Learning from prepandemic data to forecast viral escape.

Effective pandemic preparedness relies on anticipating viral mutations that are able to evade host immune responses to facilitate vaccine and therapeutic design. However, current strategies for viral evolution prediction are not available early in a pandemic-experimental approaches require host polyclonal antibodies to test against1-16, and existing computational methods draw heavily from current strain prevalence to make reliable predictions of variants of concern17-19. To address this, we developed EVEscape, a generalizable modular framework that combines fitness predictions from a deep learning model of historical sequences with biophysical and structural information. EVEscape quantifies the viral escape potential of mutations at scale and has the advantage of being applicable before surveillance sequencing, experimental scans or three-dimensional structures of antibody complexes are available. We demonstrate that EVEscape, trained on sequences available before 2020, is as accurate as high-throughput experimental scans at anticipating pandemic variation for SARS-CoV-2 and is generalizable to other viruses including influenza, HIV and understudied viruses with pandemic potential such as Lassa and Nipah. We provide continually revised escape scores for all current strains of SARS-CoV-2 and predict probable further mutations to forecast emerging strains as a tool for continuing vaccine development ( evescape.org ).

Reprogramming Cancer into Antigen-Presenting Cells as a Novel Immunotherapy.

Therapeutic cancer vaccination seeks to elicit activation of tumor-reactive T cells capable of recognizing tumor-associated antigens (TAA) and eradicating malignant cells. Here, we present a cancer vaccination approach utilizing myeloid-lineage reprogramming to directly convert cancer cells into tumor-reprogrammed antigen-presenting cells (TR-APC). Using syngeneic murine leukemia models, we demonstrate that TR-APCs acquire both myeloid phenotype and function, process and present endogenous TAAs, and potently stimulate TAA-specific CD4+ and CD8+ T cells. In vivo TR-APC induction elicits clonal expansion of cancer-specific T cells, establishes cancer-specific immune memory, and ultimately promotes leukemia eradication. We further show that both hematologic cancers and solid tumors, including sarcomas and carcinomas, are amenable to myeloid-lineage reprogramming into TR-APCs. Finally, we demonstrate the clinical applicability of this approach by generating TR-APCs from primary clinical specimens and stimulating autologous patient-derived T cells. Thus, TR-APCs represent a cancer vaccination therapeutic strategy with broad implications for clinical immuno-oncology. SIGNIFICANCE: Despite recent advances, the clinical benefit provided by cancer vaccination remains limited. We present a cancer vaccination approach leveraging myeloid-lineage reprogramming of cancer cells into APCs, which subsequently activate anticancer immunity through presentation of self-derived cancer antigens. Both hematologic and solid malignancies derive significant therapeutic benefit from reprogramming-based immunotherapy. This article is highlighted in the In This Issue feature, p. 1027.