Potent antibiotic design via guided search from antibacterial activity evaluations

Abstract

Motivation The emergence of drug-resistant bacteria makes the discovery of new antibiotics an urgent issue, but finding new molecules with the desired antibacterial activity is an extremely difficult task. To address this challenge, we established a framework, MDAGS (Molecular Design via Attribute-Guided Search), to optimize and generate potent antibiotic molecules. Results By designing the antibacterial activity latent space and guiding the optimization of functional compounds based on this space, the model MDAGS can generate novel compounds with desirable antibacterial activity without the need for extensive expensive and time-consuming evaluations. Compared with existing antibiotics, candidate antibacterial compounds generated by MDAGS always possessed significantly better antibacterial activity and ensured high similarity. Furthermore, although without explicit constraints on similarity to known antibiotics, these candidate antibacterial compounds all exhibited the highest structural similarity to antibiotics of expected function in the DrugBank database query. Overall, our approach provides a viable solution to the problem of bacterial drug resistance. Availability Code of the model and datasets can be downloaded from GitHub (https://github.com/LiangYu-Xidian/MDAGS). Supplementary information Supplementary data are available at Bioinformatics online.

A Machine Learning Method to Identify Umami Peptide Sequences by Using Multiplicative LSTM Embedded Features

“…K-fold cross-validation and independent testing methods are commonly used to evaluate ML models [ 51 ]. The raw data are separated into k-folds in K-fold cross-validation.…”

ACP-GBDT: An improved anticancer peptide identification method with gradient boosting decision tree

“…The following evaluation indicators are used to demonstrate the performance of our model, including accuracy (ACC), sensitivity (SE), specificity (SP), Mathew’s correlation coefficient (MCC), and the area under the ROC curve (AUC). These evaluation indicators are commonly used in bioinformatics ( Zhou et al, 2022 ; Zhou and Wang, 2022 ; Chen et al, 2023 ; Zhang et al, 2023 ). The calculation formulas of these indicators are as follows: where TP (true positive) represents the number of anticancer peptides correctly predicted, FP (false positive) represents the number of non-anticancer peptides predicted as anticancer peptides, TN (true negative) indicates the number of non-anticancer peptides correctly predicted, and FN (false negative) represents the number of anticancer peptides predicted as non-anticancer.…”

“…The following evaluation indicators are used to demonstrate the performance of our model, including accuracy (ACC), sensitivity (SE), specificity (SP), Mathew's correlation coefficient (MCC), and the area under the ROC curve (AUC). These evaluation indicators are commonly used in bioinformatics Chen et al, 2023;Zhang et al, 2023). The calculation formulas of these indicators are as follows:…”

A systematic pan-cancer analysis reveals the clinical prognosis and immunotherapy value of C-X3-C motif ligand 1 (CX3CL1)

“…The STRING database collects, scores, and integrates information on protein-protein interactions (PPI) ( Szklarczyk et al, 2019 ; Chen et al, 2020 ; Dholaniya and Rizvi, 2021 ; Cui et al, 2022a ; Chen et al, 2023 ). The purpose of the website is to develop a comprehensive and unbiased global network that incorporates both physical and functional interactions.…”