eMIC-AntiKP: Estimating minimum inhibitory concentrations of antibiotics towards Klebsiella pneumoniae using deep learning

Identifying the DNA methylation preference of transcription factors using ProtBERT and SVM

Transcription factors (TFs) can affect gene expression by binding to certain specific DNA sequences. This binding process of TFs may be modulated by DNA methylation. A subset of TFs that serve as methylation readers preferentially binds to certain methylated DNA and is defined as TFPM. The identification of TFPMs enhances our understanding of DNA methylation's role in gene regulation. However, their experimental identification is resource-demanding. In this study, we propose a novel two-step computational approach to classify TFs and TFPMs. First, we employed a fine-tuned ProtBERT model to differentiate between the classes of TFs and non-TFs. Second, we combined the Reduced Amino Acid Category (RAAC) with K-mer and SVM to predict the potential of TFs to bind to methylated DNA. Comparative experiments demonstrate that our proposed methods outperform all existing approaches and emphasize the efficiency of our computational framework in classifying TFs and TFPMs. Cross-species validation on an independent mouse dataset further demonstrates the generalizability of our proposed framework In addition, we conducted predictions on all human transcription factors and found that most of the top 20 proteins belong to the Krueppel C2H2-type Zinc-finger family. So far, some studies have demonstrated a partial correlation between this family and DNA methylation and confirmed the preference of some of its members, thereby showing the robustness of our approach.

Integrating genomic and molecular data to predict antimicrobial minimum inhibitory concentration in Klebsiella pneumoniae

Minimum inhibitory concentration (MIC) denotes the in vitro benchmark indicating the quantity of antibiotic required to inhibit proliferation of specific bacterial strains. Determining MIC values corresponding to the infecting bacterial strain is paramount for tailoring appropriate antibiotic therapy. In the interim between specimen collection and laboratory-derived MIC outcomes, clinicians frequently resort to empirical therapy informed by retrospective analyses. Here introduces two deep learning approaches, a Convolutional Neural Network (CNN)-based model and an Enformer-based model, integrating genomic data of Klebsiella Pneumoniae and molecular structural data of 20 antibiotics to anticipate the MIC value of the bacterium for each antibiotic under consideration. These models demonstrate enhanced raw accuracy over the existing state-of-the-art model, which rely exclusively on genomic data. The CNN-based model achieves a notable 20% increase in raw accuracy while further mirroring the 1-tier accuracy of the state-of-the-art model. Although the Enformer-based model does not quite reach the performance levels of the CNN-based model, it offers an advantage by eliminating the need for arbitrary data processing steps. This streamlining of the data processing pipeline facilitates fast updates and improves the model interpretability. It is expected that these deep learning paradigms can significantly inform and bolster clinician decision-making during the empirical treatment phase.

Machine learning and feature extraction for rapid antimicrobial resistance prediction of Acinetobacter baumannii from whole-genome sequencing data

Background

Whole-genome sequencing (WGS) has contributed significantly to advancements in machine learning methods for predicting antimicrobial resistance (AMR). However, the comparisons of different methods for AMR prediction without requiring prior knowledge of resistance remains to be conducted.

Methods

We aimed to predict the minimum inhibitory concentrations (MICs) of 13 antimicrobial agents against Acinetobacter baumannii using three machine learning algorithms (random forest, support vector machine, and XGBoost) combined with k-mer features extracted from WGS data.

Results

A cohort of 339 isolates was used for model construction. The average essential agreement and category agreement of the best models exceeded 90.90% (95%CI, 89.03-92.77%) and 95.29% (95%CI, 94.91-95.67%), respectively; the exceptions being levofloxacin, minocycline and imipenem. The very major error rates ranged from 0.0 to 5.71%. We applied feature selection pipelines to extract the top-ranked 11-mers to optimise training time and computing resources. This approach slightly improved the prediction performance and enabled us to obtain prediction results within 10 min. Notably, when employing these top-ranked 11-mers in an independent test dataset (120 isolates), we achieved an average accuracy of 0.96.

Conclusion

Our study is the first to demonstrate that AMR prediction for A. baumannii using machine learning methods based on k-mer features has competitive performance over traditional workflows; hence, sequence-based AMR prediction and its application could be further promoted. The k-mer-based workflow developed in this study demonstrated high recall/sensitivity and specificity, making it a dependable tool for MIC prediction in clinical settings.