---
title: "04-spur-gene-sym"
output: html_document
---


Will recreate and SPur gene symbol join however using the SPUR blastx with no evalue limit.


```{r}
library(tidyverse)
```


```{r}

spur <- read.csv("../analyses/CgR-blastp-spur.tab", header = FALSE, sep="\t") %>%
  distinct(V1, .keep_all = TRUE)
```


```{r}
head(spur)
```


```{r}
ncbiP <- read.csv("../../../nb-2021/C_gigas/data/NcbiProteinEchinobaseGene_Spur.txt", header = FALSE, sep="\t")

head(ncbiP)
```
```{r}
library(fuzzyjoin)

```



```{r}
betterspur <- spur %>% fuzzy_inner_join(ncbiP, by = "V2", match_fun = str_detect)

```

```{r}
#spur %>% stringdist_inner_join(ncbiP, by = "V2", max_dist = 2)
```



```{r}
write_tsv(
  betterspur,
  "../analyses/Spur-blastx-LOCsym.tab"
)

```