★ Latest
AI-Driven Individualized Neoantigen Therapies for Precision Cancer Treatment
Merck and Moderna leverage machine learning to design personalized vaccines targeting unique tumor mutations
TRACKING / ANALYSIS
Analysis of the neoantigen-vaccine field
Deeper, hand-written takes — what the daily brief adds up to over time, read against the data.
More analysis
Fungal Genome Editing Tools Open New Paths for Cancer Therapy
Researchers develop a novel fungal genome-editing mechanism that could revolutionize precision medicine · 2026-07-04
Global Review Confirms mRNA Vaccine Safety and Efficacy After Billions of Doses
A comprehensive UBC-led analysis affirms the safety and effectiveness of mRNA vaccines across billions of administrations · 2026-07-02
China's AI-Powered Personalized Cancer Vaccine Manufacturing Plant
Likang Life Sciences constructs China's first AI-driven facility for personalized tumor vaccines · 2026-07-01
Likang Life Sciences Launches AI-Driven Personalized Cancer Vaccine Production in China
China establishes its first production line for AI-assisted personalized tumor vaccines, targeting tumor-specific mutations with rapid analysis · 2026-06-29
NVIDIA BioNeMo Agent Toolkit Accelerates Life Sciences Discovery
NVIDIA introduces the BioNeMo Agent Toolkit to empower AI agents with domain-specific tools for protein design and drug discovery · 2026-06-28
Transgene's TG4070 Bets In-House AI and Cell-Line Manufacturing on Lung Cancer
With its second myvac candidate, Transgene moves neoantigen selection fully in-house under SNIPER and swaps egg-based vaccine production for scalable cell lines — testing whether a viral-vector platfo · 2026-06-25
AI Redesigns Ionizable Lipids for Neoantigen mRNA Vaccine Delivery
Generative models and molecular dynamics are transforming ionizable lipid discovery from combinatorial screening to computational design · 2026-06-25
Invoke Bio's AI Platform for Custom Neoantigen Cancer Vaccines
This article examines Invoke Bio's proprietary machine learning engine that integrates biomolecular signals to predict immunogenic targets with high accuracy · 2026-06-24
Neoantigen vaccine vs TCR-T cell therapy: key differences
A direct comparison of neoantigen vaccines and neoantigen-reactive TCR-T cell therapy: same upstream target-selection problem, different delivery. Vaccines induce the patient's own T-cell response; TCR-T manufactures and infuses target-specific cells. The trade-offs are HLA restriction, speed, breadth, safety, durability, and trial maturity. · 2026-06-23
Blocking DNA Repair to Overcome Cancer Drug Resistance
Researchers identify UNI418 molecule that degrades RAD51, reversing PARP inhibitor resistance in preclinical models · 2026-06-17
FDA Form 3926: the expanded-access workflow for a personalized cancer vaccine
FDA Form 3926 is the form a physician uses to request individual-patient expanded access ("compassionate use") to an investigational drug — and for a patient who is excluded from every trial, it is the only path to an AI-designed personalized cancer vaccine. A field guide to the Single Patient IND workflow: how Form 3926 works, the clinical rationale and letter of authorization it must carry, the 30-day and emergency timelines, IRB clearance, the ~$100k out-of-pocket reality, and where it fits the N-of-1 regulatory picture. · 2026-06-15
Navigating FDA Expanded Access for Personalized Neoantigen Cancer Vaccines
Explore the pipeline from tumor sequencing to mRNA synthesis for personalized immunotherapies · 2026-06-15
Optimizing Prime Editing via Lipid Nanoparticles for Precision Medicine
This article explores a systematic optimization platform for prime editing lipid nanoparticles to enhance in vivo delivery efficiency · 2026-06-15
Lilly TuneLab: Federated Learning for Biotech Drug Discovery
Eli Lilly launches an AI platform enabling early-stage biotechs to access proprietary drug discovery models · 2026-06-12
AI Is Redesigning the Lipid Shell That Carries Neoantigen mRNA Into Cells
Generative models, transfection predictors, and molecular-dynamics simulations are turning ionizable-lipid discovery from combinatorial guesswork into computation — and reaching the spleen-targeting c · 2026-06-11
ASCO 2026 Abstract Intelligence: Key Trends in Oncology and AI
Analyze 7,282 ASCO 2026 abstracts revealing top drugs like pembrolizumab and the rise of pan-RAS inhibitors · 2026-06-10
ASCO 2026: where personalized cancer vaccines stand — and the landscape around them
A neoag reader's map of ASCO 2026: the three personalized-vaccine readouts that matter (intismeran's five-year melanoma update, NeoVax in glioblastoma, NOUS-209 in Lynch syndrome), the arrival of neoantigen-reactive TCR-T as a real category, the competing modalities (bispecifics, ADCs, ctDNA-guided therapy, pan-RAS), and the readouts that were notably absent. · 2026-06-04
AI neoantigen prediction tools, compared (2026)
A maintained field guide to the neoantigen-prediction toolchain: the end-to-end open-source pipelines (pVACtools, Seq2Neo, NeoPredPipe, pTuneos, OmniNeo and more), the peptide–HLA presentation predictors beneath them (NetMHCpan, MHCflurry, MixMHCpred), and the immunogenicity frontier where the hard, unsolved problem lives. · 2026-05-30
TCR–pMHC models compared: tools, inputs, and limits (2026)
A comparison of TCR–pMHC prediction models by input data, intended regime, availability, and failure mode: NetTCR, ERGO-II, TITAN, STAPLER, MixTCRpred, TABR-BERT, TULIP, tcrLM, pMTnet, epiTCR, TCR-ESM, and structure-based newcomers. · 2026-05-30
NetMHCpan vs MHCflurry: which peptide–HLA predictor should you use?
NetMHCpan-4.1 and MHCflurry 2.0 both predict whether a peptide will be presented by an HLA molecule, but they differ in licensing, scriptability, allele coverage, and class II support. Neither is uniformly better. Here is how to choose, and the caveat that matters more than the choice. · 2026-05-30
Why neoantigen immunogenicity is so hard to predict
HLA binding is largely a solved problem. Antigen presentation is mostly solved. Immunogenicity — whether a presented peptide actually triggers a T-cell response — is not. We unpack why the prediction pipeline breaks at the last step, and how the field is trying to fix it. · 2026-05-30
Foundation models are coming for neoantigen design
Protein and biology foundation models — the ESM lineage, AlphaFold2/3, and BERT-style sequence models — are being aimed at the hardest parts of neoantigen vaccine design: pMHC binding, TCR recognition, and de novo peptide generation. A sharp look at what is demonstrated, what is promised, and the under-appreciated HLA-equity dividend. · 2026-05-30
Personalized vs off-the-shelf neoantigen vaccines
Personalized and off-the-shelf neoantigen vaccines make opposite bets on precision versus scale. We map the tradeoffs in manufacturing, turnaround, cost, applicability and the prevention angle — and where AI fits each — citing the lead programs from Moderna/Merck, BioNTech, Nouscom, Elicio and others. · 2026-05-30
Who’s building neoantigen cancer vaccines (2026)
The companies, platforms, and catalysts in neoantigen cancer vaccines as of mid-2026 — personalized mRNA leaders, AI-native mid-caps, and off-the-shelf shared-antigen approaches, with endpoints and risks called straight. · 2026-05-30
How FDA regulates personalized N-of-1 cancer vaccines
How FDA handles personalized N-of-1 cancer vaccines: process validation, CMC and release specifications, individualized-product precedents, Platform Technology Designation, real program status, and the approval questions a first neoantigen vaccine would settle. · 2026-05-30
A computational blueprint for personalized cancer vaccines
Eight computational phases turn a patient's tumor mutations into a vaccine: HLA typing, variant calling, pMHC binding, immunogenicity, construct assembly, and mRNA optimization. A practical map of the tools — OptiType, pVACtools, ESM-2, LinearDesign — that run each one. · 2026-05-30
The models you can fine-tune for neoantigen design
Foundation models have reached neoantigen discovery — but only some can actually be fine-tuned on your own data. A field guide to the ones that can, grouped by the problem they solve. · 2026-05-30
The neoantigen attention curve
Search interest in “neoantigen” sat near zero for years, then broke out in 2026 to its highest point on record. What the curve means — and its limits. · 2026-05-30