HMD-ARG: hierarchical multi-task deep learning for annotating antibiotic resistance genes

Abstract

Background The spread of antibiotic resistance has become one of the most urgent threats to global health, which is estimated to cause 700,000 deaths each year globally. Its surrogates, antibiotic resistance genes (ARGs), are highly transmittable between food, water, animal, and human to mitigate the efficacy of antibiotics. Accurately identifying ARGs is thus an indispensable step to understanding the ecology, and transmission of ARGs between environmental and human-associated reservoirs. Unfortunately, the previous computational methods for identifying ARGs are mostly based on sequence alignment, which cannot identify novel ARGs, and their applications are limited by currently incomplete knowledge about ARGs. Results Here, we propose an end-to-end Hierarchical Multi-task Deep learning framework for ARG annotation (HMD-ARG). Taking raw sequence encoding as input, HMD-ARG can identify, without querying against existing sequence databases, multiple ARG properties simultaneously, including if the input protein sequence is an ARG, and if so, what antibiotic family it is resistant to, what resistant mechanism the ARG takes, and if the ARG is an intrinsic one or acquired one. In addition, if the predicted antibiotic family is beta-lactamase, HMD-ARG further predicts the subclass of beta-lactamase that the ARG is resistant to. Comprehensive experiments, including cross-fold validation, third-party dataset validation in human gut microbiota, wet-experimental functional validation, and structural investigation of predicted conserved sites, demonstrate not only the superior performance of our method over the state-of-art methods, but also the effectiveness and robustness of the proposed method. Conclusions We propose a hierarchical multi-task method, HMD-ARG, which is based on deep learning and can provide detailed annotations of ARGs from three important aspects: resistant antibiotic class, resistant mechanism, and gene mobility. We believe that HMD-ARG can serve as a powerful tool to identify antibiotic resistance genes and, therefore mitigate their global threat. Our method and the constructed database are available at http://www.cbrc.kaust.edu.sa/HMDARG/.

CLMB: deep contrastive learning for robust metagenomic binning

“…CLMB is promising to handle noise, a significant factor that interferes the data precision. Therefore, we believe that our findings can inspire not only the field of metagenomics [41], but also other related fields, like structural and functional fields [42,43,44,45]. For any given number of samples, samples were randomly drawn 3 times and executed independently.…”

Antibiotic resistance: Time of synthesis in a post-genomic age

“…This information is fundamental for manual annotation of the results, but is less amenable for the automatic analysis of ARGs. Hierarchically organized databases as HMD-ARG [218] may help in solving this problem. However, even in these cases further refinement in the annotation is needed to distinguish between phenotypically validated ARGs and predicted ones.…”

“…Information on whether the cause of resistance is a mutation in the gene included in the database and not just to the presence of the gene, if the gene can confer by itself resistance or is a regulator of the expression of the actual ARG, as well as if the gene has been found in mobile elements or is just an intrinsic ARG, must be included in annotations to allow an accurate analysis of resistomes. Hierarchically organized databases, based on well-curated data, including information on resistance antibiotic class, resistance mechanism and gene mobility [218] can help solve this problem.…”

USPNet: unbiased organism-agnostic signal peptide predictor with deep protein language model

“…In addition, we will explore the performance of the proposed USPNet on more datasets and other relevant problems to evaluate the robustness of USPNet. Finally, meta-learning and multi-task learning [31], which have been successfully applied for many data-imbalance and hyperparameter-sensitive problems, will be introduced to continuously improve the robustness of the model.…”