Identifying Structure-Activity Relationships for Cyanine-Derived Antibiotics Using Machine Learning and Commercial Large Language Models

Understanding the structure-activity relationship (SAR) of antibiotic scaffolds is crucial for the development of antibiotics to counter the growing crisis of antimicrobial resistant bacteria. However, an overwhelming space of structural features impairs a comprehensive understanding of the mechanism of action for potential antibiotic candidates. In this study, antibacterial data of a set of newly synthesized cyanine molecules are analyzed with both traditional machine learning (ML) and commercially available large language models (LLMs) to elucidate the SAR. Some LLMs, particularly Grok-3 Think and ChatGPT o1, outperform the traditional ML classifiers, and both approaches highlight positive charges and lipophilicity as key properties for effective cyanine antibiotics.

• Publication year

  2025

• Venue

  Journal of Chemical Information and Modeling

• Publication date

  2025-11-09

• Fields of study

  Medicine, Chemistry, Computer Science

• Identifiers
  DOI 10.1021/acs.jcim.5c01321PMID 41208124
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Application of Large Language Models in Drug-Induced Osteotoxicity Prediction

  2025cited by this paper
• How to Build Plasmon‐Driven Molecular Jackhammers that Disassemble Cell Membranes and Cytoskeletons in Cancer

  2024cited by this paper
• Cyanine dyes in the mitochondria-targeting photodynamic and photothermal therapy

  2024cited by this paper
• Improving the Accuracy of Permeability Data to Gain Predictive Power: Assessing Sources of Variability in Assays Using Cell Monolayers

  2024cited by this paper
• Towards structurally new cyanine dyes—investigating the photophysical and potential antifungal properties of linear substituted heptamethine dyes

  2024cited by this paper
• How successful are AI-discovered drugs in clinical trials? A first analysis and emerging lessons.

  2024cited by this paper
• Evaluation metrics and statistical tests for machine learning

  2024cited by this paper
• In-context learning enables multimodal large language models to classify cancer pathology images

  2024cited by this paper
• Discovery of new antiviral agents through artificial intelligence: In vitro and in vivo results.

  2024cited by this paper
• Quaternary Ammonium Compounds: A Chemical Class of Emerging Concern

  2023cited by this paper
• Why open-source generative AI models are an ethical way forward for science

  2023cited by this paper
• A Survey on In-context Learning

  2022cited by this paper
• Global burden of bacterial antimicrobial resistance in 2019: a systematic analysis

  2022cited by this paper
• Artificial intelligence to guide precision anticancer therapy with multitargeted kinase inhibitors

  2022cited by this paper
• Highly efficient near-IR cyclohexene cyanine photosensitizers for antibacterial photodynamic therapy

  2022cited by this paper
• On evaluation metrics for medical applications of artificial intelligence

  2021cited by this paper
• Ensemble modeling with machine learning and deep learning to provide interpretable generalized rules for classifying CNS drugs with high prediction power

  2021cited by this paper
• Estimating clinical research project duration from idea to publication

  2021cited by this paper
• Cyanine dye mediated mitochondrial targeting enhances the anti-cancer activity of small-molecule cargoes.

  2020cited by this paper
• A pleurocidin analogue with greater conformational flexibility, enhanced antimicrobial potency and in vivo therapeutic efficacy

  2020cited by this paper
• Array programming with NumPy

  2020cited by this paper
• The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation

  2020cited by this paper
• A Deep Learning Approach to Antibiotic Discovery.

  2020cited by this paper
• FP2VEC: a new molecular featurizer for learning molecular properties

  2019cited by this paper
• Recent development of membrane-active molecules as antibacterial agents.

  2019cited by this paper
• Analysis of the Destabilization of Bacterial Membranes by Quaternary Ammonium Compounds: A Combined Experimental and Computational Study

  2019cited by this paper
• Molecular Dynamics Simulations of Membrane Permeability.

  2019cited by this paper
• Vital Signs: Epidemiology and Recent Trends in Methicillin-Resistant and in Methicillin-Susceptible Staphylococcus aureus Bloodstream Infections — United States

  2019cited by this paper
• Antimicrobial Resistance: Implications and Costs

  2019cited by this paper
• Targeting and Imaging of Mitochondria Using Near-Infrared Cyanine Dye and Its Application to Multicolor Imaging

  2019cited by this paper
• Cell penetrating, mitochondria targeting multiply charged DABCO-cyanine dyes

  2018cited by this paper
• Estimation of clinical trial success rates and related parameters

  2018cited by this paper
• Mordred: a molecular descriptor calculator

  2018cited by this paper
• A new structure–activity relationship for cyanine dyes to improve photostability and fluorescence properties for live cell imaging† †Electronic supplementary information (ESI) available: Synthetic procedures, experimental procedures, DNA preparation, optical measurements, cell images and complete an

  2018cited by this paper
• Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric

  2017cited by this paper
• An overview of molecular fingerprint similarity search in virtual screening

  2016cited by this paper
• Synthesis, spectroscopic and antimicrobial studies of some novel cyanine dyes based on bis-coumarin heterocycles derivatives

  2016cited by this paper
• Antimicrobial Activity of Cationic Antimicrobial Peptides against Gram-Positives: Current Progress Made in Understanding the Mode of Action and the Response of Bacteria

  2016cited by this paper
• Analysis of Antimicrobial-Triggered Membrane Depolarization Using Voltage Sensitive Dyes

  2016cited by this paper
• Cross-validation pitfalls when selecting and assessing regression and classification models

  2014cited by this paper
• Testing Physical Models of Passive Membrane Permeation

  2012cited by this paper
• A Review of Indocyanine Green Fluorescent Imaging in Surgery

  2012cited by this paper
• Classification and regression trees

  2012cited by this paper
• Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions

  2009cited by this paper
• Where are all the new antibiotics? The new antibiotic paradox.

  2005cited by this paper
• Numeric mapping and learnability of naive bayes

  2003cited by this paper
• Quinoline and cyanine dyes--putative anti-MRSA drugs.

  2003cited by this paper
• Generalized Linear Models

  2002cited by this paper
• Greedy function approximation: A gradient boosting machine.

  2001cited by this paper
• Low Prevalence of Methicillin-Resistant Strains among Staphylococcus aureus Colonizing Young and Healthy Members of the Community in Portugal

  2001cited by this paper
• Acridine-a neglected antibacterial chromophore.

  2001cited by this paper
• Parameter Based Methods for Compound Selection from Chemical Databases

  1996cited by this paper
• SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules

  1988cited by this paper
• The antibacterial action of crystal violet *

  1967cited by this paper
• Individual Comparisons by Ranking Methods

  1945cited by this paper
• THE ANTISEPTIC PROPERTIES OF CYANINE DYES *

  1922cited by this paper
• Promoting Access to White Rose Research Papers Similarity-based Virtual Screening Using 2d Fingerprints

  year unknowncited by this paper

• No citing papers are available for this paper.