[bug#46946] (no subject)

[bug#46946] (no subject)

[Mădălin Ionel Patrașcu]

[bug#46946] [PATCH 1/2] gnu: Add python-bioframe.

[Mădălin Ionel Patrașcu]

* gnu/packages/bioinformatics.scm (python-bioframe): New variable.
---
 gnu/packages/bioinformatics.scm | 46 +++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index d617736e57..fb357b8b6c 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -120,6 +120,7 @@
   #:use-module (gnu packages popt)
   #:use-module (gnu packages protobuf)
   #:use-module (gnu packages python)
+  #:use-module (gnu packages python-build)
   #:use-module (gnu packages python-check)
   #:use-module (gnu packages python-compression)
   #:use-module (gnu packages python-science)
@@ -923,6 +924,51 @@ Python.")
        `(("python2-pathlib" ,python2-pathlib)
          ,@(package-native-inputs pybedtools))))))
 
+(define-public python-bioframe
+  (package
+    (name "python-bioframe")
+    (version "0.2.0")
+    ;;pypi sources does not contain requirements.txt
+    (source
+     (origin
+       (method git-fetch)
+       (uri (git-reference
+             (url "https://github.com/open2c/bioframe")
+             (commit (string-append "v" version))))
+       (file-name (git-file-name name version))
+       (sha256
+        (base32
+         "0w5xrb93cf3hx3d1lw48a0l1ranghpj260b05b1rpk58wwwcsqfh"))))
+    (build-system python-build-system)
+    (propagated-inputs
+     `(("python-click" ,python-click)
+       ("python-numpy" ,python-numpy)
+       ("python-pandas" ,python-pandas)
+       ("python-requests" ,python-requests)))
+    (native-inputs
+     `(("python-dask" ,python-dask)             ;;for unittest.loader
+       ("python-matplotlib" ,python-matplotlib) ;;for unittest.loader
+       ("python-numba" ,python-numba)           ;;for unittest.loader
+       ("python-pypairix" ,python-pypairix)     ;;for unittest.loader
+       ("python-pytest" ,python-pytest)
+       ("python-wheel" ,python-wheel)))
+    (home-page "https://github.com/open2c/bioframe")
+    (synopsis
+     "Framework for genomic data analysis using Pandas dataframes")
+    (description
+     "This package is a library to enable flexible and scalable operations on
+genomic interval dataframes in python.  @code{python-bioframe} enables access
+to a rich set of dataframe operations.  Working in python enables rapid
+visualization (e.g. matplotlib, seaborn) and iteration of genomic analyses.
+The philosophy underlying @code{python-bioframe} is to enable flexible
+operations: instead of creating a function for every possible use-case, we
+instead encourage users to compose functions to achieve their goals.  As a
+rough rule of thumb, if a function requires three steps and is crucial for
+genomic interval arithmetic we have included it; conversely if it can be
+performed in a single line by composing two of the core functions, we have not
+included it.")
+    (license license:expat)))
+
 (define-public python-biom-format
   (package
     (name "python-biom-format")
-- 
2.30.1

[bug#46946] [PATCH 2/2] gnu: Add python-cooltools.

[Mădălin Ionel Patrașcu]

* gnu/packages/bioinformatics.scm (python-cooltools): New variable.
---
 gnu/packages/bioinformatics.scm | 45 +++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index fb357b8b6c..a6ea8f831d 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -13652,6 +13652,51 @@ storage format, called @code{cool}, used to store genomic interaction data,
 such as Hi-C contact matrices.")
     (license license:bsd-3)))
 
+(define-public python-cooltools
+;;pypi sources requiere bioframe<0.1 while github latest version requires
+;; bioframe>=0.1.0
+  (let ((revision "1")
+        (commit "53ce4fc11d046e84ca36f3591e9e5d548de9f7b2"))
+    (package
+      (name "python-cooltools")
+      (version (git-version "0.3.2" revision commit))
+      (source
+       (origin
+         (method git-fetch)
+         (uri (git-reference
+              (url "https://github.com/open2c/cooltools")
+              (commit commit)))
+         (file-name (git-file-name name version))
+         (sha256
+          (base32
+           "0y1wf7a0by2kih2iy5xrwzdgw1i24cwigfz4352aq5npxrpjvj6q"))))
+      (build-system python-build-system)
+      (propagated-inputs
+       `(("python-bioframe" ,python-bioframe)
+         ("python-click" ,python-click)
+         ("python-cooler" ,python-cooler)
+         ("python-cytoolz" ,python-cytoolz)
+         ("python-joblib" ,python-joblib)
+         ("python-matplotlib" ,python-matplotlib)
+         ("python-multiprocess" ,python-multiprocess)
+         ("python-numba" ,python-numba)
+         ("python-numpy" ,python-numpy)
+         ("python-pandas" ,python-pandas)
+         ("python-scikit-learn" ,python-scikit-learn)
+         ("python-scipy" ,python-scipy)
+         ("python-tables" ,python-tables)))
+      (native-inputs
+       `(("python-cython" ,python-cython)))
+      (home-page
+       "https://github.com/open2c/cooltools")
+      (synopsis
+       "Analysis tools for genomic interaction data stored in .cool format")
+      (description
+       "This package provides necessary tools for the analysis of the genomic
+interaction data stored in .cool format.  This collection of tools includes
+operations like compartment, insulation or peak calling.")
+      (license license:expat))))
+
 (define-public python-hicmatrix
   (package
     (name "python-hicmatrix")
-- 
2.30.1

[bug#46946] [PATCH 1/2] gnu: Add python-bioframe.

[Ricardo Wurmus]

Hi Mădălin,

> * gnu/packages/bioinformatics.scm (python-bioframe): New variable.

Thanks for the patch.

Despite all the test inputs the test suite is not actually run:

--8<---------------cut here---------------start------------->8---
starting phase `check'
running "python setup.py" with command "test" and parameters ()
running test
running egg_info
writing bioframe.egg-info/PKG-INFO
writing dependency_links to bioframe.egg-info/dependency_links.txt
writing requirements to bioframe.egg-info/requires.txt
writing top-level names to bioframe.egg-info/top_level.txt
reading manifest file 'bioframe.egg-info/SOURCES.txt'
reading manifest template 'MANIFEST.in'
warning: no previously-included files matching '__pycache__/*' found anywhere in distribution
warning: no previously-included files matching '*.so' found anywhere in distribution
warning: no previously-included files matching '*.pyd' found anywhere in distribution
warning: no previously-included files matching '*.pyc' found anywhere in distribution
warning: no previously-included files matching '.git*' found anywhere in distribution
warning: no previously-included files matching '.deps/*' found anywhere in distribution
warning: no previously-included files matching '.DS_Store' found anywhere in distribution
writing manifest file 'bioframe.egg-info/SOURCES.txt'
running build_ext
/tmp/guix-build-python-bioframe-0.2.0.drv-0/source/bioframe/io/dask.py:47: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "reg2bins" failed type inference due to: No conversion from list(int64)<iv=None> to int32 for '$262return_value.1', defined at None

File "bioframe/io/dask.py", line 79:
def reg2bins(rbeg, rend):
    <source elided>

    return lst
    ^

During: typing of assignment at /tmp/guix-build-python-bioframe-0.2.0.drv-0/source/bioframe/io/dask.py (79)

File "bioframe/io/dask.py", line 79:
def reg2bins(rbeg, rend):
    <source elided>

    return lst
    ^

  @numba.jit("int32(int32, int32)")
/tmp/guix-build-python-bioframe-0.2.0.drv-0/source/bioframe/io/dask.py:47: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "reg2bins" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "bioframe/io/dask.py", line 59:
def reg2bins(rbeg, rend):
    <source elided>

    k = 9 + (rbeg >> 23)
    ^

  @numba.jit("int32(int32, int32)")
/gnu/store/sm6k3ar46q11w77s7cc2q1hv33q8p3v0-python-numba-0.51.2/lib/python3.8/site-packages/numba/core/object_mode_passes.py:177: NumbaWarning: Function "reg2bins" was compiled in object mode without forceobj=True, but has lifted loops.

File "bioframe/io/dask.py", line 50:
def reg2bins(rbeg, rend):
    <source elided>

    MAX_BIN = ((1 << 18) - 1) // 7
    ^

  warnings.warn(errors.NumbaWarning(warn_msg,
/gnu/store/sm6k3ar46q11w77s7cc2q1hv33q8p3v0-python-numba-0.51.2/lib/python3.8/site-packages/numba/core/object_mode_passes.py:187: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "bioframe/io/dask.py", line 50:
def reg2bins(rbeg, rend):
    <source elided>

    MAX_BIN = ((1 << 18) - 1) // 7
    ^

  warnings.warn(errors.NumbaDeprecationWarning(msg,

----------------------------------------------------------------------
Ran 0 tests in 0.000s

OK
phase `check' succeeded after 3.1 seconds
--8<---------------cut here---------------end--------------->8---


I made a couple of cosmestic changes:

--8<---------------cut here---------------start------------->8---
(define-public python-bioframe
  (package
    (name "python-bioframe")
    (version "0.2.0")
    ;; Sources on pypi do not contain requirements.txt
    (source
     (origin
       (method git-fetch)
       (uri (git-reference
             (url "https://github.com/open2c/bioframe")
             (commit (string-append "v" version))))
       (file-name (git-file-name name version))
       (sha256
        (base32
         "0w5xrb93cf3hx3d1lw48a0l1ranghpj260b05b1rpk58wwwcsqfh"))))
    (build-system python-build-system)
    (propagated-inputs
     `(("python-click" ,python-click)
       ("python-numpy" ,python-numpy)
       ("python-pandas" ,python-pandas)
       ("python-requests" ,python-requests)))
    (native-inputs
     `(("python-dask" ,python-dask)             ; for tests
       ("python-matplotlib" ,python-matplotlib) ; for tests
       ("python-numba" ,python-numba)           ; for tests
       ("python-pypairix" ,python-pypairix)     ; for tests
       ("python-pytest" ,python-pytest)
       ("python-wheel" ,python-wheel)))
    (home-page "https://github.com/open2c/bioframe")
    (synopsis "Framework for genomic data analysis using Pandas dataframes")
    (description
     "This package is a library to enable flexible and scalable operations on
genomic interval dataframes in Python.  @code{python-bioframe} enables access;
to a rich set of dataframe operations.  Working in Python enables rapid
visualization (e.g. matplotlib, seaborn) and iteration of genomic analyses.")
    (license license:expat)))
--8<---------------cut here---------------end--------------->8---


Please note that the lack of requirements.txt on pypi shouldn’t be an
obstacle to use the sources from pypi.  It should build just as well.

-- 
Ricardo

[bug#46946] [ext] Re: [PATCH 1/2] gnu: Add python-bioframe.

[MadalinIonel.Patrascu]

[-- Attachment #1: Type: text/plain, Size: 6487 bytes --]

Dear Ricardo,


I am very sorry that I started this and abandon it!
After a long period, I remembered about this and I found some time to finish this and amend my initial patches as you already pointed out.
The next two definitions are updated and they come with the latest releases and also I solved the issues mentioned.

All the best!

Mădălin Ionel Patrașcu

System Administrator
The Berlin Institute for Medical Systems Biology (BIMSB)
Max Delbrück Center (MDC)
Hannoversche Straße 28
House 101, room 1.89
10115 Berlin, Germany


________________________________
From: Ricardo Wurmus <rekado@elephly.net>
Sent: Thursday, April 1, 2021 17:38
To: Patrascu, Madalin Ionel
Cc: 46946@debbugs.gnu.org
Subject: [ext] Re: [PATCH 1/2] gnu: Add python-bioframe.


Hi Mădălin,

> * gnu/packages/bioinformatics.scm (python-bioframe): New variable.

Thanks for the patch.

Despite all the test inputs the test suite is not actually run:

--8<---------------cut here---------------start------------->8---
starting phase `check'
running "python setup.py" with command "test" and parameters ()
running test
running egg_info
writing bioframe.egg-info/PKG-INFO
writing dependency_links to bioframe.egg-info/dependency_links.txt
writing requirements to bioframe.egg-info/requires.txt
writing top-level names to bioframe.egg-info/top_level.txt
reading manifest file 'bioframe.egg-info/SOURCES.txt'
reading manifest template 'MANIFEST.in'
warning: no previously-included files matching '__pycache__/*' found anywhere in distribution
warning: no previously-included files matching '*.so' found anywhere in distribution
warning: no previously-included files matching '*.pyd' found anywhere in distribution
warning: no previously-included files matching '*.pyc' found anywhere in distribution
warning: no previously-included files matching '.git*' found anywhere in distribution
warning: no previously-included files matching '.deps/*' found anywhere in distribution
warning: no previously-included files matching '.DS_Store' found anywhere in distribution
writing manifest file 'bioframe.egg-info/SOURCES.txt'
running build_ext
/tmp/guix-build-python-bioframe-0.2.0.drv-0/source/bioframe/io/dask.py:47: NumbaWarning:
Compilation is falling back to object mode WITH looplifting enabled because Function "reg2bins" failed type inference due to: No conversion from list(int64)<iv=None> to int32 for '$262return_value.1', defined at None

File "bioframe/io/dask.py", line 79:
def reg2bins(rbeg, rend):
    <source elided>

    return lst
    ^

During: typing of assignment at /tmp/guix-build-python-bioframe-0.2.0.drv-0/source/bioframe/io/dask.py (79)

File "bioframe/io/dask.py", line 79:
def reg2bins(rbeg, rend):
    <source elided>

    return lst
    ^

  @numba.jit("int32(int32, int32)")
/tmp/guix-build-python-bioframe-0.2.0.drv-0/source/bioframe/io/dask.py:47: NumbaWarning:
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "reg2bins" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "bioframe/io/dask.py", line 59:
def reg2bins(rbeg, rend):
    <source elided>

    k = 9 + (rbeg >> 23)
    ^

  @numba.jit("int32(int32, int32)")
/gnu/store/sm6k3ar46q11w77s7cc2q1hv33q8p3v0-python-numba-0.51.2/lib/python3.8/site-packages/numba/core/object_mode_passes.py:177: NumbaWarning: Function "reg2bins" was compiled in object mode without forceobj=True, but has lifted loops.

File "bioframe/io/dask.py", line 50:
def reg2bins(rbeg, rend):
    <source elided>

    MAX_BIN = ((1 << 18) - 1) // 7
    ^

  warnings.warn(errors.NumbaWarning(warn_msg,
/gnu/store/sm6k3ar46q11w77s7cc2q1hv33q8p3v0-python-numba-0.51.2/lib/python3.8/site-packages/numba/core/object_mode_passes.py:187: NumbaDeprecationWarning:
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "bioframe/io/dask.py", line 50:
def reg2bins(rbeg, rend):
    <source elided>

    MAX_BIN = ((1 << 18) - 1) // 7
    ^

  warnings.warn(errors.NumbaDeprecationWarning(msg,

----------------------------------------------------------------------
Ran 0 tests in 0.000s

OK
phase `check' succeeded after 3.1 seconds
--8<---------------cut here---------------end--------------->8---


I made a couple of cosmestic changes:

--8<---------------cut here---------------start------------->8---
(define-public python-bioframe
  (package
    (name "python-bioframe")
    (version "0.2.0")
    ;; Sources on pypi do not contain requirements.txt
    (source
     (origin
       (method git-fetch)
       (uri (git-reference
             (url "https://github.com/open2c/bioframe")
             (commit (string-append "v" version))))
       (file-name (git-file-name name version))
       (sha256
        (base32
         "0w5xrb93cf3hx3d1lw48a0l1ranghpj260b05b1rpk58wwwcsqfh"))))
    (build-system python-build-system)
    (propagated-inputs
     `(("python-click" ,python-click)
       ("python-numpy" ,python-numpy)
       ("python-pandas" ,python-pandas)
       ("python-requests" ,python-requests)))
    (native-inputs
     `(("python-dask" ,python-dask)             ; for tests
       ("python-matplotlib" ,python-matplotlib) ; for tests
       ("python-numba" ,python-numba)           ; for tests
       ("python-pypairix" ,python-pypairix)     ; for tests
       ("python-pytest" ,python-pytest)
       ("python-wheel" ,python-wheel)))
    (home-page "https://github.com/open2c/bioframe")
    (synopsis "Framework for genomic data analysis using Pandas dataframes")
    (description
     "This package is a library to enable flexible and scalable operations on
genomic interval dataframes in Python.  @code{python-bioframe} enables access;
to a rich set of dataframe operations.  Working in Python enables rapid
visualization (e.g. matplotlib, seaborn) and iteration of genomic analyses.")
    (license license:expat)))
--8<---------------cut here---------------end--------------->8---


Please note that the lack of requirements.txt on pypi shouldn’t be an
obstacle to use the sources from pypi.  It should build just as well.

--
Ricardo

[-- Attachment #2: Type: text/html, Size: 10804 bytes --]

[bug#46946] [PATCH 1/2] gnu: Add python-bioframe.

[Mădălin Ionel Patrașcu]

 X-Debbugs-Cc: rekado@elephly.net

* gnu/packages/bioinformatics.scm (python-bioframe): New variable.
---
 gnu/packages/bioinformatics.scm | 46 +++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index f2de09aa32..1478ba0c46 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -946,6 +946,52 @@ (define (cythonized? c/c++-file)
     ;; licensed lgpl2.1+
     (license (list license:expat license:lgpl2.1+))))
 
+(define-public python-bioframe
+  (package
+    (name "python-bioframe")
+    (version "0.3.3")
+    (source
+      (origin
+        (method git-fetch)
+        ;; pypi version does not contain tests and requirements.txt
+        (uri (git-reference
+               (url "https://github.com/open2c/bioframe")
+               (commit (string-append "v" version))))
+       (file-name (git-file-name name version))
+       (sha256
+        (base32
+         "14lvb18d4npapyi6j2zqh9q94l658dzmka5riiizw1h0zb0kp9xb"))))
+    (build-system python-build-system)
+    (arguments
+     `(#:phases
+       (modify-phases %standard-phases
+         (replace 'check
+           (lambda* (#:key tests? #:allow-other-keys)
+             (setenv "MPLCONFIGDIR" "/tmp")
+             (when tests?
+               (invoke "pytest" "-v")))))))
+    (native-inputs
+      (list python-biopython
+            python-pysam
+            python-pytest
+            python-wheel))
+    (propagated-inputs
+      (list python-matplotlib
+            python-numpy
+            python-pandas
+            python-requests))
+    (home-page "https://github.com/open2c/bioframe")
+    (synopsis "Pandas utilities for tab-delimited and other genomic files")
+    (description
+     "This package is a library to enable flexible and scalable operations on
+genomic interval dataframes in @code{python}.  @code{python-bioframe} enables
+access to a rich set of dataframe operations.  Working in @code{python} enables
+rapid visualization (e.g. @code{matplotlib}, @code{seaborn}) and iteration of
+genomic analyses.  The philosophy underlying @code{python-bioframe} is to enable
+flexible operations.  Instead of creating a function for every possible use-case,
+we encourage users to compose functions to achieve their goals.")
+    (license license:expat)))
+
 (define-public python-biom-format
   (package
     (name "python-biom-format")

base-commit: 10d429f2fce321d8285684503094694ec3979865
-- 
2.37.3

[bug#46946] [PATCH 2/2] gnu: Add python-cooltools.

[Mădălin Ionel Patrașcu]

 X-Debbugs-Cc: rekado@elephly.net

* gnu/packages/bioinformatics.scm (python-cooltools): New variable.
---
 gnu/packages/bioinformatics.scm | 45 +++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/gnu/packages/bioinformatics.scm b/gnu/packages/bioinformatics.scm
index 1478ba0c46..6f228fb907 100644
--- a/gnu/packages/bioinformatics.scm
+++ b/gnu/packages/bioinformatics.scm
@@ -12977,6 +12977,51 @@ (define-public python-cooler
 such as Hi-C contact matrices.")
     (license license:bsd-3)))
 
+(define-public python-cooltools
+  (package
+    (name "python-cooltools")
+    (version "0.5.1")
+    (source (origin
+              (method url-fetch)
+              (uri (pypi-uri "cooltools" version))
+              (sha256
+               (base32
+                "08hyzd3kazr87nvv6rwp5i1g9rwj7jmrly925lqnvippz4wp7k4g"))))
+    (build-system python-build-system)
+    (arguments
+      (list
+       #:phases
+       #~(modify-phases %standard-phases
+           (replace 'check
+             (lambda* (#:key tests? #:allow-other-keys)
+               (setenv "MPLCONFIGDIR" "/tmp")
+               (when tests?
+                 (invoke "pytest" "-v")))))))
+    (native-inputs
+      (list python-cython
+            python-pytest))
+    (propagated-inputs
+      (list python-bioframe
+            python-click
+            python-cooler
+            python-joblib
+            python-matplotlib
+            python-multiprocess
+            python-numba
+            python-numpy
+            python-pandas
+            python-scikit-image
+            python-scikit-learn
+            python-scipy))
+    (home-page "https://github.com/open2c/cooltools")
+    (synopsis
+     "Analysis tools for genomic interaction data stored in .cool format")
+    (description
+     "This package provides necessary tools for the analysis of the genomic
+interaction data stored in @code{.cool} format.  This collection of tools includes
+operations like compartment, insulation or peak calling.")
+    (license license:expat)))
+
 (define-public python-hicmatrix
   (package
     (name "python-hicmatrix")
-- 
2.37.3

bug#46946: Add python-bioframe, python-cooltools

[Ricardo Wurmus]

Applied with indentation changes.  Thanks!

-- 
Ricardo