Exploring Gut Microbiome in Predicting the Efficacy of Immunotherapy in Non-Small Cell Lung Cancer

Abstract

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.

Too Much of a Good Thing: The Association of Elevated Vitamin B12 Levels and Outcomes in Patients With Cancer Treated With Immunotherapy

“…In a non-small cell lung cancer cohort, gut microbiota composition by functional rather than taxonomic classification successfully predicted responses to IO, and it is interesting to note that, the model suggested that interactive metabolic processes were regulating the response. 28 These findings were supported by previous studies that demonstrated the importance of amino acids, folate, and VitB12 in the activity of cytotoxic T cells. Meanwhile, in mouse models, probiotics were associated with impaired responses to checkpoint inhibitors and larger tumors.…”

“…The intricate balance of gut microbiota, in turn, has been shown to affect host immune responses, in an immune-metabolic interplay. In a non–small cell lung cancer cohort, gut microbiota composition by functional rather than taxonomic classification successfully predicted responses to IO, and it is interesting to note that, the model suggested that interactive metabolic processes were regulating the response 28 . These findings were supported by previous studies that demonstrated the importance of amino acids, folate, and VitB12 in the activity of cytotoxic T cells.…”

The artificial intelligence and machine learning in lung cancer immunotherapy

“…Immune regulation-related gene profiles in patient biopsy samples were analyzed by Wiesweg et al . [ 52 ] to develop an ML model to predict the impact of genomic information and TME on the therapeutic response for IV NSCLC.…”

The Microbiome-TIME Axis: A Host of Possibilities

“…In fact, in mouse models, disruption of the gut microbiome impacted the response of tumors to immunotherapy [ 65 ]. Studies in humans have also found an association between certain bacterial species within the microbiome and the patient’s response to immunotherapy [ 24 , 25 , 66 ]. Intestinal microbiota have previously been implicated in the modulation of cancer immunotherapy [ 65 ] and chemotherapy [ 67 ].…”

“…As previously discussed, different species within the microbiome confer beneficial immunomodulation while other species result in a cancer-promoting environment. Because of the microbiome-TIME axis, it has been proposed that the microbiome could be used as a clinical predictor of disease course and to predict the likelihood of response and adverse events related to immunotherapy treatment [ 14 , 66 ]. It is imperative that further work is conducted to identify optimal combinations of bacteria so as to optimize the antitumor response and minimize adverse events.…”