comparison coral_multilocus_genotype.R @ 9:3c42de11ea1d draft default tip

Uploaded

8:33d759858625

        select("id", "coral_mlg_clonal_id", "coral_mlg_rep_sample_id", "genetic_coral_species_call"),
        by=c("genotype_id"="id"));
# Name the columns.
smlg_data_frame <- as.data.frame(smlg);
colnames(smlg_data_frame) <- c("user_specimen_id", "affy_id", "bcoral_genet_id", "genotype_id",
		               "coral_mlg_clonal_id", "coral_mlg_rep_sample_id", "genetic_coral_species_call");
log_data_frame("smlg_data_frame", smlg_data_frame);
# Missing GT in samples submitted.
start_time <- time_start("Discovering missing GT in samples");
gt <- extract.gt(vcf, element="GT", as.numeric=FALSE);
missing_gt <- apply(gt, MARGIN=2, function(x){ sum(is.na(x))});

        select("coral_mlg_rep_sample_id", "coral_mlg_clonal_id"),
        by='coral_mlg_clonal_id') %>%
        mutate(coral_mlg_rep_sample_id=ifelse(is.na(coral_mlg_rep_sample_id.x),coral_mlg_rep_sample_id.y,coral_mlg_rep_sample_id.x)) %>%
    ungroup() %>%
    dplyr::select(-coral_mlg_rep_sample_id.x,-coral_mlg_rep_sample_id.y, -group.x,-group.y) %>%
    distinct();

# Confirm that the representative mlg is the same between runs.
uniques2 <- unique(prep_genotype_tibble[c("group", "coral_mlg_rep_sample_id")]);
uniques2 <- uniques2[!is.na(uniques2$coral_mlg_rep_sample_id),];
na.mlg3 <- which(is.na(prep_genotype_tibble$coral_mlg_rep_sample_id));

# <chr>                      <chr>
# A.palmata                  C1651
representative_mlg_tibble <- prep_genotype_tibble %>%
    mutate(coral_mlg_rep_sample_id=ifelse(is.na(coral_mlg_rep_sample_id) & (db_match =="no_match"), affy_id, coral_mlg_rep_sample_id)) %>%
    ungroup() %>%
    select(-group)%>%
    distinct();
# prep_genotype_table_tibble looks like this:
# affy_id       coral_mlg_clonal_id user_specimen_id db_match
# a550962...CEL HG0120              1090             match
# genetic_coral_species_call coral_mlg_rep_sample_id
# A.palmata                  1104
prep_genotype_table_tibble <- stag_db_report %>%
    select("affy_id", "coral_mlg_clonal_id", "user_specimen_id", "db_match", "genetic_coral_species_call") %>%
    left_join(representative_mlg_tibble %>%
        select("affy_id", "coral_mlg_rep_sample_id"),
        by='affy_id');
# genotype_table_tibble looks like this:
# affy_id         coral_mlg_clonal_id user_specimen_id db_match
# a550962-436.CEL HG0120              1090             match
# genetic_coral_species_call coral_mlg_rep_sample_id bcoral_genet_id
# A.palmata                  1104                    <NA>
genotype_table_tibble <- prep_genotype_table_tibble %>%
    left_join(affy_metadata_data_frame %>%
        select("user_specimen_id", "bcoral_genet_id"),
        by='user_specimen_id') %>%
    drop_na(coral_mlg_rep_sample_id);
write_data_frame(output_data_dir, "genotype.tabular", genotype_table_tibble);

# Output the file needed for populating the person table.
person_table_data_frame <- data.frame(matrix(ncol=4, nrow=num_rows));
colnames(person_table_data_frame) <- c("last_name", "first_name", "organization", "email");

    sample_table_data_frame$percent_apalm_coral[i] <- sample_prep_data_frame$percent_apalm_coral[i];
    sample_table_data_frame$percent_alternative_sym[i] <- DEFAULT_MISSING_NUMERIC_VALUE;
    sample_table_data_frame$percent_heterozygous_coral[i] <- sample_prep_data_frame$percent_heterozygous_coral[i];
    sample_table_data_frame$percent_heterozygous_sym[i] <- DEFAULT_MISSING_NUMERIC_VALUE;
    sample_table_data_frame$field_call[i] <- sample_prep_data_frame$field_call[i];
	sample_table_data_frame$bcoral_genet_id[i] <- sample_prep_data_frame$bcoral_genet_id[i];
}
write_data_frame(output_data_dir, "sample.tabular", sample_table_data_frame);

# Output the file needed for populating the taxonomy table.
# taxonomy_table_data_frame looks like this:

9:3c42de11ea1d

        select("id", "coral_mlg_clonal_id", "coral_mlg_rep_sample_id", "genetic_coral_species_call"),
        by=c("genotype_id"="id"));
# Name the columns.
smlg_data_frame <- as.data.frame(smlg);
colnames(smlg_data_frame) <- c("user_specimen_id", "affy_id", "bcoral_genet_id", "genotype_id",
                               "coral_mlg_clonal_id", "coral_mlg_rep_sample_id", "genetic_coral_species_call");
log_data_frame("smlg_data_frame", smlg_data_frame);
# Missing GT in samples submitted.
start_time <- time_start("Discovering missing GT in samples");
gt <- extract.gt(vcf, element="GT", as.numeric=FALSE);
missing_gt <- apply(gt, MARGIN=2, function(x){ sum(is.na(x))});

        select("coral_mlg_rep_sample_id", "coral_mlg_clonal_id"),
        by='coral_mlg_clonal_id') %>%
        mutate(coral_mlg_rep_sample_id=ifelse(is.na(coral_mlg_rep_sample_id.x),coral_mlg_rep_sample_id.y,coral_mlg_rep_sample_id.x)) %>%
    ungroup() %>%
    dplyr::select(-coral_mlg_rep_sample_id.x,-coral_mlg_rep_sample_id.y, -group.x,-group.y) %>%
    group_by(coral_mlg_clonal_id) %>%
    arrange(coral_mlg_rep_sample_id) %>%
    slice(1);

# Confirm that the representative mlg is the same between runs.
uniques2 <- unique(prep_genotype_tibble[c("group", "coral_mlg_rep_sample_id")]);
uniques2 <- uniques2[!is.na(uniques2$coral_mlg_rep_sample_id),];
na.mlg3 <- which(is.na(prep_genotype_tibble$coral_mlg_rep_sample_id));

# <chr>                      <chr>
# A.palmata                  C1651
representative_mlg_tibble <- prep_genotype_tibble %>%
    mutate(coral_mlg_rep_sample_id=ifelse(is.na(coral_mlg_rep_sample_id) & (db_match =="no_match"), affy_id, coral_mlg_rep_sample_id)) %>%
    ungroup() %>%
    select(-group);
# prep_genotype_table_tibble looks like this:
# affy_id       coral_mlg_clonal_id user_specimen_id db_match
# a550962...CEL HG0120              1090             match
# genetic_coral_species_call coral_mlg_rep_sample_id
# A.palmata                  1104
prep_genotype_table_tibble <- stag_db_report %>%
    select("affy_id", "coral_mlg_clonal_id", "user_specimen_id", "db_match", "genetic_coral_species_call") %>%
    left_join(representative_mlg_tibble %>%
        select("coral_mlg_rep_sample_id", "coral_mlg_clonal_id"),
        by='coral_mlg_clonal_id');
# genotype_table_tibble looks like this:
# affy_id         coral_mlg_clonal_id user_specimen_id db_match
# a550962-436.CEL HG0120              1090             match
# genetic_coral_species_call coral_mlg_rep_sample_id bcoral_genet_id
# A.palmata                  1104                    <NA>
genotype_table_tibble <- prep_genotype_table_tibble %>%
    left_join(affy_metadata_data_frame %>%
        select("user_specimen_id", "bcoral_genet_id"),
        by='user_specimen_id');
write_data_frame(output_data_dir, "genotype.tabular", genotype_table_tibble);

# Output the file needed for populating the person table.
person_table_data_frame <- data.frame(matrix(ncol=4, nrow=num_rows));
colnames(person_table_data_frame) <- c("last_name", "first_name", "organization", "email");

    sample_table_data_frame$percent_apalm_coral[i] <- sample_prep_data_frame$percent_apalm_coral[i];
    sample_table_data_frame$percent_alternative_sym[i] <- DEFAULT_MISSING_NUMERIC_VALUE;
    sample_table_data_frame$percent_heterozygous_coral[i] <- sample_prep_data_frame$percent_heterozygous_coral[i];
    sample_table_data_frame$percent_heterozygous_sym[i] <- DEFAULT_MISSING_NUMERIC_VALUE;
    sample_table_data_frame$field_call[i] <- sample_prep_data_frame$field_call[i];
    sample_table_data_frame$bcoral_genet_id[i] <- sample_prep_data_frame$bcoral_genet_id[i];
}
write_data_frame(output_data_dir, "sample.tabular", sample_table_data_frame);

# Output the file needed for populating the taxonomy table.
# taxonomy_table_data_frame looks like this: