Hepatocellular carcinoma (HCC) remains a leading cause of cancer-related mortality, and response rates to anti-PD-1 therapy are suboptimal. Previous models predicting therapy response often fail to provide reliable early predictions, limiting their clinical utility. To develop a robust predictive model based on gut microbiota features that can accurately discriminate between responders (R) and non-responders (NR) to anti-PD-1 therapy at baseline, enhancing early clinical decision-making. We reanalyzed microbiome abundance data from a cohort of HCC patients receiving anti-PD-1 therapy, originally published by Wu et al. 1. By incorporating microbial taxa from phylum to genus levels, we addressed taxonomic assignment uncertainty. Simultaneously, we leveraged low-abundance, informative features via data transformation. Using statistical and machine learning tools, we rectified the informative features, reducing them to 8 key taxa. A neural network model was developed and performance-assessed. Our predictive model, utilizing 8 key microbial taxa, demonstrated an AUROC of 0.784 +/- 0.024 on test data. Also, unlike the negative result of the original publication, our model could also successfully discriminate responders from non-responders at baseline, providing a critical advantage at the early intervention stage. This study presents a clinically valuable predictive model that enhances the ability to forecast responses to anti-PD-1 therapy in HCC patients using gut microbiota features. The model's simplicity and high predictive accuracy offer advantages in personalized treatment planning, contributing to the improvement of patient outcomes in HCC immunotherapy.

All the authors are either current or former employees or shareholders of BluMaiden Biosciences. The authors declare no additional competing interests.

Institutional Research Ethics Committee of the Third Affiliated Hospital were obtained (ID: [2019]02-510-01).

This study did not receive any funding

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study used (or will use) ONLY openly available human data that were originally deposited to NCBI Sequence Read Archive, BioProject PRJCA006814

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes