v1.4.1.3

malabz · Aug 7, 2023 · 94b83dd · 94b83dd
1 parent bf62969
commit 94b83dd
Show file tree

Hide file tree

Showing 19 changed files with 720 additions and 25 deletions.
diff --git a/Makefile b/Makefile
@@ -74,17 +74,23 @@ endif
 		$(CC) -c $(CFLAGS) $< -I$(INC_DIR) -o $@
 
 BIN      = $(BIN_DIR)/abpoa
+BIN_PROF = $(BIN_DIR)/abpoa_profile
 ifneq ($(gdb),)
 	BIN  = $(BIN_DIR)/gdb_abpoa
 endif
 ABPOALIB = $(LIB_DIR)/libabpoa.a
 EXAMPLE  = example
 
 
-all:       $(BIN)
-abpoa:     $(BIN)
-libabpoa:  $(ABPOALIB)
-example:   $(EXAMPLE)
+all:           $(BIN) $(BIN_PROF)
+abpoa:         $(BIN)
+abpoa_profile: $(BIN_PROF)
+libabpoa:      $(ABPOALIB)
+example:       $(EXAMPLE)
+
+$(BIN_PROF): $(SRC_DIR)/abpoa_profile.o $(ABPOALIB)
+	if [ ! -d $(BIN_DIR) ]; then mkdir $(BIN_DIR); fi
+	$(CC) $(CFLAGS) $< -I$(INC_DIR) -L$(LIB_DIR) -labpoa $(LIB) -o $@ $(PG_FLAG)
 
 $(BIN):$(SRC_DIR)/abpoa.o $(ABPOALIB)
 	if [ ! -d $(BIN_DIR) ]; then mkdir $(BIN_DIR); fi
@@ -108,4 +114,4 @@ $(SRC_DIR)/simd_abpoa_align.o:$(SRC_DIR)/simd_abpoa_align.c $(SRC_DIR)/abpoa_gra
 	$(CC) -c $(CFLAGS) $(SIMD_FLAG) -I$(INC_DIR) $< -o $@
 
 clean:
-	rm -f $(SRC_DIR)/*.[oa] $(LIB_DIR)/*.[oa] $(BIN)
+	rm -f $(SRC_DIR)/*.[oa] $(LIB_DIR)/*.[oa] $(BIN) $(BIN_PROF)
diff --git a/README.md b/README.md
@@ -13,6 +13,13 @@
 
 Modified by wym6912 wym6912@outlook.com
 
+## Updates (v1.4.1.3)
+
+- Fix a bug related to uninitialized values in local mode
+- Add `HOXD70` matrix arugment with gap open penalty\=400 and gap extension penalty\=30 (`-H/--hoxd`)
+- Add two profile alignment modes in new program `abpoa_profile`
+- Fix output bug in printing sequences has gaps
+
 ## Updates (v1.4.1.2)
 
 - Fix bug in outputting RNA sequences in `v1.4.1.1`
@@ -46,8 +53,8 @@ abPOA is not only a stand-alone tool for MSA and consensus calling, it can also
 
 Download the [latest release](https://github.com/malabz/abPOA/releases):
 ```bash
-wget https://github.com/malabz/abPOA/releases/download/v1.4.1.1/abPOA-v1.4.1.1.tar.gz
-tar -zxvf abPOA-v1.4.1.1.tar.gz && cd abPOA-v1.4.1.1
+wget https://github.com/malabz/abPOA/releases/download/v1.4.1.3/abPOA-v1.4.1.3.tar.gz
+tar -zxvf abPOA-v1.4.1.3.tar.gz && cd abPOA-v1.4.1.3
 ```
 Make from source and run with test data:
 ```bash

diff --git a/abPOA.rc b/abPOA.rc
diff --git a/abPOA.sln b/abPOA.sln
@@ -13,6 +13,8 @@ Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "abPOA_example", "abPOA_exam
 EndProject
 Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "abPOA_sub_example", "abPOA_sub_example.vcxproj", "{3C4CFBB1-36E1-4237-9DD5-3EE3A9EBB83E}"
 EndProject
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "abPOA_profile", "abPOA_profile.vcxproj", "{B0559055-ABBA-4035-B384-3DFCBE335E68}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|x64 = Debug|x64
@@ -61,6 +63,14 @@ Global
 		{3C4CFBB1-36E1-4237-9DD5-3EE3A9EBB83E}.Release|x64.Build.0 = Release|x64
 		{3C4CFBB1-36E1-4237-9DD5-3EE3A9EBB83E}.Release|x86.ActiveCfg = Release|Win32
 		{3C4CFBB1-36E1-4237-9DD5-3EE3A9EBB83E}.Release|x86.Build.0 = Release|Win32
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Debug|x64.ActiveCfg = Debug|x64
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Debug|x64.Build.0 = Debug|x64
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Debug|x86.ActiveCfg = Debug|Win32
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Debug|x86.Build.0 = Debug|Win32
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Release|x64.ActiveCfg = Release|x64
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Release|x64.Build.0 = Release|x64
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Release|x86.ActiveCfg = Release|Win32
+		{B0559055-ABBA-4035-B384-3DFCBE335E68}.Release|x86.Build.0 = Release|Win32
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE

diff --git a/abPOA_profile.rc b/abPOA_profile.rc
diff --git a/abPOA_profile.vcxproj b/abPOA_profile.vcxproj
@@ -0,0 +1,157 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup Label="ProjectConfigurations">
+    <ProjectConfiguration Include="Debug|Win32">
+      <Configuration>Debug</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|Win32">
+      <Configuration>Release</Configuration>
+      <Platform>Win32</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Debug|x64">
+      <Configuration>Debug</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|x64">
+      <Configuration>Release</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+  </ItemGroup>
+  <PropertyGroup Label="Globals">
+    <VCProjectVersion>16.0</VCProjectVersion>
+    <Keyword>Win32Proj</Keyword>
+    <ProjectGuid>{b0559055-abba-4035-b384-3dfcbe335e68}</ProjectGuid>
+    <RootNamespace>abPOAprofile</RootNamespace>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <PlatformToolset>v143</PlatformToolset>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <PlatformToolset>v143</PlatformToolset>
+    <WholeProgramOptimization>true</WholeProgramOptimization>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <PlatformToolset>v143</PlatformToolset>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <PlatformToolset>v143</PlatformToolset>
+    <WholeProgramOptimization>true</WholeProgramOptimization>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+  <ImportGroup Label="ExtensionSettings">
+  </ImportGroup>
+  <ImportGroup Label="Shared">
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <PropertyGroup Label="UserMacros" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <IncludePath>$(ProjectDir)include;$(IncludePath)</IncludePath>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <IncludePath>$(ProjectDir)include;$(IncludePath)</IncludePath>
+  </PropertyGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <DisableSpecificWarnings>4996</DisableSpecificWarnings>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <DisableSpecificWarnings>4996</DisableSpecificWarnings>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemGroup>
+    <ProjectReference Include="include\getopt9\src\getopt.vcxproj">
+      <Project>{a2169bc8-cf99-40bf-83f3-b0e38f7067bd}</Project>
+    </ProjectReference>
+    <ProjectReference Include="lib_abPOA.vcxproj">
+      <Project>{a193f522-5fe5-4012-beea-acfc6be9fc72}</Project>
+    </ProjectReference>
+  </ItemGroup>
+  <ItemGroup>
+    <ClCompile Include="src\abpoa_profile.c" />
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="resource.h" />
+  </ItemGroup>
+  <ItemGroup>
+    <ResourceCompile Include="abPOA_profile.rc" />
+  </ItemGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets">
+  </ImportGroup>
+</Project>
diff --git a/abPOA_profile.vcxproj.filters b/abPOA_profile.vcxproj.filters
@@ -0,0 +1,32 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup>
+    <Filter Include="源文件">
+      <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D752A2FF}</UniqueIdentifier>
+      <Extensions>cpp;c;cc;cxx;c++;cppm;ixx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
+    </Filter>
+    <Filter Include="头文件">
+      <UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
+      <Extensions>h;hh;hpp;hxx;h++;hm;inl;inc;ipp;xsd</Extensions>
+    </Filter>
+    <Filter Include="资源文件">
+      <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
+      <Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;png;wav;mfcribbon-ms</Extensions>
+    </Filter>
+  </ItemGroup>
+  <ItemGroup>
+    <ClCompile Include="src\abpoa_profile.c">
+      <Filter>源文件</Filter>
+    </ClCompile>
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="resource.h">
+      <Filter>头文件</Filter>
+    </ClInclude>
+  </ItemGroup>
+  <ItemGroup>
+    <ResourceCompile Include="abPOA_profile.rc">
+      <Filter>资源文件</Filter>
+    </ResourceCompile>
+  </ItemGroup>
+</Project>
diff --git a/abPOA_profile.vcxproj.user b/abPOA_profile.vcxproj.user
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="Current" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <PropertyGroup />
+</Project>
diff --git a/include/abpoa.h b/include/abpoa.h
@@ -76,6 +76,7 @@ typedef struct {
     double min_freq; // for multiploid data
     int verbose; // to control output msg
     int has_u; // detect RNA sequences
+    int changed_gap_pen;
 
     // char LogTable65536[65536];
     // char bit_table16[65536];

diff --git a/src/abpoa.c b/src/abpoa.c
@@ -20,7 +20,7 @@ char PROG[20] = "abpoa";
 #define _bO BOLD UNDERLINE "O" NONE
 #define _bA BOLD UNDERLINE "A" NONE
 char DESCRIPTION[200] = _ba "daptive " _bb "anded " _bP "artial " _bO "rder " _bA "lignment";
-char VERSION[20] = "1.4.1.2";
+char VERSION[20] = "1.4.1.3";
 char CONTACT[30] = "gaoy1@chop.edu";
 
 const struct option abpoa_long_opt [] = {
@@ -56,7 +56,9 @@ const struct option abpoa_long_opt [] = {
     { "max-num-cons", 1, NULL, 'd', },
     { "min-freq", 1, NULL, 'q', },
     { "blosum", 0, NULL, 'B', },
+    { "hoxd", 0, NULL, 'H', },
 
+    { "verbose", 0, NULL, 'V' },    
     { "help", 0, NULL, 'h' },
     { "version", 0, NULL, 'v' },
 
@@ -95,6 +97,8 @@ int abpoa_usage(void)
     err_printf("    -s --amb-strand         ambiguous strand mode [False]\n");
     err_printf("                            for each input sequence, try the reverse complement if the current\n");
     err_printf("                            alignment score is too low, and pick the strand with a higher score\n");
+    err_printf("    -B --blosum             use BLOSUM62 scoring matrix for %sprotein%s sequence alignment [False]\n", RED, NONE);
+    err_printf("    -H --hoxd               use HOXD70 scoring matrix for %sDNA/RNA%s sequence alignment [False]\n", RED, NONE);
     err_printf("  Adaptive banded DP:\n");
     err_printf("    -b --extra-b    INT     first adaptive banding parameter [%d]\n", ABPOA_EXTRA_B);
     err_printf("                            set b as < 0 to disable adaptive banded DP\n");
@@ -116,11 +120,10 @@ int abpoa_usage(void)
     err_printf("  Input/Output:\n");
     err_printf("    -Q --use-qual-weight    take base quality score from FASTQ input file as graph edge weight [False]\n");
     err_printf("    -c --amino-acid         input sequences are amino acid (default is nucleotide) [False]\n");
-    err_printf("    -B --blosum             use BLOSUM62 for protein alignment [False]\n");
     err_printf("    -l --in-list            input file is a list of sequence file names [False]\n");
     err_printf("                            each line is one sequence file containing a set of sequences\n");
     err_printf("                            which will be aligned by abPOA to generate a consensus sequence\n");
-    err_printf("    -i --incrmnt    FILE    incrementally align sequences to an existing graph/MSA [Null]\n");
+    err_printf("    -i --increment  FILE    incrementally align sequences to an existing graph/MSA [Null]\n");
     err_printf("                            graph could be in GFA or MSA format generated by abPOA\n");
     err_printf("    -o --output     FILE    output to FILE [stdout]\n");
     err_printf("    -r --result      INT    output result mode [%d]\n", ABPOA_OUT_CONS);
@@ -134,6 +137,8 @@ int abpoa_usage(void)
     err_printf("    -q --min-freq  FLOAT    min. frequency of each consensus sequence (only effective when -d/--num-cons > 1) [%.2f]\n", MULTIP_MIN_FREQ);
     err_printf("    -g --out-pog    FILE    dump final alignment graph to FILE (.pdf/.png) [Null]\n\n");
 
+    err_printf(" Others: \n");
+    err_printf("    -V --verbose            verbose some output\n");
     err_printf("    -h --help               print this help usage information\n");
     err_printf("    -v --version            show version number\n");
 
@@ -163,7 +168,7 @@ int abpoa_main(char *file_fn, int is_list, abpoa_para_t *abpt){
 
 int main(int argc, char **argv) {
     int c, m, in_list=0; char *s; abpoa_para_t *abpt = abpoa_init_para();
-    while ((c = getopt_long(argc, argv, "m:M:X:t:O:E:b:f:z:e:QSk:w:n:i:clpsBo:r:g:d:q:hvV:", abpoa_long_opt, NULL)) >= 0) {
+    while ((c = getopt_long(argc, argv, "m:M:X:t:O:E:b:f:z:e:QSk:w:n:i:clpsBHo:r:g:d:q:hvV", abpoa_long_opt, NULL)) >= 0) {
         switch(c)
         {
             case 'm': m = atoi(optarg);
@@ -173,8 +178,8 @@ int main(int argc, char **argv) {
             case 'M': abpt->match = atoi(optarg); break;
             case 'X': abpt->mismatch = atoi(optarg); break;
             case 't': abpt->use_score_matrix = 1; abpt->mat_fn = strdup(optarg); break;
-            case 'O': abpt->gap_open1 = strtol(optarg, &s, 10); if (*s == ',') abpt->gap_open2 = strtol(s+1, &s, 10); break;
-            case 'E': abpt->gap_ext1 = strtol(optarg, &s, 10); if (*s == ',') abpt->gap_ext2 = strtol(s+1, &s, 10); break;
+            case 'O': abpt->changed_gap_pen = 1; abpt->gap_open1 = strtol(optarg, &s, 10); if (*s == ',') abpt->gap_open2 = strtol(s+1, &s, 10); break;
+            case 'E': abpt->changed_gap_pen = 1; abpt->gap_ext1 = strtol(optarg, &s, 10); if (*s == ',') abpt->gap_ext2 = strtol(s+1, &s, 10); break;
 
             case 'b': abpt->wb = atoi(optarg); break;
             case 'f': abpt->wf = atof(optarg); break;
@@ -206,12 +211,13 @@ int main(int argc, char **argv) {
                       break;
             case 'g': abpt->out_pog= strdup(optarg); break;
             case 'B': abpt->use_score_matrix = 2; break;
+            case 'H': abpt->use_score_matrix = 3; break;
 
             case 'd': abpt->max_n_cons = atoi(optarg); break; 
             case 'q': abpt->min_freq = atof(optarg); break;
 
             case 'h': return abpoa_usage();
-            case 'V': abpt->verbose = atoi(optarg); break;
+            case 'V': abpt->verbose ++; break;
             case 'v': printf("%s\n", VERSION); goto End; break;
             default:
                       err_printf("Error: unknown option: %s.\n", optarg);

diff --git a/src/abpoa.h b/src/abpoa.h
@@ -76,6 +76,7 @@ typedef struct {
     double min_freq; // for multiploid data
     int verbose; // to control output msg
     int has_u; // detect RNA sequences
+    int changed_gap_pen;
 
     // char LogTable65536[65536];
     // char bit_table16[65536];