Neoantigen Discovery Engine 2017-10-05T22:56:30+00:00

A Culture of Rigorous Innovation

We’re always striving to do better and build solutions that accelerate the discovery of new biomarkers, and the development and commercialization of next-gen cancer immunotherapies.

From improved processes, to advanced assays and analytics, to investing in the latest technology to help scale efficiently, we’re helping biopharma harness the power of genomic data to make precision medicine a reality for all patients.

Our patented ACE™ (Accuracy and Content Enhanced) Technology is the foundation of ACE ImmunoID and all Personalis products. ACE improves processes from nucleic acid preparation, to sequencing, to analytics for superior sequencing results.

Nucleic Acid Extraction and Sample Preparation

Personalis has developed protocols to overcome the challenges of working with difficult samples including FFPE, FNAs, fresh frozen, and PBMCs.
We realize these are precious patient samples. In the past, traditional processes have required multiple samples sent to multiple vendors to obtain the data needed to meet study objectives. At Personalis, we have a simplified process using a dual simultaneous extraction of both DNA and RNA from challenging materials in a sparing manner.


Gaps or inconsistent coverage can result in missed content. Personalis ACE Technology augments sequencing gaps for more complete coverage.

Alignment and Variant Discovery

Our state-of-the-art bioinformatics pipelines are optimized for accuracy and performance, resulting in superior sequence alignments and variant calls, including improved SNV and indel detection.

Variant Annotation

We’ve implemented comprehensive annotation to overcome mapping/nomenclature issues, and errors and inconsistencies in database curation.


Data is delivered with convenient QC reports, and in specialized formats such as our Neoantigen Discovery and Immungeonomics Reports.

Related links:

Powered by our ACE Technology, our DNA Assays provide more uniform coverage at high depths than standard assays.

Specifically, the ACE Cancer Exome outperforms conventional exome assays by enhances coverage across coding regions and supplementing more complex areas in the genomic architecture such as GC-rich content.

The Personalis solution  provides targeted sequencing to augment coverage gaps present in typical exomes. For example, in a paper published by van Buuren et al. in OncoImmunology, the PRDX5 gene is reported to harbor variants that result in immunogenic epitopes, the part of an antigen recognized by the immune system. Figure 1 highlights superior, uniform coverage of exonic regions with the ACE Cancer Exome (green plus blue) compared to the most widely used standard exome (blue) for clinical and translational research. Variants residing in green regions (red rectangles) would be missed with a standard exome platform.

Figure 1: Coverage of the PRDX5 gene by the ACE Cancer Exome.

Many clinical studies depend on tissue archives that have been fixed using FFPE procedures. This preservation process makes it difficult to obtain a pure sample and often leads to RNA degradation. To overcome this challenge, Personalis has developed an exome-capture transcriptome protocol based on our ACE Technology that allows us to produce high-quality transcriptome sequencing results from challenging FFPE samples.

Our enrichment protocol directly selects for transcripts using the optimized ACE capture probes, eliminating background and focusing the sequencing on regions of interest. Sequencing using the ACE Transcriptome protocol demonstrated that >95% of the bases mapped within the coding and UTR regions of the RNA (Figure 2).  Thus, the ACE approach results in high quality data and low off-target reads.

Figure 2: ACE Cancer Transcriptome Focuses on Regions of High Interest

Comprehensive characterization of tumor gene expression is an important overlay for interpreting somatic mutations, identifying neoantigens, assessing expression of checkpoint genes in immunotherapy, and identifying prognostic expression signatures. Whether Fresh Frozen or fixed specimens are available for your analysis, the ACE approach produces high quality transcriptome sequencing results.  Using paired FFPE and matched adjacent Fresh Frozen tissues; we found high correlation of normalized (TPM) gene expression (Figure 3.) across various tumor types.  This data demonstrates the Personalis ACE Cancer Transcriptome for gene expression is an accurate, reliable method for characterizing expression in even challenging materials such as FFPE.

FIGURE 3: Correlation Plots of Log2 Transcripts Per Million (TPM) between matched FF (x-axis) and FFPE (y-axis) pairs in A–D) Colon E) Lung and F) Rectum tumor tissues.

Related Links:

Leveraging our enhanced exome and transcriptome, we’ve applied these assays for deeper bioinformatics analysis to accurately predict neoantigens.  Using neoantigens as a predictor for determining likelihood of response to immunotherapies is one exciting application (Rizvi et al., 2015), but also using these analyses to develop personalized cancer vaccines is increasingly critical.  Although standard research pipelines have been developed to assist in neoantigen identification, developing a strong analytically validated neoantigen identification platform suitable for clinical applications is complex.

Within our neoantigen workflow (Figure 4), somatic DNA and RNA variants are processed for antigen identification, including SNVs, indels, and fusion events. Importantly, both in-frame and out-of-frame events are accurately considered by transcript, allowing for a rich source of putative candidate neoantigens. Our pipeline includes assessment of potentially important criteria including HLA prediction, MHC binding (class I and II), immunogenicity, similarity to self, and similarity to known antigens.

Further, peptides are evaluated for both gene and variant-level expression.

Taken together, the ACE ImmunoID product provides a comprehensive assessment of features allowing the ability to identify and rank potentially immunogenic neoantigens.

Figure 4

The Neoantigen Discovery Engine enables the identification of neoantigens and allows you to assess:

  • The mutational landscape with neoantigen load and mutational burden
  • The peptides derived from SNVs, indels and gene fusions
  • Critical metrics such as:
    • Gene- and variant-level expression
    • MHC Class I and select Class II binding affinity
    • Immunogenicity

Correct HLA Typing for accurate neoantigen prediction

Additional features within our Neoantigen Discovery Engine are the in silico HLA Typing of both Class I and select Class II alleles and further refinement of peptide prediction by the incorporation of phasing within the pipeline.

HLA typing is an essential component of the neoantigen prediction process. Incorrect typing can lead to downstream inaccuracies in binding predictions. In order to provide accurate HLA typing within ACE ImmunoID, we have optimized and validated an extremely accurate tool.  To accomplish, we validated hundreds of HLA alleles across both Class I and select Class II that had previously been typed with clinical grade PCR-based methods. We performed a blinded clinical validation with 62 orthogonally typed samples involving ~700 HLA alleles, achieving high concordance with the ACE Exome.

Table 1: Results of HLA Typing

HLA Locus Number of Calls Number in Agreement Concordance
Class I 318 311 98%
Class II 378 355 94%
Class I + II 696 666 96%
122/23 experimentally-validated immunogenic neoantigens accurately predicted
2DRB1, DPA1, DPB1, DQA1, DQB1, and DRB5 included

HLA binding is currently the most well-established criteria for ranking neoantigen candidates. Recent advances in training data generated from mass spectrometry, provide a larger dataset of peptide binders and non-binders for individual HLA alleles. This new binding data takes two important additional components into consideration: cleavage and transportation, which are critically important for presentation assessment. We leverage this advancement, developing a brand new MHC binding prediction algorithm which outperforms both NetMHC predictors across the range of prediction score cut-offs (Figure 5).

Figure 5

Related Links:

We use machine learning and neural networks to provide you with advanced analytics to better inform your discovery and translational research programs.

The Immunogenomics Engine guides the investigation of critical immuno-oncology genes with information including expression, variant effect impact, and DNA/RNA allelic fractions.  Unlike targeted therapies, there tends to be general agreement that it is unlikely that a single predictive biomarker in tumor biopsies will be found for determining response to immunotherapies. Thus, multidimensional biomarker analysis is needed to accurately assess patient response.  The Personalis Immunogenomics Engine enables the ability to look across critical areas to characterize tumor biology for focused analysis.

Rapidly evaluate the tumor biology of a sample in key areas including:

  • Antigen Presentation –
    • Translational research empowers a better understanding of the pathways that tumor cells use to evade immune surveillance. Detecting critical mutations in genes such as B2M are important to comprehend the mechanisms of acquired resistance to immunotherapies.  B2M deficiency has been shown in Adoptive Cell therapies (Restifo et al., 1996), Checkpoint Inhibitors (Zaretsky et al., 2016) and Neoantigen Vaccine strategies (Sahin et al., 2017)
  • Repair and Replication
    • Microsatellite instability High (MSI- H) or DNA mismatch repair deficiency tumors are thought to be an important biomarker for patient response.  Recently the FDA approved the use of pembrolizumab based upon the tumor’s MSI status.
  • Checkpoint Modulators
    • The activation of T-cells is regulated by both stimulatory and inhibitory signals. Understanding the tumors checkpoint ligand expression is key to understand the likely mechanisms of tumor escape.

Our CAP-accredited, CLIA-certified Laboratory is equipped with robots for efficient scale up, our custom Genomics Workflow Management System, Symphony, and the latest technology including Illumina NovaSeq Instruments to ensure your projects are delivered with reliable high quality and rapid timelines.

1. Arrival: ACE ImmunoID requires paired tumor/normal analysis. The moment samples arrive at our CAP-accredited, CLIA-certified laboratory, the samples given a unique sample ID and are tracked in LIMS and Symphony.

2. Sample sparing preparation: Our laboratory staff bring a wealth of operational expertise, allowing us to hone our sample sparing methods.

3. Quality review: Prior to sequencing, samples undergo robust QC assessment.

4. Sequencing: The ACE ImmunoID ACE Cancer Exome and ACE Cancer Transcriptome assays run simultaneously to streamline processes and save time.

5. Analysis: Data is then run on our somatic variant pipeline for standard data deliverables. Additional analytics provided through our Neonatigen Discovery and ImmunoProfile Analytics Engines can be included based on your research and project needs.

6. FAS Support: Upon data delivery, your dedicated Field Application Scientist is available to walk through the data with you to answer any questions, and follow up with our scientific team as needed.