Skip to content

databases: accept local FASTA paths for easy nucleotide DB creation #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
antonvnv wants to merge 1 commit into
base: master
Choose a base branch
from
Open

databases: accept local FASTA paths for easy nucleotide DB creation #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
44 changes: 44 additions & 0 deletions data/workflow/databases.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,14 @@ case "${SELECTION}" in
push_back "${TMP_PATH}/kalamari.fasta"
INPUT_TYPE="FASTA_LIST"
;;
*)
if [ ! -f "${SELECTION}" ]; then
fail "Local file not found: ${SELECTION}"
fi
push_back "${SELECTION}"
date "+%s" > "${TMP_PATH}/version"
INPUT_TYPE="LOCAL_FASTA"
;;
esac

if notExists "${OUTDB}.dbtype"; then
Expand All @@ -312,6 +320,42 @@ case "${INPUT_TYPE}" in
rm -f -- "$i"
done
;;
"LOCAL_FASTA")
eval "set -- $ARR"
export MMSEQS_FORCE_MERGE=1
# shellcheck disable=SC2086
set +e
CREATEDB_LOG=$("${MMSEQS}" createdb "${@}" "${TMP_PATH}/createdb" ${THREADS_COMP_PAR} 2>&1)
CREATEDB_RET=$?
set -e
printf "%s\n" "${CREATEDB_LOG}"
[ $CREATEDB_RET -ne 0 ] && fail "createdb died"
case "${CREATEDB_LOG}" in
*"Database type: Nucleotide"*) ;;
*) fail "Local file indexing only supports nucleotide databases" ;;
esac
# shellcheck disable=SC2086
"${MMSEQS}" splitsequence "${TMP_PATH}/createdb" "${TMP_PATH}/splitdb" \
--sequence-overlap 0 --sequence-split-mode 0 --headers-split-mode 1 \
${THREADS_PAR} \
|| fail "splitsequence died"
# shellcheck disable=SC2086
"${MMSEQS}" makepaddedseqdb "${TMP_PATH}/splitdb" "${OUTDB}" \
${THREADS_PAR} \
|| fail "makepaddedseqdb died"
mkdir -p "${TMP_PATH}/indexdb"
# shellcheck disable=SC2086
"${MMSEQS}" createindex "${OUTDB}" "${TMP_PATH}/indexdb" \
--split 1 --index-subset 2 ${THREADS_PAR} \
|| fail "createindex died"
rm -rf -- "${TMP_PATH}/indexdb"
if [ -n "${REMOVE_TMP}" ]; then
# shellcheck disable=SC2086
"${MMSEQS}" rmdb "${TMP_PATH}/createdb" ${VERB_PAR}
# shellcheck disable=SC2086
"${MMSEQS}" rmdb "${TMP_PATH}/splitdb" ${VERB_PAR}
fi
;;
"FSA")
# shellcheck disable=SC2086
"${MMSEQS}" createdb "${TMP_PATH}/"*.fsa "${OUTDB}" ${COMP_PAR} --gpu 1 \
Expand Down
8 changes: 6 additions & 2 deletions src/MMseqsBase.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,9 +129,13 @@ std::vector<Command> baseCommands = {
{"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
{"databases", databases, &par.databases, COMMAND_DATABASE_CREATION,
"List and download databases",
NULL,
"# Download a known database\n"
"mmseqs databases UniRef30_2302 db tmp\n\n"
"# Index a local FASTA file (use ./relative or /absolute paths)\n"
"mmseqs databases ./input.fasta.gz db tmp\n"
"mmseqs databases /data/rnacentral_active.fasta.gz db tmp\n\n",
"Milot Mirdita <milot@mirdita.de>",
"<name> <o:sequenceDB> <tmpDir>",
"<name|path> <o:sequenceDB> <tmpDir>",
CITATION_TAXONOMY|CITATION_MMSEQS2, {{"selection", 0, DbType::ZERO_OR_ALL, &DbValidator::empty },
{"sequenceDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
Expand Down
25 changes: 18 additions & 7 deletions src/workflow/Databases.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,9 +276,12 @@ int databases(int argc, const char **argv, const Command &command) {
}
}
if (downloadIdx == -1) {
par.printUsageMessage(command, par.help ? MMseqsParameter::COMMAND_EXPERT : 0, description.c_str());
Debug(Debug::ERROR) << "Selected database " << par.db1 << " was not found\n";
EXIT(EXIT_FAILURE);
if (par.db1.find('/') == std::string::npos) {
par.printUsageMessage(command, par.help ? MMseqsParameter::COMMAND_EXPERT : 0, description.c_str());
Debug(Debug::ERROR) << "Selected database " << par.db1 << " was not found\n";
EXIT(EXIT_FAILURE);
}
// Path contains '/' — treat as local file, shell script validates existence
}
par.printParameters(command.cmd, argc, argv, par.databases);
std::string tmpDir = par.db3;
Expand All @@ -291,10 +294,14 @@ int databases(int argc, const char **argv, const Command &command) {
par.filenames.push_back(tmpDir);

CommandCaller cmd;
for (size_t i = 0; i < usedDownloads[downloadIdx].environment.size(); ++i) {
cmd.addVariable(usedDownloads[downloadIdx].environment[i].key, usedDownloads[downloadIdx].environment[i].value);
if (downloadIdx >= 0) {
for (size_t i = 0; i < usedDownloads[downloadIdx].environment.size(); ++i) {
cmd.addVariable(usedDownloads[downloadIdx].environment[i].key, usedDownloads[downloadIdx].environment[i].value);
}
cmd.addVariable("TAXONOMY", usedDownloads[downloadIdx].hasTaxonomy ? "TRUE" : NULL);
} else {
cmd.addVariable("TAXONOMY", NULL);
}
cmd.addVariable("TAXONOMY", usedDownloads[downloadIdx].hasTaxonomy ? "TRUE" : NULL);
cmd.addVariable("REMOVE_TMP", par.removeTmpFiles ? "TRUE" : NULL);
cmd.addVariable("VERB_PAR", par.createParameterString(par.onlyverbosity).c_str());
cmd.addVariable("COMP_PAR", par.createParameterString(par.verbandcompression).c_str());
Expand All @@ -303,7 +310,11 @@ int databases(int argc, const char **argv, const Command &command) {
cmd.addVariable("THREADS_PAR", par.createParameterString(par.onlythreads).c_str());
cmd.addVariable("THREADS_COMP_PAR", par.createParameterString(par.threadsandcompression).c_str());
std::string program = tmpDir + "/download.sh";
FileUtil::writeFile(program, usedDownloads[downloadIdx].script, usedDownloads[downloadIdx].scriptLength);
if (downloadIdx >= 0) {
FileUtil::writeFile(program, usedDownloads[downloadIdx].script, usedDownloads[downloadIdx].scriptLength);
} else {
FileUtil::writeFile(program, databases_sh, databases_sh_len);
}
cmd.execProgram(program.c_str(), par.filenames);

// Should never get here
Expand Down