Neoantigen × AI
Daily research signal
№48Brief

Evaxion: two-year responses in 12 of 16 melanoma patients

Today's brief spans the full neoantigen stack: clinical proof points (Evaxion's two-year phase 2 melanoma data, a randomized Phase I viral-vector vaccine in resected head and neck cancer), institutional compute investment (a NEDO-backed quantum computing consortium led by NEC and Taiho), and discovery methods aimed at the field's core bottleneck of finding neoantigens T cells actually see.Stock TitanNatureelectronicsmedia.info

The through-line for investors: target identification and immune validation are getting more capital and better tools just as clinical programs broaden beyond advanced melanoma.

4new stories3 in context
ClinicaltodayNew

Two-year data showed 12 of 16 melanoma patients responded. Evaxion will present new immune data in November. - Stock Titan

Evaxion (EVAX) reported two-year phase 2 data for its personalized neoantigen vaccine EVX-01 plus pembrolizumab in advanced melanoma: 12 of 16 patients responded, and 86% of EVX-01 neoantigen targets triggered a tumor-specific immune response. New analyses looking beyond vaccine-specific T-cell responses at effects across the immune system will be presented orally and as posters at SITC 2026 in November. Durable follow-up paired with mechanistic depth is the data package a clinical-stage vaccine developer needs for partnership conversations and next-trial design.

news · today · Stock Titan

03

01
CommercialtodayNew

Quantum Computing in Cancer Immunotherapy: NEC and Partners Launch New Drug Discovery Project - electronicsmedia.info

A five-organization consortium of NEC, Taiho Pharmaceutical, the Japanese Foundation for Cancer Research, AIST, and Waseda University was selected under NEDO's Large-Scale Demonstration for Use Case Creation (Post-5G ICT infrastructure program) to build a quantum-computing-based computational and evaluation platform for next-generation cancer immunotherapy, integrating quantum computing, AI, drug discovery, and immunology to enable optimal design and immunological validation. The implication: a pharma sponsor plus national institutes treating immunotherapy design as a government-funded compute-infrastructure problem rather than a one-off pipeline asset.

news · today · electronicsmedia.info
02
AI / MethodstodayNew

Organoid Platform Uncovers mITGB2 as a Promising CD4-Targeting Neoantigen in Liver Cancer - Bioengineer.org

A team at Sichuan Cancer Hospital and collaborating institutions in Chengdu reports in Cancer Immunology, Immunotherapy a tumor organoid screening platform that surfaced mITGB2, an MHC class II-restricted neoantigen in hepatocellular carcinoma capable of driving a CD4-positive Th1 response against liver cancer cells. Two things matter: it works the underexploited CD4/class II axis rather than the standard CD8/MHC I route, and it validates organoids as a functional discovery screen in a tumor where poor antigen presentation and T-cell exhaustion blunt checkpoint inhibitor benefit. For target discovery pipelines, class II-restricted antigens remain an underbuilt asset class.

news · today · Bioengineer.org
03
AI / Methods2 days agoNew

Beyond HCD: complementary fragmentation chemistries expand HLA class I immunopeptidome discovery

A preprint reports what the authors describe as the first application of ion trap CID and IRMPD fragmentation to HLA class I immunopeptidomics, testing four HLA-typed cell lines in technical triplicate against the canonical proteome and a Ribo-seq-derived cryptic ORF database on an Orbitrap Tribrid Apex MultiOmics. Because the peptide is itself the therapeutic target, ligands that HCD misses are targets never found, so complementary activation chemistries directly widen the addressable neoantigen pool. The catch for the AI stack: fragment-intensity predictors like AlphaPeptDeep are trained almost exclusively on HCD spectra and had to be fine-tuned per method, meaning wet-lab protocol changes propagate straight into model pipelines.

biorxiv · 2 days ago · Lim Kam Sian, T. C. C.; Salvato, F.; Selvakumar, N.; Shamekhi, T.; Hinkle, J.; Mullen, C.;

03

Relevant work from earlier we're still surfacing — not today's news.