database of Acinetobacter baumannii specific antimicrobial peptides. Database (Oxford). 2024;2024:baae096. https://doi.org/10.1093/database/baae096
  • Mant CT, Jiang Z, Gera L, Davis T, Nelson KL, Bevers S, Hodges RS. De novo designed amphipathic alpha-helical antimicrobial peptides incorporating Dab and Dap residues on the polar face to treat the Gram-negative pathogen Acinetobacter baumannii. J Med Chem. 2019;62(7):3354-3366. https://doi.org/10.1021/acs.jmedchem.8b01785
  • Chen SP, Chen EHL, Yang SY, Kuo PS, Jan HM, Yang TC, Hsieh MY, Lee KT, Lin CH, Chen RPY. A systematic study of the stability, safety, and efficacy of the de novo designed antimicrobial peptide PepD2 and its modified derivatives against Acinetobacter baumannii. Front Microbiol. 2021;12:678330. https://doi.org/10.3389/fmicb.2021.678330
  • Huang J, Zhang W, Wang A, Jiang Y, Lai Y, Xu Y, Wang C, Zhao J, Zhang P, Ji J. Discovery of antimicrobial peptides targeting Acinetobacter baumannii via a pre-trained and fine-tuned few-shot learning-based pipeline. Nat Commun. 2026;17:2475. https://doi.org/10.1038/s41467-026-69306-2
  • Walsh I, Fishman D, Garcia-Gasulla D, Titma T, Pollastri G, ELIXIR Machine Learning Focus Group, Harrow J, Psomopoulos FE, Tosatto SCE. DOME: recommendations for supervised machine learning validation in biology. Nat Methods. 2021;18(10):1122-1127. https://doi.org/10.1038/s41592-021-01205-4
  • Sidorczuk K, Gagat P, Pietluch F, Kala J, Rafacz D, Bakala L, Slowik J, Kolenda R, Rodiger S, Fingerhut LCHW, Cooke IR, Mackiewicz P, Burdukiewicz M. Benchmarks in antimicrobial peptide prediction are biased due to the selection of negative data. Brief Bioinform. 2022;23(5):bbac343. https://doi.org/10.1093/bib/bbac343
  • Eisenberg D, Weiss RM, Terwilliger TC. The helical hydrophobic moment: a measure of the amphiphilicity of a helix. Nature. 1982;299(5881):371-374. https://doi.org/10.1038/299371a0
  • Rice P, Longden I, Bleasby A. EMBOSS: the European Molecular Biology Open Software Suite. Trends Genet. 2000;16(6):276-277. https://doi.org/10.1016/S0168-9525(00)02024-2
  • Ikai A. Thermostability and aliphatic index of globular proteins. J Biochem. 1980;88(6):1895-1898. https://doi.org/10.1093/oxfordjournals.jbchem.a133168
  • Shannon CE. A mathematical theory of communication. Bell Syst Tech J. 1948;27:379-423, 623-656.
  • MacKinnon JG, White H. Some heteroskedasticity-consistent covariance matrix estimators with improved finite sample properties. J Econom. 1985;29(3):305-325. https://doi.org/10.1016/0304-4076(85)90158-7
  • Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Stat Soc Series B Stat Methodol. 2005;67(2):301-320. https://doi.org/10.1111/j.1467-9868.2005.00503.x
  • Breiman L. Random forests. Mach Learn. 2001;45:5-32. https://doi.org/10.1023/A:1010933404324
  • Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006;63:3-42. https://doi.org/10.1007/s10994-006-6226-1
  • Varma S, Simon R. Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics. 2006;7:91. https://doi.org/10.1186/1471-2105-7-91
  • Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825-2830.
  • Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765-4774.
  • Efron B. Bootstrap methods: another look at the jackknife. Ann Stat. 1979;7(1):1-26. https://doi.org/10.1214/aos/1176344552