Using scarHRD for Predicting HRD Scores with ASCAT in Tumor-Only Mode

Answer:

Sure, I can provide a general outline of the steps to use scarHRD for predicting HRD (Homologous Recombination Deficiency) scores using ASCAT (Allele-Specific Copy number Analysis of Tumors) in tumor-only mode. Note that this is a high-level overview, and you should refer to the specific documentation of the tools for detailed instructions.

Step-by-Step Guide

1. Prepare Input Data

Tumor Sample: Obtain the sequencing data (e.g., BAM files) for the tumor sample.
Reference Genome: Ensure you have the appropriate reference genome (e.g., hg19 or hg38) for alignment and analysis.

2. Preprocessing

Alignment: Align the tumor sequencing reads to the reference genome using an aligner like BWA.
Sorting and Indexing: Sort and index the aligned BAM files using tools like SAMtools.

3. Run ASCAT in Tumor-Only Mode

Generate BAF and LogR Files: Use tools like GATK or custom scripts to generate B-allele frequency (BAF) and logR ratio files from the tumor BAM file.
Run ASCAT: Execute ASCAT to infer allele-specific copy numbers. In tumor-only mode, ASCAT will use the BAF and logR files to estimate the copy number profile of the tumor.
```
library(ASCAT)
ascat.bc = ascat.loadData("tumor_logR.txt", "tumor_BAF.txt")
ascat.bc = ascat.aspcf(ascat.bc)
ascat.output = ascat.runAscat(ascat.bc)
```

4. Prepare Input for scarHRD

Segment File: Convert the ASCAT output to a format compatible with scarHRD. This typically involves creating a segmented file with columns for chromosome, start position, end position, and copy number.

Example Format:

Chromosome  Start   End     CopyNumber
1           10000   50000   2
1           50001   100000  3

5. Run scarHRD

Install scarHRD: Ensure you have scarHRD installed. You can install it from CRAN or Bioconductor.
```
install.packages("scarHRD")
```

Execute scarHRD: Run scarHRD using the segmented file generated from ASCAT.

library(scarHRD)
hrd_results = scarHRD::scar_score("segmented_file.txt", reference = "hg19")

6. Interpret Results

HRD Scores: The output from scarHRD will include various HRD scores such as HRD-LOH, LST, and TAI. These scores can be used to infer the level of homologous recombination deficiency in the tumor sample.

Example Workflow in R

# Load necessary libraries
library(ASCAT)
library(scarHRD)

# Load and preprocess data with ASCAT
ascat.bc = ascat.loadData("tumor_logR.txt", "tumor_BAF.txt")
ascat.bc = ascat.aspcf(ascat.bc)
ascat.output = ascat.runAscat(ascat.bc)

# Convert ASCAT output to segmented file format
# This step will depend on the specific format of your ASCAT output
# Example: write.table(ascat.output$segments, "segmented_file.txt", sep="\t", row.names=FALSE, col.names=TRUE)

# Run scarHRD
hrd_results = scarHRD::scar_score("segmented_file.txt", reference = "hg19")

# View results
print(hrd_results)

Notes

Reference Genome: Ensure consistency in the reference genome used throughout the process.
Quality Control: Perform quality control checks at each step to ensure data integrity.
Documentation: Refer to the official documentation of ASCAT and scarHRD for detailed instructions and troubleshooting.

This workflow provides a general guideline, and specific steps may vary based on the versions of the tools