Abstract: Contemplated cancer treatments comprise recursive analysis of patient-, cancer-, and location-specific neoepitopes from various biopsy sites of a patient after treatment or between successive rounds of immunotherapy and/or chemotherapy to inform further immunotherapy. Recursive analysis preferably includes various neoepitope attributes to so identify treatment relevant neoepitopes.

Abstract: Certain universal neoepitopes and cancer specific neoepitopes and methods therefor are presented that may be used in immunotherapy and cancer diagnosis. Preferred therapeutic and diagnostic compositions include antibodies or fragments thereof that bind to neoepitopes on cancer cells.

Abstract: A distributed, online machine learning system is presented. Contemplated systems include many private data servers, each having local private data. Researchers can request that relevant private data servers train implementations of machine learning algorithms on their local private data without requiring de-identification of the private data or without exposing the private data to unauthorized computing systems. The private data servers also generate synthetic or proxy data according to the data distributions of the actual data. The servers then use the proxy data to train proxy models. When the proxy models are sufficiently similar to the trained actual models, the proxy data, proxy model parameters, or other learned knowledge can be transmitted to one or more non-private computing devices. The learned knowledge from many private data servers can then be aggregated into one or more trained global models without exposing private data.

Abstract: A computer implemented method of generating at least one shape of a region of interest in a digital image is provided.

Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.

Abstract: A computer implemented method of generating at least one shape of a region of interest in a digital image is provided.

Abstract: Methods and compositions for preparation and use of recombinant viruses or other recombinant expression systems are presented in which neoepitopes are first identified in a patient- and cancer-specific manner and then further filtered by HLA-match to the patient. Selected neoepitopes are then expression using sequence elements that direct the expressed neoepitope to the HLA-type (MHC-I and/or MHC-II subtype) that has desirable affinity to the filtered neoepitope.

Abstract: Systems and methods are presented that allow for predicting treatment response of a tumor to a checkpoint inhibitor. In one exemplary aspect, the treatment response is directly associated with a relatively high number of patient- and tumor-specific immunologically visible neoepitopes. Specific mutational patterns in the nucleic acid encoding the neoepitope may be further indicative of treatment response.

Abstract: Techniques are provided for predicting MHC-peptide binding affinity. A plurality of training peptide sequences is obtained, and a neural network model is trained to predict MHC-peptide binding affinity using the training peptide sequences. An encoder of the neural network model comprising an RNN is configured to process an input training peptide sequence to generate a fixed-dimension encoding output by applying a final hidden state of the RNN at intermediate state outputs of the RNN to generate attention weighted outputs, and linearly combining the attention weighted outputs. A fully connected layer following the encoder is configured to process the fixed-dimension encoding output to generate an MHC-peptide binding affinity prediction output. A computing device is configured to use the trained neural network to predict MHC-peptide binding affinity for a test peptide sequence.

Abstract: Systems and methods are presented that allow for determination and prediction of payload toxicity in therapeutic viruses. Disclosed herein are methods of determining payload toxicity of an expressed polypeptide in a cell, comprising: generating or procuring a plurality of expression vectors, each containing a different recombinant nucleic acid sequence that encodes a corresponding recombinant polypeptide; expressing the recombinant nucleic acid sequence in a plurality of host cells while culturing the host cells; sequencing the plurality of expression vectors after culturing the host cells; and correlating at least portions of the recombinant nucleic acid sequence with a toxicity measure.

Abstract: Techniques are provided for determining a cell count within a whole slide pathology image. The image is segmented using a global threshold value to define a tissue area. A plurality of patches comprising the tissue area are selected. Stain intensity vectors are determined within the plurality of patches to generate a stain intensity image. The stain intensity image is iteratively segmented to generate a cell mask using a local threshold value that is and gradually reduced after each iteration. A chamfer distance transform is applied to the cell mask to generate a distance map. Cell seeds are determined on the distance map. Cell segments are determined using a watershed transformation, and a whole cell count is calculated for the plurality of patches based on the cell segments. A client device may be configured for real-time cell counting based on the whole cell count.

Abstract: Certain universal neoepitopes and cancer specific neoepitopes and methods therefore are presented that may be used in immunotherapy and cancer diagnosis. Preferred therapeutic and diagnostic compositions include antibodies or fragments thereof that bind to neoepitopes on cancer cells.

Abstract: A distributed, online machine learning system is presented. Contemplated systems include many private data servers, each having local private data. Researchers can request that relevant private data servers train implementations of machine learning algorithms on their local private data without requiring de-identification of the private data or without exposing the private data to unauthorized computing systems. The private data servers also generate synthetic or proxy data according to the data distributions of the actual data. The servers then use the proxy data to train proxy models. When the proxy models are sufficiently similar to the trained actual models, the proxy data, proxy model parameters, or other learned knowledge can be transmitted to one or more non-private computing devices. The learned knowledge from many private data servers can then be aggregated into one or more trained global models without exposing private data.

Abstract: The present disclosure provides methods and systems of identifying a tumor patient for treatment with a combination of targeted therapy and immune oncology based on differential checkpoint expression patterns, and their association with mutation status, irrespective of the tumor tissue type. Also provided herein are methods of treatment for a tumor with a combination of targeted therapy and immune-oncology (IO) therapy.

Abstract: Techniques are provided for determining a cell count within a whole slide pathology image. The image is segmented using a global threshold value to define a tissue area. A plurality of patches comprising the tissue area are selected. Stain intensity vectors are determined within the plurality of patches to generate a stain intensity image. The stain intensity image is iteratively segmented to generate a cell mask using a local threshold value that is and gradually reduced after each iteration. A chamfer distance transform is applied to the cell mask to generate a distance map. Cell seeds are determined on the distance map. Cell segments are determined using a watershed transformation, and a whole cell count is calculated for the plurality of patches based on the cell segments. A client device may be configured for real-time cell counting based on the whole cell count.

Abstract: Contemplated compositions and methods are directed to cancer neoepitopes and uses of such neoepitopes, especially to generate synthetic antibodies against neoepitopes that may then be employed in the manufacture of a therapeutic agent. Preferred therapeutic agents will comprise a synthetic antibody against a neoepitope, and most preferably in combination with a cellular or non-cellular component for use as a diagnostic or therapeutic agent.

Abstract: Systems and methods for in silico prediction of HLA type of a patient are presented in which patient sequence reads and a reference sequence with known and distinct HLA alleles are used in a de Bruijn graph. A composite match score is then used to rank HLA alleles, thus providing a first HLA type. A second HLA type is identified by re-ranking using an adjusted composite match score.

Abstract: Various devices, systems, structures and methods are disclosed related to securely authorizing a transaction by synchronizing digital genomic data with associated synthetic genomic variants. An embodiment of the present invention utilizes digital genomic data associated with an entity, such as a person, who may utilize a genome-based security device to complete a transaction. In one embodiment, a person may use a genome-based security device to communicate with an external device over a wireless or other communication interface, synchronize digital genomic data and an associated synthetic variant received from the external device with digital genomic data and associated synthetic variant stored on the genome-based security device.

Abstract: Systems and methods are presented that allow for selection of tumor neoepitopes that are filtered for various criteria. In particularly contemplated aspects, filtering includes a step in which the mutation leading to the neoepitope is ascertained as being located in a cancer driver gene.

Abstract: Techniques are provided for determining classifications based on WSIs. A varied-size feature map is generated for each training WSI by generating a grid of patches for the training WSI, segmenting the training WSI into tissue and non-tissue areas, and converting patches comprising the tissue areas into tensors. Bounding boxes are generated based on the patches comprising tissue areas and segmented into feature map patches. A fixed-size feature map is generated based on a subset of the feature map patches. A classifier model is trained to process fixed-size feature maps corresponding to the training WSIs such that, for each fixed-size feature map, the classifier model is operable to assign a WSI-level tissue or cell morphology classification or regression based on the tensors. A classification engine is configured to use the trained classifier model to determine a WSI-level tissue or cell morphology classification or regression for a test WSI.