Immunology

Immunity by design

The Immunology Team is rooted in biology and holds deep expertise in bioinformatics, machine learning, and software engineering. Ardigen’s in-house datasets, together with advanced AI platforms, empower the development of effective therapies.
Our technologies unlock the fast track to therapies driven by engineered TCRs,
TCRm-Abs, immunogenic epitopes, as well as AI-based biomarker discovery.

 

We are open to partnerships and scientific collaborations. Let’s talk and see how we can help you with your challenges.

TCR therapy

Accelerate discovery and improve safety using Artificial Intelligence

Following the unique opportunity for curing patients provided by the development of cell therapies, Ardigen has set on the path to advance the field with the application of its Artificial Intelligence platform. Many challenges stand in the way of successful therapy discovery and development. Let us know how we can help you!

Are you facing similar challenges?

Target epitopeselection and validationOff-target toxicityTCR optimizationTCR functionalityassessmentTCR promiscuityLimitations of TCRscreening library

Value we deliver

  • Refining selection and validation of the target pMHCs (Peptide-Major Histocompatibility Complexes) with AI predictions
  • Detection of off-target immunotoxicity
  • Accessing the full TCR (T-cell receptor) sequence space for hit identification                         
  • Optimizing time and costs of TCR development

ArdImmune TCRact Platform

pMHC targetidentificationpMHC: TCRbinding predictionTCRvalidationTCR stabilityassessmentOff-targettoxicity predictionTCROptimizationStructuralanalysis of pMHCcomplexBest TCRs list withcharacteristics

Cancer vaccines

Rapid solutions for effective immune response in clinical trials

We have created an Artificial Intelligence platform dedicated to be a part of the cancer vaccine therapeutics process. The ArdImmune Vax AI Platform uses sequencing data to generate and prioritize antigen targets for cancer vaccines and T-cell therapies.

Are you facing similar challenges?

Value we deliver

  • AI predictions of functional T-cell responses
  • Evasion off-target immunotoxicity
  • Providing help of CD4+ T cells
  • Selecting clonal epitopes
  • Detecting immune escape mechanisms
  • Designing an off-the-shelf or personalized cancer vaccine
ArdImmune Vax Platform key functionalities to augment therapy development

The platform consists of bioinformatics and machine learning set of algorithms that generate putative antigens, assess patients’ MHC, antigen(peptide)-MHC binding affinity, likelihood of peptide presentation by the MHC molecules on the cell surface and the likelihood of pMHC attracting T-cells to generate functional responses described as immunogenicity.

ArdImmune
Vax Platform

CandidateantigenspMHCpresentationImmunogenicityArdImmune RankPrioritized antigens for the vaccinecompositionClonality /HeterogeneitypMHCbindingOff-targettoxicityAnalysis of theWES & RNAsequencing dataSequencingof the samples
ArdImmune Vax incorporates the best-in-class algorithms for each task performed, starting from patient samples and sequencing data, to designed vaccine composition.
  • Sample processing

    We use WES NGS data from the bulk sequencing of a patient’s FPPE sample (tumor sample), along with the PBMC sample (normal sample). The data are processed to identify SV (Structural Variants), somatic SNVs (single nucleotide variants), short indels (insertions/deletions) and other alterations, using multiple variant calling tools. The resulting mutations are then carefully examined to eliminate false positives. Only mutations that are present in a sufficient percentage of tumor cells to elicit an immune response are retained.

    RNAseq data from the bulk sequencing of a patient’s FPPE sample (tumor sample) are processed to obtain expression level for each gene in the sample and to identify new chimeric genes created by SVs (Structural Variants).

  • Diverse sources of epitopes

    Short indels (especially those which affect the protein reading frame) may lead to serious distortions of the protein sequence and thus, might be a rich source of neoepitopes.

     

     

    Tumor Associated Antigens (TAAs) are non-mutated proteins or peptides that have expressions which are restricted to the tumor (and/or embryonic) tissue – making them powerful targets for immune therapies.

    Somatic SNVs within a tumor lead to local changes in protein sequence. One SNV event produces a handful of neoepitopes, and being the most common genetic alteration, SNVs are a rich source of new, possibly immunogenic neoepitopes.

    Retrotranspositions are events in which transposons (mobile genomic sequences)  are copied and pasted in new genomic locations. This event may lead to the appearance of new fusion proteins, which might in turn contain new neoepitopes.

    Alternative splicing events, especially intron retentions, lead to the appearance of new protein fragments. They are normally very rarely expressed within healthy tissue, which makes them another important source of possibly highly immunogenic neoepitopes.

    Structural Variants (SVs) are large genomic alterations, which may affect the substantial part of the chromosome. Some of them, such as translocations, large indels and inversions are likely to cause fusion/chimeric genes, which can bring substantial alterations in the resulting protein sequences, which in turn might lead to the appearance of new neoepitopes.

  • Vaccine design modules

    pMHC immunogenicity is acquired only for the minority of presented pMHC complexes. We are able to accurately assess the immunogenic potential of the pMHC complex with our proprietary AI model. This model was trained on the curated set of neoantigens tested in-vitro for immunogenicity.

    Off-target toxicity is one of the greatest challenges in modern cancer vaccine development. It happens when TCR binds another antigens presented on a patient’s healthy tissue, thus damaging it. We are able to identify possible off-targets for selected epitopes and neoepitopes and eliminate those, which are associated with the risk of off-target toxicity.

    The presentation of the pMHC complex on the cancer cell’s surface is another essential process needed for pMHC-TCR interaction. With the help of our proprietary AI model, we can identify epitopes and neoepitopes which have the highest probability of being presented on the cancer cells by a patient’s MHCs. This model is trained on the large set of the data obtained from numerous experiments via mass spectrometry.

    Immune escape mechanisms, such as HLA LOH (Lost of Heterozygosity) or HLA downregulation, are known cancer microevolutionary processes which significantly lower the immunotherapies efficiency. We identify such events and counteract with a selection of efficient epitopes and neoepitopes for HLA types, which are not affected by the immune escape mechanisms.

    pMHC binding of selected neoepitopes to the patient’s HLA types is necessary for the MHC related immunogenicity. We are able to accurately identify strong MHC binders via usage of different binding tools.

    Our process accounts for tumor heterogeneity as well, by prioritization of clonal epitopes, driver genes, and hotspot mutations. This maximizes the cleaning potential of our anti-cancer vaccine, by targeting the genetic alterations which are vital for tumor development.

    Variant Filtering based on our Machine Learning models, is performed in order to choose variants with the highest feasibility.

    We also provide Peptide Manufacturability predictions to determine which peptides are potentially difficult to manufacture.

    We are relying on the Model Confidence of our Machine Learning models to present only meaningful and important information.

    Tumor Microenvironment analysis assesses the accessibility of tumors to the immune system and hence the effectiveness of the therapy.

  • Other applications

    Our process, along with pMHC models for mice, choose the best targets for in-vivo immunogenicity experiments.

    Viral epitope models are created for vaccine target selection.

    Our process helps decrease the risk of immuno-toxicity of peptide-based drugs.

    We can streamline your therapy development pipelines with Target ID selection.

Our science

We are driven by science and collaborations!

Since 2015, we’ve successfully executed a variety of exciting and complex projects, both for our clients and internally.
High degree of trust and confidentiality is the foundation for our business. That’s why we are always very excited to share results of our scientific projects.
Whenever possible we publish and present materials, such as journal publications, posters, case studies or technical notes, aiming to advance the scientific field and showcase the achievements and experience of our team.

Publications

26 August 2020 Community Assessment of the Predictability of Cancer Protein and Phosphoprotein Levels from Genomics and (...)
Download publication

    26 August 2020 AI aided design of epitope-based vaccine for the induction of cellular immune responses against SARS-CoV-2
    Download publication

      30 November 2019 Understanding contribution and independence of multiple biomarkers for predicting response to Atezolizumab
      Download publication

        Posters and case studies

        18 November 2019 Predicting response to anti-PD1 therapy from metagenomic sequencing data with machine learning See the poster
        17 November 2019 AI-augmented design of effective therapeutic cancer vaccines and adoptive cell therapies See the poster
        8 June 2020 Accounting for immune escape mechanisms in personalized and shared neoantigen cancer vaccine design See the poster

        On demand webinars

        Decreasing the Risk of Immunotoxicity for Cancer Immunotherapies
        19 May 2021 Decreasing the Risk of Immunotoxicity for Cancer Immunotherapies

          Immune escape mechanisms in neoantigen driven therapies
          19 March 2021 Immune escape mechanisms in neoantigen driven therapies

            Using AI to design vaccine protecting from COVID-19
            16 September 2020 Using AI to design vaccine protecting from COVID-19

              Short movies and interviews

               Methods for understanding and modeling
              10 June 2021 Methods for understanding and modeling Watch the video
              High quality immuno-oncology data for machine learning
              7 June 2021 High quality immuno-oncology data for machine learning Watch the video
              Peptide lottery
              31 May 2021 Peptide lottery Watch the video

              Meet us at upcoming events

              • Coming soon
                14 - 18 June
                digital
                PMWC 2021 COVID Virtual
              • 10 - 11 & 14 - 18 June
                digital
                BIO Digital 2021
              • 28 September - 1 October
                digital
                WORLD VACCINE CONGRESS WASHINGTON
              • 14 - 17 September
                digital
                CAR-TCR DIGITAL WEEK

              Contact us

              Are you interested in Ardigen's Immunology Platforms and solutions?

                • https://ardigen.com/wp-content/uploads/2021/05/Mask-Group-115543@2x.jpg Agnieszka Blum, PhD General Director of Immunology Unit
                • https://ardigen.com/wp-content/uploads/2021/05/Mask-Group-116@2x.jpg Piotr Stępniak Director of Strategy and Alliance
                Go up