A method of determining copy number variation of chromosomes and genes in a sample from a subject having cancer or suspected of having cancer and of determining diagnosis, prognosis, and potential therapy when compared to a reference sample.

A method of determining copy number variation of chromosomes and genes in a sample from a subject having cancer or suspected of having cancer and of determining diagnosis, prognosis, and potential therapy when compared to a reference sample.

The present invention relates to a starter culture comprising at least two Streptococcus thermophilus strains, wherein a first and a second Streptococcus thermophilus strain are chosen from RGP group 1, RGP group 2, RGP group 3 and RGP group 4, with the proviso that the first and second Streptococcus thermophilus strains do not belong to the same RGP group.

The present invention relates to a starter culture comprising at least two Streptococcus thermophilus strains, wherein a first and a second Streptococcus thermophilus strain are chosen from RGP group 1, RGP group 2, RGP group 3 and RGP group 4, with the proviso that the first and second Streptococcus thermophilus strains do not belong to the same RGP group.

Provided herein are methods of identifying a group of complementarity determining region (CDR)3, 2 and/or 1 nanobody amino acid sequences (CDR3, CDR2 and/or CDR1 sequences) wherein a reduced number of the CDR3, CDR2 and/or CDR1 sequences are false positives as compared to a control, methods for determining antigen affinity of nanobody peptide sequences, and related methods for training a deep learning model.

Provided herein are methods of identifying a group of complementarity determining region (CDR)3, 2 and/or 1 nanobody amino acid sequences (CDR3, CDR2 and/or CDR1 sequences) wherein a reduced number of the CDR3, CDR2 and/or CDR1 sequences are false positives as compared to a control, methods for determining antigen affinity of nanobody peptide sequences, and related methods for training a deep learning model.

Systems and methods that receive as input microscopy images, extract features, and apply layers of processing units to compute one or more sets of cellular phenotype features, particularly antibodies, corresponding to cellular densities and/or fluorescence measured under different conditions. The system is a machine learning architecture having, in one aspect, a deep neural network, typically a convolutional neural network. The deep neural network can be trained and tested directly on raw microscopy images. The system computes class specific feature maps for every phenotype variable using a deep neural network. The system produces predictions for one or more reference antibody variables based on microscopy images within populations of cells.

Systems and methods that receive as input microscopy images, extract features, and apply layers of processing units to compute one or more sets of cellular phenotype features, particularly antibodies, corresponding to cellular densities and/or fluorescence measured under different conditions. The system is a machine learning architecture having, in one aspect, a deep neural network, typically a convolutional neural network. The deep neural network can be trained and tested directly on raw microscopy images. The system computes class specific feature maps for every phenotype variable using a deep neural network. The system produces predictions for one or more reference antibody variables based on microscopy images within populations of cells.

A system for screening phenotypic targets associated with a disease using in-silico techniques. The system communicably coupled to a phenotype ontological databank including a plurality of phenotypes and phenotypic targets associated with each of the plurality of phenotypes; wherein the system includes a processor communicably coupled to a memory. The processor configured to receive a first input of the disease, receive a second input relating to at least one phenotype associated with the disease, identify for each of the at least one phenotype a plurality of similar phenotypes relating to a particular phenotype of the at least one phenotype of the second input, determine a similarity score for each of the plurality of similar phenotypes in comparison with the particular phenotype of the at least one phenotype of the second input, extract, from the phenotype ontological databank, phenotypic targets associated with similar phenotypes having similarity score higher than a first predefined threshold, compute a cumulative score of the phenotypic targets based on a plurality of parameters, wherein the cumulative score of a given phenotypic target is indicative of relevance thereof with respect to the disease, screen out phenotypic targets with cumulative score lower than a second predefined threshold, compute relevant pathways for the phenotypic targets by performing Highly dysregulated pathway analysis (HDPA) for the screened phenotypic targets, compute mechanistic factors attributing to regulation of similar phenotypes and pathological information of the disease in association with the screened phenotypic targets.

The present disclosure provides methods and systems for identifying natural product-encoding multi-gene clusters (MGCs). In some embodiments, the present disclosure also teaches methods for producing sequenced and assembled metagenomic libraries that are amenable to MGC search bioinformatic tools and techniques.