v2.2.5

Author: bbuchfink

src/ChangeLog

@@ -3,12 +3,12 @@
 - Linear-time stages of the clustering workflows now by default use banded instead of full-matrix
   extension (set `--ext full` to use full-matrix extension instead).
 - Added the option `--reseek-diags` to recompute diagonals prior to chaining.
-- Added the option `--reseek-xdrop` to set ungapped x-drop, `--word-threshold` to set the
-  word threshold in bits for k-mer neighbors for the Aho�Corasick automaton, `--double-hit-window`
-  to set the window for double hits when using `--reseek-diags`.
+- Added the options `--reseek-xdrop` to set ungapped x-drop, `--word-threshold` to set the
+  word threshold in bits for k-mer neighbors and `--double-hit-window` to set the window for double hits
+  when using `--reseek-diags`.
 - Removed the `--linclust-banded-ext` and `--lin-combo` options.
 - Fixed a potential issue of increased memory use in the clustering workflows.
-- Improved the performance of reading FASTA files.
+- Improved the performance of reading sequence files.
 - Fixed a potential inter-toolchain inconsistency in search workflows using sketching.
 - Fixed a potential non-determinism in the clustering workflows.
 - Fixed a bug causing invalid line breaks in the output file when using the `qtitle` output field

src/basic/config.cpp

@@ -360,7 +360,6 @@ Config::Config(int argc, const char **argv, bool check_io, CommandLineParser& pa
 		("round-approx-id", 0, "Per-round approx-id cutoffs for cascaded clustering", round_approx_id)
 		("aln-out", 0, "Output file for clustering alignments", aln_out)
 		("reps", 0, "Output file for representative sequences in FASTA format. Only includes id and sequence (no additional header data).", reps_out)
-		("seed-index", 0, "Use precomputed block seed indexes in linear clustering rounds", seed_index)
 		("single-step", 0, "Perform one computational step of clustering then exit", single_step);
 
 	auto& memory_opt = parser.add_group("Memory options", { cluster, RECLUSTER, CLUSTER_REASSIGN, GREEDY_VERTEX_COVER, DEEPCLUST, LINCLUST, CLUSTER_REALIGN });
@@ -633,6 +632,7 @@ Config::Config(int argc, const char **argv, bool check_io, CommandLineParser& pa
 		("hamming-ext", 0, "", hamming_ext)
 		("diag-filter-id", 0, "", diag_filter_id)
 		("diag-filter-cov", 0, "", diag_filter_cov)
+		("seed-index", 0, "", seed_index)
 		("dbtype", 0, "type of sequences in database file (nucl/prot)", dbstring, string("prot"))
 		("cluster-similarity", 0, "Clustering similarity measure (default=\"normalized_bitscore_global\")", cluster_similarity)
 		("cluster-threshold", 0, "Threshold for the similarity measure (default=50%)", cluster_threshold)