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

A method for determining the presence of multiple nucleotide sequences of interest in multiple samples while preserving the identity of each sample, by contacting the samples with a plurality of probe sets. The probes are designed to indicate the presence of the sequences of interest and the identity of the sample containing the sequence of interest in complex mixtures. Applications of the method include genotyping, expression analysis, and identification of individual species in complex samples. Kits of probe sets for use in the methods are also provided

Multi-sample indexing for multiplex genotyping

The present disclosure provides a method for sequencing nucleic acids. The method can include polymerase catalyzed incorporation of nucleotides into a nascent nucleic acid strand against a nucleic acid template, wherein the polymerase is attached to a charge sensor that detects nucleotide incorporation events. One or more non-natural nucleotide types that each produce a unique signatures at the charge sensor can be used to uniquely identify different nucleotides in the template nucleic acid.

Field-effect apparatus and methods for sequencing nucelic acids

The invention provides methods of identifying a plurality of reactive recognition sites for a restriction endonuclease in genomic DNA In particular embodiments, the methods can be used to identify methylation state of a plurality of CpG target sites in genomic DNA The method can include steps of treating genomic DNA with a restriction endonuclease, thereby producing genomic DNA fragments; ligating the fragments, thereby forming a concatenated DNA; and identifying sequence portions of the concatenated DNA that are re-ordered compared to the genomic DNA

Methylation-sensitive restriction enzyme endonuclease method of whole genome methylation analysis

Most genomes to date have been sequenced without taking into account the diploid nature of the genome. However, the distribution of variants on each individual chromosome can (1) significantly impact gene regulation and protein function, (2) have important implications for analyses of population history and medical genetics, and (3) be of great value for accurate interpretation of medically relevant genetic variation. Here, we describe a comprehensive and detailed protocol for an ultra fast ( 95 % of the whole human genome in Mb-scale phasing blocks. Additionally, the same workflow can be used to aid de novo assembly (Adey et al., Genome Res 24(12):2041-2049, 2014), detect structural variants, and perform single cell ATAC-seq analysis (Cusanovich et al., Science 348(6237):910-914, 2015).

Contiguity-Preserving Transposition Sequencing (CPT-Seq) for Genome-Wide Haplotyping, Assembly, and Single-Cell ATAC-Seq.

Aberrations in DNA methylation patterns are widely recognized as a hallmark of the cancer cell. DNA methylation has emerged as a promising biomarker for the detection and classification of various types of cancer, and ability to accurately assess the DNA methylation changes plays an important role in understanding of disease onset and progression. We developed a new generation of genome-wide DNA methylation BeadChip which allows high-throughput methylation profiling of human genome. The new high density BeadChip can assay over 480K CpG sites and analyze twelve samples in parallel. The innovative content includes coverage of 99% of RefSeq genes with multiple probes per gene, 96% of CpG islands from the UCSC database, CpG island shores and additional content selected from whole-genome bisulfite sequencing data and input from DNA methylation experts. The well-characterized Infinium® assay is used for analysis of CpG methylation using bisulfite-converted genomic DNA. In this assay, unmethylated cytosines (C) are converted to uracil (U) when treated with bisulfite, while methylated cytosines remain unchanged. The assay design is using single probe assays for CpG loci with up to two underlying CpG dinucleotides, and two-probe assays for CpG loci with multiple underlying CpG sites, with one probe querying the “unmethylated” allele and the other probe querying the “methylated” allele. The assays are designed under the assumption that methylation is regionally correlated (within 50 base pairs) and that all CpG sites underlying the probe are assumed to be “in phase” with the queried CpG site. For the BeadChip development, we used methylation standards created by de-methylating gDNA with Phi29 whole genome amplification, methylating the amplified DNA with SssI methylase and mixing the unmethylated and methylated DNA in a 1:1 ratio to create a 50% methylation state. 500 ng gDNA input is used for bisulfite conversion and is sufficient for two assays. Reproducible DNA methylation profiles were obtained between replicates (an average R 2 of 0.98). We applied this technology to DNA methylation analyses in cancer cell lines of different tissue of origin and normal DNA samples derived from multiple tissues. Highly specific methylation signatures were obtained for each sample type. The ability to determine genome-wide methylation patterns will rapidly advance methylation research and ultimately lead to the development of powerful tools for diagnosis, prognosis, and treatment of human diseases. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr LB-176. doi:10.1158/1538-7445.AM2011-LB-176

Kevin L. Gunderson

Papers

Multi-sample indexing for multiplex genotyping

Field-effect apparatus and methods for sequencing nucelic acids

Methylation-sensitive restriction enzyme endonuclease method of whole genome methylation analysis

Contiguity-Preserving Transposition Sequencing (CPT-Seq) for Genome-Wide Haplotyping, Assembly, and Single-Cell ATAC-Seq.

Abstract LB-176: A novel high density DNA methylation array with single CpG site resolution