mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-11-09 09:24:41 +00:00
Feature: Implement constrained k-mer generation and clique search
This commit introduces core functionality for oligonucleotide family tagging, constrained k-mer generation, and clique finding. It also includes updates to the Go language version and refactors the logic for k-mer dissimilarity metrics.
This commit is contained in:
Eric Coissac committed
1 parent
f76e7f03c6
commit
3087c70daa
17 files changed
+1791
-13
No files matched your search
Executable
+205
@@ -0,0 +1,205 @@
|
||||
#!/bin/bash
|
||||
|
||||
#
|
||||
# Here give the name of the test serie
|
||||
#
|
||||
|
||||
TEST_NAME=obioligotag
|
||||
CMD=obioligotag
|
||||
|
||||
######
|
||||
#
|
||||
# Some variable and function definitions: please don't change them
|
||||
#
|
||||
######
|
||||
TEST_DIR="$(dirname "$(readlink -f "${BASH_SOURCE[0]}")")"
|
||||
OBITOOLS_DIR="${TEST_DIR/obitest*/}build"
|
||||
export PATH="${OBITOOLS_DIR}:${PATH}"
|
||||
|
||||
MCMD="$(echo "${CMD:0:4}" | tr '[:lower:]' '[:upper:]')$(echo "${CMD:4}" | tr '[:upper:]' '[:lower:]')"
|
||||
|
||||
TMPDIR="$(mktemp -d)"
|
||||
ntest=0
|
||||
success=0
|
||||
failed=0
|
||||
|
||||
cleanup() {
|
||||
echo "========================================" 1>&2
|
||||
echo "## Results of the $TEST_NAME tests:" 1>&2
|
||||
|
||||
echo 1>&2
|
||||
echo "- $ntest tests run" 1>&2
|
||||
echo "- $success successfully completed" 1>&2
|
||||
echo "- $failed failed tests" 1>&2
|
||||
echo 1>&2
|
||||
echo "Cleaning up the temporary directory..." 1>&2
|
||||
echo 1>&2
|
||||
echo "========================================" 1>&2
|
||||
|
||||
rm -rf "$TMPDIR" # Suppress the temporary directory
|
||||
|
||||
if [ $failed -gt 0 ]; then
|
||||
log "$TEST_NAME tests failed"
|
||||
log
|
||||
log
|
||||
exit 1
|
||||
fi
|
||||
|
||||
log
|
||||
log
|
||||
|
||||
exit 0
|
||||
}
|
||||
|
||||
log() {
|
||||
echo -e "[$TEST_NAME @ $(date)] $*" 1>&2
|
||||
}
|
||||
|
||||
log "Testing $TEST_NAME..."
|
||||
log "Test directory is $TEST_DIR"
|
||||
log "obitools directory is $OBITOOLS_DIR"
|
||||
log "Temporary directory is $TMPDIR"
|
||||
log "files: $(find $TEST_DIR | awk -F'/' '{print $NF}' | tail -n +2)"
|
||||
|
||||
######################################################################
|
||||
####
|
||||
#### Below are the tests
|
||||
####
|
||||
#### Before each test :
|
||||
#### - increment the variable ntest
|
||||
####
|
||||
#### Run the command as the condition of an if / then /else
|
||||
#### - The command must return 0 on success
|
||||
#### - The command must return an exit code different from 0 on failure
|
||||
#### - The datafiles are stored in the same directory than the test script
|
||||
#### - The test script directory is stored in the TEST_DIR variable
|
||||
#### - If result files have to be produced they must be stored
|
||||
#### in the temporary directory (TMPDIR variable)
|
||||
####
|
||||
#### then clause is executed on success of the command
|
||||
#### - Write a success message using the log function
|
||||
#### - increment the variable success
|
||||
####
|
||||
#### else clause is executed on failure of the command
|
||||
#### - Write a failure message using the log function
|
||||
#### - increment the variable failed
|
||||
####
|
||||
######################################################################
|
||||
|
||||
|
||||
|
||||
#
|
||||
# Every result is checked on its properties (size, alphabet, constraints),
|
||||
# not against a reference file, because several equivalent families exist.
|
||||
#
|
||||
|
||||
printf 'acgtac\nacgtat\nttttgg\nggcaac\ncaccat\nacgtac\n' > "${TMPDIR}/oligos.txt"
|
||||
printf '>a\nACGTAC\n>b\nACGTAT\n>c\nTTTTGG\n>d\nGGCAAC\n>e\nCACCAT\n' > "${TMPDIR}/oligos.fasta"
|
||||
|
||||
((ntest++))
|
||||
if $CMD -h > "${TMPDIR}/help.txt" 2>&1
|
||||
then
|
||||
log "$MCMD: printing help OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: printing help failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if $CMD -s 5 -f 24 -d 3 -g 3 -p 2 > "${TMPDIR}/tags.fasta" 2> /dev/null \
|
||||
&& [ "$(grep -vc '>' "${TMPDIR}/tags.fasta")" -ge 24 ] \
|
||||
&& ! grep -v '>' "${TMPDIR}/tags.fasta" | grep -qE '(a{3}|c{3}|g{3}|t{3})'
|
||||
then
|
||||
log "$MCMD: generating a family with homopolymer constraint OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: generating a family with homopolymer constraint failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if $CMD -s 7 -f 60 -d 3 --alphabet ACT > "${TMPDIR}/noG.fasta" 2> /dev/null \
|
||||
&& [ "$(grep -vc '>' "${TMPDIR}/noG.fasta")" -ge 60 ] \
|
||||
&& ! grep -v '>' "${TMPDIR}/noG.fasta" | grep -q 'g'
|
||||
then
|
||||
log "$MCMD: restricted alphabet OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: restricted alphabet failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if $CMD -s 6 -f 20 -d 3 --distance-type lcs > "${TMPDIR}/lcs.fasta" 2> /dev/null \
|
||||
&& [ "$(grep -vc '>' "${TMPDIR}/lcs.fasta")" -ge 20 ]
|
||||
then
|
||||
log "$MCMD: LCS distance OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: LCS distance failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if $CMD -s 7 -f 40 -d 3 -r cnnnnnn > "${TMPDIR}/rejected.fasta" 2> /dev/null \
|
||||
&& [ "$(grep -vc '>' "${TMPDIR}/rejected.fasta")" -ge 40 ] \
|
||||
&& ! grep -v '>' "${TMPDIR}/rejected.fasta" | grep -q '^c'
|
||||
then
|
||||
log "$MCMD: rejected pattern OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: rejected pattern failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if $CMD -L "${TMPDIR}/oligos.txt" -f 3 -d 3 > "${TMPDIR}/from_text.fasta" 2> /dev/null \
|
||||
&& [ "$(grep -vc '>' "${TMPDIR}/from_text.fasta")" -ge 3 ]
|
||||
then
|
||||
log "$MCMD: selecting oligonucleotides from a text file OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: selecting oligonucleotides from a text file failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if $CMD -L "${TMPDIR}/oligos.fasta" -f 3 -d 3 > "${TMPDIR}/from_fasta.fasta" 2> /dev/null \
|
||||
&& [ "$(grep -vc '>' "${TMPDIR}/from_fasta.fasta")" -ge 3 ]
|
||||
then
|
||||
log "$MCMD: selecting oligonucleotides from a fasta file OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: selecting oligonucleotides from a fasta file failed"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if ! $CMD -s 5 -f 100 -d 3 > /dev/null 2>&1
|
||||
then
|
||||
log "$MCMD: family size beyond the Hamming bound refused OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: family size beyond the Hamming bound not refused"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
((ntest++))
|
||||
if ! $CMD -s 5 -L "${TMPDIR}/oligos.txt" -f 3 > /dev/null 2>&1
|
||||
then
|
||||
log "$MCMD: --oligo-size with --oligo-list refused OK"
|
||||
((success++))
|
||||
else
|
||||
log "$MCMD: --oligo-size with --oligo-list not refused"
|
||||
((failed++))
|
||||
fi
|
||||
|
||||
#########################################
|
||||
#
|
||||
# At the end of the tests
|
||||
# the cleanup function is called
|
||||
#
|
||||
#########################################
|
||||
|
||||
cleanup
|
||||
Reference in new issue
Block a user