Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The 1000 Genomes Project set out to provide a comprehensive description of common human genetic variation by applying whole-genome sequencing to a diverse set of individuals from multiple populations. Here we report completion of the project, having reconstructed the genomes of 2,504 individuals from 26 populations using a combination of low-coverage whole-genome sequencing, deep exome sequencing, and dense microarray genotyping. We characterized a broad spectrum of genetic variation, in total over 88 million variants (84.7 million single nucleotide polymorphisms (SNPs), 3.6 million short insertions/deletions (indels), and 60,000 structural variants), all phased onto high-quality haplotypes. This resource includes >99% of SNP variants with a frequency of >1% for a variety of ancestries. We describe the distribution of genetic variation across the global sample, and discuss the implications for common disease studies.

https://cdr.lib.unc.edu/downloads/v692t8920

A global reference for human genetic variation.

Comprehensive Integration of Single-Cell Data.

Genome-wide association studies have identified hundreds of genetic variants associated with complex human diseases and traits, and have provided valuable insights into their genetic architecture. Most variants identified so far confer relatively small increments in risk, and explain only a small proportion of familial clustering, leading many to question how the remaining, 'missing' heritability can be explained. Here we examine potential sources of missing heritability and propose research strategies, including and extending beyond current genome-wide association approaches, to illuminate the genetics of complex diseases and enhance its potential to enable effective disease prevention or treatment.

/pdf/finding-the-missing-heritability-of-complex-diseases-3b6mbqztnq.pdf

Finding the missing heritability of complex diseases

By characterizing the geographic and functional spectrum of human genetic variation, the 1000 Genomes Project aims to build a resource to help to understand the genetic contribution to disease. Here we describe the genomes of 1,092 individuals from 14 populations, constructed using a combination of low-coverage whole-genome and exome sequencing. By developing methods to integrate information across several algorithms and diverse data sources, we provide a validated haplotype map of 38 million single nucleotide polymorphisms, 1.4 million short insertions and deletions, and more than 14,000 larger deletions. We show that individuals from different populations carry different profiles of rare and common variants, and that low-frequency variants show substantial geographic differentiation, which is further increased by the action of purifying selection. We show that evolutionary conservation and coding consequence are key determinants of the strength of purifying selection, that rare-variant load varies substantially across biological pathways, and that each individual contains hundreds of rare non-coding variants at conserved sites, such as motif-disrupting changes in transcription-factor-binding sites. This resource, which captures up to 98% of accessible single nucleotide polymorphisms at a frequency of 1% in related populations, enables analysis of common and low-frequency variants in individuals from diverse, including admixed, populations.

/pdf/an-integrated-map-of-genetic-variation-from-1-092-human-4vxat9g1wd.pdf

An integrated map of genetic variation from 1,092 human genomes

Oligonucleotide probe arrays have enabled massively parallel analysis of gene expression levels from a single cDNA sample. Application of microarray technology to analyzing genomic DNA has been stymied by the sequence complexity of the entire human genome. A robust, single base-resolution direct genomic assay would extend the reach of microarray technology. We developed an array-based whole-genome genotyping assay that does not require PCR and enables effectively unlimited multiplexing. The assay achieves a high signal-to-noise ratio by combining specific hybridization of picomolar concentrations of whole genome-amplified DNA to arrayed probes with allele-specific primer extension and signal amplification. As proof of principle, we genotyped several hundred previously characterized SNPs. The conversion rate, call rate and accuracy were comparable to those of high-performance PCR-based genotyping assays.

/pdf/a-genome-wide-scalable-snp-genotyping-assay-using-microarray-43be5ic204.pdf

A genome-wide scalable SNP genotyping assay using microarray technology.

Aims: Bisulfite sequence analysis of individual CpG sites within genomic DNA is a powerful approach for methylation analysis in the genome. The major limitation of bisulfite-based methods is parallelization. Both array and next-generation sequencing technology are capable of addressing this bottleneck. In this report, we describe the application of Infinium® genotyping technology to analyze bisulfite-converted DNA to simultaneously query the methylation state of over 27,000 CpG sites from promoters of consensus coding sequences (CCDS) genes. Materials & methods: We adapted the Infinium genotyping assay to readout an array of over 27,000 pairs of CpG methylation-specific query probes complementary to bisulfite-converted DNA. Two probes were designed to each CpG site: a ‘methylated’ and an ‘unmethylated’ query probe. The probe design assumed that all underlying CpG sites were ‘in phase’ with the queried CpG site due to their close proximity. Bisulfite conversion was performed with a modified version of the ...

Genome-wide DNA methylation profiling using Infinium® assay.

The present invention provides a simplified method for identifying differences in nucleic acid abundances (e.g., expression levels) between two or more samples. The methods involve providing an array containing a large number (e.g. greater than 1,000) of arbitrarily selected different oligonucleotide probes where the sequence and location of each different probe is known. Nucleic acid samples (e.g. mRNA) from two or more samples are hybridized to the probe arrays and the pattern of hybridization is detected. Differences in the hybridization patterns between the samples indicates differences in expression of various genes between those samples. This invention also provides a method of end-labeling a nucleic acid. In one embodiment, the method involves providing a nucleic acid, providing a labeled oligonucleotide and then enzymatically ligating the oligonucleotide to the nucleic acid. Thus, for example, where the nucleic acid is an RNA, a labeled oligoribonucleotide can be ligated using an RNA ligase. In another embodiment, the end labeling can be accomplished by providing a nucleic acid, providing labeled nucleoside triphosphates, and attaching the nucleoside triphosphates to the nucleic acid using a terminal transferase.

Nucleic acid analysis techniques

Array-CGH is a powerful tool for the detection of chromosomal aberrations. The introduction of high-density SNP genotyping technology to genomic profiling, termed SNP-CGH, represents a further advance, since simultaneous measurement of both signal intensity variations and changes in allelic composition makes it possible to detect both copy number changes and copy-neutral loss-of-heterozygosity (LOH) events. We demonstrate the utility of SNP-CGH with two Infinium whole-genome genotyping BeadChips, assaying 109,000 and 317,000 SNP loci, to detect chromosomal aberrations in samples bearing constitutional aberrations as well tumor samples at sub-100 kb effective resolution. Detected aberrations include homozygous deletions, hemizygous deletions, copy-neutral LOH, duplications, and amplifications. The statistical ability to detect common aberrations was modeled by analysis of an X chromosome titration model system, and sensitivity was modeled by titration of gDNA from a tumor cell with that of its paired normal cell line. Analysis was facilitated by using a genome browser that plots log ratios of normalized intensities and allelic ratios along the chromosomes. We developed two modes of SNP-CGH analysis, a single sample and a paired sample mode. The single sample mode computes log intensity ratios and allelic ratios by referencing to canonical genotype clusters generated from ∼120 reference samples, whereas the paired sample mode uses a paired normal reference sample from the same individual. Finally, the two analysis modes are compared and contrasted for their utility in analyzing different types of input gDNA: low input amounts, fragmented gDNA, and Phi29 whole-genome pre-amplified DNA.

/pdf/high-resolution-genomic-profiling-of-chromosomal-aberrations-2okug8nrd2.pdf

High-resolution genomic profiling of chromosomal aberrations using Infinium whole-genome genotyping

The invention relates to compositions and methods for detecting and quantifying a target nucleic acid using a variety of both signal amplification and target amplification techniques.

Kevin L. Gunderson

Papers

A genome-wide scalable SNP genotyping assay using microarray technology.

Genome-wide DNA methylation profiling using Infinium® assay.

Nucleic acid analysis techniques

High-resolution genomic profiling of chromosomal aberrations using Infinium whole-genome genotyping

Detection of nucleic acid amplification reactions using bead arrays