A whole-slide foundation model for digital pathology from real-world data.

Digital pathology poses unique computational challenges, as a standard gigapixel slide may comprise tens of thousands of image tiles1-3. Prior models have often resorted to subsampling a small portion of tiles for each slide, thus missing the important slide-level context4. Here we present Prov-GigaPath, a whole-slide pathology foundation model pretrained on 1.3 billion 256 × 256 pathology image tiles in 171,189 whole slides from Providence, a large US health network comprising 28 cancer centres. The slides originated from more than 30,000 patients covering 31 major tissue types. To pretrain Prov-GigaPath, we propose GigaPath, a novel vision transformer architecture for pretraining gigapixel pathology slides. To scale GigaPath for slide-level learning with tens of thousands of image tiles, GigaPath adapts the newly developed LongNet5 method to digital pathology. To evaluate Prov-GigaPath, we construct a digital pathology benchmark comprising 9 cancer subtyping tasks and 17 pathomics tasks, using both Providence and TCGA data6. With large-scale pretraining and ultra-large-context modelling, Prov-GigaPath attains state-of-the-art performance on 25 out of 26 tasks, with significant improvement over the second-best method on 18 tasks. We further demonstrate the potential of Prov-GigaPath on vision-language pretraining for pathology7,8 by incorporating the pathology reports. In sum, Prov-GigaPath is an open-weight foundation model that achieves state-of-the-art performance on various digital pathology tasks, demonstrating the importance of real-world data and whole-slide modelling.

Perspectives in Immunotherapy: meeting report from Immunotherapy Bridge (Naples, November 30th-December 1st, 2022).

The discovery and development of novel treatments that harness the patient's immune system and prevent immune escape has dramatically improved outcomes for patients across cancer types. However, not all patients respond to immunotherapy, acquired resistance remains a challenge, and responses are poor in certain tumors which are considered to be immunologically cold. This has led to the need for new immunotherapy-based approaches, including adoptive cell transfer (ACT), therapeutic vaccines, and novel immune checkpoint inhibitors. These new approaches are focused on patients with an inadequate response to current treatments, with emerging evidence of improved responses in various cancers with new immunotherapy agents, often in combinations with existing agents. The use of cell therapies, drivers of immune response, and trends in immunotherapy were the focus of the Immunotherapy Bridge (November 30th-December 1st, 2022), organized by the Fondazione Melanoma Onlus, Naples, Italy, in collaboration with the Society for Immunotherapy of Cancer.

PCM1-JAK2 Fusion Tyrosine Kinase Gene-Related Neoplasia: A Systematic Review of the Clinical Literature.

BACKGROUND: This review summarizes the case studies of PCM1-JAK2 fusion tyrosine kinase gene-related neoplasia. Recommended treatment includes JAK2 inhibitors and hematologic stem cell transplantation (HSCT), although the small number of patients has limited study of their efficacy. Herein, we present all available cases in the current searchable literature with their demographics, diagnoses, treatments, and outcomes. METHODS: PubMed, ScienceDirect, Publons, the Cochrane Library, and Google were searched with the following terms: PCM1-JAK2, ruxolitinib and myeloid/lymphoid. RESULTS: Sixty-six patients (mean age = 50, 77% male) had an initial diagnosis of myeloproliferative neoplasm (MPN) in 40, acute leukemia in 21 and T-cell cutaneous lymphoma in 5. Thirty-five patients (53%) had completed 5-year follow-up. The 5-year survival for the MPN, acute myelogenous leukemia (AML), acute lymphocytic leukemia, and lymphoma groups are 62.7, 14.9%, 40.0%, and 100%, respectively. Too few patients have been treated with ruxolitinib to draw conclusions regarding its effect on survival while the 5-year survival for MPN patients with or without HSCT was 80.2% (40.3%-94.8%) versus 51.5% (22.3%-74.6%), respectively. The T-cell cutaneous lymphoma patients have all survived at least 7 years. CONCLUSION: This rare condition may be increasingly detected with wider use of genomics. Ruxolitinib can yield hematologic and molecular remissions. However, HSCT is, at this time, the only potentially curative treatment. Useful prognostic markers are needed to determine appropriate timing for HSCT in patients with MPN. Patients presenting with acute leukemia have a poor prognosis.

Perspectives in Immunotherapy: meeting report from the Immunotherapy Bridge, December 1st-2nd, 2021.

Over the past decade, immunotherapy has become an increasingly fundamental modality in the treatment of cancer. The positive impact of immune checkpoint inhibition, especially anti-programmed death (PD)-1/PD-ligand (L)1 blockade, in patients with different cancers has focused attention on the potential for other immunotherapeutic approaches. These include inhibitors of additional immune checkpoints, adoptive cell transfer (ACT), and therapeutic vaccines. Patients with advanced cancers who previously had limited treatment options available may now benefit from immunotherapies that can offer durable responses and improved survival outcomes. However, despite this, a significant proportion of patients fail to respond to immunotherapy, especially those with less immunoresponsive cancer types, and there remains a need for new treatment strategies.The virtual Immunotherapy Bridge (December 1st-2nd, 2021), organized by the Fondazione Melanoma Onlus, Naples, Italy in collaboration with the Society for Immunotherapy of Cancer addressed several areas of current research in immunotherapy, including lessons learned from cell therapies, drivers of immune response, and trends in immunotherapy across different cancers, and these are summarised here.

Perspectives in immunotherapy: meeting report from the immunotherapy bridge (December 2nd-3rd, 2020, Italy).

Improved understanding of tumor immunology has enabled the development of therapies that harness the immune system and prevent immune escape. Numerous clinical trials and real-world experience has provided evidence of the potential for long-term survival with immunotherapy in various types of malignancy. Recurring observations with immuno-oncology agents include their potential for clinical application across a broad patient population with different tumor types, conventional and unconventional response patterns, durable responses, and immune-related adverse events. Despite the substantial achievements to date, a significant proportion of patients still fail to benefit from current immunotherapy options, and ongoing research is focused on transforming non-responders to responders through the development of novel treatments, new strategies to combination therapy, adjuvant and neoadjuvant approaches, and the identification of biomarkers of response. These topics were the focus of the virtual Immunotherapy Bridge (December 2nd-3rd, 2020), organized by the Fondazione Melanoma Onlus, Naples, Italy, in collaboration with the Society for Immunotherapy of Cancer and are summarised in this report.

International validation of the consensus Immunoscore for the classification of colon cancer: a prognostic and accuracy study.

BACKGROUND: The estimation of risk of recurrence for patients with colon carcinoma must be improved. A robust immune score quantification is needed to introduce immune parameters into cancer classification. The aim of the study was to assess the prognostic value of total tumour-infiltrating T-cell counts and cytotoxic tumour-infiltrating T-cells counts with the consensus Immunoscore assay in patients with stage I-III colon cancer. METHODS: An international consortium of 14 centres in 13 countries, led by the Society for Immunotherapy of Cancer, assessed the Immunoscore assay in patients with TNM stage I-III colon cancer. Patients were randomly assigned to a training set, an internal validation set, or an external validation set. Paraffin sections of the colon tumour and invasive margin from each patient were processed by immunohistochemistry, and the densities of CD3+ and cytotoxic CD8+ T cells in the tumour and in the invasive margin were quantified by digital pathology. An Immunoscore for each patient was derived from the mean of four density percentiles. The primary endpoint was to evaluate the prognostic value of the Immunoscore for time to recurrence, defined as time from surgery to disease recurrence. Stratified multivariable Cox models were used to assess the associations between Immunoscore and outcomes, adjusting for potential confounders. Harrell's C-statistics was used to assess model performance. FINDINGS: Tissue samples from 3539 patients were processed, and samples from 2681 patients were included in the analyses after quality controls (700 patients in the training set, 636 patients in the internal validation set, and 1345 patients in the external validation set). The Immunoscore assay showed a high level of reproducibility between observers and centres (r=0·97 for colon tumour; r=0·97 for invasive margin; p<0·0001). In the training set, patients with a high Immunoscore had the lowest risk of recurrence at 5 years (14 [8%] patients with a high Immunoscore vs 65 (19%) patients with an intermediate Immunoscore vs 51 (32%) patients with a low Immunoscore; hazard ratio [HR] for high vs low Immunoscore 0·20, 95% CI 0·10-0·38; p<0·0001). The findings were confirmed in the two validation sets (n=1981). In the stratified Cox multivariable analysis, the Immunoscore association with time to recurrence was independent of patient age, sex, T stage, N stage, microsatellite instability, and existing prognostic factors (p<0·0001). Of 1434 patients with stage II cancer, the difference in risk of recurrence at 5 years was significant (HR for high vs low Immunoscore 0·33, 95% CI 0·21-0·52; p<0·0001), including in Cox multivariable analysis (p<0·0001). Immunoscore had the highest relative contribution to the risk of all clinical parameters, including the American Joint Committee on Cancer and Union for International Cancer Control TNM classification system. INTERPRETATION: The Immunoscore provides a reliable estimate of the risk of recurrence in patients with colon cancer. These results support the implementation of the consensus Immunoscore as a new component of a TNM-Immune classification of cancer. FUNDING: French National Institute of Health and Medical Research, the LabEx Immuno-oncology, the Transcan ERAnet Immunoscore European project, Association pour la Recherche contre le Cancer, CARPEM, AP-HP, Institut National du Cancer, Italian Association for Cancer Research, national grants and the Society for Immunotherapy of Cancer.

Perspectives in melanoma: Meeting report from the Melanoma Bridge (30 November-2 December, 2017, Naples, Italy).

Metastatic melanoma represents a challenging clinical situation and, until relatively recently, there was an absence of effective treatment options. However, in 2011, the advanced melanoma treatment landscape was revolutionised with the approval of the anti-cytotoxic T-lymphocyte-associated protein-4 checkpoint inhibitor ipilimumab and the selective BRAF kinase inhibitor vemurafenib, both of which significantly improved overall survival. Since then, availability of new immunotherapies, especially the anti-programmed death-1 checkpoint inhibitors, as well as other targeted therapies, have further improved outcomes for patients with advanced melanoma. Seven years on from the first approval of these novel therapies, evidence for the use of various immune-based and targeted approaches is continuing to increase at a rapid rate. Improved understanding of the tumour microenvironment and tumour immuno-evasion strategies has resulted in different approaches to target and harness the immune response. These new immune-based approaches offer the opportunity for various approaches with distinct modes of action being used in combination with one another, as well as combined with other treatment modalities such as targeted therapy, electrochemotherapy and surgery. The increasing number of treatment options that are now available has resulted in a growing need to identify which patients will derive most benefit from which treatments. Much research is now focused on the identification of biomarkers that can be utilised to help select patients for treatment. These and other recent advances in the management of melanoma were the focus of discussions at the third Melanoma Bridge meeting (30 November-2 December, 2017, Naples, Italy), which is summarised in this report.

Multispectral Imaging of T and B Cells in Murine Spleen and Tumor.

Recent advances in multiplex immunohistochemistry techniques allow for quantitative, spatial identification of multiple immune parameters for enhanced diagnostic and prognostic insight. However, applying such techniques to murine fixed tissues, particularly sensitive epitopes, such as CD4, CD8α, and CD19, has been difficult. We compared different fixation protocols and Ag-retrieval techniques and validated the use of multiplex immunohistochemistry for detection of CD3(+)CD4(+) and CD3(+)CD8(+) T cell subsets in murine spleen and tumor. This allows for enumeration of these T cell subsets within immune environments, as well as the study of their spatial distribution.

World-Wide Immunoscore Task Force: meeting report from the "Melanoma Bridge", Napoli, November 30th-December 3rd, 2016.

The predictive accuracy of the traditional staging system is based on disease progression as a tumour cell-autonomous process, but it fails to incorporate the effects of the host immune response. A precise analysis of the immune component of the tumour microenvironment by computer-based analysis may be essential to managing patients better, opening the road to an expertise in this new emerging field. The Immunoscore as a new possible approach in the classification of cancer, designated TNM-Immune, studied in colon cancer patients with predictive and prognostic value. This new scoring system is derived from the immune contexture, and is based on the numeration of lymphocyte populations, both in the core of the tumour and in the invasive margin of tumours. The Immunoscore demonstrated to be quantitative, reproducible and robust. The usefulness of Immunoscore in advanced melanoma cancer patients has been as well demonstrated; the correlation of marker expression profile with clinical outcome is ongoing. More recently, the Immunoscore could be a useful prognostic marker in patients with rectal cancer treated by primary surgery. A multivariable Cumulative "Suppression Index" scoring system has been also studied in Oral Squamous Cell Carcinoma patients: it evaluates both the tumor and stromal microcompartments at the invasive margin and summarizes them into the score, providing an accurate stratification, independent of stage, tumour classification. The introduction of Immunoscore requires a redefinition of the Laboratory system according to the LEAN Management process, which has been already implemented in referral research labs. The definition and test of hundreds of biomarkers, in the tumour contexture represents a definitive scientific progression. However, there is still a need of substantial body of work to reach the end of the tunnel to assure a personalize treatment.

Future perspectives in melanoma research: meeting report from the "Melanoma Bridge": Napoli, December 3rd-6th 2014.

The fourth "Melanoma Bridge Meeting" took place in Naples, December 3-6th, 2014. The four topics discussed at this meeting were: Molecular and Immunological Advances, Combination Therapies, News in Immunotherapy, and Tumor Microenvironment and Biomarkers. Until recently systemic therapy for metastatic melanoma patients was ineffective, but recent advances in tumor biology and immunology have led to the development of new targeted and immunotherapeutic agents that prolong progression-free survival (PFS) and overall survival (OS). New therapies, such as mitogen-activated protein kinase (MAPK) pathway inhibitors as well as other signaling pathway inhibitors, are being tested in patients with metastatic melanoma either as monotherapy or in combination, and all have yielded promising results. These include inhibitors of receptor tyrosine kinases (BRAF, MEK, and VEGFR), the phosphatidylinositol 3 kinase (PI3K) pathway [PI3K, AKT, mammalian target of rapamycin (mTOR)], activators of apoptotic pathway, and the cell cycle inhibitors (CDK4/6). Various locoregional interventions including radiotherapy and surgery are still valid approaches in treatment of advanced melanoma that can be integrated with novel therapies. Intrinsic, adaptive and acquired resistance occur with targeted therapy such as BRAF inhibitors, where most responses are short-lived. Given that the reactivation of the MAPK pathway through several distinct mechanisms is responsible for the majority of acquired resistance, it is logical to combine BRAF inhibitors with inhibitors of targets downstream in the MAPK pathway. For example, combination of BRAF/MEK inhibitors (e.g., dabrafenib/trametinib) have been demonstrated to improve survival compared to monotherapy. Application of novel technologies such sequencing have proven useful as a tool for identification of MAPK pathway-alternative resistance mechanism and designing other combinatorial therapies such as those between BRAF and AKT inhibitors. Improved survival rates have also been observed with immune-targeted therapy for patients with metastatic melanoma. Immune-modulating antibodies came to the forefront with anti-CTLA-4, programmed cell death-1 (PD-1) and PD-1 ligand 1 (PD-L1) pathway blocking antibodies that result in durable responses in a subset of melanoma patients. Agents targeting other immune inhibitory (e.g., Tim-3) or immune stimulating (e.g., CD137) receptors and other approaches such as adoptive cell transfer demonstrate clinical benefit in patients with melanoma as well. These agents are being studied in combination with targeted therapies in attempt to produce longer-term responses than those more typically seen with targeted therapy. Other combinations with cytotoxic chemotherapy and inhibitors of angiogenesis are changing the evolving landscape of therapeutic options and are being evaluated to prevent or delay resistance and to further improve survival rates for this patient population. This meeting's specific focus was on advances in combination of targeted therapy and immunotherapy. Both combination targeted therapy approaches and different immunotherapies were discussed. Similarly to the previous meetings, the importance of biomarkers for clinical application as markers for diagnosis, prognosis and prediction of treatment response was an integral part of the meeting. The overall emphasis on biomarkers supports novel concepts toward integrating biomarkers into contemporary clinical management of patients with melanoma across the entire spectrum of disease stage. Translation of the knowledge gained from the biology of tumor microenvironment across different tumors represents a bridge to impact on prognosis and response to therapy in melanoma.

Towards the introduction of the 'Immunoscore' in the classification of malignant tumours.

The American Joint Committee on Cancer/Union Internationale Contre le Cancer (AJCC/UICC) TNM staging system provides the most reliable guidelines for the routine prognostication and treatment of colorectal carcinoma. This traditional tumour staging summarizes data on tumour burden (T), the presence of cancer cells in draining and regional lymph nodes (N) and evidence for distant metastases (M). However, it is now recognized that the clinical outcome can vary significantly among patients within the same stage. The current classification provides limited prognostic information and does not predict response to therapy. Multiple ways to classify cancer and to distinguish different subtypes of colorectal cancer have been proposed, including morphology, cell origin, molecular pathways, mutation status and gene expression-based stratification. These parameters rely on tumour-cell characteristics. Extensive literature has investigated the host immune response against cancer and demonstrated the prognostic impact of the in situ immune cell infiltrate in tumours. A methodology named 'Immunoscore' has been defined to quantify the in situ immune infiltrate. In colorectal cancer, the Immunoscore may add to the significance of the current AJCC/UICC TNM classification, since it has been demonstrated to be a prognostic factor superior to the AJCC/UICC TNM classification. An international consortium has been initiated to validate and promote the Immunoscore in routine clinical settings. The results of this international consortium may result in the implementation of the Immunoscore as a new component for the classification of cancer, designated TNM-I (TNM-Immune).

Future perspectives in melanoma research: meeting report from the "Melanoma Bridge", Napoli, December 5th-8th 2013.

The fourth "Melanoma Bridge Meeting" took place in Naples, December 5 to 8th, 2013. The four topics discussed at this meeting were: Diagnosis and New Procedures, Molecular Advances and Combination Therapies, News in Immunotherapy, and Tumor Microenvironment and Biomarkers.

Digital Pathology for Better Clinical Practice.

(1) Background: Digital pathology (DP) is transforming the landscape of clinical practice, offering a revolutionary approach to traditional pathology analysis and diagnosis. (2) Methods: This innovative technology involves the digitization of traditional glass slides which enables pathologists to access, analyze, and share high-resolution whole-slide images (WSI) of tissue specimens in a digital format. By integrating cutting-edge imaging technology with advanced software, DP promises to enhance clinical practice in numerous ways. DP not only improves quality assurance and standardization but also allows remote collaboration among experts for a more accurate diagnosis. Artificial intelligence (AI) in pathology significantly improves cancer diagnosis, classification, and prognosis by automating various tasks. It also enhances the spatial analysis of tumor microenvironment (TME) and enables the discovery of new biomarkers, advancing their translation for therapeutic applications. (3) Results: The AI-driven immune assays, Immunoscore (IS) and Immunoscore-Immune Checkpoint (IS-IC), have emerged as powerful tools for improving cancer diagnosis, prognosis, and treatment selection by assessing the tumor immune contexture in cancer patients. Digital IS quantitative assessment performed on hematoxylin-eosin (H&E) and CD3+/CD8+ stained slides from colon cancer patients has proven to be more reproducible, concordant, and reliable than expert pathologists' evaluation of immune response. Outperforming traditional staging systems, IS demonstrated robust potential to enhance treatment efficiency in clinical practice, ultimately advancing cancer patient care. Certainly, addressing the challenges DP has encountered is essential to ensure its successful integration into clinical guidelines and its implementation into clinical use. (4) Conclusion: The ongoing progress in DP holds the potential to revolutionize pathology practices, emphasizing the need to incorporate powerful AI technologies, including IS, into clinical settings to enhance personalized cancer therapy.

Recommendations for Tumor Mutational Burden Assay Validation and Reporting: A Joint Consensus Recommendation of the Association for Molecular Pathology, College of American Pathologists, and Society for Immunotherapy of Cancer.

Tumor mutational burden (TMB) has been recognized as a predictive biomarker for immunotherapy response in several tumor types. Several laboratories offer TMB testing, but there is significant variation in how TMB is calculated, reported, and interpreted among laboratories. TMB standardization efforts are underway, but no published guidance for TMB validation and reporting is currently available. Recognizing the current challenges of clinical TMB testing, the Association for Molecular Pathology convened a multidisciplinary collaborative working group with representation from the American Society of Clinical Oncology, the College of American Pathologists, and the Society for the Immunotherapy of Cancer to review the laboratory practices surrounding TMB and develop recommendations for the analytical validation and reporting of TMB testing based on survey data, literature review, and expert consensus. These recommendations encompass pre-analytical, analytical, and postanalytical factors of TMB analysis, and they emphasize the relevance of comprehensive methodological descriptions to allow comparability between assays.

FcγRIIB Is an Immune Checkpoint Limiting the Activity of Treg-Targeting Antibodies in the Tumor Microenvironment.

Preclinical murine data indicate that fragment crystallizable (Fc)-dependent depletion of intratumoral regulatory T cells (Treg) is a major mechanism of action of anti-CTLA-4. However, the two main antibodies administered to patients (ipilimumab and tremelimumab) do not recapitulate these effects. Here, we investigate the underlying mechanisms responsible for the limited Treg depletion observed with these therapies. Using an immunocompetent murine model humanized for CTLA-4 and Fcγ receptors (FcγR), we show that ipilimumab and tremelimumab exhibit limited Treg depletion in tumors. Immune profiling of the tumor microenvironment (TME) in both humanized mice and humans revealed high expression of the inhibitory Fc receptor, FcγRIIB, which limits antibody-dependent cellular cytotoxicity/phagocytosis. Blocking FcγRIIB in humanized mice rescued the Treg-depleting capacity and antitumor activity of ipilimumab. Furthermore, Fc engineering of antibodies targeting Treg-associated targets (CTLA-4 or CCR8) to minimize FcγRIIB binding significantly enhanced Treg depletion, resulting in increased antitumor activity across various tumor models. Our results define the inhibitory FcγRIIB as an immune checkpoint limiting antibody-mediated Treg depletion in the TME, and demonstrate Fc engineering as an effective strategy to overcome this limitation and improve the efficacy of Treg-targeting antibodies.

The additional facet of immunoscore: immunoprofiling as a possible predictive tool for cancer treatment.

Recent investigations of the tumor microenvironment have shown that many tumors are infiltrated by inflammatory and lymphocytic cells. Increasing evidence suggests that the number, type and location of these tumor-infiltrating lymphocytes in primary tumors has prognostic value, and this has led to the development of an 'immunoscore. As well as providing useful prognostic information, the immunoscore concept also has the potential to help predict response to treatment, thereby improving decision- making with regard to choice of therapy. This predictive aspect of the tumor microenvironment forms the basis for the concept of immunoprofiling, which can be described as 'using an individual's immune system signature (or profile) to predict that patient's response to therapy' The immunoprofile of an individual can be genetically determined or tumor-induced (and therefore dynamic). Ipilimumab is the first in a series of immunomodulating antibodies and has been shown to be associated with improved overall survival in patients with advanced melanoma. Other immunotherapies in development include anti-programmed death 1 protein (nivolumab), anti-PD-ligand 1, anti-CD137 (urelumab), and anti-OX40. Biomarkers that can be used as predictive factors for these treatments have not yet been clinically validated. However, there is already evidence that the tumor microenvironment can have a predictive role, with clinical activity of ipilimumab related to high baseline expression of the immune-related genes FoxP3 and indoleamine 2,3-dioxygenase and an increase in tumor-infiltrating lymphocytes. These biomarkers could represent the first potential proposal for an immunoprofiling panel in patients for whom anti-CTLA-4 therapy is being considered, although prospective data are required. In conclusion, the evaluation of systemic and local immunological biomarkers could offer useful prognostic information and facilitate clinical decision making. The challenge will be to identify the individual immunoprofile of each patient and the consequent choice of optimal therapy or combination of therapies to be used.

FcyRIIB is a novel immune checkpoint in the tumor microenvironment limiting activity of Treg-targeting antibodies.

Despite pre-clinical murine data supporting T regulatory (Treg) cell depletion as a major mechanism by which anti-CTLA-4 antibodies function in vivo, the two main antibodies tested in patients (ipilimumab and tremelimumab) have failed to demonstrate similar effects. We report analogous findings in an immunocompetent murine model humanized for CTLA-4 and Fcy receptors (hCTLA-4/hFcyR mice), where both ipilimumab and tremelimumab fail to show appreciable Treg depletion. Immune profiling of the tumor microenvironment (TME) in both mice and human samples revealed upregulation of the inhibitory Fcy receptor, FcyRIIB, which limits the ability of the antibody Fc fragment of human anti-CTLA-4 antibodies to induce effective antibody dependent cellular cytotoxicty/phagocytosis (ADCC/ADCP). Blocking FcyRIIB in humanized mice rescues Treg depleting capacity and anti-tumor activity of ipilimumab. For another target, CC motif chemokine receptor 8 (CCR8), which is selectively expressed on tumor infiltrating Tregs, we show that Fc engineering to enhance binding to activating Fc receptors, while limiting binding to the inhibitory Fc receptor, leads to consistent Treg depletion and single-agent activity across multiple tumor models, including B16, MC38 and MB49. These data reveal the importance of reducing engagement to the inhibitory Fc receptor to optimize Treg depletion by TME targeting antibodies. Our results define the inhibitory FcyRIIB receptor as a novel immune checkpoint limiting antibody-mediated Treg depletion in tumors, and demonstrate Fc variant engineering as a means to overcome this limitation and augment efficacy for a repertoire of antibodies currently in use or under clinical evaluation in oncology.

Toward structuring real-world data: Deep learning for extracting oncology information from clinical text with patient-level supervision.

Most detailed patient information in real-world data (RWD) is only consistently available in free-text clinical documents. Manual curation is expensive and time consuming. Developing natural language processing (NLP) methods for structuring RWD is thus essential for scaling real-world evidence generation. We propose leveraging patient-level supervision from medical registries, which are often readily available and capture key patient information, for general RWD applications. We conduct an extensive study on 135,107 patients from the cancer registry of a large integrated delivery network (IDN) comprising healthcare systems in five western US states. Our deep-learning methods attain test area under the receiver operating characteristic curve (AUROC) values of 94%-99% for key tumor attributes and comparable performance on held-out data from separate health systems and states. Ablation results demonstrate the superiority of these advanced deep-learning methods. Error analysis shows that our NLP system sometimes even corrects errors in registrar labels.