组装或定量 kallisto_sleuth

# 建立一个索引
kallisto index -i transcripts.idx transcripts.fasta.gz
# 进行定量
kallisto quant -i transcripts.idx -o output -b 100 reads_1.fastq.gz reads_2.fastq.gz
# single-end
# kallisto quant -i transcripts.idx -o output -b 100 --single -l 180 -s 20 reads.fastq.gz

conda install kallisto

kallisto index [arguments] ref.fa[.gz]

# 必需参数
-i, --index=STRING          存放索引的目录名字

# 可选参数
-k, --kmer-size=INT         k-mer (odd) length (default: 31, max value: 31)
    --make-unique           Replace repeated target names with unique names

kallisto quant [arguments] reads.fastq

示例: pair-end / single-end
kallisto quant -i index -o output pairA_1.fastq pairA_2.fastq pairB_1.fastq pairB_2.fastq
kallisto quant -i index -o output --single -l 200 -s 20 file1.fastq.gz file2.fastq.gz file3.fastq.gz

# 必需参数
-i, --index=STRING            索引所在目录
-o, --output-dir=STRING       输出目录。默认输出三个文件,abuncance.h5, abundance.tsv, run_info.json

Optional arguments:
    --bias                    Perform sequence based bias correction
-b, --bootstrap-samples=INT   Number of bootstrap samples (default: 0)
    --seed=INT                Seed for the bootstrap sampling (default: 42)
    --plaintext               指定输出纯文本文件,而非HDF5格式
    --fusion                  搜索融合位点?(Search for fusions for Pizzly)
    --single                  输入的文件是single-end reads
    --single-overhang         对不再转录本上的read也进行定量
    --fr-stranded             Strand specific reads, first read forward
    --rf-stranded             Strand specific reads, first read reverse
-l, --fragment-length=DOUBLE  Estimated average fragment length
-s, --sd=DOUBLE               Estimated standard deviation of fragment length
                              (default: -l, -s values are estimated from paired
                               end data, but are required when using --single)
-t, --threads=INT             Number of threads to use (default: 1)
    --pseudobam               Save pseudoalignments to transcriptome to BAM file
    --genomebam               Project pseudoalignments to genome sorted BAM file
-g, --gtf                     GTF file for transcriptome information
                              (required for --genomebam)
-c, --chromosomes             Tab separated file with chrosome names and lengths
                              (optional for --genomebam, but recommended)

kallisto pseudo [arguments] FASTQ-files

# 必需参数
-i, --index=STRING            Filename for the kallisto index to be used for
                              pseudoalignment
-o, --output-dir=STRING       Directory to write output to

# 可选参数
-u  --umi                     First file in pair is a UMI file
-b  --batch=FILE              Process files listed in FILE
    --single                  Quantify single-end reads
-l, --fragment-length=DOUBLE  Estimated average fragment length
-s, --sd=DOUBLE               Estimated standard deviation of fragment length
                              (default: -l, -s values are estimated from paired
                               end data, but are required when using --single)
-t, --threads=INT             Number of threads to use (default: 1)

# batch file的形式, single-end只有一个fastq,2变成1
{	
	#id file1 file 2
	cell1 cell1_1.fastq.gz cell1_1.fastq.gz
	cell2 cell2_1.fastq.gz cell2_1.fastq.gz
	cell3 cell3_1.fastq.gz cell3_1.fastq.gz
}
# 对于--umi指定后的形式
{
	#id umi-file file-1
	cell1 cell_1.umi cell_1.fastq.gz
	cell2 cell_2.umi cell_2.fastq.gz
	cell3 cell_3.umi cell_3.fastq.gz
}

kallisto h5dump -o output_path abundance.h5