analiza aiqbench
This research presents a lightweight, sequence-aware machine learning framework that effectively predicts antimicrobial resistance by combining 1D CNNs with XGBoost on genomic SNP data. The approach addresses the computational constraints of larger models like Transformers while maintaining high accuracy and interpretability in identifying key genetic markers for drug resistance.
Fusing Sequence Motifs and Pan-Genomic Features: Antimicrobial Resistance Prediction using an Explainable Lightweight 1D CNN-XGBoost Ensemble
arXiv:2509.23552v2 Announce Type: replace Abstract: Antimicrobial Resistance (AMR) is a rapidly escalating global health crisis. While genomic sequencing enables rapid prediction of resistance phenotypes, current computational methods have limitations. Standard machine learning models treat the genome as an unordered collection of features, ignoring the sequential context of Single Nucleotide Polymorphisms (SNPs). State-of-the-art sequence models like Transformers are often too data-hungry and computationally expensive for the moderately sized datasets that are typical in this domain. To address these challenges, we propose AMR-EnsembleNet, an ensemble framework that synergistically combines sequence-based and feature-based learning. We developed a lightweight, custom 1D Convolutional Neural Network (CNN) to efficiently learn predictive sequence motifs from high-dimensional SNP data. This sequence-aware model was ensembled with an XGBoost model, a powerful gradient boosting system adept at capturing complex, non-local feature interactions. We trained and evaluated our framework on a benchmark dataset of 809 E. coli strains, predicting resistance across four antibiotics with varying class imbalance. Our 1D CNN-XGBoost ensemble consistently achieved top-tier performance across all the antibiotics, reaching a Matthews Correlation Coefficient (MCC) of 0.926 for Ciprofloxacin (CIP) and the highest Macro F1-score of 0.691 for the challenging Gentamicin (GEN) AMR prediction. We also show that our model consistently focuses on SNPs within well-known AMR genes like fusA and parC, confirming that it learns the correct genetic signals for resistance. Our work demonstrates that our ensemble model overcomes the limitations of using either an order-agnostic or a standalone sequence model. Our codes are publicly available on GitHub at: https://github.com/Saiful185/AMR-EnsembleNet.
Abstract:Antimicrobial Resistance (AMR) is a rapidly escalating global health crisis. While genomic sequencing enables rapid prediction of resistance phenotypes, current computational methods have limitations. Standard machine learning models treat the genome as an unordered collection of features, ignoring the sequential context of Single Nucleotide Polymorphisms (SNPs). State-of-the-art sequence models like Transformers are often too data-hungry and computationally expensive for the moderately sized datasets that are typical in this domain. To address these challenges, we propose AMR-EnsembleNet, an ensemble framework that synergistically combines sequence-based and feature-based learning. We developed a lightweight, custom 1D Convolutional Neural Network (CNN) to efficiently learn predictive sequence motifs from high-dimensional SNP data. This sequence-aware model was ensembled with an XGBoost model, a powerful gradient boosting system adept at capturing complex, non-local feature interactions. We trained and evaluated our framework on a benchmark dataset of 809 E. coli strains, predicting resistance across four antibiotics with varying class imbalance. Our 1D CNN-XGBoost ensemble consistently achieved top-tier performance across all the antibiotics, reaching a Matthews Correlation Coefficient (MCC) of 0.926 for Ciprofloxacin (CIP) and the highest Macro F1-score of 0.691 for the challenging Gentamicin (GEN) AMR prediction. We also show that our model consistently focuses on SNPs within well-known AMR genes like fusA and parC, confirming that it learns the correct genetic signals for resistance. Our work demonstrates that our ensemble model overcomes the limitations of using either an order-agnostic or a standalone sequence model. Our codes are publicly available on GitHub at: this https URL.
Published in the proceedings of SCA/HPCAsia 2026. Also available on bioRxiv for visibility to the life sciences community. Published version is available at: this https URL
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Genomics (q-bio.GN); Quantitative Methods (q-bio.QM)
arXiv:2509.23552 [cs.LG]
(or arXiv:2509.23552v2 [cs.LG] for this version)
https://doi.org/10.1145/3773656.3773682 DOI(s) linking to related resources
From: Md. Saiful Bari Siddiqui [view email] [v1] Sun, 28 Sep 2025 01:19:11 UTC (453 KB) [v2] Sat, 5 Sep 2026 20:06:10 UTC (457 KB)
Text integral sub licența deschisă a publicației · 323 cuvinte
Subiecte conexe
AlphaGenome Atlas: A predictive map of every possible DNA letter change in the human genome
Google DeepMind · 8 sept. 2026
Accelerating the search for antimicrobial peptides with Google Antigravity
Google DeepMind · 15 oct. 2026
Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models
arXiv · 23 iul. 2026
Google DeepMind Releases AlphaGenome Atlas With Precomputed Molecular Effect Predictions and AVI Scores for 9 Billion Human DNA Variants
MarkTechPost · 8 sept. 2026