diff --git a/src/main/java/nl/wur/bif/pantools/pangenome/Phylogeny.java b/src/main/java/nl/wur/bif/pantools/pangenome/Phylogeny.java
index 19cb69582b3c270bb6529aa7686c5f34473b6466..b698844bde9533dd87beebbc875e4316a0207f8d 100644
--- a/src/main/java/nl/wur/bif/pantools/pangenome/Phylogeny.java
+++ b/src/main/java/nl/wur/bif/pantools/pangenome/Phylogeny.java
@@ -132,9 +132,10 @@ public class Phylogeny {
ResourceIterator<Node> all_gene_nodes = graphDb.findNodes(gene_label);
int gene_nodes = (int) count_nodes(gene_label);
int gene_node_counter = 0;
+ System.out.print("\rSearching for gene names in gene nodes: ");
while (all_gene_nodes.hasNext()) {
- gene_node_counter ++;
- if (gene_node_counter % 100 == 0 || gene_nodes == gene_node_counter) {
+ gene_node_counter++;
+ if (gene_node_counter % 10000 == 0 || gene_nodes == gene_node_counter ) {
System.out.print("\rSearching for gene names in gene nodes: " + gene_node_counter + "/" + gene_nodes + " ");
}
Node gene_node = all_gene_nodes.next();
@@ -557,7 +558,7 @@ public class Phylogeny {
continue;
}
if (line.contains(">")) {
- seq_count ++;
+ seq_count++;
line = line.replace(">","");
String[] line_array = line.split("_gn_");
String[] line_array2 = line_array[1].split("_");
@@ -604,7 +605,7 @@ public class Phylogeny {
continue;
}
if (line.contains(">")) {
- line_count ++;
+ line_count++;
String[] line_list = line.split("gn_");
String[] line_list2 = line_list[1].split("_");
current_genome = line_list2[0];
@@ -645,7 +646,7 @@ public class Phylogeny {
log_builder.append(genome_key).append(", ").append(seq_str.length()).append("bp\n");
all_sizes.add(seq_str.length());
output.append(">").append(genome_key).append("\n").append(seq_str).append("\n");
- counter ++;
+ counter++;
}
String info = counter + " genomes\n"
@@ -679,7 +680,7 @@ public class Phylogeny {
ArrayList<Integer> protein_length_list = new ArrayList<>();
HashMap<Integer, Integer> gene_genome_map = new HashMap<>();
int [] presence_array = new int[total_genomes];
- for(int i = 1 ; i < total_genomes + 1; ++i) {
+ for(int i = 1 ; i <= total_genomes; i++) {
gene_genome_map.put(i, 0);
}
HashMap<String, String> prot_seqs_per_genome = new HashMap<>();
@@ -744,20 +745,19 @@ public class Phylogeny {
.append(", Protein sequence is missing! Something wrong with GFF?\n");
continue;
}
- presence_array[genome_nr-1] ++;
+ presence_array[genome_nr-1]++;
log_builder.append(gene_name).append("; ").append(genome_nr).append("; ").append(gene_node.getId()).append("; ").append(mrna_node_str).append("; ")
.append(hm_node_str).append("; ").append(gene_length).append("; ").append(protein_length).append("; ").append(address_str).append("\n");
int gene_count = gene_genome_map.get(genome_nr);
- gene_count ++;
+ gene_count++;
gene_genome_map.put(genome_nr, gene_count);
prot_seqs_per_genome.put(genome_nr + "_" + gene_count + "_header", seq_header);
prot_seqs_per_genome.put(genome_nr + "_" + gene_count, prot_sequence);
nuc_seqs_per_genome.put(genome_nr + "_" + gene_count, nuc_sequence);
}
- boolean multi_groups = false;
+ boolean multi_groups = false; // when true, the genes are found in multiple homology groups
if (prot_seqs_per_hmgroup.size() > 1) {
- // the genes are found in multiple homology groups
multi_groups = true;
if (mlsa_function) {
create_directory_in_DB("/mlsa/input/protein/" + SELECTED_NAME);
@@ -842,7 +842,7 @@ public class Phylogeny {
// do nothing
} else {
log_builder.append("\nWarning! Gene was not found!\n\n");
- warning_counter ++;
+ warning_counter++;
return false;
}
String[] present_array = present_genomes.split(",");
@@ -852,7 +852,7 @@ public class Phylogeny {
if (absent_genomes.length() > 27) {
log_builder.append(present_genomes).append("\n")
.append(absent_genomes).append("\n");
- warning_counter ++;
+ warning_counter++;
} else {
log_builder.append("Gene was found in every genome!\n");
absent = false;
@@ -860,7 +860,7 @@ public class Phylogeny {
if (multiple_copies.length() > 29) {
log_builder.append("Warning! ").append(multiple_copies).append("\n");
- warning_counter ++;
+ warning_counter++;
}
if (all_hms.size() == 1) {
@@ -869,16 +869,16 @@ public class Phylogeny {
log_builder.append("Warning! You must remove duplicate copies from the input files\n ")
.append(WORKING_DIRECTORY).append("/mlsa/input/nucleotide/").append(SELECTED_NAME).append(".fasta\n ")
.append(WORKING_DIRECTORY).append("/mlsa/input/protein/").append(SELECTED_NAME).append(".fasta\n");
- warning_counter ++;
+ warning_counter++;
}
} else if (all_hms.size() > 1) {
log_builder.append("Warning! Genes were found in ").append(all_hms.size()).append(" different homology groups! Sequences for are written to:\n")
.append(" ").append(WORKING_DIRECTORY).append("mlsa/input/protein/").append(SELECTED_NAME).append("/\n")
.append(" ").append(WORKING_DIRECTORY).append("mlsa/input/nucleotide/").append(SELECTED_NAME).append("/\n\n");
- warning_counter ++;
+ warning_counter++;
} else {
log_builder.append("Warning! No (active) homology grouping is present!\n");
- warning_counter ++;
+ warning_counter++;
}
StringBuilder hm_builder = new StringBuilder();
@@ -900,9 +900,9 @@ public class Phylogeny {
.append(".fasta as the group size matches the number of genomes.\n");
prot_seq_builder = prot_seqs_per_hmgroup.get(hm_node);
nuc_seq_builder = nuc_seqs_per_hmgroup.get(hm_node);
- warning_counter ++;
- perfect_group_counter ++;
- } else {
+ warning_counter++;
+ perfect_group_counter++;
+ } else if (multi_groups && num_members == total_genomes) {
log_builder.append("Warning! Group ").append(hm_node.getId()).append(" is also suitable for the analysis for ").append(SELECTED_NAME)
.append(". It was not selected because a suitable candidate was already found. \n");
}
@@ -1034,7 +1034,7 @@ public class Phylogeny {
}
StringBuilder seq = new StringBuilder();
try (BufferedWriter out = new BufferedWriter(new FileWriter(WORKING_DIRECTORY + "/databases/genome.db/Genome_" + genome_nr + ".fasta"))) {
- for (int sequence = 1; sequence <= genomeDb.num_sequences[genome_nr]; ++sequence) {
+ for (int sequence = 1; sequence <= genomeDb.num_sequences[genome_nr]; sequence++) {
out.write(">" + genomeDb.sequence_titles[genome_nr][sequence] + "\n");
int begin = 0;
int end = (int) genomeDb.sequence_length[genome_nr][sequence] - 1;
@@ -1763,7 +1763,7 @@ public class Phylogeny {
} else {
phylogeny = phylogeny.replace("(" + i + ":", "(" + i + phenotype + ":");
}
- changes_counter ++;
+ changes_counter++;
} else if (phylogeny.contains("(" + i + "_")) {
String[] phylogeny_array = phylogeny.split("\\(" + i + "_");
if (phylogeny_array.length != 2) {
@@ -1777,30 +1777,30 @@ public class Phylogeny {
} else {
phylogeny = phylogeny_array[0] + "(" + i + phenotype + str.substring(index1, str.length());
}
- changes_counter ++;
+ changes_counter++;
} else if (phylogeny.contains("(" + i + ",")) {
if (exclude_numbers) {
phylogeny = phylogeny.replace("(" + i + ",", "(" + phenotype + ",");
} else {
phylogeny = phylogeny.replace("(" + i + ",", "(" + i + phenotype + ",");
}
- changes_counter ++;
+ changes_counter++;
} else if (phylogeny.contains("," + i + ")")) {
- changes_counter ++;
+ changes_counter++;
if (exclude_numbers) {
phylogeny = phylogeny.replace("," + i + ")", "," + phenotype + ")");
} else {
phylogeny = phylogeny.replace("," + i + ")", "," + i + phenotype + ")");
}
} else if (phylogeny.contains("," + i + ":")) {
- changes_counter ++;
+ changes_counter++;
if (exclude_numbers) {
phylogeny = phylogeny.replace("," + i + ":", "," + phenotype + ":");
} else {
phylogeny = phylogeny.replace("," + i + ":", "," + i + phenotype + ":");
}
} else if (phylogeny.contains("," + i + "_")) {
- changes_counter ++;
+ changes_counter++;
String[] phylogeny_array = phylogeny.split("," + i + "_");
if (phylogeny_array.length != 2) {
correct_tree = false;
@@ -1821,7 +1821,7 @@ public class Phylogeny {
} else if (changes_counter == 0) { // genome nr is not present in the phylogeny
// do nothing
} else { // 1 change
- total_changes ++;
+ total_changes++;
}
}
@@ -1953,7 +1953,7 @@ public class Phylogeny {
int line_counter = 0;
for (int c = 0; in.ready();) {
phylogeny = in.readLine().trim();
- line_counter ++;
+ line_counter++;
}
if (line_counter > 1) {
System.out.println("\n" + INPUT_FILE + " is not a (correctly formatted) Newick file\n");
@@ -2157,7 +2157,7 @@ public class Phylogeny {
for (Node hm_node : sco_node_list) {
int[] copy_number_array = (int[]) hm_node.getProperty("copy_number");
boolean sco_group = true;
- for (int i = 1; i < copy_number_array.length; ++i) { // walk over the cnv array in the homology node
+ for (int i = 1; i < copy_number_array.length; i++) { // walk over the cnv array in the homology node
if (skip_array[i - 1]) {
continue;
}
@@ -2265,7 +2265,7 @@ public class Phylogeny {
try_incr_hashmap(pos_count_map, nuc, 1);
}
if (pos_count_map.size() == 1) {
- conserved_positions ++;
+ conserved_positions++;
continue;
}
boolean informative = check_if_informative_position(pos_count_map);
@@ -2310,7 +2310,7 @@ public class Phylogeny {
if (skip_array[genome_nr-1]) {
continue;
}
- sequence_counter ++;
+ sequence_counter++;
all_seq_position_array[genome_nr-1] = sequence.split(""); // -1 because data in array
}
return all_seq_position_array;
@@ -2337,7 +2337,7 @@ public class Phylogeny {
boolean first = true;
for (String group_id : sco_string_list) {
- group_counter ++;
+ group_counter++;
System.out.print("\r Reading alignments: " + group_counter + "/" + sco_string_list.size());
int[] var_inf_sites = get_snps_from_msa_and_create_alignments(
WORKING_DIRECTORY + "alignments/msa_" + msaMethod + "/grouping_v" + grouping_version + "/" + group_id + "/output/" + nuc_or_prot + "_trimmed.afa",
@@ -2472,7 +2472,7 @@ public class Phylogeny {
System.out.println("Reading in all alignments belonging to user-specified homology groups\n");
int group_counter = 0;
for (Node hm_node : hmNodeList) {
- group_counter ++;
+ group_counter++;
if (group_counter % 1000 == 0) {
System.out.print("\rReading gene tree: " + group_counter + "/" + hmNodeList.size());
}
@@ -2843,10 +2843,12 @@ public class Phylogeny {
}
/**
- * @param single_copy_input_file
+ * @param single_copy_input_file file location to single-copy homology group identifiers
+ * @param sco_node_list list with 'homology_group' node identifiers
* @return
*/
- public static HashMap<String, String> gather_info_for_core_snp_tree_log(String single_copy_input_file, ArrayList<Node> sco_node_list) {
+ public static HashMap<String, String> gather_info_for_core_snp_tree_log(String single_copy_input_file,
+ ArrayList<Node> sco_node_list) {
check_if_graphDb_is_available();
SELECTED_HMGROUPS = single_copy_input_file; // SCOs need to be read again because the database was closed
HashMap<String, String> info_map = new HashMap<>();
@@ -2854,7 +2856,7 @@ public class Phylogeny {
int counter = 0;
for (Node hm_node : sco_node_list) {
String group_id = hm_node.getId() +"";
- counter ++;
+ counter++;
if (counter % 100 == 0 || counter == sco_node_list.size()) {
System.out.print("\r Retrieving gene information: " + counter + "/" + sco_node_list.size() + " groups");
}