compute_average_similarity_matrix {GaMaBioMD}

Compute Average Similarity Matrix

Description

This function computes the average similarity matrix based on the percent similarity matrix.

Usage

compute_average_similarity_matrix(percent_similarity_matrix)

Arguments

percent_similarity_matrix

A matrix containing percent similarity values between sequences. Rows and columns should be labeled with SequenceIDs.

Value

A matrix containing average similarity values between SampleIDs.

Examples

accession_ranges <- list(
  SRU1 = "AJ240966 to AJ240970",
  STU2 = "AB015240 to AB015245",
  WPU13 = "L11934 to L11939",
  INU20 = c("AF277467 to AF277470", "AF333080 to AF333085")
)

# Use the function to expand accession ranges
sam_acc <- expand_accession_ranges(accession_ranges)
print(sam_acc)

# 2 get_sequence_information
accessions_to_query <- sam_acc$accession
seq_info <- get_sequence_information(accessions_to_query, remove_dot_1 = TRUE)
print(seq_info)
result <- preprocess_for_alignment(sam_acc, seq_info)

# Access the resulting data frames
merged_data <- result$merged_data
main_data <- result$main_data
final_data <- result$final_data

# If you want to sample 10% from each SampleID group:
sampled_data <- data_sampling(final_data, sample_proportion = 0.1)

alignment_results <- alignment_info(final_data, type = "global", verbose = 1)

# Access the resulting data frames
score_matrix <- alignment_results$score_matrix
normalized_score_matrix <- alignment_results$normalized_score_matrix

total_aligned_positions_matrix <- alignment_results$total_aligned_positions_matrix
number_of_matching_positions_matrix <- alignment_results$number_of_matching_positions_matrix

percent_similarity_matrix <- alignment_results$percent_similarity_matrix

alignment_results_list <- alignment_results$alignment_results_list

alignment_info_matrix <- alignment_results$alignment_info_matrix

output_directory <- tempdir()

# Save the list of alignment results to an RDS file
saveRDS(alignment_results_list, file.path(output_directory, "alignment_results_list.rds"))

# Save matrices to files
write.table(score_matrix, file.path(output_directory, "score_matrix.txt"), sep = "\t")
average_percent_similarity <- compute_average_similarity_matrix(percent_similarity_matrix)
print(average_percent_similarity)