Add biorxiv citation

steineggerlab · Feb 9, 2022 · 3c64211 · 3c64211
1 parent 4927694
commit 3c64211
Show file tree

Hide file tree

Showing 4 changed files with 32 additions and 22 deletions.
diff --git a/README.md b/README.md
@@ -1,10 +1,16 @@
 # Foldseek 
-Software suite for searching and clustering protein structures.
+Foldseek enables fast and sensitive comparisons of large structure sets. It reaches sensitivities similar to state-of-the-art structural aligners while being at least 20,000 times faster.
 
 <p align="center"><img src="https://github.com/steineggerlab/foldseek/blob/master/.github/foldseek.png" height="250"/></p>
 
+## Publications
+
+[van Kempen M, Kim S, Tumescheit C, Mirdita M, Söding J, and Steinegger M. Foldseek:  fast and accurate protein structure search. bioRxiv, doi:10.1101/2022.02.07.479398  (2021)](https://www.biorxiv.org/content/10.1101/2022.02.07.479398)
+
 ## Webserver 
-Search your protein structures against [AlphaFold DBs](https://alphafold.ebi.ac.uk/) and [PDB](https://www.rcsb.org/) in seconds using our Foldseek webserver.  🚀 [search.foldseek.com](https://search.foldseek.com)
+Search your protein structures against the [AlphaFoldDB](https://alphafold.ebi.ac.uk/) and [PDB](https://www.rcsb.org/) in seconds using our Foldseek webserver:
+
+[🚀search.foldseek.com](https://search.foldseek.com)
 
 ## Installation
 
@@ -21,7 +27,7 @@ Precompiled binaries for other architectures (ARM64, PPC64LE) and very old AMD/I
 
 ### Quick start
 
-`easy-search` can search single or multiple queries formatted in pdb/mcif format (flat or gz) against a target database (`example/`) of protein structures. It outputs a tab separated file of the alignments (`.m8`) the fields are `query,target,fident,alnlen,mismatch,gapopen,qstart,qend,tstart,tend,evalue,bits`.
+`easy-search` can search single or multiple queries formatted in PDB/mmCIF format (flat or `.gz`) against a target database (`example/`) of protein structures. It outputs a tab-separated file of the alignments (`.m8`) the fields are `query,target,fident,alnlen,mismatch,gapopen,qstart,qend,tstart,tend,evalue,bits`.
 
     foldseek easy-search example/d1asha_ example/ aln.m8 tmpFolder
 
@@ -47,7 +53,7 @@ The target database can be pre-processed by `createdb`. This make sense if searc
 
 
 ### Databases 
-Setup the PDB or AlphaFold using the `databases` module.
+Setup the PDB or AlphaFoldDB using the `databases` module.
 
     # pdb  
     foldseek databases PDB pdb tmp 
@@ -78,7 +84,7 @@ In case of the alignment type (`--alignment-type 1`) tmalign we sort the results
 foldseek easy-search example/d1asha_ example/ aln tmp --alignment-type 1
 ```
 
-It is possible to compute the TMscores for the any kind of alignment output (e.g. 3Di/AA) using the following commands: 
+It is possible to compute TMscores for the kind of alignment output (e.g. 3Di/AA) using the following commands: 
 ```
     foldseek createdb example/ targetDB
     foldseek createdb example/ queryDB
@@ -102,9 +108,9 @@ Compiling `foldseek` from source has the advantage of system-specific optimizati
     make install
     export PATH=$(pwd)/foldseek/bin/:$PATH
 
-:exclamation: If you want to compile `foldseek` on macOS, please install and use `gcc` from Homebrew. The default macOS `clang` compiler does not support OpenMP and `foldseek` will not be able to run multi-threaded. Adjust the `cmake` call above to:
+:exclamation: If you want to compile `foldseek` on macOS, please install and use `gcc` from Homebrew. The default macOS `clang` compiler does not support OpenMP (by default) and `foldseek` will not be able to run multi-threaded. Adjust the `cmake` call above to:
 
-    CC="$(brew --prefix)/bin/gcc-10" CXX="$(brew --prefix)/bin/g++-10" cmake -DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_INSTALL_PREFIX=. ..
+    CC="$(brew --prefix)/bin/gcc-11" CXX="$(brew --prefix)/bin/g++-11" cmake -DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_INSTALL_PREFIX=. ..
 
 
 ## Hardware requirements

diff --git a/src/commons/LocalParameters.cpp b/src/commons/LocalParameters.cpp
@@ -105,9 +105,11 @@ LocalParameters::LocalParameters() :
     chainNameMode = 0;
     tmAlignFast = 1;
     nsample = 5000;
+
+    citations.emplace(CITATION_FOLDSEEK, "van Kempen M, Kim S,Tumescheit C, Mirdita M, Söding J, and Steinegger M. Foldseek: fast and accurate protein structure search. bioRxiv, doi:10.1101/2022.02.07.479398 (2021)");
 }
 
 std::vector<int> FoldSeekDbValidator::tmscore = {LocalParameters::DBTYPE_TMSCORE};
 std::vector<int> FoldSeekDbValidator::cadb = {LocalParameters::DBTYPE_CA_ALPHA};
 std::vector<int> FoldSeekDbValidator::flatfileStdinAndFolder = {LocalParameters::DBTYPE_FLATFILE, LocalParameters::DBTYPE_STDIN,LocalParameters::DBTYPE_DIRECTORY};
-std::vector<int> FoldSeekDbValidator::flatfileAndFolder = {LocalParameters::DBTYPE_FLATFILE, LocalParameters::DBTYPE_DIRECTORY};
+std::vector<int> FoldSeekDbValidator::flatfileAndFolder = {LocalParameters::DBTYPE_FLATFILE, LocalParameters::DBTYPE_DIRECTORY};
diff --git a/src/commons/LocalParameters.h b/src/commons/LocalParameters.h
@@ -3,6 +3,8 @@
 
 #include <Parameters.h>
 
+const int CITATION_FOLDSEEK = CITATION_END;
+
 struct FoldSeekDbValidator : public DbValidator {
     static std::vector<int> tmscore;
     static std::vector<int> cadb;

diff --git a/src/foldseek.cpp b/src/foldseek.cpp
@@ -5,9 +5,9 @@
 
 const char* binary_name = "foldseek";
 const char* tool_name = "foldseek";
-const char* tool_introduction = "Protein Structure Search and Clustering.";
-const char* main_author = "Michel van Kempen, Stephanie Kim, Charlotte Tumescheit, Martin Steinegger";
-const char* show_extended_help = NULL;
+const char* tool_introduction = "Foldseek enables fast and sensitive comparisons of large structure sets. It reaches sensitivities similar to state-of-the-art structural aligners while being at least 20,000 times faster.\n\nPlease cite: van Kempen M, Kim S,Tumescheit C, Mirdita M, Söding J, and Steinegger M. Foldseek: fast and accurate protein structure search. bioRxiv, doi:10.1101/2022.02.07.479398 (2021)";
+const char* main_author = "Michel van Kempen, Stephanie Kim, Charlotte Tumescheit, Milot Mirdita, Johannes Söding, Martin Steinegger";
+const char* show_extended_help = "1";
 const char* show_bash_info = NULL;
 const char* index_version_compatible = "fs1";
 bool hide_base_commands = true;
@@ -31,7 +31,7 @@ std::vector<struct Command> commands = {
                 "Convert PDB/mmCIF files to an db.",
                 "Martin Steinegger <[email protected]>",
                 "<i:PDB|mmCIF[.gz]> ... <i:PDB|mmCIF[.gz]> <o:sequenceDB>",
-                CITATION_MMSEQS2, {{"PDB|mmCIF[.gz]|stdin", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA | DbType::VARIADIC, &DbValidator::flatfileStdinAndGeneric },
+                CITATION_FOLDSEEK, {{"PDB|mmCIF[.gz]|stdin", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA | DbType::VARIADIC, &DbValidator::flatfileStdinAndGeneric },
                                           {"sequenceDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::flatfile }}},
         {"easy-search",          easystructuresearch,           &localPar.easystructuresearchworkflow,   COMMAND_EASY,
                 "Sensitive homology search",
@@ -43,7 +43,7 @@ std::vector<struct Command> commands = {
                 "foldseek easy-search examples/d1asha_ examples/ result.m8 tmp --alignment-type 1\n\n",
                 "Martin Steinegger <[email protected]>",
                 "<i:PDB|mmCIF[.gz]> ... <i:PDB|mmCIF[.gz]>|<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, &FoldSeekDbValidator::flatfileStdinAndFolder },
+                CITATION_FOLDSEEK, {{"fastaFile[.gz|.bz2]", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::VARIADIC, &FoldSeekDbValidator::flatfileStdinAndFolder },
                                           {"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::flatfileAndFolder },
                                           {"alignmentFile", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::flatfile },
                                           {"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
@@ -54,7 +54,7 @@ std::vector<struct Command> commands = {
                 "foldseek convertalis queryDB targetDB resultDB result.m8\n\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_FOLDSEEK, {{"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 }}},
@@ -74,15 +74,15 @@ std::vector<struct Command> commands = {
                 "mmseqs cluster sequenceDB clusterDB tmp --cluster-reassign\n",
                 "Martin Steinegger <[email protected]> & Lars von den Driesch",
                 "<i:sequenceDB> <o:clusterDB> <tmpDir>",
-                CITATION_LINCLUST|CITATION_MMSEQS1|CITATION_MMSEQS2, {{"sequenceDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
+                CITATION_FOLDSEEK|CITATION_MMSEQS2, {{"sequenceDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
                                           {"clusterDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::clusterDb },
                                           {"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
         {"tmalign",      tmalign,      &localPar.tmalign,      COMMAND_ALIGNMENT,
                 "Compute tm-score ",
                 NULL,
                 "Martin Steinegger <[email protected]>",
                 "<i:queryDB> <i:targetDB> <i:prefilterDB> <o:resultDB>",
-                CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
+                CITATION_FOLDSEEK, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
                                           {"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
                                           {"resultDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::resultDb },
                                           {"alnDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &FoldSeekDbValidator::alignmentDb }}},
@@ -91,7 +91,7 @@ std::vector<struct Command> commands = {
                 NULL,
                 "Charlotte Tumescheit <[email protected]> & Martin Steinegger <[email protected]>",
                 "<i:queryDB> <i:targetDB> <i:prefilterDB> <o:resultDB>",
-                CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
+                CITATION_FOLDSEEK, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
                                           {"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::sequenceDb },
                                           {"resultDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::resultDb },
                                           {"alnDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &FoldSeekDbValidator::alignmentDb }}},
@@ -100,7 +100,7 @@ std::vector<struct Command> commands = {
                 NULL,
                 "Martin Steinegger <[email protected]>",
                 "<i:queryDB> <i:targetDB> <i:alnDB> <o:resultDB>",
-                CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::cadb },
+                CITATION_FOLDSEEK, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::cadb },
                                           {"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::cadb },
                                           {"alignmentDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &DbValidator::alignmentDb },
                                           {"tmDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &FoldSeekDbValidator::tmscore }}},
@@ -109,15 +109,15 @@ std::vector<struct Command> commands = {
                 NULL,
                 "Martin Steinegger <[email protected]>",
                 "<i:queryDB> <i:targetDB> <o:resultDB>",
-                CITATION_MMSEQS2, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::sequenceDb },
+                CITATION_FOLDSEEK, {{"queryDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::sequenceDb },
                                   {"targetDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, &FoldSeekDbValidator::sequenceDb },
                                   {"tmDB", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &FoldSeekDbValidator::genericDb }}},
         {"databases",            databases,            &localPar.databases,            COMMAND_DATABASE_CREATION,
                 "List and download databases",
                 NULL,
                 "Milot Mirdita <[email protected]>",
                 "<name> <o:sequenceDB> <tmpDir>",
-                CITATION_TAXONOMY|CITATION_MMSEQS2, {{"selection", 0, DbType::ZERO_OR_ALL, &DbValidator::empty },
+                CITATION_TAXONOMY|CITATION_FOLDSEEK, {{"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 }}},
         {"createindex",          structureindex,       &localPar.createindex,          COMMAND_DATABASE_CREATION,
@@ -126,7 +126,7 @@ std::vector<struct Command> commands = {
                 "mmseqs createindex sequenceDB tmp\n",
                 "Martin Steinegger <[email protected]>",
                 "<i:sequenceDB> <tmpDir>",
-                CITATION_SERVER | CITATION_MMSEQS2,{{"sequenceDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::NEED_HEADER, &DbValidator::sequenceDb },
+                CITATION_SERVER | CITATION_FOLDSEEK,{{"sequenceDB", DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA|DbType::NEED_HEADER, &DbValidator::sequenceDb },
                                                            {"tmpDir", DbType::ACCESS_MODE_OUTPUT, DbType::NEED_DATA, &DbValidator::directory }}},
         {"mmcreateindex",        createindex,          &localPar.createindex,          COMMAND_HIDDEN,
                 NULL,
@@ -140,7 +140,7 @@ std::vector<struct Command> commands = {
                 NULL,
                 "",
                 "",
-                CITATION_MMSEQS2, {{"",DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, NULL}}}
+                CITATION_FOLDSEEK, {{"",DbType::ACCESS_MODE_INPUT, DbType::NEED_DATA, NULL}}}
 };
 
 #include "structdatabases.sh.h"