Merge pull request #129 from rigdenlab/changes

SIMBAD fixes and changes

.coveragerc

@@ -0,0 +1,12 @@
+[run]
+branch = True
+source = simbad
+[report]
+exclude_lines =
+    if self.debug:
+    pragma: no cover
+    raise NotImplementedError
+    if __name__ == .__main__.:
+ignore_errors = True
+omit =
+    simbad/*/tests/*

.travis.yml

@@ -1,9 +1,16 @@
 language: python
+os:
+  - linux
 python:
   - "2.7"
-
+cache: pip
 install:
   - sudo apt-get update
-  - wget https://raw.githubusercontent.com/cctbx/cctbx_project/master/libtbx/auto_build/bootstrap.py
-  - python ./bootstrap.py
-  - cctbx-python setup.py install
+  - pip install codecov
+  - pip install -r requirements.txt
+  - python setup.py install
+script:
+  - coverage run scripts/run_tests.py
+
+after_success:
+  - codecov

CHANGELOG.rst

@@ -2,14 +2,36 @@
 Changelog
 =========
 
-[unreleased]
-------------
+0.2.0
+-----
 
 Added
 ~~~~~
+- Added MTZ parser which uses GEMMI to get information about the input MTZ
+- Added nmol flag to MR submit options [default 1] (0 for automatic selection)
+- Added run.bat files to examples for testing on windows
+- Added bibliography file for CCP4i2 interface
 
 Changed
 ~~~~~~~
+- Set Phaser as default rotation and MR program
+- Altered Phaser to allow it to search for more than 1 search model in MR mode
+- Removed GetLabels function from mtz_util and replaced with MTZ parser
+- Removed CCTBX for calculating the Matthews coefficient
+- Improved the efficiency of the Matthews coefficient calculation
+- Removed CCTBX for PDB manipulations
+- Updated PDB tests to accomodate subtle changes in output
+- Replaced deprecated PyJob imports
+- Altered how MR search deals with low solvent content predictions
+- Modified anomalous util to work with new MTZ parser
+- Altered parent class for parsers
+- Made a parent class for Matthews probability
+- Made a parent class for Rotation functions
+- Fixed issues preventing contaminant search from working on windows
+- Fixed Windows tests
+- Fixed CCP4i2 interface issues
+- Added rot_program and nmol options to ccp4i2 interface
+- Updated pyrapi output to plot graphs for the phaser rotation search
 
 0.1.20
 ------

LICENSE.txt

@@ -1,6 +1,6 @@
 BSD 3-Clause License
 
-Copyright (c) 2018, University of Liverpool
+Copyright (c) 2020, University of Liverpool
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without

README.rst

@@ -6,13 +6,21 @@ Sequence Independent Molecular Replacement Based on Available Database
    :target: http://simbad.readthedocs.io/en/latest/?badge=latest
    :alt: Documentation Status
 
+.. image:: https://travis-ci.com/rigdenlab/SIMBAD.svg?branch=master
+   :target: https://travis-ci.com/rigdenlab/SIMBAD
+   :alt: CI Status
+
 .. image:: https://img.shields.io/badge/solution%20count-8-blue.svg?style=flat
    :alt: Solution count
 
 .. image:: https://img.shields.io/badge/DOI-10.1107/S2059798318005752-blue.svg
    :target: https://doi.org/10.1107/S2059798318005752
    :alt: SIMBAD paper
 
+.. image:: https://codecov.io/gh/rigdenlab/SIMBAD/branch/master/graph/badge.svg
+  :target: https://codecov.io/gh/rigdenlab/SIMBAD
+
+
 About
 +++++
 

examples/contaminant_example/run.bat

@@ -0,0 +1,12 @@
+# Written by: Adam Simpkin
+# Date:       21 July 2020
+#
+# This script is an example of how to run the contaminant
+# search in SIMBAD. Various command line flags could be set
+# but below's example is the most basic usage and illustrates
+# its purporse.
+
+%CCP4%\bin\simbad-contaminant.bat ^
+-nproc 4 ^
+-organism CHICK ^
+input/2fbb.mtz

examples/lattice_example/run.bat

@@ -0,0 +1,9 @@
+# Written by: Adam Simpkin
+# Date:       21 July 2020
+#
+# This script is an example of how to run the lattice search
+# SIMBAD. Various command line flags could be set but below's
+# example is the most basic usage and illustrates its purpose.
+
+%CCP4%\bin\simbad-lattice.bat ^
+input/1dtx.mtz

examples/morda_example/run.bat

@@ -0,0 +1,16 @@
+# Written by: Adam Simpkin
+# Date:       21 July 2020
+#
+# This script is an example of how to run the a MoRDa search in
+# SIMBAD. Various command line flags could be set but below's
+# example is the most basic usage and illustrates its purpose
+#.
+# Note: the MoRDa database needs to be installed separately.
+
+set morda_db="<PATH TO MORDA DB>"
+set nproc=4
+
+%CCP4%\bin\simbad-morda ^
+-morda_db %morda_db% ^
+-nproc %nproc% ^
+input/1dtx.mtz

i2/SIMBAD.bibtex.txt

@@ -0,0 +1,28 @@
+
+% 29968670
+@Article{pmid29968670,
+   Author="Simpkin, Adam J. and Simkovic, Felix and Thomas, Jens M. H. and Savko, Martin and Lebedev, Andrey and Uski, Ville and Ballard, Charles and Wojdyr, Marcin and Wu, Rui and Sanishvili, Ruslan and Xu, Yibin and Lisa, Mar{\'\i}a-Natalia and Buschiazzo, Alejandro and Shepard, William and Rigden, Daniel J. and Keegan, Ronan M.",
+   Title="{{\it SIMBAD}: a sequence-independent molecular-replacement pipeline}",
+   Journal="Acta Crystallographica Section D",
+   Year="2018",
+   Volume="74",
+   Number="7",
+   Pages="595--605",
+   Month="Jul",
+   Doi={10.1107/S2059798318005752},
+   Url={https://doi.org/10.1107/S2059798318005752},
+}
+
+% 31909738
+@Article{pmid31909738,
+   Author="Simpkin, Adam J. and Simkovic, Felix and Thomas, Jens M. H. and Savko, Martin and Lebedev, Andrey and Uski, Ville and Ballard, Charles C. and Wojdyr, Marcin and Shepard, William and Rigden, Daniel J. and Keegan, Ronan M.",
+   Title="{Using {\it Phaser} and ensembles to improve the performance of {\it SIMBAD}}",
+   Journal="Acta Crystallographica Section D",
+   Year="2020",
+   Volume="76",
+   Number="1",
+   Pages="1--8",
+   Month="Jan",
+   Doi={10.1107/S2059798319015031},
+   Url={https://doi.org/10.1107/S2059798319015031},
+}

i2/SIMBAD.def.xml

@@ -13,13 +13,15 @@
     <ccp4i2_body id="SIMBAD">
 <!--You must provide an inputData container, although it can be empty-->
         <container id="inputData">
-            <content id="SIMBAD_F_SIGF">
+            <content id="F_SIGF">
                 <className>CObsDataFile</className>
                 <qualifiers>
-                    <allowUndefined>False</allowUndefined>
-                    <mustExist>True</mustExist>
+                  <mustExist>True</mustExist>
+                  <allowUndefined>False</allowUndefined>
+                  <fromPreviousJob>True</fromPreviousJob>
+                  <requiredContentFlag>4</requiredContentFlag>
                 </qualifiers>
-            </content>
+              </content>
 			<content id="SIMBAD_SEARCH_LEVEL">
 			  <className>CString</className>
 			  <qualifiers>
@@ -29,31 +31,6 @@
 			  </qualifiers>
 			</content>
 			<content id="SIMBAD_ORGANISM">
-<!--
-
-ALCXX : Alcaligenes xylosoxydans xylosoxydans
-BACTH : Bacillus thermoproteolyticus
-BOVIN : Bos taurus
-CHICK : Gallus gallus
-ECOLI : Escherichia coli (strain K12)
-ENGAL : Parengyodontium album (Tritirachium album)
-GRIFR : Grifola frondosa
-HRV14 : Human rhinovirus 14
-HRV2 : Human rhinovirus 2
-HUMAN : Homo sapiens
-LYSEN : Lysobacter enzymogenes
-PIG : Sus scrofa
-PSEAE : Pseudomonas aeruginosa (strain ATCC 15692 / DSM 22644 / CIP 104116 / JCM 14847 / LMG 12228 / 1C / PRS 101 / PAO1)
-RHORH : Rhodococcus rhodochrous
-SALET : Salmonella enterica I
-SCHJA : Schistosoma japonicum
-SERP5 : Serratia proteamaculans (strain 568)
-STRM5 : Stenotrophomonas maltophilia (strain R551-3)
-TEV : Tobacco etch virus
-UNKP : Unknown prokaryotic organism
-YEAST : Saccharomyces cerevisiae (strain ATCC 204508 / S288c)
-
--->
 			  <className>CString</className>
 			  <qualifiers>
 			    <onlyEnumerators>True</onlyEnumerators>
@@ -95,10 +72,28 @@ YEAST : Saccharomyces cerevisiae (strain ATCC 204508 / S288c)
 			  <qualifiers>
 			    <onlyEnumerators>True</onlyEnumerators>
 			    <enumerators>phaser,molrep</enumerators>
-			    <default>molrep</default>
+			    <default>phaser</default>
 	            <guiLabel>Molecular Replacement Program:</guiLabel>
 			  </qualifiers>
 			</content>
+            <content id="SIMBAD_ROT_PROGRAM">
+			  <className>CString</className>
+			  <qualifiers>
+			    <onlyEnumerators>True</onlyEnumerators>
+			    <enumerators>amore,phaser</enumerators>
+			    <default>phaser</default>
+	            <guiLabel>Rotation Search Program:</guiLabel>
+			  </qualifiers>
+			</content>
+            <content id="SIMBAD_NMOL">
+	            <className>CInt</className>
+	            <qualifiers>
+		              <guiLabel>Number of Molecules to place</guiLabel>
+		              <toolTip>Number of Molecules to place in MR step, set to 0 to select automatically</toolTip>
+		              <min>0</min>
+		              <default>1</default>
+	            </qualifiers>
+            </content>
         </container>
         <container id="controlParameters">
         </container>

i2/SIMBAD.medline.txt

@@ -0,0 +1,38 @@
+PMID- 29968670
+AU  - A. J. SIMPKIN
+AU  - F. SIMKOVIC
+AU  - J. J. THOMAS
+AU  - M. SAVKO
+AU  - A. LEBEDEV
+AU  - V. USKI
+AU  - C. BALLARD
+AU  - M. WOJDYR
+AU  - R. WU
+AU  - R. SANISHVILI
+AU  - Y. XU
+AU  - L. MARIA-NATALIA
+AU  - A. BUSCHIAZZO
+AU  - W. SHEPARD
+AU  - D. J. RIGDEN
+AU  - R. M. KEEGAN
+TI  - SIMBAD: a sequence-independent molecular-replacement pipeline
+SO  - Acta Crystallographica Section D 2018;74(7):595-605
+UR  - https://doi.org/10.1107/S2059798318005752
+N1  - doi:10.1107/S2059798318005752
+
+PMID- 31909738
+AU  - A. J. SIMPKIN
+AU  - F. SIMKOVIC
+AU  - J. J. THOMAS
+AU  - M. SAVKO
+AU  - A. LEBEDEV
+AU  - V. USKI
+AU  - C. BALLARD
+AU  - M. WOJDYR
+AU  - W. SHEPARD
+AU  - D. J. RIGDEN
+AU  - R. M. KEEGAN
+TI  - Using Phaser and ensembles to improve the performance of SIMBAD
+SO  - Acta Crystallographica Section D 2020;76(1):1-8
+UR  - https://doi.org/10.1107/S2059798319015031
+N1  - doi:10.1107/S2059798319015031