Skip to content

Commit

Permalink
Add GPU paper citation
Browse files Browse the repository at this point in the history
  • Loading branch information
@milot-mirdita
milot-mirdita committed Nov 16, 2024
1 parent 23503f3 commit 3740224
Show file tree
Hide file tree
Showing 4 changed files with 17 additions and 13 deletions.
2 changes: 2 additions & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ MMseqs2 (Many-against-Many sequence searching) is a software suite to search and

[Mirdita M, Steinegger M, Breitwieser F, Soding J, Levy Karin E: Fast and sensitive taxonomic assignment to metagenomic contigs. Bioinformatics, doi: 10.1093/bioinformatics/btab184 (2021)](https://doi.org/10.1093/bioinformatics/btab184).

[Kallenborn F, Chacon A, Hundt C, Sirelkhatim H, Didi K, Dallago C, Mirdita M, Schmidt B, Steinegger M: GPU-accelerated homology search with MMseqs2. bioRxiv, doi: 10.1101/2024.11.13.623350 (2024)](https://www.biorxiv.org/content/10.1101/2024.11.13.623350v1)

[![BioConda Install](https://img.shields.io/conda/dn/bioconda/mmseqs2.svg?style=flag&label=BioConda%20install)](https://anaconda.org/bioconda/mmseqs2) [![Github All Releases](https://img.shields.io/github/downloads/soedinglab/mmseqs2/total.svg)](https://github.com/soedinglab/mmseqs2/releases/latest) [![Biocontainer Pulls](https://img.shields.io/endpoint?url=https%3A%2F%2Fmmseqs.com%2Fbiocontainer.php%3Fcontainer%3Dmmseqs2)](https://biocontainers.pro/#/tools/mmseqs2) [![Build Status](https://dev.azure.com/themartinsteinegger/mmseqs2/_apis/build/status/soedinglab.MMseqs2?branchName=master)](https://dev.azure.com/themartinsteinegger/mmseqs2/_build/latest?definitionId=2&branchName=master)

<p align="center"><img src="https://raw.githubusercontent.com/soedinglab/mmseqs2/master/.github/mmseqs2_logo.png" height="256" /></p>
Expand Down
20 changes: 10 additions & 10 deletions src/MMseqsBase.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ std::vector<Command> baseCommands = {
"mmseqs easy-search examples/QUERY.fasta examples/DB.fasta result.m8 tmp --start-sens 2 -s 7 --sens-steps 3\n",
"Milot Mirdita <[email protected]> & Martin Steinegger <[email protected]>",
"<i:queryFastaFile1[.gz|.bz2]> ... <i:queryFastaFileN[.gz|.bz2]>|<i:stdin> <i:targetFastaFile[.gz]>|<i:targetDB> <o:alignmentFile> <tmpDir>",
CITATION_SERVER | CITATION_MMSEQS2,{{"fastaFile[.gz|.bz2]", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::VARIADIC, &DbValidator::flatfileAndStdin },
CITATION_SERVER | CITATION_MMSEQS2 | CITATION_GPU ,{{"fastaFile[.gz|.bz2]", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::VARIADIC, &DbValidator::flatfileAndStdin },
{"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::flatfile },
{"alignmentFile", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::flatfile },
{"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
Expand Down Expand Up @@ -133,9 +133,9 @@ std::vector<Command> baseCommands = {
{"makepaddedseqdb", makepaddedseqdb, &par.makepaddedseqdb, COMMAND_HIDDEN,
"Generate a padded sequence DB",
"Generate a padded sequence DB",
"Martin Steinegger <[email protected]>",
"Milot Mirdita <[email protected]> & Martin Steinegger <[email protected]>",
"<i:sequenceDB> <o:sequenceDB>",
CITATION_MMSEQS2, {{"sequenceDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::NEED_HEADER, &DbValidator::sequenceDb },
CITATION_GPU, {{"sequenceDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::NEED_HEADER, &DbValidator::sequenceDb },
{"sequenceIndexDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::sequenceDb }}},
{"appenddbtoindex", appenddbtoindex, &par.appenddbtoindex, COMMAND_HIDDEN,
NULL,
Expand Down Expand Up @@ -219,7 +219,7 @@ std::vector<Command> baseCommands = {
"mmseqs search queryDB targetDB resultDB --start-sens 2 -s 7 --sens-steps 3\n",
"Martin Steinegger <[email protected]>",
"<i:queryDB> <i:targetDB> <o:alignmentDB> <tmpDir>",
CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
CITATION_MMSEQS2 | CITATION_GPU, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"alignmentDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::alignmentDb },
{"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
Expand Down Expand Up @@ -585,17 +585,17 @@ std::vector<Command> baseCommands = {
{"ungappedprefilter", ungappedprefilter, &par.ungappedprefilter, COMMAND_PREFILTER,
"Optimal diagonal score search",
NULL,
"Martin Steinegger <[email protected]>",
"Milot Mirdita <[email protected]> & Martin Steinegger <[email protected]>",
"<i:queryDB> <i:targetDB> <o:prefilterDB>",
CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
CITATION_MMSEQS2 | CITATION_GPU, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"prefilterDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::prefilterDb }}},
{"gappedprefilter", gappedprefilter, &par.gappedprefilter, COMMAND_PREFILTER,
"Optimal Smith-Waterman-based prefiltering (slow)",
NULL,
"Martin Steinegger <[email protected]>",
"Milot Mirdita <[email protected]> & Martin Steinegger <[email protected]>",
"<i:queryDB> <i:targetDB> <o:prefilterDB>",
CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
CITATION_MMSEQS2 | CITATION_GPU, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
{"prefilterDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::prefilterDb }}},
{"kmermatcher", kmermatcher, &par.kmermatcher, COMMAND_PREFILTER,
Expand Down Expand Up @@ -760,9 +760,9 @@ std::vector<Command> baseCommands = {
{"gpuserver", gpuserver, &par.gpuserver, COMMAND_STORAGE,
"Start a GPU server",
NULL,
"Martin Steinegger <[email protected]> ",
"Milot Mirdita <[email protected]> & Martin Steinegger <[email protected]>",
"<i:DB>",
CITATION_MMSEQS2, {{"DB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::allDb }}},
CITATION_GPU, {{"DB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::allDb }}},
{"createsubdb", createsubdb, &par.createsubdb, COMMAND_SET,
"Create a subset of a DB from list of DB keys",
"# Create a new sequenceDB from sequenceDB entries with keys 1, 2 and 3\n"
Expand Down
3 changes: 2 additions & 1 deletion src/commons/Command.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,10 +10,11 @@ const unsigned int CITATION_LINCLUST = 1U << 3;
const unsigned int CITATION_PLASS = 1U << 4;
const unsigned int CITATION_SERVER = 1U << 5;
const unsigned int CITATION_TAXONOMY = 1U << 6;
const unsigned int CITATION_GPU = 1U << 7;

// Make sure this is always the last bit
// citations from inheriting modules will start from here
const unsigned int CITATION_END = CITATION_TAXONOMY << 1;
const unsigned int CITATION_END = CITATION_GPU << 1;

struct MMseqsParameter;

Expand Down
5 changes: 3 additions & 2 deletions src/commons/Parameters.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1598,7 +1598,7 @@ void Parameters::printUsageMessage(const Command& command, const unsigned int ou
if (command.citations > 0) {
ss << "\nreferences:\n";
for (unsigned int pos = 0; pos != sizeof(command.citations) * CHAR_BIT; ++pos) {
unsigned int citation = 1 << pos;
unsigned int citation = 1U << pos;
if (command.citations & citation && citations.find(citation) != citations.end()) {
ss << " - " << citations.at(citation) << "\n";
}
Expand Down Expand Up @@ -2643,8 +2643,9 @@ void Parameters::setDefaults() {
{ CITATION_UNICLUST, "Mirdita M, von den Driesch L, Galiez C, Martin M, Soding J, Steinegger M: Uniclust databases of clustered and deeply annotated protein sequences and alignments. Nucleic Acids Research 45(D1), D170-D176 (2017)" },
{ CITATION_LINCLUST, "Steinegger M, Soding J: Clustering huge protein sequence sets in linear time. Nature Communications, 9(1), 2542 (2018)" },
{ CITATION_PLASS, "Steinegger M, Mirdita M, Soding J: Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold. Nature Methods, 16(7), 603-606 (2019)" },
{ CITATION_SERVER, "Mirdita M, Steinegger M, Soding J: MMseqs2 desktop and local web server app for fast, interactive sequence searches. Bioinformatics, 35(16), 2856–2858 (2019)" },
{ CITATION_SERVER, "Mirdita M, Steinegger M, Soding J: MMseqs2 desktop and local web server app for fast, interactive sequence searches. Bioinformatics, 35(16), 2856-2858 (2019)" },
{ CITATION_TAXONOMY, "Mirdita M, Steinegger M, Breitwieser F, Soding J, Levy Karin E: Fast and sensitive taxonomic assignment to metagenomic contigs. Bioinformatics, btab184 (2021)" },
{ CITATION_GPU, "Kallenborn F, Chacon A, Hundt C, Sirelkhatim H, Didi K, Dallago C, Mirdita M, Schmidt B, Steinegger M: GPU-accelerated homology search with MMseqs2. bioRxiv, 2024.11.13.623350 (2024)" },
};
}

Expand Down

0 comments on commit 3740224

Please sign in to comment.