The biological logic behind neoantigen vaccines is compelling. Neoantigens arise from somatic mutations that exist only in tumor cells, which means the immune system has not been trained to tolerate them, and the risk of off-target autoimmunity is theoretically low. Advances in next-generation sequencing, HLA typing, immunopeptidomics and synthetic vaccine platforms have made it feasible to sequence a patient’s tumor, identify candidate mutation-derived antigens and manufacture an individualized vaccine in a matter of weeks. Early clinical studies have now established feasibility, safety and immunogenicity across a striking range of solid tumors, including melanoma, pancreatic ductal adenocarcinoma, hepatocellular carcinoma, non-small cell lung cancer, bladder cancer and renal cell carcinoma, using platforms that span mRNA, peptide, DNA, viral vector and dendritic cell technologies.

The clinical momentum is real. In the phase 2b KEYNOTE-942 trial, the individualized mRNA vaccine mRNA-4157, known as V940, combined with pembrolizumab achieved 18-month recurrence-free survival of 79 percent versus 62 percent with pembrolizumab alone in resected melanoma, a hazard ratio of 0.561, with no grade 4 or 5 adverse events attributed to the vaccine. In pancreatic cancer, one of the hardest immunologic targets in oncology, responders to the personalized RNA vaccine autogene cevumeran showed markedly prolonged recurrence-free survival compared with non-responders, with a median not yet reached versus 13.4 months. A phase 3 trial in resected high-risk melanoma, INTerpath-001, is now enrolling roughly 1,089 patients, a sign that the field is moving from proof of concept toward pivotal testing.

Yet beneath these headline numbers lies an uncomfortable attrition problem that the review dissects stage by stage. Only a small fraction of the mutations identified in a tumor ever become genuinely immunogenic vaccine targets. In the autogene cevumeran pancreatic cancer trial, just 11 percent of the administered vaccine neoantigens, 25 out of 230, elicited measurable T-cell responses. In the NeoVax melanoma study, roughly 60 percent of vaccine neoantigens induced CD4-positive T-cell responses but only about 16 percent triggered CD8-positive cytotoxic T cells. A recent systematic evaluation found that only around 22 percent of predicted neoepitopes are actually presented on HLA molecules. Each false positive dilutes the effective immunogenic content of a vaccine that has limited room for passengers.

The root of the problem is that antigen presentation is a multi-step biological process, involving proteasomal cleavage, TAP-mediated transport and peptide-HLA loading, that most computational pipelines compress into a single binding-affinity prediction. Even when a peptide is presented, whether it provokes a functional T-cell response depends on the three-dimensional docking geometry between the peptide-HLA complex and a cognate T-cell receptor, governed by molecular flexibility and peptide conformation that sequence-based models capture poorly. Compounding matters, the scarcity of paired TCR-peptide-MHC datasets and the staggering diversity of the TCR repertoire make generalization across patients extraordinarily difficult. Manufacturing timelines, typically seven to eight weeks for peptide and viral vector platforms, add a further constraint, since tumors can evolve while the vaccine is being built.

This is where the review sees artificial intelligence earning its place, not as a replacement for experiments but as a way to narrow enormous biological and chemical search spaces. At the discovery stage, machine learning frameworks now integrate genomic, transcriptomic and mass spectrometry-based proteomic data to prioritize candidates with multi-layer evidence of expression and presentation. Tools such as ProGeo-neo combine proteomics with patient-specific genomic profiles to confirm protein-level expression, while ImmuneMirror merges whole-exome and RNA sequencing data, and modular workflows like TIminer and pVACtools automate reproducible end-to-end immunogenomic profiling. The authors also highlight the growing importance of noncanonical antigens, derived from alternative open reading frames, aberrant splicing, intron retention, fusion transcripts, circular RNA products and endogenous retroviral elements, some of which may be shared across patients and could inform semi-shared vaccine strategies.

Presentation prediction is where measurable gains have been most convincing. Pan-allelic tools such as NetMHCpan integrate eluted ligand data with binding affinities, and MHCflurry 2.0 folds antigen-processing features into neural network models, achieving an area under the curve of roughly 0.911 for binding classification in a benchmark of 18 predictors across 32 HLA alleles. Newer architectures such as CapHLA jointly model class I and class II presentation, and protein language model-based approaches like MUNIS improve prioritization of presented epitopes. The review also makes a pointed case for CD4-positive T cells, which clinical studies have repeatedly activated, sometimes more frequently than CD8 responses, arguing that HLA class II prediction, despite its computational challenges from open binding grooves and variable peptide lengths, deserves far more attention in vaccine design.

At the T-cell recognition frontier, deep learning is pushing into structure. AlphaFold-based modeling of peptide-HLA and TCR-peptide-HLA complexes can discriminate true target epitopes from decoys, while tools such as NetTCR-2.0, DeepTCR, TRAP and SageTCR integrate paired TCR sequences and three-dimensional structural features to predict receptor binding. Benchmarking studies, however, consistently show that these models remain strongly data-dependent and often fail to generalize to unseen epitopes, so the authors position them as prioritization and hypothesis-generating tools rather than definitive immunogenicity predictors. Downstream, AI is also reshaping formulation science: the AGILE platform uses deep learning-guided screening to identify ionizable lipids for mRNA delivery, and the LiON framework applies message-passing neural networks to large lipid nanoparticle datasets, narrowing chemical design spaces before any wet-lab testing begins.

To tie these threads together, the authors propose an evidence-weighted, closed-loop decision-gate framework spanning six stages: candidate generation, tumor relevance filtering, HLA presentation evidence, immunogenicity refinement, portfolio-level selection, and manufacturability and clinical delivery, with post-vaccination immune monitoring data fed back to refine future models. They stress that repertoire size should reflect biologically meaningful coverage rather than numerical abundance, since no clinically validated optimal neoantigen count exists. On the regulatory front, the UK’s Medicines and Healthcare products Regulatory Agency has released draft guidance for individualized mRNA cancer immunotherapies, in which AI selection algorithms may qualify as Software as a Medical Device, requiring Good Machine Learning Practice, transparent pipelines, version tracking and barcode-based traceability linking genomic data to the administered dose. The review’s bottom line is measured but optimistic: AI will not conjure effective cancer vaccines on its own, but embedded within rigorous experimental validation, scalable manufacturing and evolving regulatory oversight, it may finally make personalized neoantigen vaccination a reproducible pillar of precision oncology.

Subject of Research: The application of artificial intelligence across the translational development pipeline of personalized neoantigen cancer vaccines, including neoantigen discovery, HLA presentation prediction, T-cell recognition modeling and formulation optimization.

Article Title: Artificial intelligence for translational personalized neoantigen cancer vaccine development

Article References: Artificial intelligence for translational personalized neoantigen cancer vaccine development. (n.d.). https://doi.org/10.1186/s12929-026-01286-3

Image Credits: AI Generated

DOI: 10.1186/s12929-026-01286-3

Keywords: neoantigen cancer vaccine, artificial intelligence, personalized immunotherapy, HLA presentation, T-cell receptor, lipid nanoparticle, mRNA vaccine, precision oncology, immunopeptidomics, machine learning, cancer immunotherapy, translational oncology

Circulating tumor DNA refers to tiny fragments of cancer-derived DNA that circulate freely in a patient’s bloodstream. Its detection after surgery indicates minimal residual disease (MRD), a state where microscopic tumor cells persist and could eventually drive cancer relapse. Traditionally, clinicians lacked robust tools to identify MRD, leading to a one-size-fits-all approach in post-operative treatment. The IMvigor011 trial utilized a highly personalized ctDNA assay, with blood samples screened every six weeks for up to a year following surgery. This rigorous monitoring enabled researchers to classify patients into ctDNA-positive or ctDNA-negative groups, guiding targeted immunotherapeutic intervention.

Atezolizumab functions by blocking PD-L1, a protein frequently overexpressed on cancer cells that suppresses the immune system’s ability to recognize and attack tumors. By inhibiting this checkpoint, atezolizumab effectively unmasks cancer cells, allowing T cells to mount an immune response. While previous studies, including the IMvigor010 trial, tested atezolizumab in unselected MIBC patients post-surgery, they failed to demonstrate a clear overall survival benefit. Retrospective analyses suggested that this lack of effect was due to the inclusion of patients without residual disease who were unlikely to benefit from immunotherapy, highlighting the need for better patient stratification.

In IMvigor011, 800 patients with no clinical evidence of disease following surgery were enrolled and subjected to personalized ctDNA testing every six weeks. Approximately 250 patients who tested positive for ctDNA were randomized to receive either atezolizumab or placebo in a 2:1 ratio. Strikingly, patients receiving atezolizumab demonstrated a 36% reduction in the risk of disease recurrence compared to placebo. More impressively, the risk of death was reduced by 41% among ctDNA-positive patients receiving the immunotherapy, a landmark finding in the context of adjuvant treatments for MIBC.

Another vital insight from the trial was that ctDNA screening captured patients with residual disease regardless of when ctDNA positivity emerged—from immediately post-surgery or during subsequent surveillance within the first year. This dynamic ability to identify MRD highlights the utility of ctDNA as a real-time biomarker, refining treatment decisions dynamically and enabling clinicians to escalate or withhold therapy based on evolving risk profiles.

Equally important was the observation that ctDNA-negative patients, who did not receive immunotherapy, experienced excellent outcomes. Approximately 89% remained disease-free and over 90% were alive at a median follow-up of 21.8 months without additional treatment. This finding confirms that ctDNA negativity reliably identifies patients with a low risk of recurrence, creating an opportunity to avoid overtreatment and the associated financial and physical burdens.

The absence of new or unexpected adverse effects in the atezolizumab-treated cohort reinforces the safety of this approach when guided by ctDNA stratification. Given the immune-related toxicities known for checkpoint inhibitors, such selective treatment minimizes unnecessary exposure among those unlikely to benefit. This targeted methodology exemplifies personalized medicine’s promise by matching treatment intensity with individual patient biology.

Dr. Joaquim Bellmunt, co-principal investigator and director of the Bladder Cancer Center at Dana-Farber, emphasized the clinical significance: “This is the first adjuvant immunotherapy trial that has demonstrated a survival benefit for patients selected by ctDNA testing. It marks a pivotal step towards precision oncology where therapeutic decisions are no longer ‘one size fits all’ but are tailored to the molecular fingerprints of residual disease.”

The implications for regulatory frameworks and clinical guidelines are profound. Regulatory agencies are currently evaluating whether ctDNA-guided use of atezolizumab should become the new standard of care for MIBC patients after surgery. Adoption of such biomarkers into routine practice could redefine oncological workflows by embedding minimally invasive blood-based diagnostics as decision-making tools for adjuvant therapies.

This study was funded by F. Hoffmann-La Roche Ltd, with collaboration from Natera, a leader in ctDNA assay development. The partnership underscores the critical role of industry-scientific collaboration in rapidly translating molecular diagnostics into clinical impact.

Dana-Farber Cancer Institute, known for its integrative approach to cancer treatment and research, continues to pioneer innovations that bridge laboratory discoveries with patient care. Its involvement in trials like IMvigor011 reinforces its mission to reduce the global cancer burden through scientific inquiry and compassionate, evidence-based care.

In summary, the IMvigor011 trial charts a new course in bladder cancer therapy by harnessing the precision of ctDNA to focus immunotherapy on patients most likely to benefit. This approach offers hope for improved survival while preserving quality of life, setting a precedent for similar strategies in other malignancies where minimal residual disease detection and targeted therapy can intersect to optimize outcomes.

Subject of Research: Muscle-invasive bladder cancer, circulating tumor DNA-guided immunotherapy

Article Title: ctDNA-Guided Adjuvant Atezolizumab in Muscle-Invasive Bladder Cancer

News Publication Date: 20-Oct-2025

Web References:
ESMO 2025 Congress Presentation
New England Journal of Medicine Article

References:
IMvigor011 Phase 3 Clinical Trial Data, Dana-Farber Cancer Institute et al., NEJM, 2025

Image Credits: Dana-Farber Cancer Institute

Keywords: Cancer, Muscle-invasive bladder cancer, Circulating tumor DNA, Immunotherapy, Atezolizumab, Minimal residual disease, Precision oncology