Update regression

regression/run_cluster.sh

@@ -3,12 +3,12 @@
 CLUDB="${RESULTS}/clu"
 "${MMSEQS}" createdb "${DATADIR}/clu.fasta" "${CLUDB}" --shuffle 0
 
-"${MMSEQS}" cluster "${CLUDB}" "$RESULTS/results_clu" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 --cluster-steps 3
+"${MMSEQS}" cluster "${CLUDB}" "$RESULTS/results_clu" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 --cluster-steps 3 --linclust-version 1
 "${MMSEQS}" createtsv "${CLUDB}" "${CLUDB}" "$RESULTS/results_clu" "$RESULTS/results_cluster.tsv"
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
 ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
-TARGET="15698"
+TARGET="15695"
 awk -v actual="$ACTUAL" -v target="$TARGET" \
     'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
     > "${RESULTS}.report"

regression/run_cluster2.sh

@@ -0,0 +1,14 @@
+#!/bin/sh -e
+
+CLUDB="${RESULTS}/clu"
+"${MMSEQS}" createdb "${DATADIR}/clu.fasta" "${CLUDB}" --shuffle 0
+
+"${MMSEQS}" cluster "${CLUDB}" "$RESULTS/results_clu" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 --cluster-steps 3 --linclust-version 2 --cluster-version 2
+"${MMSEQS}" createtsv "${CLUDB}" "${CLUDB}" "$RESULTS/results_clu" "$RESULTS/results_cluster.tsv"
+
+awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
+ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
+TARGET="13619"
+awk -v actual="$ACTUAL" -v target="$TARGET" \
+    'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
+    > "${RESULTS}.report"

regression/run_cluster_update.sh

@@ -9,8 +9,8 @@ cat "$RESULTS/clu1.fasta" "$RESULTS/clu2.fasta" > "$RESULTS/cluCombined.fasta"
 "${MMSEQS}" createdb "$RESULTS/clu1.fasta" "${SEQCLUDB1}"
 "${MMSEQS}" createdb "$RESULTS/cluCombined.fasta" "${SEQCLUDB2}"
 
-"${MMSEQS}" linclust "${SEQCLUDB1}" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 -a -c 0.50 --min-seq-id 0.50
-"${MMSEQS}" clusterupdate "${SEQCLUDB1}" "${SEQCLUDB2}" "$RESULTS/results_clu" "$RESULTS/seqdb_update" "$RESULTS/clu_updated" "$RESULTS/tmp" --cov-mode 1 -c 0.50 --min-seq-id 0.50
+"${MMSEQS}" linclust "${SEQCLUDB1}" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 -a -c 0.50 --min-seq-id 0.50 --linclust-version 1
+"${MMSEQS}" clusterupdate "${SEQCLUDB1}" "${SEQCLUDB2}" "$RESULTS/results_clu" "$RESULTS/seqdb_update" "$RESULTS/clu_updated" "$RESULTS/tmp" --cov-mode 1 -c 0.50 --min-seq-id 0.50 --linclust-version 1
 "${MMSEQS}" createtsv "$RESULTS/seqdb_update" "$RESULTS/seqdb_update" "$RESULTS/clu_updated" "$RESULTS/clu_updated.tsv"
 
 CLUSTERMEMEBER=$(wc -l "$RESULTS/clu_updated.tsv" | awk '{print $1}')

regression/run_easy_cluster.sh

@@ -1,9 +1,9 @@
 #!/bin/sh -e
-"${MMSEQS}" easy-cluster "${DATADIR}/clu.fasta" "$RESULTS/results" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 --cluster-steps 3
+"${MMSEQS}" easy-cluster "${DATADIR}/clu.fasta" "$RESULTS/results" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 --cluster-steps 3 --linclust-version 1
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
 ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
-TARGET="15698"
+TARGET="15695"
 awk -v actual="$ACTUAL" -v target="$TARGET" \
     'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
     > "${RESULTS}.report"

regression/run_easy_cluster_reassign.sh

@@ -1,10 +1,10 @@
 #!/bin/sh -e
 
-cat  "${DATADIR}/clu.fasta" | "${MMSEQS}" easy-cluster stdin "$RESULTS/results" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 -c 0.8 --cov-mode 1 --cluster-reassign 1
+cat  "${DATADIR}/clu.fasta" | "${MMSEQS}" easy-cluster stdin "$RESULTS/results" "$RESULTS/tmp" --min-seq-id 0.3 -s 2 -c 0.8 --cov-mode 1 --cluster-reassign 1 --linclust-version 1
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
 ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
-TARGET="17234"
+TARGET="17229"
 awk -v actual="$ACTUAL" -v target="$TARGET" \
     'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
     > "${RESULTS}.report"

regression/run_easy_linclust.sh

@@ -1,9 +1,9 @@
 #!/bin/sh -e
-"${MMSEQS}" easy-linclust "${DATADIR}/clu.fasta" "$RESULTS/results" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50
+"${MMSEQS}" easy-linclust "${DATADIR}/clu.fasta" "$RESULTS/results" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50 --linclust-version 1 --alignment-mode 2
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
 ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
-TARGET="26493"
+TARGET="26477"
 awk -v actual="$ACTUAL" -v target="$TARGET" \
     'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
     > "${RESULTS}.report"

regression/run_easy_nuclcluster.sh

@@ -1,7 +1,7 @@
 #!/bin/sh -e
 TARGET="${DATADIR}/genes.fasta"
 
-"${MMSEQS}" easy-cluster "${TARGET}" "$RESULTS/results" "$RESULTS/tmp" -k 13 --min-seq-id 0.8 -c 0.5 --cov-mode 1
+"${MMSEQS}" easy-cluster "${TARGET}" "$RESULTS/results" "$RESULTS/tmp" -k 13 --min-seq-id 0.8 -c 0.5 --cov-mode 1 --linclust-version 1
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
 ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"

regression/run_linclust.sh

@@ -2,7 +2,7 @@
 CLUDB=
 "${MMSEQS}" createdb "${DATADIR}/clu.fasta" "${RESULTS}/clu"
 
-"${MMSEQS}" linclust "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50
+"${MMSEQS}" linclust "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50 --linclust-version 1 --alignment-mode 2
 "${MMSEQS}" createtsv "${RESULTS}/clu" "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/results_cluster.tsv"
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"

regression/run_linclust2.sh

@@ -0,0 +1,13 @@
+#!/bin/sh -e
+CLUDB=
+"${MMSEQS}" createdb "${DATADIR}/clu.fasta" "${RESULTS}/clu"
+
+"${MMSEQS}" linclust "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50 --linclust-version 2
+"${MMSEQS}" createtsv "${RESULTS}/clu" "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/results_cluster.tsv"
+
+awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
+ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
+TARGET="25666"
+awk -v actual="$ACTUAL" -v target="$TARGET" \
+    'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
+    > "${RESULTS}.report"

regression/run_linclust2_split.sh

@@ -0,0 +1,12 @@
+#!/bin/sh -e
+"${MMSEQS}" createdb "${DATADIR}/clu.fasta" "${RESULTS}/clu"
+
+"${MMSEQS}" linclust "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50 --split-memory-limit 10M --linclust-version 2
+"${MMSEQS}" createtsv "${RESULTS}/clu" "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/results_cluster.tsv"
+
+awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"
+ACTUAL="$(cut -f1 "$RESULTS/results_summary.tsv")"
+TARGET="25666"
+awk -v actual="$ACTUAL" -v target="$TARGET" \
+    'BEGIN { print (actual == target) ? "GOOD" : "BAD"; print "Expected: ", target; print "Actual: ", actual; }' \
+    > "${RESULTS}.report"

regression/run_linclust_split.sh

@@ -1,7 +1,7 @@
 #!/bin/sh -e
 "${MMSEQS}" createdb "${DATADIR}/clu.fasta" "${RESULTS}/clu"
 
-"${MMSEQS}" linclust "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50 --split-memory-limit 10M
+"${MMSEQS}" linclust "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/tmp" --cov-mode 1 --cluster-mode 0 -c 0.90 --min-seq-id 0.50 --split-memory-limit 10M --linclust-version 1 --alignment-mode 2
 "${MMSEQS}" createtsv "${RESULTS}/clu" "${RESULTS}/clu" "$RESULTS/results_clu" "$RESULTS/results_cluster.tsv"
 
 awk 'BEGIN { l = "" } l != $1 { l = $1; cnt++; } { t++; } END { print cnt"\t"t"\t"(t/cnt) }' "$RESULTS/results_cluster.tsv" > "$RESULTS/results_summary.tsv"

run_regression.sh

@@ -74,11 +74,14 @@ run_test NUCLPROT_SEARCH "run_nuclprot.sh"
 run_test NUCLNUCL_SEARCH "run_nuclnucl.sh"
 run_test NUCLNUCL_TRANS_SEARCH "run_nuclnucl_translated.sh"
 run_test CLUSTER "run_cluster.sh"
+run_test CLUSTER2 "run_cluster2.sh"
 run_test EASY_CLUSTER "run_easy_cluster.sh"
 run_test EASY_NUCL_CLUSTER "run_easy_nuclcluster.sh"
 run_test CLUSTER_REASSIGN "run_easy_cluster_reassign.sh"
 run_test LINCLUST "run_linclust.sh"
+run_test LINCLUST2 "run_linclust2.sh"
 run_test LINCLUST_SPLIT "run_linclust_split.sh"
+run_test LINCLUST2_SPLIT "run_linclust2_split.sh"
 run_test EASY_LINCLUST "run_easy_linclust.sh"
 run_test CLUSTHASH "run_clusthash.sh"
 run_test PROTNUCL_SEARCH "run_protnucl.sh"