Abstract: Provided is a computer-implemented method, including inputting to a trained machine learning classifier genomic information of a non-training subject that includes features from a tumor sample, wherein the trained machine learning classifier trained on features of tumor samples obtained from training subjects and their a responsiveness to checkpoint inhibition treatment and the machine-learning classifier is trained to predict responsiveness to the treatment, and generating a checkpoint inhibition responsiveness classification predictive of the subject's responding to the checkpoint inhibition with the trained machine-learning classifier, and reporting the checkpoint inhibition responsiveness classification using a graphical user interface. Also provided are a computer system for performing the method and a machine learning classifier trained by the method.

Abstract: The present disclosure relates to a binder that specifically binds to an N-terminally modified polypeptide through interaction with a modified N-terminal amino acid. Also provided herein is a method and related kits for treating a polypeptide using or comprising the binder and/or modified cleavase. In some embodiments, also provided herein is a method and related kits for transferring information using a plurality of enzymes, including for performing a ligation, extension, and cleavage reaction with nucleic acid molecules associated with the polypeptide for analysis.

Abstract: The present disclosure relates to a metalloprotein binder that specifically binds to a N-terminally modified peptide. Also provided herein is a method and related kits for treating or analyzing a peptide using the metalloprotein binder and/or modified cleavase. In some embodiments, the method provided herein comprises binding metalloprotein binder-coding tag conjugates to a modified N-terminal amino acid residue of an immobilized peptide associated with a recording tag, transferring identifying information from the coding tag to the recording tag using a ligation or primer extension, and cleaving the modified N-terminal amino acid residue. The method and metalloprotein binders provided herein are useful for de novo peptide identification or sequencing.

Abstract: A potential prognostic biomarker is based on a combination of a composite score generated by sequence analysis of global human endogenous retrovirus (hERV)/retro-transposon transactivation and a cell signature generated using deconvolution of immune cells within a tumor sample for predicting the efficacy of chemotherapeutic agents and immune checkpoint inhibitors. Correlation analysis of the composite score with cell signature within a tumor sample enables survival analysis in individuals receiving chemotherapeutic agents and immune checkpoint inhibitors.

Abstract: Provided is a computer-implemented method, including inputting to a trained machine learning classifier genomic information of a non-training subject that includes features from a tumor sample, wherein the trained machine learning classifier trained on features of tumor samples obtained from training subjects and their a responsiveness to checkpoint inhibition treatment and the machine-learning classifier is trained to predict responsiveness to the treatment, and generating a checkpoint inhibition responsiveness classification predictive of the subject's responding to the checkpoint inhibition with the trained machine-learning classifier, and reporting the checkpoint inhibition responsiveness classification using a graphical user interface. Also provided are a computer system for performing the method and a machine learning classifier trained by the method.

Abstract: We introduce a variant classifier that uses trained deep neural networks to predict whether a given variant is somatic or germline. Our model has two deep neural networks: a convolutional neural network (CNN) and a fully-connected neural network (FCNN), and two inputs: a DNA sequence with a variant and a set of metadata features correlated with the variant. The metadata features represent the variant's mutation characteristics, read mapping statistics, and occurrence frequency. The CNN processes the DNA sequence and produces an intermediate convolved feature. A feature sequence is derived by concatenating the metadata features with the intermediate convolved feature. The FCNN processes the feature sequence and produces probabilities for the variant being somatic, germline, or noise. A transfer learning strategy is used to train the model on two mutation datasets. Results establish advantages and superiority of our model over traditional classifiers.