A machine learning framework to predict antibiotic resistance traits and yet unknown genes underlying resistance to specific antibiotics in bacterial strains.

Recently, the frequency of observing bacterial strains without known genetic components underlying phenotypic resistance to antibiotics has increased. There are several strains of bacteria lacking known resistance genes; however, they demonstrate resistance phenotype to drugs of that family. Although such strains are fewer compared to the overall population, they pose grave emerging threats to an already heavily challenged area of antimicrobial resistance (AMR), where death tolls have reached ~700 000 per year and a grim projection of ~10 million deaths per year by 2050 looms. Considering the fact that development of novel antibiotics is not keeping pace with the emergence and dissemination of resistance, there is a pressing need to decipher yet unknown genetic mechanisms of resistance, which will enable developing strategies for the best use of available interventions and show the way for the development of new drugs. In this study, we present a machine learning framework to predict novel AMR factors that are potentially responsible for resistance to specific antimicrobial drugs. The machine learning framework utilizes whole-genome sequencing AMR genetic data and antimicrobial susceptibility testing phenotypic data to predict resistance phenotypes and rank AMR genes by their importance in discriminating the resistance from the susceptible phenotypes. In summary, we present here a bioinformatics framework for training machine learning models, evaluating their performances, selecting the best performing model(s) and finally predicting the most important AMR loci for the resistance involved.

Elicitors and defense gene induction in plants with altered lignin compositions.

A reduction in the lignin content in transgenic plants induces the ectopic expression of defense genes, but the importance of altered lignin composition in such phenomena remains unclear. Two Arabidopsis lines with similar lignin contents, but strikingly different lignin compositions, exhibited different quantitative and qualitative transcriptional responses. Plants with lignin composed primarily of guaiacyl units overexpressed genes responsive to oomycete and bacterial pathogen attack, whereas plants with lignin composed primarily of syringyl units expressed a far greater number of defense genes, including some associated with cis-jasmone-mediated responses to aphids; these plants exhibited altered responsiveness to bacterial and aphid inoculation. Several of the defense genes were differentially induced by water-soluble extracts from cell walls of plants of the two lines. Glycome profiling, fractionation and enzymatic digestion studies indicated that the different lignin compositions led to differential extractability of a range of heterogeneous oligosaccharide epitopes, with elicitor activity originating from different cell wall polymers. Alteration of lignin composition affects interactions with plant cell wall matrix polysaccharides to alter the sequestration of multiple latent defense signal molecules with an impact on biotic stress responses.

Using Machine Learning to Predict Genes Underlying Differentiation of Multipartite and Unipartite Traits in Bacteria.

Since the discovery of the second chromosome in the Rhodobacter sphaeroides 2.4.1 by Suwanto and Kaplan in 1989 and the revelation of gene sequences, multipartite genomes have been reported in over three hundred bacterial species under nine different phyla. This phenomenon shattered the dogma of a unipartite genome (a single circular chromosome) in bacteria. Recently, Artificial Intelligence (AI), machine learning (ML), and Deep Learning (DL) have emerged as powerful tools in the investigation of big data in a plethora of disciplines to decipher complex patterns in these data, including the large-scale analysis and interpretation of genomic data. An important inquiry in bacteriology pertains to the genetic factors that underlie the structural evolution of multipartite and unipartite bacterial species. Towards this goal, here we have attempted to leverage machine learning as a means to identify the genetic factors that underlie the differentiation of, in general, bacteria with multipartite genomes and bacteria with unipartite genomes. In this study, deploying ML algorithms yielded two gene lists of interest: one that contains 46 discriminatory genes obtained following an assessment on all gene sets, and another that contains 35 discriminatory genes obtained based on an investigation of genes that are differentially present (or absent) in the genomes of the multipartite bacteria and their respective close relatives. Our study revealed a small pool of genes that discriminate bacteria with multipartite genomes and their close relatives with single-chromosome genomes. Machine learning thus aided in uncovering the genetic factors that underlie the differentiation of bacterial multipartite and unipartite traits.

Identification of Novel Antimicrobial Resistance Genes Using Machine Learning, Homology Modeling, and Molecular Docking.

Antimicrobial resistance (AMR) threatens the healthcare system worldwide with the rise of emerging drug resistant infectious agents. AMR may render the current therapeutics ineffective or diminish their efficacy, and its rapid dissemination can have unmitigated health and socioeconomic consequences. Just like with many other health problems, recent computational advances including developments in machine learning or artificial intelligence hold a prodigious promise in deciphering genetic factors underlying emergence and dissemination of AMR and in aiding development of therapeutics for more efficient AMR solutions. Current machine learning frameworks focus mainly on known AMR genes and are, therefore, prone to missing genes that have not been implicated in resistance yet, including many uncharacterized genes whose functions have not yet been elucidated. Furthermore, new resistance traits may evolve from these genes leading to the rise of superbugs, and therefore, these genes need to be characterized. To infer novel resistance genes, we used complete gene sets of several bacterial strains known to be susceptible or resistant to specific drugs and associated phenotypic information within a machine learning framework that enabled prioritizing genes potentially involved in resistance. Further, homology modeling of proteins encoded by prioritized genes and subsequent molecular docking studies indicated stable interactions between these proteins and the antimicrobials that the strains containing these proteins are known to be resistant to. Our study highlights the capability of a machine learning framework to uncover novel genes that have not yet been implicated in resistance to any antimicrobials and thus could spur further studies targeted at neutralizing AMR.