We performed various analyses on the taxonomic and functional features of the gut microbiome from NSCLC patients treated with immunotherapy to establish a model that may predict whether a patient will benefit from immunotherapy. We collected 65 published whole metagenome shotgun sequencing samples along with 14 samples from our previous study. We systematically studied the taxonomical characteristics of the dataset and used both the random forest (RF) and the multilayer perceptron (MLP) neural network models to predict patients with progression-free survival (PFS) above 6 months versus those below 3 months. Our results showed that the RF classifier achieved the highest F-score (85.2%) and the area under the receiver operating characteristic curve (AUC) (95%) using the protein families (Pfam) profile, and the MLP neural network classifier achieved a 99.9% F-score and 100% AUC using the same Pfam profile. When applying the model trained in the Pfam profile directly to predict the treatment response, we found that both trained RF and MLP classifiers significantly outperformed the stochastic predictor in F-score. Our results suggested that such a predictive model based on functional (e.g., Pfam) rather than taxonomic profile might be clinically useful to predict whether an NSCLC patient will benefit from immunotherapy, as both the F-score and AUC of functional profile outperform that of taxonomic profile. In addition, our model suggested that interactive biological processes such as methanogenesis, one-carbon, and amino acid metabolism might be important in regulating the immunotherapy response that warrants further investigation.

Noncoding RNA plays important regulatory and functional roles in microorganisms, such as gene expression regulation, signaling, protein synthesis, and RNA processing. Given its essential role in microbial physiology, it is natural to question whether we can use noncoding RNAs as biomarkers to distinguish among environments under different biological conditions, such as those between healthy versus disease status. The current metagenomic sequencing technology primarily generates short reads, which contain incomplete structural information that may complicate noncoding RNA homology detection. On the other hand, de novo assembly of the metagenomics sequencing data remains fragmentary and has a risk of missing low-abundant noncoding RNAs. To tackle these challenges, we have developed DRAGoM ( D etection of R NA using A ssembly G raph fr o m M etagenomics data), a novel noncoding RNA homology search algorithm. DRAGoM operates on a metagenome assembly graph, rather than on unassembled reads or assembled contigs. Our benchmark experiments show DRAGoM’s improved performance and robustness over the traditional approaches. We have further demonstrated DRAGoM’s real-world applications in disease characterization via analyzing a real case-control gut microbiome dataset for Type-2 diabetes (T2D). DRAGoM revealed potential ncRNA biomarkers that can clearly separate the T2D gut microbiome from those of healthy controls. DRAGoM is freely available from https://github.com/benliu5085/DRAGoM .