Merge commit '15a2e1e842d6af8b4d2c6f12c8cd2cb2653bb7d4'

lib/foldseek/CMakeLists.txt

@@ -6,6 +6,8 @@ project(foldseek C CXX)
 #set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
 set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} "${CMAKE_CURRENT_SOURCE_DIR}/lib/mmseqs/cmake")
 
+set(ENABLE_PROSTT5 1 CACHE BOOL "Enable ProstT5")
+set(ENABLE_CUDA 0 CACHE BOOL "Enable CUDA")
 set(IGNORE_RUST_VERSION 0 CACHE BOOL "Ignore Rust version check")
 
 if (NOT CMAKE_BUILD_TYPE)
@@ -31,8 +33,8 @@ include_directories(lib)
 include_directories(lib/3di)
 include_directories(lib/pulchra)
 include_directories(lib/kerasify)
-include_directories(lib/gemmi)
 
+set(ENV{CARGO_NET_OFFLINE} true)
 add_subdirectory(lib/corrosion)
 # don't try to link to gcc_s, its not needed anyway
 list(REMOVE_ITEM Rust_CARGO_TARGET_LINK_NATIVE_LIBS "gcc_s")
@@ -75,8 +77,30 @@ corrosion_import_crate(
 )
 include_directories(lib/block-aligner/c)
 if(EMSCRIPTEN)
-    corrosion_add_target_local_rustflags(block-aligner-c "-Clink-args=--no-entry -sRELOCATABLE=1")
+    corrosion_add_target_local_rustflags(block_aligner_c "-Clink-args=--no-entry -sRELOCATABLE=1")
 endif()
 
+set(CANDLE_FEATURE "")
+if(ENABLE_CUDA)
+    if(NOT DEFINED CUDAToolkit_ROOT)
+        message(FATAL_ERROR "please set -DCUDAToolkit_ROOT=path-to-cuda")
+    endif()
+    set(CANDLE_FEATURE cuda)
+endif()
+
+if(ENABLE_PROSTT5)
+    corrosion_import_crate(
+        MANIFEST_PATH lib/prostt5/c/Cargo.toml
+        CRATE_TYPES staticlib
+        FEATURES "${CANDLE_FEATURE}"
+    )
+    if(ENABLE_CUDA)
+        corrosion_set_env_vars(cprostt5 CUDA_ROOT=${CUDAToolkit_ROOT})
+    endif()
+    include_directories(lib/prostt5/c)
+    if(EMSCRIPTEN)
+        corrosion_add_target_local_rustflags(cprostt5 "-Clink-args=--no-entry -sRELOCATABLE=1")
+    endif()
+endif()
 
 add_subdirectory(src)

lib/foldseek/README.md

@@ -5,9 +5,12 @@ Foldseek enables fast and sensitive comparisons of large protein structure sets.
 <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, Lee J, Gilchrist C, Söding J, and Steinegger M. Fast and accurate protein structure search with Foldseek. Nature Biotechnology, doi:10.1038/s41587-023-01773-0 (2023)](https://www.nature.com/articles/s41587-023-01773-0)
+[van Kempen M, Kim S, Tumescheit C, Mirdita M, Lee J, Gilchrist CLM, Söding J, and Steinegger M. Fast and accurate protein structure search with Foldseek. Nature Biotechnology, doi:10.1038/s41587-023-01773-0 (2023)](https://www.nature.com/articles/s41587-023-01773-0)
+
+[Barrio-Hernandez I, Yeo J, Jänes J, Mirdita M, Gilchrist CLM, Wein T, Varadi M, Velankar S, Beltrao P and Steinegger M. Clustering predicted structures at the scale of the known protein universe. Nature, doi:10.1038/s41586-023-06510-w (2023)](https://www.nature.com/articles/s41586-023-06510-w)
+
+[Kim W, Mirdita M, Levy Karin E, Gilchrist CLM, Schweke H, Söding J, Levy E, and Steinegger M. Rapid and Sensitive Protein Complex Alignment with Foldseek-Multimer. bioRxiv, doi:10.1101/2024.04.14.589414 (2024)](https://www.biorxiv.org/content/10.1101/2024.04.14.589414v1)
 
-[Barrio-Hernandez I, Yeo J, Jänes J, Mirdita M, Gilchrist LMC, Wein T, Varadi M, Velankar S, Beltrao P and Steinegger M. Clustering predicted structures at the scale of the known protein universe. Nature, doi:10.1038/s41586-023-06510-w (2023)](https://www.nature.com/articles/s41586-023-06510-w)
 # Table of Contents
 
 - [Foldseek](#foldseek)
@@ -21,13 +24,14 @@ Foldseek enables fast and sensitive comparisons of large protein structure sets.
     - [Output](#output-search)
     - [Important Parameters](#important-search-parameters)
     - [Alignment Mode](#alignment-mode)
+    - [Structure search from FASTA input](#structure-search-from-fasta-input)
   - [Databases](#databases)
     - [Create Custom Databases and Indexes](#create-custom-databases-and-indexes)
   - [Cluster](#cluster)
     - [Output](#output-cluster)
     - [Important Parameters](#important-cluster-parameters)
-  - [Complexsearch](#complexsearch)
-    - [Output](#complex-search-output)
+  - [Multimer](#multimersearch)
+    - [Output](#multimer-search-output)
 - [Main Modules](#main-modules)
 - [Examples](#examples)
 
@@ -135,6 +139,24 @@ By default, Foldseek uses its local 3Di+AA structural alignment but it also supp
 
 If alignment type is set to tmalign (`--alignment-type 1`), the results will be sorted by the TMscore normalized by query length. The TMscore is used for reporting two fields: the e-value=(qTMscore+tTMscore)/2 and the score=(qTMscore*100). All output fields (e.g., pident, fident, and alnlen) are calculated based on the TMalign alignment.
 
+#### Structure search from FASTA input
+Search by predicting 3Di directly from amino acid sequences without the need for existing protein structures. 
+This feature uses the [ProstT5](https://www.biorxiv.org/content/10.1101/2023.07.23.550085v2) protein language model and runs by default on CPU and is about 400-4000x compared to predicted structures by [ColabFold](https://github.com/sokrypton/ColabFold).
+
+```
+foldseek databases ProstT5 weights tmp
+foldseek databases PDB pdb tmp
+foldseek easy-search QUERY.fasta pdb result.m8 tmp --prostt5-model weights
+```
+
+Or create your a structural database from a fasta files.
+
+```
+foldseek createdb db.fasta db --prostt5-model weights
+```
+
+Faster inference using GPU/CUDA is also supported. Compile from source with `cmake -DCMAKE_BUILD_TYPE=Release  -DENABLE_CUDA=1 -DCUDAToolkit_ROOT=Path-To-Cuda-Toolkit` and call with `createdb/easy-search --prostt5-model weights --gpu 1`.
+
 ### Databases 
 The `databases` command downloads pre-generated databases like PDB or AlphaFoldDB.
 
@@ -219,26 +241,26 @@ MCAR...Q
 | --lddt-threshold      | Alignment  | accept alignments with an alignment LDDT score > thr                               |
 
 
-### Complexsearch
-The `easy-complexsearch` module is designed for querying one or more protein complex (multi-chain) structures (supported input formats: PDB/mmCIF, flat or gzipped) against a target database of protein complex structures. It reports the similarity metrices between the complexes (e.g., the TMscore).
+### Multimersearch
+The `easy-multimersearch` module is designed for querying one or more protein complex (multi-chain) structures (supported input formats: PDB/mmCIF, flat or gzipped) against a target database of protein complex structures. It reports the similarity metrices between the complexes (e.g., the TMscore).
 
-#### Using Complexsearch
+#### Using Multimersearch
 The examples below use files that can be found in the `example` directory, which is part of the Foldseek repo, if you clone it. 
 If you use the precompiled version of the software, you can download the files directly: [1tim.pdb.gz](https://github.com/steineggerlab/foldseek/raw/master/example/1tim.pdb.gz) and [8tim.pdb.gz](https://github.com/steineggerlab/foldseek/raw/master/example/8tim.pdb.gz).
 
-For a pairwise alignment of complexes using `easy-complexsearch`, run the following command:
+For a pairwise alignment of complexes using `easy-multimersearch`, run the following command:
 ```
-foldseek easy-complexsearch example/1tim.pdb.gz example/8tim.pdb.gz result tmpFolder
+foldseek easy-multimersearch example/1tim.pdb.gz example/8tim.pdb.gz result tmpFolder
 ```
-Foldseek `easy-complexsearch` can also be used for searching one or more query complexes against a target database: 
+Foldseek `easy-multimersearch` can also be used for searching one or more query complexes against a target database: 
 ```
 foldseek databases PDB pdb tmp 
-foldseek easy-complexsearch example/1tim.pdb.gz pdb result tmpFolder
+foldseek easy-multimersearch example/1tim.pdb.gz pdb result tmpFolder
 ```
 
-#### Complex Search Output
+#### Multimer Search Output
 ##### Tab-separated-complex
-By default, `easy-complexsearch` reports the output alignment in a tab-separated file.
+By default, `easy-multimersearch` reports the output alignment in a tab-separated file.
 The default output fields are: `query,target,fident,alnlen,mismatch,gapopen,qstart,qend,tstart,tend,evalue,bits,complexassignid` but they can be customized with the `--format-output` option e.g., `--format-output "query,target,complexqtmscore,complexttmscore,complexassignid"` alters the output to show specific scores and identifiers.
 
 | Code | Description |
@@ -260,7 +282,7 @@ The default output fields are: `query,target,fident,alnlen,mismatch,gapopen,qsta
 ```
 
 ##### Complex Report
-`easy-complexsearch` also generates a report (prefixed `_report`), which provides a summary of the inter-complex chain matching, including identifiers, chains, TMscores, rotation matrices, translation vectors, and assignment IDs. The report includes the following fields:
+`easy-multimersearch` also generates a report (prefixed `_report`), which provides a summary of the inter-complex chain matching, including identifiers, chains, TMscores, rotation matrices, translation vectors, and assignment IDs. The report includes the following fields:
 | Column | Description |
 | --- | --- |
 | 1 | Identifier of the query complex |

lib/foldseek/data/CMakeLists.txt

@@ -13,8 +13,8 @@ set(COMPILED_RESOURCES
         evalue_nn.kerasify
         main.js
         vendor.js.zst
-        complexsearch.sh
-        easycomplexsearch.sh
+        multimersearch.sh
+        easymultimersearch.sh
         )
 
 set(GENERATED_OUTPUT_HEADERS "")

lib/foldseek/data/easycomplexsearch.sh → lib/foldseek/data/easymultimersearch.sh

@@ -26,31 +26,25 @@ if notExists "${TARGET}.dbtype"; then
     TARGET="${TMP_PATH}/target"
 fi
 
-if notExists "${TMP_PATH}/complex_result.dbtype"; then
+if notExists "${TMP_PATH}/multimer_result.dbtype"; then
     # shellcheck disable=SC2086
-    "$MMSEQS" complexsearch "${QUERY}" "${TARGET}" "${TMP_PATH}/complex_result" "${TMP_PATH}/complexsearch_tmp" ${COMPLEXSEARCH_PAR} \
-    || fail "ComplexSearch died"
+    "$MMSEQS" multimersearch "${QUERY}" "${TARGET}" "${TMP_PATH}/multimer_result" "${TMP_PATH}/multimersearch_tmp" ${MULTIMERSEARCH_PAR} \
+    || fail "multimersearch died"
 fi
 
 # shellcheck disable=SC2086
-"$MMSEQS" convertalis "${QUERY}" "${TARGET}" "${TMP_PATH}/complex_result" "${OUTPUT}" ${CONVERT_PAR} \
+"$MMSEQS" convertalis "${QUERY}" "${TARGET}" "${TMP_PATH}/multimer_result" "${OUTPUT}" ${CONVERT_PAR} \
     || fail "Convert Alignments died"
 
 if [ -z "${NO_REPORT}" ]; then
     # shellcheck disable=SC2086
-    "$MMSEQS" createcomplexreport "${QUERY}" "${TARGET}" "${TMP_PATH}/complex_result" "${OUTPUT}_report" ${REPORT_PAR} \
-        || fail "createcomplexreport died"
+    "$MMSEQS" createmultimerreport "${QUERY}" "${TARGET}" "${TMP_PATH}/multimer_result" "${OUTPUT}_report" ${REPORT_PAR} \
+        || fail "createmultimerreport died"
 fi
 
 if [ -n "${REMOVE_TMP}" ]; then
     # shellcheck disable=SC2086
-    "$MMSEQS" rmdb "${TMP_PATH}/result" ${VERBOSITY}
-    if [ "$PREFMODE" != "EXHAUSTIVE" ]; then
-        # shellcheck disable=SC2086
-        "$MMSEQS" rmdb "${TMP_PATH}/result_expand_aligned" ${VERBOSITY}
-    fi
-    # shellcheck disable=SC2086
-    "$MMSEQS" rmdb "${TMP_PATH}/complex_result" ${VERBOSITY}
+    "$MMSEQS" rmdb "${TMP_PATH}/multimer_result" ${VERBOSITY}
     if [ -z "${LEAVE_INPUT}" ]; then
         if [ -f "${TMP_PATH}/target" ]; then
             # shellcheck disable=SC2086
@@ -71,6 +65,6 @@ if [ -n "${REMOVE_TMP}" ]; then
         # shellcheck disable=SC2086
         "$MMSEQS" rmdb "${TMP_PATH}/query_ss" ${VERBOSITY}
     fi
-    rm -rf "${TMP_PATH}/complexsearch_tmp"
-    rm -f "${TMP_PATH}/easycomplexsearch.sh"
+    rm -rf "${TMP_PATH}/multimersearch_tmp"
+    rm -f "${TMP_PATH}/easymultimersearch.sh"
 fi

lib/foldseek/data/easystructuresearch.sh

@@ -11,7 +11,7 @@ notExists() {
 if notExists "${1}.dbtype"; then
     if notExists "${TMP_PATH}/query.dbtype"; then
         # shellcheck disable=SC2086
-        "$MMSEQS" createdb "$@" "${TMP_PATH}/query" ${CREATEDB_PAR} \
+        "$MMSEQS" createdb "$@" "${TMP_PATH}/query" ${CREATEDB_QUERY_PAR} \
             || fail "query createdb died"
     fi
     QUERY="${TMP_PATH}/query"

lib/foldseek/data/multimersearch.sh

@@ -0,0 +1,58 @@
+#!/bin/sh -e
+fail() {
+    echo "Error: $1"
+    exit 1
+}
+
+notExists() {
+	[ ! -f "$1" ]
+}
+
+if notExists "${TMP_PATH}/result.dbtype"; then
+    # shellcheck disable=SC2086
+    "$MMSEQS" search "${QUERYDB}" "${TARGETDB}" "${TMP_PATH}/result" "${TMP_PATH}/search_tmp" ${SEARCH_PAR} \
+        || fail "Search died"
+fi
+
+RESULT="${TMP_PATH}/result"
+if [ "$PREFMODE" != "EXHAUSTIVE" ]; then
+    if notExists "${TMP_PATH}/result_expand_pref.dbtype"; then
+        # shellcheck disable=SC2086
+        "$MMSEQS" expandmultimer "${QUERYDB}" "${TARGETDB}" "${RESULT}" "${RESULT}_expand_pref" ${THREADS_PAR} \
+            || fail "expandmultimer died"
+    fi
+    if notExists "${TMP_PATH}/result_expand_aligned.dbtype"; then
+        if [ "$MULTIMER_ALIGNMENT_ALGO" = "tmalign" ]; then
+#            # shellcheck disable=SC2086
+#            "$MMSEQS" structurealign "${QUERYDB}" "${TARGETDB}" "${RESULT}_expand_pref" "${RESULT}_expand_aligned_tmp" ${MULTIMER_ALIGN_PREF_PAR} \
+#                || fail $MULTIMER_ALIGNMENT_ALGO "died"
+            # shellcheck disable=SC2086
+            "$MMSEQS" structurealign "${QUERYDB}" "${TARGETDB}" "${RESULT}_expand_pref" "${RESULT}_expand_aligned_tmp" -e 100 ${THREADS_PAR} \
+                || fail $MULTIMER_ALIGNMENT_ALGO "died"
+            # shellcheck disable=SC2086
+            "$MMSEQS" tmalign "${QUERYDB}" "${TARGETDB}" "${RESULT}_expand_aligned_tmp" "${RESULT}_expand_aligned" ${MULTIMER_ALIGN_PAR} \
+                || fail $MULTIMER_ALIGNMENT_ALGO "died"
+        else
+            # shellcheck disable=SC2086
+            "$MMSEQS" $MULTIMER_ALIGNMENT_ALGO "${QUERYDB}" "${TARGETDB}" "${RESULT}_expand_pref" "${RESULT}_expand_aligned" ${MULTIMER_ALIGN_PAR} \
+                || fail $MULTIMER_ALIGNMENT_ALGO "died"
+        fi
+    fi
+    RESULT="${TMP_PATH}/result_expand_aligned"
+fi
+if notExists "${OUTPUT}.dbtype"; then
+    # shellcheck disable=SC2086
+    $MMSEQS scoremultimer "${QUERYDB}" "${TARGETDB}" "${RESULT}" "${OUTPUT}" ${SCOREMULTIMER_PAR} \
+        || fail "scoremultimer died"
+fi
+
+if [ -n "${REMOVE_TMP}" ]; then
+    # shellcheck disable=SC2086
+    "$MMSEQS" rmdb "${TMP_PATH}/result" ${VERBOSITY}
+    if [ "$PREFMODE" != "EXHAUSTIVE" ]; then
+        # shellcheck disable=SC2086
+        "$MMSEQS" rmdb "${TMP_PATH}/result_expand_aligned" ${VERBOSITY}
+    fi
+    rm -rf "${TMP_PATH}/search_tmp"
+    rm -f "${TMP_PATH}/multimersearch.sh"
+fi