Abstract: The present invention relates to a method of identifying a patient suffering from cancer as benefiting or not benefiting from immune checkpoint inhibition therapy comprising the steps of measuring an expression level of one or more preselected markers in a cancerous biological sample obtained from the patient, identifying a differentially expressed alternative promoter based on the expression level of the one or more preselected markers, calculating an alternative promoter usage score and identifying the patient as benefiting or not benefiting from immune checkpoint inhibition therapy using the alternative promoter usage score. The present invention also relates to a biomarker for excluding a patient suffering from cancer from immune checkpoint inhibition therapy.

Abstract: Techniques for identifying production-fit amino acid sequence libraries are disclosed. The techniques may include accessing a statistical model relating an input amino acid sequence to production fitness of a protein having the input amino acid sequence, obtaining production fitness information for production-fit variant amino acid sequences, and generating an amino acid sequence library having amino acid sequences with predicted production fitness in accordance with the production fitness information. The techniques further include using a statistical model for a protein characteristic other than production fitness to generate an amino acid sequence library having amino acid sequences that are both predicted to be production-fit and have the protein characteristic.

Abstract: This application provides methods and systems for determining transplant status. In some embodiments, the method comprises obtaining a biological sample from an organ transplant recipient who has received an organ; isolating cell-free nucleic acids from the biological sample; measuring the amount of each allele of one or more polymorphic nucleic acid targets in the biological sample; identifying the donor specific allele using a computer algorithm based on the measurements of the one or more polymorphic nucleic acid targets, whereby detecting one or more donor-specific circulating cell-free nucleic acids, detecting tissue injury based on the presence or amount of said one or more donor-specific nucleic acids, thereby determining transplant status.

Abstract: Techniques for improving continuous glucose monitoring (“CGM”) are described herein. In some embodiments, the techniques involve obtaining sensor data; applying, to the sensor data, a machine learning model trained to identify sensor data error patterns; and detecting an erroneous sensor use condition based on output of the machine learning model indicating an error pattern identified in the sensor data.

Abstract: The present invention relates to methods for evaluating and/or predicting the outcome of a clinical condition, such as cancer, metastasis, AIDS, autism, Alzheimer's, and/or Parkinson's disorder. The methods can also be used to monitor and track changes in a patient's DNA and/or RNA during and following a clinical treatment regime. The methods may also be used to evaluate protein and/or metabolite levels that correlate with such clinical conditions. The methods are also of use to ascertain the probability outcome for a patient's particular prognosis.

Abstract: A method for nucleic acid sequencing includes receiving nucleic acid sequencing data from a sequencing instrument that receives and processes a sample nucleic acid in a sequencing-by-synthesis process. The method also includes generating a set of candidate sequences of bases for the observed or measured nucleic acid sequencing data by determining a predicted signal for candidate sequences using a simulation framework. The simulation framework incorporates an estimated carry forward rate (CFR), an estimated incomplete extension rate (IER), an estimated droop rate (DR), an estimated reactivated molecules rate (RMR), and an estimated termination failure rate (TFR), the RMR being greater than or equal to zero and the TFR being lesser than one. The method also includes identifying, from the set of candidate sequences of bases, a candidate sequence as corresponding to the sequence for the sample nucleic acid.

Abstract: Immunogenic response prediction techniques are described. In an example, a system receives first training data that identifies a peptide, a first set of multiple major histocompatibility complex (MHC) molecules, and an immunogenic response associated with the peptide and the first set. The system updates a parameter of a first model based at least in part on the first training data. The first model is configured to determine a probability of causing the immunogenic response by a pair formed by the peptide and a MHC molecule from the first set. The system also receives second data that identifies a second set of MHC molecules, and generates, by using the first model and a second model, an immunologic response prediction of pairing the peptide with a MHC molecule from the second set. The second model is configured to generate at least one of peptide-MHC binding predictions or peptide-MHC cell surface presentation predictions.

Abstract: A method generates new binding peptides to Major Histocompatibility Complex (MHC) proteins. The method includes training a Generative Adversarial Network (GAN) having a generator and a discriminator only on a set of binding peptide sequences given training data comprising the set of binding peptide sequences and a set of non-binding peptide sequences. A GAN training objective includes the discriminator being iteratively updated to distinguish generated peptide sequences from sampled binding peptide sequences as fake or real and the generator being updated to fool the discriminator. The GAN training objective is optimized while learning two projection vectors for a binding class with two cross-entropy losses. A first loss discriminates binding peptide sequences in the training data from non-binding peptide sequences in the training data. A second loss discriminates generated binding peptide sequences from non-binding peptide sequences in the training data.

Abstract: The present invention relates to several biomarkers, including IL-1RA, IFN-? and GM-CSF, whose expressions at the mRNA level and at the protein level, correlate with chronic pathologies, such as Lyme disease, in particular the late chronic form of Lyme disease. More specifically, the invention provides methods and kits for the diagnosis of such chronic pathologies and for the assessment of a patient's response to a treatment, as well as methods and therapeutic agents for the treatment of such chronic pathologies.

Abstract: A method generates new binding peptides to Major Histocompatibility Complex (MHC) proteins. The method includes training, a Generative Adversarial Network (GAN) having a generator and a discriminator only on a set of binding peptide sequences given training data comprising the set of binding peptide sequences and a set of non-binding peptide sequences. A GAN training objective includes the discriminator being iteratively updated to distinguish generated peptide sequences from sampled binding peptide sequences as fake or real and the generator being updated to fool the discriminator. The GAN training objective is optimized while learning two projection vectors for a binding class with two cross-entropy losses. A first loss discriminates binding peptide sequences in the training data from non-binding peptide sequences in the training data. A second loss discriminates generated binding peptide sequences from non-binding peptide sequences in the training data.

Abstract: Disclosed is an in vitro method for detecting, in a biological sample, the presence of a blood coagulation enzyme inhibitor selected, independently, from factor Xa and factor IIa, the method including the step of making one or more competitive kinetics measurement(s) by carrying out a competitive enzymatic assay and implementing one or more types of classification or regression decision models obtained by training automated supervised learning models. The method may include the identification in the biological sample of an inhibitor in question, or even its characterization, or even its quantification. Also disclosed is a data processing system or device including implementation for at least part of the method, a computer program or storage medium which can be read by a computer or appropriate data, and a suitable kit.

Abstract: The present invention relates to a method for selecting neoepitopes for an individual, by selecting MHC I and/or MHC II binding neoepitopes and ranking them with respect the methods as described herein.

Abstract: Provided herein is technology relating to the detection of analytes and particularly, but not exclusively, to methods, systems, compositions, and kits for detecting analytes such as nucleic acids, proteins, small molecules, and other molecules using a technology based on the transient binding of detection probes.

Abstract: Systems, methods, and apparatus for peptide ligand and small molecule dug design given target protein sequence and structure are presented. The methods use class activation mapping (CAM)-guided transformers to generate the ligand. Given a target protein structure, a CAM-guided structure refinement process is used to optimize the structure towards the desired ligand effect classification. The embedding of the target protein's refined structure along with its residue embeddings are the input array into a transformer architecture.

Abstract: Embodiments in accordance with the present disclosure are directed to polymer beads and uses thereof, including forming libraries of compounds for screening and assay purposes. An example method includes using logic circuitry to: select a plurality of molecules that include a plurality of subgroups, each of the plurality of molecules exhibiting a mass spectrometry characteristic that is distinguishable from mass spectrometry characteristics of other molecules of the plurality, and assign the plurality of molecules with a position in a sequence of a plurality of synthetic compounds forming a library. The method further includes defining, as data in a memory circuit of the logic circuitry, the plurality of synthetic compounds that are sequenceable via mass spectrometry using the assigned positions of the plurality of molecules for communicating to other circuitry for formation thereof via coupling chemistry or screening of a particular function.