Abstract: A computer method of detecting interacting DNA loci by constructing a contingency table from samples of a first trait and samples of a second trait. The samples of the first and second trait are associated with one of a plurality of genotype calls, each relating to an interaction between multiple DNA loci. The contingency table includes frequencies of each genotype call in the samples. Based on the contingency table, measuring the association between the plurality of genotype calls and the first and second traits. Classifying the genotype calls into a first group that is statistically associated with the first trait and a second group that is statistically associated with the second trait.

Abstract: This disclosure is related to further approximating multiple data vectors of a dataset. The multiple data vectors are initially approximated by one or more stored principle components. A processor performs multiple iterations of determining an updated estimate of a further principle component based on the multiple data vectors that are initially approximated by the one or more stored principle components. The processor performs this step such that the updated estimate of the further principal component further approximates the dataset. In each iteration the processor constrains the updated estimate of the further principal component to be orthogonal to each of the one or more stored principal components. The data vectors of the dataset are not manipulated but remain the same data vectors that are approximated by the stored principal components.

Abstract: This disclosure is related to further approximating multiple data vectors of a dataset. The multiple data vectors are initially approximated by one or more stored principle components. A processor performs multiple iterations of determining an updated estimate of a further principle component based on the multiple data vectors that are initially approximated by the one or more stored principle components. The processor performs this step such that the updated estimate of the further principal component further approximates the dataset. In each iteration the processor constrains the updated estimate of the further principal component to be orthogonal to each of the one or more stored principal components. The data vectors of the dataset are not manipulated but remain the same data vectors that are approximated by the stored principal components.

Abstract: A computer method of detecting interacting DNA loci by constructing a contingency table from samples of a first trait and samples of a second trait. The samples of the first and second trait are associated with one of a plurality of genotype calls, each relating to an interaction between multiple DNA loci. The contingency table includes frequencies of each genotype call in the samples. Based on the contingency table, measuring the association between the plurality of genotype calls and the first and second traits. Classifying the genotype calls into a first group that is statistically associated with the first trait and a second group that is statistically associated with the second trait.

Abstract: A computer-implemented method for annotation of a biological sequence, comprising: applying a classifier to determine a label for the first segment of a first biological sequence of a first species based on an estimated relationship between second segments in a training set and known labels of the second segments in the training set. The classifier is trained using the training set to estimate the relationship, and the second segments are of a second biological sequence of a second species that is different to, or a variant of, the first species. This disclosure also concerns a computer program and a computer system for annotation of a biological sequence.

Abstract: A computer-implemented method for detecting a regulatory single nucleotide polymorphism (rSNP). The method comprises determining a first score representative of a transcription factor binding affinity of a first allele, and a second score representative of a transcription factor binding affinity of a second allele. The first and second alleles are associated with a single nucleotide polymorphism (SNP), and the first score differs from the second score representing a change in the transcription factor binding affinity. A statistical significance value of the change in transcription factor binding affinity represented by the first score and the second score is then determined and compared with a threshold to determine whether the SNP is an rSNP. This disclosure also concerns a computer system and a computer program for detecting a regulatory single nucleotide polymorphism (rSNP).

Abstract: A computer-implemented method for evaluating performance of a classifier, the method comprising: (a) comparing labels determined by the classifier with corresponding known labels; and (b) based on the comparison, estimating a probability of observing an equal or better precision at a given recall with random ordering of the labels determined by the classifier. This disclosure also concerns a computer program and a computer system for evaluating performance of a classifier.

Abstract: A training method for a support vector machine, including executing an iterative process on a training set of data to determine parameters defining the machine, the iterative process being executed on the basis of a differentiable form of a primal optimization problem for the parameters, the problem being defined on the basis of the parameters and the data set.

Abstract: A document categorization system, including a clusterer for generating clusters of related electronic documents based on features extracted from the documents, and a filter module for generating a filter on the basis of the clusters to categorize further documents received by the system. The system may include an editor for manually browsing and modifying the clusters. The categorization of the documents is based on n-grams, which are used to determine significant features of the documents. The system includes a trend analyzer for determining trends of changing document categories over time, and for identifying novel clusters. The system may be implemented as a plug-in module for a spreadsheet application for permitting one-off or ongoing analysis of text entries in a worksheet.

Abstract: A method of assessing a signal to identify particular signal characteristics comprises application of machine learning to multi-dimensional histograms derived from multi-tap sampling of the signal. The signal is sampled from at least two tap points to retrieve a sample set, and the at least two tap points are adapted to retrieve distinct samples from the signal, such as time spaced samples or spectrally distinct samples. Multiple sample sets are retrieved from the signal over time. The at least two dimensional histogram is built from the joint probability distribution of the plurality of sample sets. A machine learning algorithm then processes the multi-dimensional histogram, and is trained to predict a value of at least one characteristic of the signal.

Abstract: Monitoring an optical signal comprises sampling the optical signal from two or more distinct tap points to retrieve a sample set. Multiple such sample sets are obtained over time. A joint probability distribution or phase portrait of the sample sets is assessed for indications of optical signal quality. The tap distinction can be polarization, for example to determine OSNR, or frequency. The tap distinction can be a time delay, which can enable diagnostic differentiation between multiple impairments, such as OSNR, dispersion, PMD, jitter, Q, and the like. Machine learning algorithms are particularly suitable for such diagnosis, particularly when provided a two dimensional histogram of sample density in the phase portrait.

Abstract: A method of assessing a signal to identify particular signal characteristics comprises application of machine learning to multi-dimensional histograms derived from multi-tap sampling of the signal. The signal is sampled from at least two tap points to retrieve a sample set, and the at least two tap points are adapted to retrieve distinct samples from the signal, such as time spaced samples or spectrally distinct samples. Multiple sample sets are retrieved from the signal over time. The at least two dimensional histogram is built from the joint probability distribution of the plurality of sample sets. A machine learning algorithm then processes the multi-dimensional histogram, and is trained to predict a value of at least one characteristic of the signal.

Abstract: Monitoring an optical signal comprises sampling the optical signal from two or more distinct tap points to retrieve a sample set. Multiple such sample sets are obtained over time. A joint probability distribution or phase portrait of the sample sets is assessed for indications of optical signal quality. The tap distinction can be polarisation, for example to determine OSNR, or frequency. The tap distinction can be a time delay, which can enable diagnostic differentiation between multiple impairments, such as OSNR, dispersion, PMD, jitter, Q, and the like. Machine learning algorithms are particularly suitable for such diagnosis, particularly when provided a two dimensional histogram of sample density in the phase portrait.

Abstract: A network optimisation system including a neural network module (200) for receiving traffic data representing traffic for a communications network and generating path configuration data representing paths between origin and destination nodes of the network for the traffic, and an analysis module (210) for processing the path configuration data and the traffic data and generating optimal path configuration data for the traffic. The analysis module may use a marginal increase heuristic (MIH) process, and a neural network may be trained on the basis of path configuration data generated from traffic data processed using a mixed integer linear programming (MILP) process.

Abstract: This invention concerns data mining, that is the extraction of information, from “unlearnable” data sets. In particular it concerns apparatus and a method for this purpose. The invention involves creating a finite training sample from the data set (14). Then training (50) a learning device (32) using a supervised learning algorithm to predict labels for each item of the training sample. Then processing other data from the data set with the trained learning device to predict labels and determining whether the predicted labels are better (learnable) or worse (anti-learnable) than random guessing (52). And, using a reverser (34) to apply negative weighting to the predicted labels if it is worse (anti-learnable) (54).

Abstract: The present invention relates to methods of profiling tumours and characterisation of the tissue types associated with the tumours. A gene expression profile is obtained from the tissue sample, the genes ranked in order of their relative expression levels and the tissue type identified by comparing the gene ranking obtained with a database of relative gene expression level rankings of different tissue types. This gives a means to identify primary tumours and to determine the identity of a tumour of unknown primary. The invention also provides a method of treatment of a tumour by diagnosis of primary tumours identified by the methods described.

Abstract: A document categorisation system, including a clusterer for generating clusters of related electronic documents based on features extracted from said documents, and a filter module for generating a filter on the basis of said clusters to categorise further documents received by said system. The system may include an editor for manually browsing and modifying the clusters. The categorisation of the documents is based on n-grams, which are used to determine significant features of the documents. The system includes a trend analyzer for determining trends of changing document categories over time, and for identifying novel clusters. The system may be implemented as a plug-in module for a spreadsheet application, providing a convenient means for one-off or ongoing analysis of text entries in a worksheet.

Abstract: A training method for a support vector machine, including executing an iterative process on a training set of data to determine parameters defining the machine, the iterative process being executed on the basis of a differentiable form of a primal optimisation problem for the parameters, the problem being defined on the basis of the parameters and the data set.