Merge pull request #118 from rseng/update/analysis-2024-04-24

Update from update/analysis-2024-04-24

Author: vsoch

_data/language_counts.json

@@ -1,13 +1,13 @@
 {
     "unknown": 176,
-    "Python": 2230,
-    "Jupyter Notebook": 448,
+    "Python": 2235,
+    "Jupyter Notebook": 449,
     "Modelica": 1,
-    "Shell": 31,
-    "HTML": 92,
+    "Shell": 32,
+    "HTML": 95,
     "Perl": 48,
-    "R": 668,
-    "C++": 565,
+    "R": 669,
+    "C++": 569,
     "Java": 104,
     "C": 332,
     "Rust": 34,
@@ -19,7 +19,7 @@
     "Clojure": 4,
     "Groovy": 6,
     "E": 1,
-    "Julia": 87,
+    "Julia": 88,
     "null": 16,
     "Matlab": 10,
     "Scala": 8,
@@ -53,7 +53,7 @@
     "CMake": 3,
     "Stan": 2,
     "Lua": 3,
-    "PHP": 5,
+    "PHP": 6,
     "Gnuplot": 3,
     "HCL": 1,
     "IDL": 33,

_data/repos.json

@@ -19983,6 +19983,71 @@
             "parallel",
             "python",
             "simulation"
+        ],
+        "github/TravisWheelerLab/VIBES": [],
+        "github/robbievanleeuwen/section-properties": [
+            "structural-engineering",
+            "finite-element-analysis",
+            "finite-element-method",
+            "computational-mechanics",
+            "python",
+            "cross-section",
+            "stress-analysis"
+        ],
+        "github/metabolomicsworkbench/MetGENE": [],
+        "github/MatthijsHak/MetalDock": [],
+        "github/CEA-MetroCarac/fitspy": [
+            "decomposition",
+            "fitting",
+            "gaussian",
+            "lmfit",
+            "lorentzian",
+            "map",
+            "python",
+            "spectral-analysis",
+            "spectrum"
+        ],
+        "github/s-will/LocARNA": [
+            "alignment",
+            "rna-structure-prediction",
+            "rna-structural-analysis"
+        ],
+        "github/tberlok/paicos": [],
+        "github/lemene/PECAT": [],
+        "github/PopGenClustering/Clumppling": [],
+        "github/Markusjsommer/BalrogCPP": [],
+        "github/eisascience/HISTA": [],
+        "github/chemprop/chemprop_benchmark": [],
+        "github/tomoyukif/MCPtaggR": [],
+        "github/musoke/UltraDark.jl": [
+            "cosmology",
+            "julia"
+        ],
+        "github/mikejohnson51/AHGestimation": [],
+        "github/SMTG-Bham/doped": [
+            "ab-initio",
+            "computational-chemistry",
+            "computational-materials-science",
+            "defect-formation-energy",
+            "defects",
+            "dft",
+            "doping",
+            "fermi-level",
+            "point-defects",
+            "pymatgen",
+            "semiconductors",
+            "vasp",
+            "defect-calculation",
+            "defect-levels",
+            "defect-thermodynamics",
+            "shakenbreak",
+            "transition-levels"
+        ],
+        "github/hpc-maths/samurai": [
+            "adaptive-mesh-refinement",
+            "amr",
+            "cartesian",
+            "scientific-computing"
         ]
     },
     "language": {
@@ -25442,7 +25507,24 @@
         "github/tesselle/aion": "R",
         "github/GRChombo/GRDzhadzha": "C++",
         "github/KenethGarcia/ClassiPyGRB": "Python",
-        "github/CEMeNT-PSAAP/MCDC": "Python"
+        "github/CEMeNT-PSAAP/MCDC": "Python",
+        "github/TravisWheelerLab/VIBES": "HTML",
+        "github/robbievanleeuwen/section-properties": "Python",
+        "github/metabolomicsworkbench/MetGENE": "PHP",
+        "github/MatthijsHak/MetalDock": "Python",
+        "github/CEA-MetroCarac/fitspy": "Python",
+        "github/s-will/LocARNA": "C++",
+        "github/tberlok/paicos": "Jupyter Notebook",
+        "github/lemene/PECAT": "C++",
+        "github/PopGenClustering/Clumppling": "Python",
+        "github/Markusjsommer/BalrogCPP": "C++",
+        "github/eisascience/HISTA": "HTML",
+        "github/chemprop/chemprop_benchmark": "Shell",
+        "github/tomoyukif/MCPtaggR": "R",
+        "github/musoke/UltraDark.jl": "Julia",
+        "github/mikejohnson51/AHGestimation": "HTML",
+        "github/SMTG-Bham/doped": "Python",
+        "github/hpc-maths/samurai": "C++"
     },
     "url": {
         "gitlab/chiemotono/mdcontactcom": "https://gitlab.com/chiemotono/mdcontactcom",
@@ -30901,7 +30983,24 @@
         "github/tesselle/aion": "https://github.com/tesselle/aion",
         "github/GRChombo/GRDzhadzha": "https://github.com/GRTLCollaboration/GRDzhadzha",
         "github/KenethGarcia/ClassiPyGRB": "https://github.com/KenethGarcia/ClassiPyGRB",
-        "github/CEMeNT-PSAAP/MCDC": "https://github.com/CEMeNT-PSAAP/MCDC"
+        "github/CEMeNT-PSAAP/MCDC": "https://github.com/CEMeNT-PSAAP/MCDC",
+        "github/TravisWheelerLab/VIBES": "https://github.com/TravisWheelerLab/VIBES",
+        "github/robbievanleeuwen/section-properties": "https://github.com/robbievanleeuwen/section-properties",
+        "github/metabolomicsworkbench/MetGENE": "https://github.com/metabolomicsworkbench/MetGENE",
+        "github/MatthijsHak/MetalDock": "https://github.com/MatthijsHak/MetalDock",
+        "github/CEA-MetroCarac/fitspy": "https://github.com/CEA-MetroCarac/fitspy",
+        "github/s-will/LocARNA": "https://github.com/s-will/LocARNA",
+        "github/tberlok/paicos": "https://github.com/tberlok/paicos",
+        "github/lemene/PECAT": "https://github.com/lemene/PECAT",
+        "github/PopGenClustering/Clumppling": "https://github.com/PopGenClustering/Clumppling",
+        "github/Markusjsommer/BalrogCPP": "https://github.com/Markusjsommer/BalrogCPP",
+        "github/eisascience/HISTA": "https://github.com/eisascience/HISTA",
+        "github/chemprop/chemprop_benchmark": "https://github.com/chemprop/chemprop_benchmark",
+        "github/tomoyukif/MCPtaggR": "https://github.com/tomoyukif/MCPtaggR",
+        "github/musoke/UltraDark.jl": "https://github.com/musoke/UltraDark.jl",
+        "github/mikejohnson51/AHGestimation": "https://github.com/mikejohnson51/AHGestimation",
+        "github/SMTG-Bham/doped": "https://github.com/SMTG-Bham/doped",
+        "github/hpc-maths/samurai": "https://github.com/hpc-maths/samurai"
     },
     "description": {
         "gitlab/chiemotono/mdcontactcom": "",
@@ -36360,6 +36459,23 @@
         "github/tesselle/aion": ":stopwatch: Archaeological Time Series",
         "github/GRChombo/GRDzhadzha": "A code to evolve matter on curved spacetimes with an analytic time and space dependence, e.g. black holes",
         "github/KenethGarcia/ClassiPyGRB": "This repository contains all the updates, code, and documentation related to ClassiPyGRB.",
-        "github/CEMeNT-PSAAP/MCDC": "MC/DC: Monte Carlo Dynamic Code"
+        "github/CEMeNT-PSAAP/MCDC": "MC/DC: Monte Carlo Dynamic Code",
+        "github/TravisWheelerLab/VIBES": "Viral Integrations in Bacterial genomES",
+        "github/robbievanleeuwen/section-properties": "Analysis of an arbitrary cross-section in python using the finite element method.",
+        "github/metabolomicsworkbench/MetGENE": "Gene-centric Metabolomics Information Retrieval Tool",
+        "github/MatthijsHak/MetalDock": "Dock organometallic compounds to proteins/DNA/biomolecules",
+        "github/CEA-MetroCarac/fitspy": "Generic tool dedicated to fit spectra in python ",
+        "github/s-will/LocARNA": "Alignment of RNAs",
+        "github/tberlok/paicos": "An object-oriented Python package for analysis of (cosmological) simulations performed with Arepo",
+        "github/lemene/PECAT": "PECAT, a phased error correct and assembly tool",
+        "github/PopGenClustering/Clumppling": null,
+        "github/Markusjsommer/BalrogCPP": "A universal protein model for prokaryotic gene prediction",
+        "github/eisascience/HISTA": "Human Infertility Single-cell Testis Atlas",
+        "github/chemprop/chemprop_benchmark": " Chemprop benchmarking scripts and data",
+        "github/tomoyukif/MCPtaggR": null,
+        "github/musoke/UltraDark.jl": "Simulations of cosmological scalar fields",
+        "github/mikejohnson51/AHGestimation": "Estimating robust, mass conserving AHG relationships",
+        "github/SMTG-Bham/doped": "doped is a Python software for the generation, pre-/post-processing and analysis of defect supercell calculations, implementing the defect simulation workflow in an efficient, reproducible, user-friendly yet powerful and fully-customisable manner.",
+        "github/hpc-maths/samurai": "Intervals coupled with algebra of set to handle adaptive mesh refinement and operators on it."
     }
 }

_data/repos_counts_languages.json

@@ -1,5 +1,5 @@
 {
-    "Python": 6006,
+    "Python": 6008,
     "R": 2241,
     "Cpp": 441,
     "Js": 1692,

_data/stats.json

@@ -1,9 +1,9 @@
 {
-    "python_deps": 4961,
+    "python_deps": 4962,
     "cpp_deps": 441,
     "r_deps": 2241,
     "js_deps": 1692,
     "go_deps": 246,
-    "total_repos": 5457,
-    "total_parsed": 2783
+    "total_repos": 5474,
+    "total_parsed": 2785
 }

_repos/github/COMBINE-lab/salmon/CMakeLists.txt

@@ -428,7 +428,7 @@ endif()
 ##
 # Set the latest version and look for what we need
 ##
-set(Boost_ADDITIONAL_VERSIONS "1.59.0" "1.60.0" "1.61.0" "1.62.0" "1.63.0" "1.64.0" "1.65.0" "1.66.0" "1.67.0" "1.68.0" "1.69.0" "1.70.0" "1.71.0" "1.72.0" "1.73.0" "1.74.0"  "1.75.0" "1.76.0" "1.77.0" "1.78.0")
+set(Boost_ADDITIONAL_VERSIONS "1.59.0" "1.60.0" "1.61.0" "1.62.0" "1.63.0" "1.64.0" "1.65.0" "1.66.0" "1.67.0" "1.68.0" "1.69.0" "1.70.0" "1.71.0" "1.72.0" "1.73.0" "1.74.0"  "1.75.0" "1.76.0" "1.77.0" "1.78.0" "1.79.0" "1.80.0" "1.81.0" "1.82.0" "1.83.0" "1.84.0")
 if (NOT BOOST_RECONFIGURE)
 find_package(Boost 1.59.0 COMPONENTS iostreams system filesystem timer chrono program_options)
 message("BOOST_INCLUDEDIR = ${BOOST_INCLUDEDIR}")
@@ -548,38 +548,6 @@ message("BOOST LIBRARIES = ${Boost_LIBRARIES}")
 
 set(EXTERNAL_LIBRARY_PATH $CMAKE_CURRENT_SOURCE_DIR/lib)
 
-#find_package(libdivsufsort)
-#if(NOT LIBDIVSUFSORT_FOUND)
-#  message("Build system will build libdivsufsort")
-#  message("==================================================================")
-#  include(ExternalProject)
-#  externalproject_add(libdivsufsort
-#    DOWNLOAD_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external
-#    URL ${CMAKE_CURRENT_SOURCE_DIR}/external/libdivsufsort.zip
-#    # Note: This zip comes from the fetched rapmap.zip, whose SHA we check
-#    # so we souldn't need to check this one separately.
-#    SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external/libdivsufsort-master
-#    INSTALL_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external/install
-#    #UPDATE_COMMAND sh -c "mkdir -p <SOURCE_DIR>/build"
-#    BINARY_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external/libdivsufsort-master/build
-#    CMAKE_ARGS -DCMAKE_INSTALL_PREFIX:PATH=<INSTALL_DIR> -DBUILD_DIVSUFSORT64=TRUE -DUSE_OPENMP=TRUE -DBUILD_SHARED_LIBS=FALSE
-#  )
-#  externalproject_add_step(libdivsufsort makedir
-#    COMMAND mkdir -p <SOURCE_DIR>/build
-#    COMMENT "Make build directory"
-#    DEPENDEES download
-#    DEPENDERS configure)
-#
-#  set(SUFFARRAY_INCLUDE_DIRS ${CMAKE_CURRENT_SOURCE_DIR}/external/install/include)
-#  set(FETCHED_LIBDIVSUFSORT TRUE)
-#else()
-#  message("SUFFARRAY_LIB = ${SUFFARRAY_LIBRARY}")
-#  set(SUFFARRAY_LIB ${SUFFARRAY_LIBRARY})
-#  message("SUFFARRAY_LIB64 = ${SUFFARRAY_LIBRARY64}")
-#  set(SUFFARRAY_LIB64 ${SUFFARRAY_LIBRARY64})
-#  set(SUFFARRAY_INCLUDE_DIRS ${SUFFARRAY_INCLUDE_DIR})
-#endif()
-
 find_package(cereal "1.3.2")
 if (NOT CEREAL_FOUND)
   message("Build system will fetch and build the cereal serialization library")
@@ -642,7 +610,7 @@ endif()
 message("Build system will fetch and build Intel Threading Building Blocks")
 message("==================================================================")
 # These are useful for the custom install step we'll do later
-set(TBB_SOURCE_DIR ${GAT_SOURCE_DIR}/external/oneTBB-2021.9.0)
+set(TBB_SOURCE_DIR ${GAT_SOURCE_DIR}/external/oneTBB-2021.11.0)
 set(TBB_INSTALL_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external/install)
 
 if("${TBB_COMPILER}" STREQUAL "gcc")
@@ -653,11 +621,13 @@ endif()
 
 set(TBB_CXXFLAGS "${TBB_CXXFLAGS} ${CXXSTDFLAG} ${SCHAR_FLAG}")
 
+
+
 ExternalProject_Add(libtbb
 DOWNLOAD_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external
-DOWNLOAD_COMMAND curl -k -L  https://github.com/oneapi-src/oneTBB/archive/refs/tags/v2021.9.0.tar.gz -o v2021.9.tar.gz &&
-${SHASUM} 1ce48f34dada7837f510735ff1172f6e2c261b09460e3bf773b49791d247d24e v2021.9.tar.gz &&
-tar -xzvf v2021.9.tar.gz
+DOWNLOAD_COMMAND curl -k -L https://github.com/oneapi-src/oneTBB/archive/refs/tags/v2021.11.0.tar.gz -o v2021.11.0.tar.gz &&
+${SHASUM} 782ce0cab62df9ea125cdea253a50534862b563f1d85d4cda7ad4e77550ac363 v2021.11.0.tar.gz &&
+tar -xzvf v2021.11.0.tar.gz
 SOURCE_DIR ${TBB_SOURCE_DIR}
 INSTALL_DIR ${TBB_INSTALL_DIR}
 PATCH_COMMAND "${TBB_PATCH_STEP}"
@@ -785,26 +755,29 @@ find_package(CURL)
 if (FETCH_STADEN)
   set(LIBSTADEN_FOUND FALSE)
 else ()
-  find_package(libstadenio 1.14.15)
+  find_package(libstadenio 1.15.0)
 endif()
 
 if (NOT LIBSTADENIO_FOUND)
   message("Build system will compile Staden IOLib")
   message("==================================================================")
   externalproject_add(libstadenio
     DOWNLOAD_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external
-    DOWNLOAD_COMMAND curl -k -L https://github.com/jkbonfield/io_lib/releases/download/io_lib-1-14-15/io_lib-1.14.15.tar.gz -o staden-io_lib-v1.14.15.tar.gz &&
-      ${SHASUM} 20814c4365e1e2fe6630fb11d0df370dec4c5688af3871de7f1cb0129671401e staden-io_lib-v1.14.15.tar.gz &&
-      mkdir -p staden-io_lib-1.14.15 &&
-      tar -xzf staden-io_lib-v1.14.15.tar.gz --strip-components=1 -C staden-io_lib-1.14.15 &&
+    DOWNLOAD_COMMAND curl -k -L https://github.com/jkbonfield/io_lib/releases/download/io_lib-1-15-0/io_lib-1.15.0.tar.gz -o staden-io_lib-v1.15.0.tar.gz &&
+      ${SHASUM} ad343dac7c77086db1b54585c5887b26eda6430d1639d111dd3304c3b749494f staden-io_lib-v1.15.0.tar.gz &&
+      mkdir -p staden-io_lib-1.15.0 &&
+      tar -xzf staden-io_lib-v1.15.0.tar.gz --strip-components=1 -C staden-io_lib-1.15.0 &&
       rm -fr staden-io_lib &&
-      mv -f staden-io_lib-1.14.15 staden-io_lib
+      mv -f staden-io_lib-1.15.0 staden-io_lib &&
+      curl -k -L https://github.com/samtools/htscodecs/releases/download/v1.6.0/htscodecs-1.6.0.tar.gz -o htscodecs-1.6.0.tar.gz &&
+      mkdir -p htscodecs-1.6.0 &&
+      tar -xzf htscodecs-1.6.0.tar.gz --strip-components=1 -C htscodecs-1.6.0 &&
+      rm -fr staden-io_lib/htscodecs &&
+      mv -f htscodecs-1.6.0 staden-io_lib/htscodecs
     SOURCE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external/staden-io_lib
     INSTALL_DIR ${CMAKE_CURRENT_SOURCE_DIR}/external/install
     CONFIGURE_COMMAND ./configure --enable-shared=no --without-libcurl --prefix=<INSTALL_DIR> LDFLAGS=${LIBSTADEN_LDFLAGS} CFLAGS=${LIBSTADEN_CFLAGS} CC=${CMAKE_C_COMPILER} CXX=${CMAKE_CXX_COMPILER}
     BUILD_COMMAND make ${QUIET_MAKE} CC=${CMAKE_C_COMPILER} CXX=${CMAKE_CXX_COMPILER} CFLAGS+=${STADEN_INC} CFLAGS+=${STADEN_LIB} LDFLAGS+=${EXTRA_CMAKE_LIBRARY_FLAGS} CFLAGS+=${EXTRA_CMAKE_INCLUDE_FLAGS} CFLAGS+=${LZFLAG} CFLAGS+=${SCHAR_FLAG}
-
-
     BUILD_IN_SOURCE 1
     INSTALL_COMMAND make install
   )

_repos/github/Markusjsommer/BalrogCPP/CMakeLists.txt

@@ -0,0 +1,71 @@
+cmake_minimum_required(VERSION 3.16)
+project(balrog)
+
+set(CMAKE_CXX_STANDARD 14)
+
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fopenmp")
+
+list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake")
+
+file(GLOB globbed
+        "*.h"
+        "*.cpp"
+        )
+
+include_directories(include)
+include_directories(include/gzip)
+
+execute_process(
+  COMMAND python -c "import torch; import os; print(os.path.dirname(torch.__file__), end='')"
+  OUTPUT_VARIABLE TorchPath
+)
+list(APPEND CMAKE_PREFIX_PATH ${TorchPath})
+
+set(CMAKE_VERBOSE_MAKEFILE ON)
+
+if (APPLE)
+  execute_process(
+    COMMAND python -c "import torch; import os; print('@executable_path/../' + '/'.join((os.path.dirname(torch.__file__)).split('/')[-4:]) + '/lib', end='')"
+    OUTPUT_VARIABLE TorchPathR
+  )
+else()
+  execute_process(
+    COMMAND python -c "import torch; import os; print('$ORIGIN/../' + '/'.join((os.path.dirname(torch.__file__)).split('/')[-4:]) + '/lib', end='')"
+    OUTPUT_VARIABLE TorchPathR
+  )
+endif()
+set(CMAKE_INSTALL_RPATH TorchPathR)
+
+
+find_package(Torch REQUIRED)
+
+add_executable(balrog main.cpp ${globbed} include/tqdm.h include/FastaReader.cpp include/FastaReader.h include/GeneFinder.cpp include/GeneFinder.h)
+
+target_link_libraries(balrog ${TORCH_LIBRARIES})
+set_property(TARGET balrog PROPERTY CXX_STANDARD 14)
+
+
+find_package( ZLIB REQUIRED )
+if ( ZLIB_FOUND )
+    include_directories( ${ZLIB_INCLUDE_DIRS} )
+    target_link_libraries( balrog ${ZLIB_LIBRARIES} )
+endif( ZLIB_FOUND )
+
+
+include(CMakeRC)
+cmrc_add_resource_library(
+        cmakeresources
+        NAMESPACE cmakeresources
+        WHENCE data
+        data/gene_model_v1.0.pt
+        data/TIS_model_v1.0.pt
+        data/reference_genes.tar.gz
+        )
+
+target_link_libraries(${PROJECT_NAME} cmakeresources)
+
+install(
+  TARGETS balrog
+  RUNTIME DESTINATION bin
+  LIBRARY DESTINATION lib
+)