From 3e3b3543a5b7e955a0b8be1f2ae21a25c151f560 Mon Sep 17 00:00:00 2001 From: Alexis Praga Date: Thu, 25 Jan 2024 23:43:14 +0100 Subject: [PATCH] hap-py: init 0.3.15 New package for genetics : helps compared variants called by a pipeline to a reference. The only tests not passing are due to a difference in float representation (same value but with different number of digits after decimal). For best results (quality and running time), the authors advice to use RTGtools vcfeval as the engine. So this package requires #230394 --- pkgs/by-name/ha/hap-py/cmake.patch | 50 ++++ pkgs/by-name/ha/hap-py/hap-py.patch | 342 ++++++++++++++++++++++++++++ pkgs/by-name/ha/hap-py/package.nix | 61 +++++ 3 files changed, 453 insertions(+) create mode 100644 pkgs/by-name/ha/hap-py/cmake.patch create mode 100644 pkgs/by-name/ha/hap-py/hap-py.patch create mode 100644 pkgs/by-name/ha/hap-py/package.nix diff --git a/pkgs/by-name/ha/hap-py/cmake.patch b/pkgs/by-name/ha/hap-py/cmake.patch new file mode 100644 index 000000000000000..e31000cebf130df --- /dev/null +++ b/pkgs/by-name/ha/hap-py/cmake.patch @@ -0,0 +1,50 @@ +--- a/CMakeLists.txt 2023-02-01 23:55:18.171758209 +0100 ++++ b/CMakeLists.txt 2023-02-02 19:32:16.574426531 +0100 +@@ -23,25 +23,11 @@ + set (VCFEVAL_AVAILABLE 0) + endif() + +-execute_process( +- COMMAND ${CMAKE_SOURCE_DIR}/external/make_dependencies.sh +- WORKING_DIRECTORY ${CMAKE_BINARY_DIR} +- RESULT_VARIABLE EXTERNAL_SUCCESS) + +-if(NOT "${EXTERNAL_SUCCESS}" STREQUAL "0") +- message(FATAL_ERROR "Building external dependencies has failed") +-endif() +- +-set(Boost_USE_STATIC_LIBS ON) # only find static libs + set(Boost_USE_MULTITHREADED ON) +-set(Boost_USE_STATIC_RUNTIME ON) + + # un-break library finding +-set(Boost_NO_BOOST_CMAKE ON) +-set(Boost_NO_SYSTEM_PATHS ON) + +-set(BOOST_ROOT ${CMAKE_BINARY_DIR}) +-message("Using our own Boost, which was built at ${HAPLOTYPES_SOURCE_DIR}/external/boost_install") + + find_package(Boost 1.55.0 COMPONENTS thread iostreams regex unit_test_framework filesystem system program_options REQUIRED) + include_directories(${Boost_INCLUDE_DIRS}) +@@ -51,7 +51,8 @@ + link_directories (${CMAKE_BINARY_DIR}/lib) + + # make sure we use the bundled zlib version +-set(ZLIB_LIBRARIES ${CMAKE_BINARY_DIR}/lib/libz.a) ++# Additional flags for nix, found by trial and error ++set(ZLIB_LIBRARIES -lz -lbz2 -lcurl -lcrypto -llzma) + + include_directories (${HAPLOTYPES_SOURCE_DIR}/external/klib) + include_directories (${HAPLOTYPES_SOURCE_DIR}/external/intervaltree) +@@ -84,11 +86,6 @@ + ${CMAKE_THREAD_LIBS_INIT}) + + +-execute_process(COMMAND git describe --tags --always +- OUTPUT_VARIABLE HAPLOTYPES_VERSION +- WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" +- OUTPUT_STRIP_TRAILING_WHITESPACE +-) + + configure_file("${CMAKE_CURRENT_SOURCE_DIR}/src/c++/include/Version.hh.in" + "${CMAKE_BINARY_DIR}/include/Version.hh") diff --git a/pkgs/by-name/ha/hap-py/hap-py.patch b/pkgs/by-name/ha/hap-py/hap-py.patch new file mode 100644 index 000000000000000..0fee6d084cd41b8 --- /dev/null +++ b/pkgs/by-name/ha/hap-py/hap-py.patch @@ -0,0 +1,342 @@ +diff --git a/src/c++/lib/tools/Roc.cpp b/src/c++/lib/tools/Roc.cpp +index fabe2be..2c6bb49 100644 +--- a/src/c++/lib/tools/Roc.cpp ++++ b/src/c++/lib/tools/Roc.cpp +@@ -34,6 +34,9 @@ + */ + + #include "helpers/Roc.hh" ++#include ++#include ++ + + #include + #include +diff --git a/src/cmake/cxx.cmake b/src/cmake/cxx.cmake +old mode 100755 +new mode 100644 +diff --git a/src/python/Haplo/happyroc.py b/src/python/Haplo/happyroc.py +index 152bd18..e439957 100644 +--- a/src/python/Haplo/happyroc.py ++++ b/src/python/Haplo/happyroc.py +@@ -97,7 +97,7 @@ def roc(roc_table, output_path, + header = l.split("\t") + else: + rec = {} +- for k, v in itertools.izip(header, l.split("\t")): ++ for k, v in zip(header, l.split("\t")): + rec[k] = v + + if filter_handling: +@@ -160,11 +160,11 @@ def roc(roc_table, output_path, + + if "all" not in result: + # minimal empty DF +- minidata = [{"Type": "SNP", "Subtype": "*", "Filter": "ALL", "Genotype": "*", "Subset": "*", "QQ": "*"} for _ in xrange(2)] ++ minidata = [{"Type": "SNP", "Subtype": "*", "Filter": "ALL", "Genotype": "*", "Subset": "*", "QQ": "*"} for _ in range(2)] + minidata[1]["Type"] = "INDEL" + result["all"] = pandas.DataFrame(minidata, columns=RESULT_ALLCOLUMNS) + for i, c in enumerate(RESULT_ALLCOLUMNS): +- result["all"][c] = result["all"][c].astype(RESULT_ALLDTYPES[i], raise_on_error=False) ++ result["all"][c] = result["all"][c].astype(RESULT_ALLDTYPES[i], errors="ignore") + + for k, v in result.items(): + result[k] = _postprocessRocData(pandas.DataFrame(v, columns=RESULT_ALLCOLUMNS)) +diff --git a/src/python/Haplo/partialcredit.py b/src/python/Haplo/partialcredit.py +index d9e22bb..0f2b2cf 100644 +--- a/src/python/Haplo/partialcredit.py ++++ b/src/python/Haplo/partialcredit.py +@@ -202,7 +202,7 @@ def partialCredit(vcfname, + try: + res = runParallel(pool, + preprocessWrapper, +- itertools.izip(itertools.repeat(vcfname), locations), ++ zip(itertools.repeat(vcfname), locations), + {"reference": reference, + "decompose": decompose, + "leftshift": leftshift, +diff --git a/src/python/Haplo/quantify.py b/src/python/Haplo/quantify.py +index 042d13e..b1d362e 100755 +--- a/src/python/Haplo/quantify.py ++++ b/src/python/Haplo/quantify.py +@@ -152,7 +152,7 @@ def run_quantify(filename, + run_str += " -v %s" % pipes.quote(write_vcf) + + if regions: +- for k, v in regions.iteritems(): ++ for k, v in regions.items(): + run_str += " -R '%s:%s'" % (k, v) + + if roc_regions: +diff --git a/src/python/Somatic/Mutect.py b/src/python/Somatic/Mutect.py +index 7ac923c..81f08b5 100755 +--- a/src/python/Somatic/Mutect.py ++++ b/src/python/Somatic/Mutect.py +@@ -148,7 +148,7 @@ def extractMutectSNVFeatures(vcfname, tag, avg_depth=None): + n_allele_alt_count = 0 + else: + n_allele_alt_count = 0 +- for a in xrange(0, len(alleles_alt)): ++ for a in range(0, len(alleles_alt)): + n_allele_alt_count += float(rec[n_sample + "AD"][a + 1]) + + if n_allele_alt_count + n_allele_ref_count == 0: +@@ -163,7 +163,7 @@ def extractMutectSNVFeatures(vcfname, tag, avg_depth=None): + t_allele_alt_count = 0 + else: + t_allele_alt_count = 0 +- for a in xrange(0, len(alleles_alt)): ++ for a in range(0, len(alleles_alt)): + t_allele_alt_count += float(rec[t_sample + "AD"][a + 1]) + + if t_allele_alt_count + t_allele_ref_count == 0: +@@ -344,7 +344,7 @@ def extractMutectIndelFeatures(vcfname, tag, avg_depth=None): + n_allele_alt_count = 0 + else: + n_allele_alt_count = 0 +- for a in xrange(0, len(alleles_alt)): ++ for a in range(0, len(alleles_alt)): + n_allele_alt_count += float(rec[n_sample + "AD"][a + 1]) + + if n_allele_alt_count + n_allele_ref_count == 0: +@@ -359,7 +359,7 @@ def extractMutectIndelFeatures(vcfname, tag, avg_depth=None): + t_allele_alt_count = 0 + else: + t_allele_alt_count = 0 +- for a in xrange(0, len(alleles_alt)): ++ for a in range(0, len(alleles_alt)): + t_allele_alt_count += float(rec[t_sample + "AD"][a + 1]) + + if t_allele_alt_count + t_allele_ref_count == 0: +diff --git a/src/python/Tools/bcftools.py b/src/python/Tools/bcftools.py +index 6146b7a..6d80d14 100755 +--- a/src/python/Tools/bcftools.py ++++ b/src/python/Tools/bcftools.py +@@ -128,8 +128,8 @@ def concatenateParts(output, *args): + to_delete.append(tf2.name) + to_delete.append(tf1.name + ".csi") + to_delete.append(tf2.name + ".csi") +- half1 = [tf1.name] + list(args[:len(args)/2]) +- half2 = [tf2.name] + list(args[len(args)/2:]) ++ half1 = [tf1.name] + list(args[:len(args)//2]) ++ half2 = [tf2.name] + list(args[len(args)//2:]) + concatenateParts(*half1) + runBcftools("index", tf1.name) + concatenateParts(*half2) +diff --git a/src/python/Tools/metric.py b/src/python/Tools/metric.py +index 71ccc99..372626d 100755 +--- a/src/python/Tools/metric.py ++++ b/src/python/Tools/metric.py +@@ -115,7 +115,7 @@ def replaceNaNs(xobject): + if type(xobject[k]) is dict or type(xobject[k]) is list or type(xobject[k]) is float: + xobject[k] = replaceNaNs(xobject[k]) + elif type(xobject) is list: +- for k in xrange(0, len(xobject)): ++ for k in range(0, len(xobject)): + if type(xobject[k]) is dict or type(xobject[k]) is list or type(xobject[k]) is float: + xobject[k] = replaceNaNs(xobject[k]) + elif type(xobject) is float: +diff --git a/src/python/Tools/parallel.py b/src/python/Tools/parallel.py +index 9d49760..5fcb37e 100755 +--- a/src/python/Tools/parallel.py ++++ b/src/python/Tools/parallel.py +@@ -17,9 +17,9 @@ import logging + import traceback + import subprocess + import multiprocessing +-import cPickle ++import pickle + import tempfile +-from itertools import islice, izip, repeat ++from itertools import islice, repeat + + from . import LoggingWriter + +@@ -93,7 +93,7 @@ def runParallel(pool, fun, par, *args, **kwargs): + + """ + if pool: +- result = pool.map(parMapper, izip(par, repeat( { "fun": fun, "args": args, "kwargs": kwargs } ))) ++ result = pool.map(parMapper, zip(par, repeat( { "fun": fun, "args": args, "kwargs": kwargs } ))) + else: + result = [] + for c in par: +diff --git a/src/python/Tools/sessioninfo.py b/src/python/Tools/sessioninfo.py +index 75650ec..b49bf59 100644 +--- a/src/python/Tools/sessioninfo.py ++++ b/src/python/Tools/sessioninfo.py +@@ -34,7 +34,6 @@ def sessionInfo(): + 'version': version, + 'runInfo': [{"key": "commandline", "value": " ".join(sys.argv)}], + 'uname': " / ".join(platform.uname()), +- 'dist': " / ".join(platform.dist()), + 'mac_ver': " / ".join([platform.mac_ver()[0], platform.mac_ver()[2]]), + 'python_implementation': platform.python_implementation(), + 'python_version': platform.python_version(), +diff --git a/src/python/Tools/vcfcallerinfo.py b/src/python/Tools/vcfcallerinfo.py +index eb7e86e..947f2c4 100755 +--- a/src/python/Tools/vcfcallerinfo.py ++++ b/src/python/Tools/vcfcallerinfo.py +@@ -33,8 +33,8 @@ class CallerInfo(object): + + def asDict(self): + kvd = ["name", "version", "parameters"] +- return {"aligners": [dict(y for y in itertools.izip(kvd, x)) for x in self.aligners], +- "callers": [dict(y for y in itertools.izip(kvd, x)) for x in self.callers]} ++ return {"aligners": [dict(y for y in zip(kvd, x)) for x in self.aligners], ++ "callers": [dict(y for y in zip(kvd, x)) for x in self.callers]} + + def addVCF(self, vcfname): + """ Add caller versions from a VCF +diff --git a/src/python/hap.py b/src/python/hap.py +index 8045936..93279a4 100755 +--- a/src/python/hap.py ++++ b/src/python/hap.py +@@ -188,7 +188,7 @@ def main(): + parser.print_help() + exit(1) + +- print "Hap.py %s" % Tools.version ++ print("Hap.py %s" % Tools.version) + if args.version: + exit(0) + +diff --git a/src/python/ovc.py b/src/python/ovc.py +index 2837255..20b4442 100755 +--- a/src/python/ovc.py ++++ b/src/python/ovc.py +@@ -34,7 +34,7 @@ lines = 1 + for line in f: + l = line.split("\t") + if len(l) > 3 and (last-1) > int(l[1]): +- print "Overlap at %s:%i (line %i)" % (l[0], int(l[1]), lines) ++ print(Overlap at %s:%i (line %i)) % (l[0], int(l[1]), lines) + exit(1) + elif len(l) > 3: + last = int(l[2]) +diff --git a/src/python/pre.py b/src/python/pre.py +index 5ca1644..a37a4b2 100755 +--- a/src/python/pre.py ++++ b/src/python/pre.py +@@ -47,8 +47,8 @@ import Haplo.partialcredit + def hasChrPrefix(chrlist): + """ returns if list of chr names has a chr prefix or not """ + +- noprefix = map(str, range(23)) + ["X", "Y", "MT"] +- withprefix = ["chr" + x for x in map(str, range(23)) + ["X", "Y", "M"]] ++ noprefix = [str(x) for x in range(23)] + ["X", "Y", "MT"] ++ withprefix = ["chr" + str(x) for x in range(23)] + ["X", "Y", "M"] + + count_noprefix = len(list(set(noprefix) & set(chrlist))) + count_prefix = len(list(set(withprefix) & set(chrlist))) +@@ -126,7 +126,7 @@ def preprocess(vcf_input, + + if gender == "auto": + logging.info(mf) +- if "female" in mf: ++ if b"female" in mf: + gender = "female" + else: + gender = "male" +@@ -392,7 +392,7 @@ def main(): + exit(0) + + if args.version: +- print "pre.py %s" % Tools.version # noqa:E999 ++ print(pre.py %s) % Tools.version # noqa:E999 + exit(0) + + args.input = args.input[0] +diff --git a/src/python/qfy.py b/src/python/qfy.py +index 4f247ee..59ed68a 100755 +--- a/src/python/qfy.py ++++ b/src/python/qfy.py +@@ -203,8 +203,8 @@ def quantify(args): + + # in default mode, print result summary to stdout + if not args.quiet and not args.verbose: +- print "Benchmarking Summary:" +- print essential_numbers.to_string(index=False) ++ print("Benchmarking Summary:") ++ print(essential_numbers.to_string(index=False)) + + # keep this for verbose output + if not args.verbose: +@@ -213,12 +213,12 @@ def quantify(args): + except: + pass + +- for t in res.iterkeys(): ++ for t in res.keys(): + metrics_output["metrics"].append(dataframeToMetricsTable("roc." + t, res[t])) + + # gzip JSON output + if args.write_json: + with gzip.open(args.reports_prefix + ".metrics.json.gz", "w") as fp: +- json.dump(metrics_output, fp) ++ fp.write(json.dumps(metrics_output, default=np_encoder).encode('ascii')) + + +@@ -362,7 +363,7 @@ def main(): + exit(0) + + if args.version: +- print "qfy.py %s" % Tools.version ++ print(qfy.py %s) % Tools.version + exit(0) + + if args.fp_bedfile and args.preprocessing_truth_confregions: +diff --git a/src/python/som.py b/src/python/som.py +index e942351..c01d522 100755 +--- a/src/python/som.py ++++ b/src/python/som.py +@@ -640,7 +640,7 @@ def main(): + "overlap):\n" + ambie.to_string(index=False)) + # in default mode, print result summary to stdout + if not args.quiet and not args.verbose: +- print "FP/ambiguity classes with info (multiple classes can " \ ++ print(FP/ambiguity classes with info (multiple classes can ) \ + "overlap):\n" + ambie.to_string(index=False) + ambie.to_csv(args.output + ".ambiclasses.csv") + metrics_output["metrics"].append(dataframeToMetricsTable("ambiclasses", ambie)) +@@ -659,7 +659,7 @@ def main(): + formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False)) + # in default mode, print result summary to stdout + if not args.quiet and not args.verbose: +- print "Reasons for defining as ambiguous (multiple reasons can overlap):\n" + ambie.to_string( ++ print(Reasons for defining as ambiguous (multiple reasons can overlap):\n) + ambie.to_string( + formatters={'reason': '{{:<{}s}}'.format(ambie['reason'].str.len().max()).format}, index=False) + ambie.to_csv(args.output + ".ambireasons.csv") + metrics_output["metrics"].append(dataframeToMetricsTable("ambireasons", ambie)) +@@ -936,7 +936,7 @@ def main(): + logging.info("\n" + res.to_string()) + # in default mode, print result summary to stdout + if not args.quiet and not args.verbose: +- print "\n" + res.to_string() ++ print(\n) + res.to_string() + + res["sompyversion"] = vstring + +diff --git a/src/python/qfy.py b/src/python/qfy.py +index 59ed68a..be8d7e1 100755 +--- a/src/python/qfy.py ++++ b/src/python/qfy.py +@@ -33,6 +33,7 @@ import pandas + import json + import tempfile + import gzip ++import numpy as np + + scriptDir = os.path.abspath(os.path.dirname(os.path.realpath(__file__))) + sys.path.append(os.path.abspath(os.path.join(scriptDir, '..', 'lib', 'python27'))) +@@ -45,6 +46,10 @@ import Haplo.happyroc + import Haplo.gvcf2bed + from Tools import fastasize + ++# Cannot convert data to json without a custom enconder ++def np_encoder(object): ++ if isinstance(object, np.generic): ++ return object.item() + + def quantify(args): + """ Run quantify and write tables """ diff --git a/pkgs/by-name/ha/hap-py/package.nix b/pkgs/by-name/ha/hap-py/package.nix new file mode 100644 index 000000000000000..6a420264d80285a --- /dev/null +++ b/pkgs/by-name/ha/hap-py/package.nix @@ -0,0 +1,61 @@ +{ pkgs, stdenv, fetchFromGitHub, boost, zlib, lib, makeWrapper }: + +let + # Bcftools needs perl + runtime = with pkgs; [ bcftools htslib my-python perl samtools ]; + my-python-packages = p: with p; [ + bx-python + pysam + cython + pandas + psutil + nose + scipy + ]; + my-python = pkgs.python3.withPackages my-python-packages; +in +stdenv.mkDerivation rec { + pname = "hap.py"; + version = "0.3.15"; + src = fetchFromGitHub { + owner = "Illumina"; + repo = pname; + rev = "v${version}"; + sha256 = "sha256-K8XXhioMGMHw56MKvp0Eo8S6R36JczBzGRaBz035zRQ="; + }; + # For illumina script + BOOST_ROOT = "${boost.out}"; + ZLIBSTATIC = "${zlib.static}"; + # For cmake : boost lib and includedir are in differernt location + BOOST_LIBRARYDIR = "${boost.out}/lib"; + BOOST_INCLUDEDIR = "${boost.dev}/include"; + patches = [ + ./hap-py.patch + ./cmake.patch + ]; + buildInputs = with pkgs; [ + autoconf + boost + bzip2 + cmake + curl + htslib + my-python + xz + zlib + ]; + nativeBuildInputs = [ pkgs.makeWrapper ]; + propagatedBuildInputs = runtime; + postFixup = '' + wrapProgram $out/bin/hap.py \ + --set PATH ${lib.makeBinPath runtime} + ''; + + meta = with lib; { + description = "Compare genetics variants against a gold dataset"; + homepage = "https://github.com/Illumina/hap.py"; + license = licenses.bsd2; + maintainers = with maintainers; [ apraga ]; + mainProgram = "hap.py"; + }; +}