| setwd("~/project_icipe") | |
| library(ggplot2) | |
| # 1. load the files | |
| oases <- read.csv('./oases.csv') | |
| soap <- read.csv('./soapdenovotrans.csv') | |
| # check the number of rows and columns | |
| dim(oases) | |
| dim(soap) |
| # This script demonstrates how to download a mapping from RefSeq mRNA to human gene symbols by using the ensembl biomart service and the bioconductor `biomaRt` package in R. | |
| source("https://bioconductor.org/biocLite.R") | |
| biocLite("biomaRt") | |
| library("biomaRt") | |
| # work around bug in resolving host (https://support.bioconductor.org/p/74304/) | |
| listMarts(host="www.ensembl.org") |
| # with example PDF URL | |
| PDF_URL"=http://www.sciencedirect.com/science/article/pii/S0191886909000877/pdfft\?md5\=25fb6461c7b1ebe114acb2cd5ab91ddd\&pid\=1-s2.0-S0191886909000877-main.pdf" | |
| wget \ | |
| --header "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.111 Safari/537.36" \ | |
| --verbose \ | |
| --save-cookies cookies.txt \ | |
| --keep-session-cookies \ | |
| $PDF_URL | |
| prefix | publisher | journals | dois | |
|---|---|---|---|---|
| 10.12679 | 0 | 0 | ||
| 10.7579 | 123Doc Education | 0 | 0 | |
| 10.3731 | 21st Century COE Program (Toplogical Science and Technology) | 1 | 40 | |
| 10.5775 | A. I. Rosu Cultural Scientific Foundation Fundatia cultural-stiintifica A. I. Rosu | 1 | 80 | |
| 10.4037 | AACN Publishing | 2 | 766 | |
| 10.1306 | AAPG/Datapages | 4 | 21817 | |
| 10.3183 | AB Svensk Papperstidning | 1 | 1550 | |
| 10.5769 | ABEAT - Associacao Brasileira de Especialistas em Alta Tecnologia | 1 | 57 | |
| 10.7597 | ACOPIOS - Revista Iberica de Mineralogia | 1 | 9 |
| var CollapsibleTree = function(elt) { | |
| var m = [20, 120, 20, 120], | |
| w = 1280 - m[1] - m[3], | |
| h = 580 - m[0] - m[2], | |
| i = 0, | |
| root, | |
| root2; | |
| var tree = d3.layout.tree() |
| { | |
| "options": { | |
| "died": true, | |
| "multigraph": true, | |
| "compound": true | |
| }, | |
| "nodes": [ | |
| { | |
| "v": "questions", | |
| "value": { |
| license: gpl-3.0 |
| sed '1d;$d' | sed 's/<\/article>/<\/article>♛/g' | tr -d '\n' | tr '♛' '\n' | less -S | |
| # e.g. download every EuropePMC archive and convert them to a stream of all articles | |
| curl --silent http://europepmc.org/ftp/oa/ | \ | |
| grep -o 'PMC[0-9]*_PMC[0-9]*\.xml\.gz' | \ | |
| sort | uniq | \ | |
| sed 's/^/http:\/\/europepmc.org\/ftp\/oa\//' | \ | |
| xargs -n 1 curl --silent | gunzip | grep -vP '<\/?articles>' | \ | |
| sed 's/<\/article>/<\/article>♛/g' | tr -d '\n' | tr '♛' '\n' | less -S |
Making an Electron app and want to embed a database? Here's a table to help you choose the right database software.
Work in progress
| Project | Language | NPM package? | Flat file? | In memory? | Full-text search? | Maturity | Embedded size | Dependencies |
|---|---|---|---|---|---|---|---|---|
| NeDB | Javascript | Yes | Always | No | High | Low | Simple | |
| Lunr | Javascript | No | Yes | Yes | High | Tiny | None | |
| Search-index | Javascript | |||||||
| Sqlite3 | C | Yes | No | Yes (fts extens |
| #!/usr/bin/env node | |
| // this script optimises the eupmc metadata for inclusion in a full-text | |
| // search index. | |
| var Transform = require("stream").Transform | |
| var util = require("util") | |
| var natural = require('natural') | |
| var tokenize = (new natural.TreebankWordTokenizer()).tokenize |