rnaseq/README.qmd

---
title: rnaseq
format: gfm
---

<!-- README.md is generated by running 'quarto render README.qmd' -->

```{r, echo = FALSE, message = FALSE, error = FALSE, warning = FALSE}
library(tidyverse)
```

## RNA-seq

```{mermaid}
flowchart TB

  subgraph inputs[Inputs]
    input_r1[Input R1 FastQ]
    input_r2[Input R2 FastQ]
    sample_metadata[Sample metadata]
    reference_fasta[Reference fasta]
    reference_gtf[Reference GTF]
  end
  inputs:::io

  input_r1 & input_r2 & sample_metadata --> prepare_reads --> processed_r1 & processed_r2 & processed_metadata
  prepare_reads[/prepare_reads/]:::comp

  reference_fasta & reference_gtf --> prepare_reference --> processed_fasta & processed_gtf & star_index
  prepare_reference[/prepare_reference/]:::comp

  processed_r1 & processed_r2 & star_index & processed_fasta & processed_gtf --> align_and_quant --> aligned_reads_bam & quant_matrix
  align_and_quant[/align_and_quant/]:::comp

  aligned_reads_bam --> postprocess_bam --> output_aligned_reads_bam
  postprocess_bam[/postprocess_bam/]:::comp

  quant_matrix & processed_metadata --> postprocess_mtx --> output_quant_matrix
  postprocess_mtx[/postprocess_mtx/]:::comp

  processed_metadata & output_quant_matrix & output_combined_qc_data --> conversion --> output_anndata & output_sce
  conversion[/conversion/]:::comp

  subgraph outputs[Outputs]
    output_aligned_reads_bam[Aligned reads]
    output_quant_matrix[Quant matrix]
    output_combined_qc_data[QC Data]
    output_combined_qc_report[QC Report]
    output_anndata[AnnData]
    output_sce[SCE]
  end
  outputs:::io

  subgraph legend[Legend]
    comp[/Component/]:::comp
  end
  legend:::info


  classDef info stroke-dasharray: 4 4
```

## RNA-seq (With reporting)

```{mermaid}
flowchart TB

  subgraph inputs[Inputs]
    input_r1[Input R1 FastQ]
    input_r2[Input R2 FastQ]
    sample_metadata[Sample metadata]
    reference_fasta[Reference fasta]
    reference_gtf[Reference GTF]
  end
  inputs:::io

  input_r1 & input_r2 & sample_metadata --> prepare_reads --> processed_r1 & processed_r2 & processed_metadata
  prepare_reads[/prepare_reads/]:::comp

  prepare_reads -.-> prepare_reads_qc_data

  reference_fasta & reference_gtf --> prepare_reference --> processed_fasta & processed_gtf & star_index
  prepare_reference[/prepare_reference/]:::comp

  prepare_reference -.-> prepare_reference_qc_data

  processed_r1 & processed_r2 & star_index & processed_fasta & processed_gtf --> align_and_quant --> aligned_reads_bam & quant_matrix
  align_and_quant[/align_and_quant/]:::comp
  align_and_quant -.-> align_and_quant_qc_data

  aligned_reads_bam --> postprocess_bam --> output_aligned_reads_bam
  postprocess_bam[/postprocess_bam/]:::comp
  postprocess_bam -.-> postprocess_bam_qc_data

  quant_matrix & processed_metadata --> postprocess_mtx --> output_quant_matrix
  postprocess_mtx[/postprocess_mtx/]:::comp
  postprocess_mtx -.-> postprocess_mtx_qc_data

  prepare_reads_qc_data & prepare_reference_qc_data & align_and_quant_qc_data & postprocess_bam_qc_data & postprocess_mtx_qc_data -.-> reporting -.-> output_combined_qc_data & output_combined_qc_report
  reporting[/reporting/]:::comp

  processed_metadata & output_quant_matrix & output_combined_qc_data --> conversion --> output_anndata & output_sce
  conversion[/conversion/]:::comp

  subgraph outputs[Outputs]
    output_aligned_reads_bam[Aligned reads]
    output_quant_matrix[Quant matrix]
    output_combined_qc_data[QC Data]
    output_combined_qc_report[QC Report]
    output_anndata[AnnData]
    output_sce[SCE]
  end
  outputs:::io

  subgraph legend[Legend]
    comp[/Component/]:::comp
  end
  legend:::info


  classDef info stroke-dasharray: 4 4
```

## Prepare reads

```{mermaid}
flowchart TB

  subgraph inputs[Inputs]
    input_r1[Input R1 FastQ]
    input_r2[Input R2 FastQ]
    sample_metadata[Sample metadata]
  end

  input_r1 --> cat_fastq_r1 --> trim_r1 --> infer_strandedness_r1 --> processed_r1
  input_r2 --> cat_fastq_r2 --> trim_r2 --> infer_strandedness_r2 --> processed_r2

  processed_r1 & processed_r2 --> fastqc --> prepare_reads_qc_data

  sample_metadata --> processed_metadata

  subgraph outputs[Outputs]
    processed_r1
    processed_r2
    processed_metadata
    prepare_reads_qc_data
  end

  classDef info stroke-dasharray: 4 4
```

## Alignment and quantification

```{mermaid}
flowchart TB

  subgraph inputs[Inputs]
    input_r1[Input R1 FASTQ]
    input_r2[Input R2 FASTQ]
    input_transcript_fasta[Transcript FASTA]
    input_gtf[GTF]
    input_star_genome_dir[STAR index]
  end

  input_r1 & input_r2 & input_star_genome_dir  & input_gtf -->
    star_align_reads -->
    output_star_bam_genome & reads_aligned_to_transcriptome & output_star_junctions & output_star_log

  reads_aligned_to_transcriptome & input_gtf & input_transcript_fasta -->
    salmon_quant_alignment  -->
    output_salmon

  reads_aligned_to_transcriptome --> output_star_bam_transcriptome

  subgraph outputs[Outputs]
    output_star_bam_genome[STAR genome BAM]
    output_star_junctions[STAR splice junctions]
    output_star_log[STAR log]
    output_star_bam_transcriptome[STAR transcipt BAM]
    output_salmon[Salmon quantification]
  end

  classDef info stroke-dasharray: 4 4
```