Merge pull request #56 from ygidtu/dev

update to v0.0.8, fix --log, add conda config

Author: ygidtu

docs/installation.md

@@ -1,35 +1,49 @@
 
-## Install from source
+## Install with pypi, conda or docker
 
-download source code using git
+###  via Conda
 ```bash
+conda install sashimi-py
+
+# create conda env from local
+
 git clone from https://github.com/ygidtu/sashimipy sashimi
 cd sashimi
+
+conda create env -n sashimi meta.yaml
 ```
 
-### Run as command line tools
+### via PyPI
 
 ```bash
 pip install sashimi.py
+```
 
-# or install from source
-python setup.py install
+### via Docker
 
-sashimipy --help
+```bash
+docker pull ygidtu/sashimi
 ```
 
-or
+## Install from source
 
+download source code using git
 ```bash
-## via Conda
-conda install sashimi-py
+git clone from https://github.com/ygidtu/sashimipy sashimi
+cd sashimi
+```
 
-## via Docker
-docker pull quay.io/biocontainers/sashimi-py
+### Run as command line tools
+
+```bash
+## install from source
 
-## via PyPI
 pip install sashimi.py
 
+# or install from source
+python setup.py install
+
+sashimipy --help
 ```
 
 ### Run as script

meta.yaml

@@ -0,0 +1,67 @@
+{% set name = "sashimi.py" %}
+{% set version = "0.0.8" %}
+
+
+package:
+  name: sashimi-py
+  version: {{ version }}
+
+source:
+  url: "https://pypi.io/packages/source/{{ name[0] }}/{{ name }}/{{ name }}-{{ version }}.tar.gz"
+  sha256: 22d444d3ae5416ddaab3a20d2fa7e254edc00bbf22165edfdea22d328852dd43
+
+build:
+  noarch: python
+  number: 0
+  script: {{ PYTHON }} -m pip install . --no-deps --ignore-installed --no-cache-dir -vvv
+
+requirements:
+  host:
+    - python
+    - wheel
+    - setuptools
+    - setuptools_scm
+    - pip
+    - filetype
+    - pysam
+    - pybigwig
+    - hicmatrix
+    - click-option-group
+  run:
+    - python
+    - wheel
+    - pysam
+    - filetype
+    - pybigwig
+    - click-option-group
+    - cairocffi
+    - hicmatrix
+    - samtools
+    - tabix
+    - matplotlib-base
+    - seaborn-base
+    - click
+    - numpy
+    - requests
+    - xmltodict
+    - pandas
+    - loguru
+
+test:
+  imports:
+    - sashimi
+
+  commands:
+    - sashimipy --help
+
+about:
+  home: https://github.com/ygidtu/sashimi.py
+  summary: "This is an pure Python version of sashimi plot"
+  doc_url: https://sashimi.readthedocs.io/en/latest/
+  license: BSD-3-Clause
+  license_family: BSD
+  license_file: LICENSE
+
+extra:
+  recipe-maintainers:
+    - ygidtu

sashimi/base/CoordinateMap.py

@@ -218,17 +218,4 @@ def pep_to_cds(self, pep_start: int, pep_end: Optional[int] = None):
 
 
 if __name__ == '__main__':
-    def test():
-        cds = [(3216025, 3216968),
-               (3421702, 3421901),
-               (3670552, 3671348)]
-
-        coord = CoordinateMapper(cds, "+")
-        domain_info = [(1, 3, "1XK-related protein 4;chain")]
-        domain_coord = coord.pep_to_cds(1, 3)
-        print(domain_coord.se)
-        # [(3216025, 3216033)]
-
-
-    test()
     pass

sashimi/base/Protein.py

@@ -182,7 +182,6 @@ def __init_protein__(self):
         )
 
         for current_transcript_id in self.cds.keys():
-            # print(current_transcript_id, len(self.cds[current_transcript_id]))
             current_pep = Uniprot(
                 uniprot_id=current_transcript_id,
                 cds_len=len(self.cds[current_transcript_id]),
@@ -227,9 +226,7 @@ def __init_protein__(self):
                     min(map(lambda x: x.start, i)) for i in domain_list
                 ])
 
-                end_site = max([
-                    max(map(lambda x: x.end, i)) for i in domain_list
-                ])
+                end_site = max([max(map(lambda x: x.end, i)) for i in domain_list])
 
                 protein_info[current_transcript_id].append(
                     Transcript(
@@ -250,26 +247,4 @@ def __init_protein__(self):
 
 
 if __name__ == '__main__':
-    def test():
-        import pysam
-        with pysam.Tabixfile("../../example/example.sorted.gtf.gz", 'r') as gtf_tabix:
-            cds_test = CdsProtein.__re_iter_gtf__(
-                gtf_tabix=gtf_tabix,
-                chromosome='chr1',
-                # transcript_id={'ENST00000421241'},
-                transcript_id={'ENST00000477196'},
-                gene_id={'ENSG00000131591'}
-            )
-            print(cds_test.pep)
-            for transcript_id, domains in cds_test.pep.items():
-                if len(domains) == 0:
-                    continue
-
-                for sub_domain in domains:
-                    print(transcript_id,
-                          sub_domain.gene,
-                          sub_domain.domain, sub_domain.exon_list)
-
-
-    test()
     pass

sashimi/base/ReadDepth.py

@@ -138,14 +138,14 @@ def add_customized_junctions(self, other):
         return new_junctions_dict
 
     def transform(self, log_trans: str):
-        funcs = {"10": np.log10, "2": np.log2, "zscore": zscore}
+        funcs = {"10": np.log10, "2": np.log2, "zscore": zscore, "e": np.log}
 
         if log_trans in funcs.keys():
             if self.plus is not None:
                 self.plus = funcs[log_trans](self.plus + 1)
 
             if self.minus is not None:
-                self.minus = -funcs[log_trans](np.abs(self.minus + 1))
+                self.minus = funcs[log_trans](self.minus + 1)
 
     def normalize(self, size_factor: float):
         self.plus = np.divide(self.plus, size_factor) # * 100

sashimi/base/pyUniprot.py

@@ -208,31 +208,4 @@ def __domain_info__(self):
 
 
 if __name__ == '__main__':
-    def test():
-        """
-        trans_id = 'ENST00000339381'
-        trans_id_pep = Uniprot(uniprot_id=trans_id, cds_len=2010)
-
-        trans_id = 'ENST00000379319'
-        trans_id_pep = Uniprot(uniprot_id=trans_id, cds_len=594)
-
-        trans_id = 'ENST00000486161'
-        # # 5736 real, 4515 false
-        trans_id_pep = Uniprot(uniprot_id=trans_id, cds_len=4515)
-
-        trans_id = 'ENST00000378891'
-        trans_id_pep = Uniprot(uniprot_id=trans_id, cds_len=2085)
-
-        """
-
-        trans_id = 'ENST00000351718'
-        trans_id_pep = Uniprot(uniprot_id=trans_id, cds_len=3549)
-
-        print(trans_id_pep.guessed_id)
-        print(trans_id_pep.domain)
-        for i in trans_id_pep.domain:
-            print(i.category, i.type, i.begin, i.end)
-
-
-    test()
     pass

sashimi/cli.py

@@ -21,7 +21,7 @@
 from sashimi.file.ATAC import ATAC
 from sashimi.plot import Plot
 
-__version__ = "0.0.7"
+__version__ = "0.0.8"
 __author__ = "ygidtu & Ran Zhou"
 __email__ = "ygidtu@gmail.com"
 
@@ -556,8 +556,8 @@ def main(**kwargs):
                                           show_site_plot=kwargs["show_site"],
                                           strand_choice=kwargs["site_strand"],
                                           density_by_strand=kwargs["density_by_strand"],
-                                          only_customized_junction=kwargs["only_customized_junction"]
-                                          )
+                                          only_customized_junction=kwargs["only_customized_junction"],
+                                          log_trans=kwargs["log"])
                     elif f.category != "atac":
                         p.add_density(f.path,
                                       category=f.category,
@@ -572,7 +572,8 @@ def main(**kwargs):
                                       show_y_label=not kwargs["hide_y_label"],
                                       show_site_plot=kwargs["show_site"],
                                       strand_choice=kwargs["site_strand"],
-                                      density_by_strand=kwargs["density_by_strand"],)
+                                      density_by_strand=kwargs["density_by_strand"],
+                                      log_trans=kwargs["log"])
             elif key == "heatmap":
                 for f in process_file_list(kwargs[key], key):
                     if barcodes and f.name in barcodes.keys() and f.category in ["bam", "atac"]:
@@ -599,7 +600,8 @@ def main(**kwargs):
                                           font_size=kwargs["font_size"],
                                           do_scale=kwargs["heatmap_scale"],
                                           vmin=kwargs["heatmap_vmin"],
-                                          vmax=kwargs["heatmap_vmax"])
+                                          vmax=kwargs["heatmap_vmax"],
+                                          log_trans=kwargs["log"])
                     elif f.category != "atac":
                         p.add_heatmap(f.path,
                                       category=f.category,
@@ -617,7 +619,8 @@ def main(**kwargs):
                                       show_row_names=kwargs["show_row_names"],
                                       do_scale=kwargs["heatmap_scale"],
                                       vmin=kwargs["heatmap_vmin"],
-                                      vmax=kwargs["heatmap_vmax"])
+                                      vmax=kwargs["heatmap_vmax"],
+                                      log_trans=kwargs["log"])
             elif key == "line":
                 for f in process_file_list(kwargs[key], key):
                     if barcodes and f.name in barcodes.keys() and f.category == "bam":
@@ -643,7 +646,8 @@ def main(**kwargs):
                                        n_y_ticks=kwargs["n_y_ticks"],
                                        show_legend=not kwargs["hide_legend"],
                                        legend_position=kwargs["legend_position"],
-                                       legend_ncol=kwargs["legend_ncol"])
+                                       legend_ncol=kwargs["legend_ncol"],
+                                       log_trans=kwargs["log"])
                     else:
                         p.add_line(f.path,
                                    category=f.category,
@@ -658,7 +662,8 @@ def main(**kwargs):
                                    n_y_ticks=kwargs["n_y_ticks"],
                                    show_legend=not kwargs["hide_legend"],
                                    legend_position=kwargs["legend_position"],
-                                   legend_ncol=kwargs["legend_ncol"])
+                                   legend_ncol=kwargs["legend_ncol"],
+                                   log_trans=kwargs["log"])
             elif key == "igv":
                 for f in process_file_list(kwargs[key], "igv"):
                     igv_features = {}
@@ -742,6 +747,7 @@ def main(**kwargs):
         included_junctions=included_junctions,
         n_jobs=kwargs.get("process", 1)
     )
+    logger.info("DONE")
 
 
 if __name__ == '__main__':

sashimi/file/ATAC.py

@@ -157,8 +157,4 @@ def load(self,
 
 
 if __name__ == '__main__':
-    bam = ATAC.create("../../example/bams/sc.bam")
-    bam.load(GenomicLoci("chr1", 1270656, 1284730, "+"), 10)
-
-    print(str(bam))
     pass

sashimi/file/Bam.py

@@ -124,7 +124,6 @@ def load(self,
              threshold: int = 0,
              reads1: Optional[bool] = None,
              required_strand: Optional[str] = None,
-             log_trans: Optional[str] = None,
              **kwargs
              ):
         """
@@ -144,10 +143,8 @@ def load(self,
         :param threshold: minimums counts of the given splice junction for visualization
         :param reads1: None -> all reads, True -> only R1 kept; False -> only R2 kept
         :param required_strand: None -> all reads, else reads on specific strand
-        :param log_trans: should one of {"10": np.log10, "2": np.log2}
         """
         self.region = region
-        self.log_trans = log_trans
         filtered_junctions = {}
 
         spanned_junctions = kwargs.get("junctions", {})
@@ -296,17 +293,4 @@ def load(self,
 
 
 if __name__ == '__main__':
-    bam = Bam.create(
-        "../../example/bams/sc.bam",
-        library="frf")
-    bam.load(GenomicLoci("chr1", 1270656, 1284730, "+"), 10)
-
-    print(str(bam))
-    print(bam.to_csv())
-    print(max(bam.data.wiggle), min(bam.data.wiggle))
-    print(bam.data.junctions_dict)
-    print(max(bam.data.plus))
-    print(min(bam.data.minus))
-    print(max(bam.data.site_plus))
-    print(min(bam.data.site_minus))
     pass

sashimi/file/BedGraph.py

@@ -47,7 +47,4 @@ def load(self, region: GenomicLoci, **kwargs):
 
 
 if __name__ == "__main__":
-    bw = Bedgraph.create("../../example/bedgraph/ENCFF260QGF_lung_filter.bedgraph.gz")
-    bw.load(GenomicLoci("chr1", 120457967, 120459467, "+"))
-    print(bw.data.wiggle)
     pass