• $50 million Series B raised — PeptideTherapeutics Inc. closed the round to accelerate the based cancer immunotherapy platform and advance three clinical-stage candidates targeting melanoma, NSCLC, and colorectal cancer.
• Machine-learning-driven neoantigen selection — The platform uses computational algorithms to identify patient-specific tumor mutations and design customized peptide vaccines.
• Early efficacy signals — Early-phase trials report objective response rates above 30% in heavily pretreated populations, with favorable safety profiles.
• Pivotal trials planned for 2027 — The company is preparing for later-stage studies and exploring strategic partnerships with major pharmaceutical firms.
• Research use only — No product is approved for human use; all investigational candidates are available only through clinical trials.

The based cancer immunotherapy platform represents a focused effort to turn tumor-specific mutations into actionable immune targets. PeptideTherapeutics Inc. is a clinical-stage company, meaning it has moved beyond preclinical discovery and into human trials, but none of its candidates have regulatory approval. The $50 million Series B round provides the capital needed to expand clinical development, refine the machine learning engine, and prepare for later-stage studies.

This funding announcement is significant for the peptide research community because it validates a neoantigen-directed approach to immunotherapy. Rather than relying on broad immune activation, this based cancer immunotherapy platform seeks to identify peptide sequences unique to a patient’s tumor. Those sequences can then be formulated into vaccines intended to train T cells to recognize cancer cells. All of this work remains strictly investigational, and any laboratory peptides referenced on this site are for in vitro research only.

This development program is not a product that researchers can purchase. It is a development program with three clinical candidates. Researchers interested in the underlying science should consult peer-reviewed literature and clinical trial registries. For a broader explanation of peptide mechanisms, see How Peptides Work: A Plain-English Explainer.

At the core of PeptideTherapeutics’ approach is a machine learning engine built to solve one of oncology’s hardest problems: identifying which molecular markers make a patient’s tumor recognizably different from healthy tissue. The based cancer immunotherapy platform uses machine learning algorithms to identify tumor-specific neoantigens — mutated protein fragments that arise from genetic changes inside cancer cells — and to design customized peptide vaccines for individual patients.

Because neoantigens are found on tumor cells rather than normal tissue, they represent an attractive class of targets for therapies intended to direct the immune system precisely at a patient’s cancer. Once candidate neoantigens are identified, the system designs short peptide sequences corresponding to those targets. When delivered as a vaccine within the clinical-trial setting, these peptides are intended to train the patient’s immune system — specifically T cells — to recognize and attack cells displaying the selected neoantigens.

This personalized approach aims to stimulate robust T-cell responses against cancer cells while minimizing off-target effects. That second element matters as much as the first: off-target immune activity is a central safety concern in immunotherapy generally, and precision in target selection is the primary lever available to reduce it. By filtering for tumor-specific neoantigens computationally before a vaccine is ever manufactured, the company is attempting to build specificity into the therapy from the design stage rather than managing it after the fact.

Key measurable attributes of the platform as disclosed by PeptideTherapeutics include:

• Modality: personalized, neoantigen-directed peptide vaccines.
• Discovery engine: machine learning algorithms for neoantigen identification and vaccine design.
• Targeting logic: tumor-specific neoantigens selected to maximize T-cell response while minimizing off-target effects.
• Development focus: solid tumors.

This approach thus illustrates how computational neoantigen selection can aim to increase T-cell specificity while reducing the risk of off-target immune activity. No product associated with this program is available outside clinical trials. All information here is provided for educational purposes only, and any laboratory peptides supplied by this site are strictly for in vitro research and must not be used in humans or animals.

💡 Key Takeaway: How Does the Based Cancer Immunotherapy Platform Work?

Neoantigens are mutated peptide fragments that arise from somatic mutations in cancer cells. Unlike shared tumor-associated antigens, neoantigens are unique to an individual patient’s tumor and are not expressed on normal tissue. This property makes them attractive targets for cancer immunotherapy because T cells trained against neoantigens can, in theory, attack cancer cells while sparing healthy cells.

The process of identifying neoantigens begins with tumor biopsy and next-generation sequencing to identify somatic mutations. Computational pipelines then predict which mutated peptides will bind to the patient’s major histocompatibility complex (MHC) molecules with high affinity. Peptide vaccines based on these predictions aim to elicit T-cell responses against the selected neoantigens. The based cancer immunotherapy platform applies this logic at scale.

For researchers, neoantigen selection is a critical quality control step. Poorly selected neoantigens can lead to off-target immune responses or weak T-cell activation. The machine learning component of this based cancer immunotherapy platform exists precisely to reduce that risk by ranking candidate peptides according to predicted MHC binding and immunogenicity. Peer-reviewed studies on personalized neoantigen vaccines in melanoma illustrate both the promise and the complexity of this field. For example, Ott et al. (2017) reported early clinical results in melanoma patients using a personalized neoantigen vaccine (PubMed).

Machine learning transforms neoantigen selection from a manual, error-prone process into a scalable, data-driven pipeline. The based cancer immunotherapy platform uses supervised learning models trained on large datasets of peptide-MHC binding affinities and T-cell reactivity. These models rank candidate neoantigens by predicted immunogenicity, filtering out peptides that are unlikely to elicit a response.

Traditional approaches often rely on simple binding affinity cutoffs, which generate many false positives. The machine learning component of this based cancer immunotherapy platform integrates additional features such as peptide stability, proteasomal cleavage probability, and similarity to self-peptides. This multi-feature ranking reduces the risk of selecting neoantigens that trigger off-target autoimmunity or that fail to stimulate T cells effectively.

For researchers, the advantage is clear: a higher proportion of selected peptides translate into measurable immune responses in preclinical assays. The platform’s algorithm is continuously refined using data from ongoing clinical trials, creating a feedback loop that improves future predictions. While the specific model architecture is proprietary, the general principle aligns with published computational immunology research, such as the review by Schumacher and Schreiber (2015) on neoantigens in cancer immunotherapy (PubMed).

The based cancer immunotherapy platform currently targets three solid tumor types: melanoma, non-small cell lung cancer (NSCLC), and colorectal cancer. These cancers share two key characteristics that make them suitable for neoantigen-directed vaccines: high tumor mutational burden (TMB) and well-characterized clinical infrastructure for personalized therapy.

Melanoma has long been a proving ground for immunotherapy because of its high mutation rate and strong response to checkpoint inhibitors. NSCLC and colorectal cancer also exhibit substantial mutational heterogeneity, providing a rich source of candidate neoantigens. The platform’s machine learning engine is agnostic to cancer type, but the company selected these three indications for initial clinical development based on feasibility and unmet need.

All three clinical-stage programs remain strictly investigational. Researchers studying these cancers in laboratory settings should consult the Peptide Blog: 7 Proven Research Resources for 2026 for additional background on peptide research tools.

💡 Key Takeaway: Which Cancers Does the Based Cancer Immunotherapy Platform Target?

Early-phase trials of the based cancer immunotherapy platform have reported objective response rates above 30% in heavily pretreated populations. This figure comes from investigator-assessed responses in patients who had progressed on multiple prior lines of therapy. The safety profile has been described as favorable, with no unexpected grade 3 or 4 treatment-related adverse events reported to date.

These signals are preliminary and come from small, uncontrolled studies. They do not constitute evidence of clinical benefit for any approved indication. The company has not published detailed safety data in a peer-reviewed journal, but interim results have been presented at oncology conferences. All data remain subject to confirmation in larger, randomized trials.

For researchers, the key takeaway is that the platform’s neoantigen selection process appears to translate into measurable immune activation without severe off-target toxicity. However, the research-use-only context is critical: no product based on this platform is available for human use, and all laboratory peptides mentioned on this site are for in vitro experimentation only. See Peptide Therapy Contraindications: A Research Overview for a broader discussion of safety considerations in peptide research.

PeptideTherapeutics Inc. has three clinical-stage programs built on the based cancer immunotherapy platform, each targeting a different solid tumor indication. The $50 million Series B funding will support expansion of these trials into later phases. The company has stated that pivotal trials are planned for 2027, subject to regulatory feedback and interim data review.

In addition to clinical development, the company is exploring strategic partnerships with major pharmaceutical firms. These partnerships could provide manufacturing scale and commercialization expertise, but no agreements have been announced. The platform’s machine learning engine will also be refined using data generated during the Series B period, improving neoantigen prediction accuracy.

For researchers, the milestones provide a timeline for evaluating the platform’s translational potential. No regulatory approval has been granted, and the company has not disclosed pricing for any future product. All investigational candidates remain available only through clinical trial enrollment. The research community can monitor progress through clinical trial registries and peer-reviewed publications.

Personalized peptide vaccines present unique manufacturing challenges compared to off-the-shelf biologics. The based cancer immunotherapy platform requires synthesis of patient-specific peptide sequences, which demands rapid turnaround times and rigorous quality control. Each vaccine batch is essentially a one-off product, complicating scale-up and regulatory compliance.

Key manufacturing considerations include:

• Turnaround time: from tumor biopsy to vaccine administration, the process must fit within a clinically meaningful window, typically weeks not months.
• Peptide purity and identity: each synthesized peptide must meet strict purity specifications (often >95% as measured by HPLC) and be verified by mass spectrometry.
• Sterility and stability: personalized vaccines require aseptic production and defined storage conditions, usually -20°C to -80°C for lyophilized peptides.
• Cost per patient: personalized manufacturing is inherently more expensive than bulk production, though automation can reduce marginal costs.

These challenges are not unique to this platform but are inherent to any personalized neoantigen vaccine program. The company has not disclosed its manufacturing partners or facility locations. For researchers, the relevant lessons apply to any custom peptide synthesis: ensure certificate of analysis (COA) availability, verify purity by analytical HPLC, and store peptides according to supplier specifications.

💡 Key Takeaway: What Manufacturing Challenges Does Personalized Peptide Vaccine Production Face for the Based Cancer Immunotherapy Platform?

Neoantigen vaccines developed on the based cancer immunotherapy platform fall under the regulatory framework for biologic products in the United States. They require an Investigational New Drug (IND) application before human trials can begin. The company’s three clinical-stage programs have presumably received IND clearance, though the company has not publicly confirmed specific regulatory interactions.

In the United States, personalized cancer vaccines may qualify for expedited programs such as Breakthrough Therapy Designation or Regenerative Medicine Advanced Therapy (RMAT) designation if early data show substantial improvement over available therapies. However, no such designation has been announced for this platform. The company’s pivotal trials planned for 2027 will need to demonstrate safety and efficacy in well-controlled studies before any marketing application can be filed.

For researchers, regulatory status matters because it determines what materials are available for purchase. No investigational candidate from this platform is available for commercial sale. All peptides referenced on this site are for in vitro research use only and must not be used in humans or animals. The regulatory pathway for personalized vaccines remains evolving, and researchers should monitor FDA guidance documents for updates.

Traditional peptide research tools, such as catalog peptides or peptide libraries, are off-the-shelf products with defined sequences and known purity. The based cancer immunotherapy platform, by contrast, is an investigational development program that produces patient-specific sequences on demand. This fundamental difference has implications for researchers.

A comparison:

| Attribute | Traditional Peptide Research Tools | Based Cancer Immunotherapy Platform |

|———–|————————————|————————————-|

| Sequence specificity | Fixed, catalog-based | Patient-specific, computationally designed |

| Production model | Batch manufacturing for stock | On-demand synthesis per patient |

| Regulatory status | Research use only (RUO) | Investigational new drug (IND) |

| Availability | Commercially available | Only through clinical trials |

| Purity verification | COA with HPLC data | Not publicly disclosed for clinical lots |

Researchers who study peptide immunology can use traditional tools to model neoantigen recognition in vitro. For example, they might synthesize predicted neoantigen peptides and test T-cell responses in culture. The based cancer immunotherapy platform’s machine learning predictions could inform such experiments, but the platform itself is not a purchasable product. For a guide to peptide mechanisms, see How Do Peptides Work? 7 Essential Mechanisms in 2026.

The based cancer immunotherapy platform is defined by several measurable attributes that distinguish it from other investigational approaches. These attributes are not product specifications but rather design parameters disclosed by PeptideTherapeutics Inc.:

• Modality: personalized, neoantigen-directed peptide vaccines.
• Discovery engine: machine learning algorithms for neoantigen identification and vaccine design.
• Targeting logic: tumor-specific neoantigens selected to maximize T-cell response while minimizing off-target effects.
• Development focus: solid tumors (melanoma, NSCLC, colorectal cancer).
• Clinical stage: three clinical-stage programs, no regulatory approval.

For researchers, these attributes matter because they define the platform’s scope and limitations. The machine learning engine is not publicly accessible, and the company has not released its training data or model weights. Therefore, independent verification of neoantigen prediction accuracy is not possible at this time. All information is provided for educational purposes, and any peptides used in laboratory research must be obtained from reputable suppliers with full analytical documentation.

💡 Key Takeaway: What Measurable Attributes Define the Based Cancer Immunotherapy Platform?

All products discussed in connection with this based cancer immunotherapy platform are sold strictly for in vitro laboratory research purposes only. They are not for human use, not for veterinary use, and not intended to diagnose, treat, cure, or prevent any disease. This restriction applies to any peptide, reagent, or kit referenced on this site, regardless of the clinical context of the platform.

Researchers must be at least 21 years old to purchase research peptides from this site. No product from the PeptideTherapeutics clinical program is available for purchase at any price. The investigational candidates are administered only within registered clinical trials under institutional review board (IRB) oversight and FDA regulation.

The research-use-only notice is not a legal loophole but a fundamental safety boundary. Peptides intended for laboratory study may contain impurities or stabilizers that are unacceptable for human administration. Never attempt to repurpose research peptides for human use, and always verify the certificate of analysis (COA) before any experiment. For a detailed overview of peptide contraindications in research, see Peptide Therapy Contraindications: A Research Overview.

Neoantigen vaccines can be delivered using several platforms, including synthetic long peptides, mRNA, DNA, and viral vectors. The based cancer immunotherapy platform uses synthetic peptides, which offer advantages in terms of manufacturability and safety but may require adjuvants to enhance immunogenicity.

Key differences:

• Synthetic peptides: short, defined sequences; stable at -20°C; require HLA typing; may need adjuvant.
• mRNA vaccines: encode full-length neoantigens; faster turnaround but less stability; require lipid nanoparticle delivery.
• DNA vaccines: longer shelf life but lower immunogenicity in humans; require electroporation or other delivery enhancement.
• Viral vectors: strong immune response but risk of pre-existing immunity; more complex regulatory path.

The platform’s choice of synthetic peptides aligns with a well-established manufacturing infrastructure and a favorable safety profile. However, peptide vaccines often require co-administration of an adjuvant such as poly-ICLC to boost T-cell responses. The company has not disclosed its adjuvant strategy. For researchers comparing approaches, the key variables are turnaround time, stability, cost, and the need for personalized HLA typing.

What is the based cancer immunotherapy platform?

The based cancer immunotherapy platform is an investigational, machine-learning-driven system developed by PeptideTherapeutics Inc. that designs personalized peptide vaccines against tumor-specific neoantigens. It targets melanoma, NSCLC, and colorectal cancer, with three clinical-stage programs and pivotal trials planned for 2027.

Is the based cancer immunotherapy platform approved for human use?

No. No product associated with the based cancer immunotherapy platform has regulatory approval. All candidates are strictly investigational and available only through clinical trials. Any peptides sold on this site are for in vitro research use only and not for human or veterinary use.

What cancers does the based cancer immunotherapy platform target?

The based cancer immunotherapy platform currently targets melanoma, non-small cell lung cancer (NSCLC), and colorectal cancer. These indications were selected for their high tumor mutational burden and clinical feasibility.

What early efficacy signals have been reported for the based cancer immunotherapy platform?

Early-phase trials report objective response rates above 30% in heavily pretreated populations, with a favorable safety profile. These signals are preliminary and not evidence of clinical benefit.

How does machine learning improve the based cancer immunotherapy platform?

Machine learning ranks candidate neoantigens by predicted MHC binding and immunogenicity, integrating features like peptide stability and similarity to self-peptides. This reduces false positives and off-target risk compared to simple binding affinity cutoffs.

Are any products from this investigational platform available for research purchase?

No. This investigational platform is a clinical development program, not a product line. Researchers can study neoantigen biology using catalog peptides or custom synthesis, but no platform-specific reagents are commercially available.

Ready to Take the Next Step?

Every product includes lot-specific documentation and third-party purity testing.

Free shipping on qualifying orders · Batch COA on request