---
title: "paper database"
format: html
editor: visual
---
```{r}
library(tidyverse)
```
```{r}
papers <- c("Katherine Silliman, Laura H Spencer, Samuel J White, Steven B Roberts (2023) Epigenetic and genetic population structure is coupled in a marine invertebrate Genome Biology and Evolution, 2023;, evad013 doi:10.1093/gbe/evad013",
"Dang, X., Lim, Y.-K., Li, Y., Roberts, S. B., Li, L., & Thiyagarajan, V. (2022). Epigenetic-associated phenotypic plasticity of the ocean acidification-acclimated edible oyster in the mariculture environment Molecular Ecology, 00, 1– 16. doi:10.1111/mec.16751")
```
```{r}
authors <- str_extract(papers, ".*(?=\\s\\(\\d{4}\\))")
years <- str_extract(papers, "(?<=\\()\\d{4}(?=\\))")
titles <- str_extract(papers, "(?<=\\d{4}\\)\\s).+?(?=\\s[A-Za-z]+,)")
journals <- str_extract(papers, "(?<=[A-Za-z]\\s)\\w+[^,]+(?=,\\s\\d{2,4})")
volume_and_pages <- str_extract(papers, "\\d{2,4},\\s\\d{1,4}(\\s–\\s\\d{1,4})?")
dois <- str_extract(papers, "doi:\\S+")
```
```{r}
df <- data.frame(Author = authors,
Year = years,
Title = titles,
Journal = journals,
Volume_and_Pages = volume_and_pages,
DOI = dois,
stringsAsFactors = FALSE)
```
```{r}
papers <- c("Katherine Silliman, Laura H Spencer, Samuel J White, Steven B Roberts (2023) Epigenetic and genetic population structure is coupled in a marine invertebrate Genome Biology and Evolution, 2023;, evad013 doi:10.1093/gbe/evad013",
"Dang, X., Lim, Y.-K., Li, Y., Roberts, S. B., Li, L., & Thiyagarajan, V. (2022). Epigenetic-associated phenotypic plasticity of the ocean acidification-acclimated edible oyster in the mariculture environment Molecular Ecology, 00, 1– 16. doi:10.1111/mec.16751",
"Crandall G, Elliott Thompson R, Eudeline B, Vadopalas B, Timmins-Schiffman E, Roberts S. (2022) Proteomic response of early juvenile Pacific oysters (Crassostrea gigas) to temperature PeerJ 10:e14158 doi:10.7717/peerj.14158",
"Hollie M. Putnam, Shelly A. Trigg, Samuel J. White, Laura H. Spencer, Brent Vadopalas, Aparna Natarajan, Jonathan Hetzel, Erich Jaeger, Jonathan Soohoo, Cristian Gallardo-Escárate, Frederick W. Goetz, Steven B. Roberts (2022) Dynamic DNA methylation contributes to carryover effects and beneficial acclimatization in geoduck clams. bioRxiv https://doi.org/10.1101/2022.06.24.497506",
"Yaamini Venkataraman, Samuel J White and Steven Roberts (2022) Differential DNA methylation in Pacific oyster reproductive tissue in response to ocean acidification. BMC Genomics 23, 556 doi:10.1186/s12864-022-08781-5")
```
```{r}
authors <- str_extract(papers, ".*(?=\\s\\(\\d{4}\\))")
years <- str_extract(papers, "(?<=\\()\\d{4}(?=\\))")
titles <- str_extract(papers, "(?<=\\d{4}\\)\\s).+?(?=\\s[A-Za-z]+(\\s|,))")
journals <- str_extract(papers, "(?<=\\s)[A-Za-z]+[\\w\\s]*?(?=,\\s\\d{2,4})")
volume_and_pages <- str_extract(papers, "\\d{2,4},\\s\\d{1,4}(\\s–\\s\\d{1,4}|\\w+)?")
dois <- str_extract(papers, "doi:\\S+|https://doi.org/\\S+")
```
```{r}
df <- data.frame(Author = authors,
Year = years,
Title = titles,
Journal = journals,
Volume_and_Pages = volume_and_pages,
DOI = dois,
stringsAsFactors = FALSE)
```
```{r}
if (!require(stringr)) {
install.packages("stringr")
library(stringr)
}
# The list of papers as a string
papers <- "Katherine Silliman, Laura H Spencer, Samuel J White, Steven B Roberts (2023) Epigenetic and genetic population structure is coupled in a marine invertebrate Genome Biology and Evolution, 2023;, evad013 doi:10.1093/gbe/evad013
Dang, X., Lim, Y.-K., Li, Y., Roberts, S. B., Li, L., & Thiyagarajan, V. (2022). Epigenetic-associated phenotypic plasticity of the ocean acidification-acclimated edible oyster in the mariculture environment Molecular Ecology, 00, 1– 16. doi:10.1111/mec.16751
Crandall G, Elliott Thompson R, Eudeline B, Vadopalas B, Timmins-Schiffman E, Roberts S. (2022) Proteomic response of early juvenile Pacific oysters (Crassostrea gigas) to temperature PeerJ 10:e14158 doi:10.7717/peerj.14158"
# Extract DOIs using a regular expression
dois <- str_extract_all(papers, "doi:[\\d.]+\\/\\S+")
# Print the extracted DOIs
print(unlist(dois))
```