---
title: "Kallisto redo"
output: html_document
date: "2024-06-04"
---

## get genome

```{r, engine='bash'}
cd ../data
curl -O https://owl.fish.washington.edu/halfshell/genomic-databank/Mtros-hq_transcripts.fasta
```


## Create indices for transcriptome with Kallisto
```{bash}

cp /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/ncbi_dataset/data/GCF_036588685.1/cds_from_genomic.fna /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/ncbi_dataset/data/GCF_036588685.1/cds_from_genomic.fasta
# Execute the Kallisto tool located at the specified path
```

```{bash}
/home/shared/kallisto_linux-v0.50.1/kallisto \
index \
-t 20 \
-i /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/Mtros-hq_transcripts_cds.index \
/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/ncbi_dataset/data/GCF_036588685.1/cds_from_genomic.fasta
```

# Quantify the indices
```{bash}
# Set the paths
DATA_DIRECTORY="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/raw-trimmed/"
KALLISTO_INDEX="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/Mtros-hq_transcripts_cds.index"
OUTPUT_DIRECTORY="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/kallisto-quant-cds/"


# Iterate over all .fq.gz files in the data directory
for FILE in "$DATA_DIRECTORY"/*.fastq.gz; do
    # Extract the base name of the file for naming the output folder
    BASENAME=$(basename "$FILE" _L099_R1_cmb.trim.fastq.gz)

    # Create output directory for this sample
    SAMPLE_OUTPUT="$OUTPUT_DIRECTORY/$BASENAME"
    mkdir -p "$SAMPLE_OUTPUT"

    # Run Kallisto quantification
    /home/shared/kallisto_linux-v0.50.1/kallisto quant -i "$KALLISTO_INDEX" -o "$SAMPLE_OUTPUT" \
        --single -t 20 -l 65 -s 2 "$FILE"
done

echo "Kallisto quantification complete."
```
# Run Kallisto on rna.fna file 

## Create indices for transcriptome with Kallisto
```{bash}

cp /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/ncbi_dataset/data/GCF_036588685.1/rna.fna /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/ncbi_dataset/data/GCF_036588685.1/rna.fasta
# Execute the Kallisto tool located at the specified path
```

# create index
```{bash}
/home/shared/kallisto_linux-v0.50.1/kallisto \
index \
-t 20 \
-i /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/Mtros-hq_transcripts_rna.index \
/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/ncbi_dataset/data/GCF_036588685.1/rna.fasta
```

# Quantify the indices
```{bash}
# Set the paths
DATA_DIRECTORY="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/data/raw-trimmed/"
KALLISTO_INDEX="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/Mtros-hq_transcripts_rna.index"
OUTPUT_DIRECTORY="/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/kallisto-quant-rna/"


# Iterate over all .fq.gz files in the data directory
for FILE in "$DATA_DIRECTORY"/*.fastq.gz; do
    # Extract the base name of the file for naming the output folder
    BASENAME=$(basename "$FILE" _L099_R1_cmb.trim.fastq.gz)

    # Create output directory for this sample
    SAMPLE_OUTPUT="$OUTPUT_DIRECTORY/$BASENAME"
    mkdir -p "$SAMPLE_OUTPUT"

    # Run Kallisto quantification
    /home/shared/kallisto_linux-v0.50.1/kallisto quant -i "$KALLISTO_INDEX" -o "$SAMPLE_OUTPUT" \
        --single -t 20 -l 65 -s 2 "$FILE"
done

echo "Kallisto quantification complete."
```


# Count matrices

## Generate count matrices
```{bash}
     
perl /home/shared/trinityrnaseq-v2.12.0/util/abundance_estimates_to_matrix.pl \
--est_method kallisto \
--gene_trans_map 'none' \
--out_prefix /home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/kallisto-quant-cds/abundance-matrices \
--name_sample_by_basedir \
/home/shared/8TB_HDD_02/graceleuchtenberger/Github/byssus-exp-analysis/output/kallisto-quant-cds/*/abundance.tsv 

```
## View abundance matrix
```{bash}
head output/kallisto-quant/abundance-matrices.isoform.counts.matrix
```
## Make counts matrix
```{r, eval = TRUE}
countmatrix <- read.delim("output/kallisto-quant/abundance-matrices.isoform.counts.matrix", header = TRUE, sep = '\t')
rownames(countmatrix) <- countmatrix$X
countmatrix <- countmatrix[,-1]
head(countmatrix)
```