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 lion's share of bacteria in various environments cannot be cloned in the laboratory and thus cannot be sequenced using existing technologies. A major goal of single-cell genomics is to complement gene-centric metagenomic data with whole-genome assemblies of uncultivated organisms. Assembly of single-cell data is challenging because of highly non-uniform read coverage as well as elevated levels of sequencing errors and chimeric reads. We describe SPAdes, a new assembler for both single-cell and standard (multicell) assembly, and demonstrate that it improves on the recently released E+V-SC assembler (specialized for single-cell data) and on popular assemblers Velvet and SoapDeNovo (for multicell data). SPAdes generates single-cell assemblies, providing information about genomes of uncultivatable bacteria that vastly exceeds what may be obtained via traditional metagenomics studies. SPAdes is available online ( http://bioinf.spbau.ru/spades ). It is distributed as open source software.

SPAdes, a new genome assembly algorithm and its applications to single-cell sequencing ( 7th Annual SFAF Meeting, 2012)

This study describes and validates a new method for metagenomic biomarker discovery by way of class comparison, tests of biological consistency and effect size estimation. This addresses the challenge of finding organisms, genes, or pathways that consistently explain the differences between two or more microbial communities, which is a central problem to the study of metagenomics. We extensively validate our method on several microbiomes and a convenient online interface for the method is provided at http://huttenhower.sph.harvard.edu/lefse/.

/pdf/metagenomic-biomarker-discovery-and-explanation-x530ilzkca.pdf

Metagenomic biomarker discovery and explanation

16S ribosomal RNA gene (rDNA) amplicon analysis remains the standard approach for the cultivation-independent investigation of microbial diversity. The accuracy of these analyses depends strongly on the choice of primers. The overall coverage and phylum spectrum of 175 primers and 512 primer pairs were evaluated in silico with respect to the SILVA 16S/18S rDNA non-redundant reference dataset (SSURef 108 NR). Based on this evaluation a selection of 'best available' primer pairs for Bacteria and Archaea for three amplicon size classes (100-400, 400-1000, ≥ 1000 bp) is provided. The most promising bacterial primer pair (S-D-Bact-0341-b-S-17/S-D-Bact-0785-a-A-21), with an amplicon size of 464 bp, was experimentally evaluated by comparing the taxonomic distribution of the 16S rDNA amplicons with 16S rDNA fragments from directly sequenced metagenomes. The results of this study may be used as a guideline for selecting primer pairs with the best overall coverage and phylum spectrum for specific applications, therefore reducing the bias in PCR-based microbial diversity studies.

Evaluation of general 16S ribosomal RNA gene PCR primers for classical and next-generation sequencing-based diversity studies

A strategy to understand the microbial components of the human genetic and metabolic landscape and how they contribute to normal physiology and predisposition to disease.

/pdf/the-human-microbiome-project-1armeyuv2c.pdf

The human microbiome project.

We tested the hypothesis that an altered community of gut microbes is associated with risk of colorectal cancer (CRC) in a study of 47 CRC case subjects and 94 control subjects. 16S rRNA genes in fecal bacterial DNA were amplified by universal primers, sequenced by 454 FLX technology, and aligned for taxonomic classification to microbial genomes using the QIIME pipeline. Taxonomic differences were confirmed with quantitative polymerase chain reaction and adjusted for false discovery rate. All statistical tests were two-sided. From 794217 16S rRNA gene sequences, we found that CRC case subjects had decreased overall microbial community diversity (P = .02). In taxonomy-based analyses, lower relative abundance of Clostridia (68.6% vs 77.8%) and increased carriage of Fusobacterium (multivariable odds ratio [OR] = 4.11; 95% confidence interval [CI] = 1.62 to 10.47) and Porphyromonas (OR = 5.17; 95% CI = 1.75 to 15.25) were found in case subjects compared with control subjects. Because of the potentially modifiable nature of the gut bacteria, our findings may have implications for CRC prevention.

/pdf/human-gut-microbiome-and-risk-for-colorectal-cancer-2jbefjs6wr.pdf

Human Gut Microbiome and Risk for Colorectal Cancer

The microbial ecology of human skin is complex, but little is known about its species composition. We examined the diversity of the skin biota from the superficial volar left and right forearms in six healthy subjects using broad-range small subunit rRNA genes (16S rDNA) PCR-based sequencing of randomly selected clones. For the initial 1,221 clones analyzed, 182 species-level operational taxonomic units (SLOTUs) belonging to eight phyla were identified, estimated as 74.0% [95% confidence interval (C.I.), approximately 64.8-77.9%] of the SLOTUs in this ecosystem; 48.0 +/- 12.2 SLOTUs were found in each subject. Three phyla (Actinobacteria, Firmicutes, and Proteobacteria) accounted for 94.6% of the clones. Most (85.3%) of the bacterial sequences corresponded to known and cultivated species, but 98 (8.0%) clones, comprising 30 phylotypes, had <97% similarity to prior database sequences. Only 6 (6.6%) of the 91 genera and 4 (2.2%) of the 182 SLOTUs, respectively, were found in all six subjects. Analysis of 817 clones obtained 8-10 months later from four subjects showed additional phyla (numbering 2), genera (numbering 28), and SLOTUs (numbering 65). Only four (3.4%) of the 119 genera (Propionibacteria, Corynebacteria, Staphylococcus, and Streptococcus) were observed in each subject tested twice, but these genera represented 54.4% of all clones. These results show that the bacterial biota in normal superficial skin is highly diverse, with few well conserved and well represented genera, but otherwise low-level interpersonal consensus.

https://www.pnas.org/content/pnas/104/8/2927.full.pdf

Molecular analysis of human forearm superficial skin bacterial biota

The esophagus, like other luminal organs of the digestive system, provides a potential environment for bacterial colonization, but little is known about the presence of a bacterial biota or its nature. By using broad-range 16S rDNA PCR, biopsies were examined from the normal esophagus of four human adults. The 900 PCR products cloned represented 833 unique sequences belonging to 41 genera, or 95 species-level operational taxonomic units (SLOTU); 59 SLOTU were homologous with culture-defined bacterial species, 34 with 16S rDNA clones, and two were not homologous with any known bacterial 16S rDNA. Members of six phyla, Firmicutes, Bacteroides, Actinobacteria, Proteobacteria, Fusobacteria, and TM7, were represented. A large majority of clones belong to 13 of the 41 genera (783/900, 87%), or 14 SLOTU (574/900, 64%) that were shared by all four persons. Streptococcus (39%), Prevotella (17%), and Veilonella (14%) were most prevalent. The present study identified ≈56–79% of SLOTU in this bacterial ecosystem. Most SLOTU of esophageal biota are similar or identical to residents of the upstream oral biota, but the major distinction is that a large majority (82%) of the esophageal bacteria are known and cultivable. These findings provide evidence for a complex but conserved bacterial population in the normal distal esophagus.

/pdf/bacterial-biota-in-the-human-distal-esophagus-1c30vvvv6r.pdf

Bacterial biota in the human distal esophagus

For psoriasis, an idiopathic inflammatory disorder of the skin, the microbial biota has not been defined using cultivation-independent methods. We used broad-range 16S rDNA PCR for archaea and bacteria to examine the microbiota of normal and psoriatic skin. From 6 patients, 19 cutaneous samples (13 from diseased skin and 6 from normal skin) were obtained. Extracted DNA was subjected to the broad range PCR, and 1,925 cloned products were compared with 2,038 products previously reported from healthy persons. Using 98% sequence identity as a species boundary, 1,841 (95.6%) clones were similar to known bacterial 16S rDNA, representing 6 phyla, 86 genera, or 189 species-level operational taxonomic unit (SLOTU); 84 (4.4%) clones with <98% identity probably represented novel species. The most abundant and diverse phylum populating the psoriatic lesions was Firmicutes (46.2%), significantly (P<0.001) overrepresented, compared to the samples from uninvolved skin of the patients (39.0%) and healthy persons (24.4%). In contrast, Actinobacteria, the most prevalent and diverse phylum in normal skin samples from both healthy persons (47.6%) and the patients (47.8%), was significantly (P<0.01) underrepresented in the psoriatic lesion samples (37.3%). Representation of Propionibacterium species were lower in the psoriatic lesions (2.9±5.5%) than from normal persons (21.1±18.2%; P<0.001), whereas normal skin from the psoriatic patients showed intermediate levels (12.3±21.6%). We conclude that psoriasis is associated with substantial alteration in the composition and representation of the cutaneous bacterial biota.

/pdf/substantial-alterations-of-the-cutaneous-bacterial-biota-in-njo3acfiza.pdf

Zhiheng Pei

Papers

Human Gut Microbiome and Risk for Colorectal Cancer

Molecular analysis of human forearm superficial skin bacterial biota

Bacterial biota in the human distal esophagus

Substantial alterations of the cutaneous bacterial biota in psoriatic lesions.

Inflammation and intestinal metaplasia of the distal esophagus are associated with alterations in the microbiome