Merge branch 'jgreer/het_metrics' of github.com:ccpem/roodmus into jg…

…reer/het_metrics

.readthedocs.yaml

@@ -0,0 +1,41 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.10"
+    # You can also specify other tool versions:
+    # nodejs: "19"
+    # rust: "1.64"
+    # golang: "1.19"
+
+python:
+  install:
+    # See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html (optional)
+    - requirements: docs/requirements.txt
+    # Install our python package before building the docs
+    # - method: pip
+    #   path: .
+
+# Build documentation in the "docs/" directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+  fail_on_warning: false
+
+# Optionally build your docs in additional formats such as PDF and ePub
+formats:
+   - pdf
+   - epub
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
+# python:
+#    install:
+#    - requirements: docs/requirements.txt

docs/requirements.txt

@@ -0,0 +1,2 @@
+sphinx
+sphinx-rtd-theme

docs/source/api.rst

@@ -0,0 +1,4 @@
+.. autosummary::
+   :toctree: generated
+
+   roodmus

docs/source/conf.py

@@ -0,0 +1,42 @@
+# Configuration file for the Sphinx documentation builder.
+
+# -- Project information
+
+project = "Roodmus"
+copyright = "2023, Joel Greer(UKRI), Tom Burnley (UKRI),\
+    Maarten Joosten (TU Delft), Arjen Jakobi (TU Delft)"
+author = "Joel Greer, Maarten Joosten, Tom Burnley, Arjen Jakobi"
+
+release = "0.2"
+version = "0.0.28"
+
+# -- General configuration
+
+extensions = [
+    "sphinx.ext.duration",
+    "sphinx.ext.doctest",
+    "sphinx.ext.autodoc",
+    "sphinx.ext.autosummary",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.napoleon",
+]
+
+intersphinx_mapping = {
+    "python": ("https://docs.python.org/3/", None),
+    "sphinx": ("https://www.sphinx-doc.org/en/master/", None),
+}
+intersphinx_disabled_domains = ["std"]
+
+templates_path = ["_templates"]
+
+# -- Options for HTML output
+
+html_theme = "sphinx_rtd_theme"
+
+# -- Options for EPUB output
+epub_show_urls = "footnote"
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]

docs/source/explanation.rst

@@ -0,0 +1,4 @@
+How Roodmus Works
+=================
+
+Information allowing you to be confident in how Roodmus works "behind-the-scenes".

docs/source/how-to-guides.rst

@@ -0,0 +1,4 @@
+How To Guides
+=============
+
+How to use/extend Roodmus to do various tasks.

docs/source/index.rst

@@ -0,0 +1,19 @@
+Roodmus Docs
+============
+
+Roodmus is software for doing stuff...
+
+.. note::
+
+   This project is under active development.
+
+Contents
+--------
+
+.. toctree::
+
+   tutorials
+   how-to-guides
+   explanation
+   reference
+   api

docs/source/reference.rst

@@ -0,0 +1,4 @@
+Reference
+=========
+
+Useful reference information germane to Roodmus

docs/source/tutorials.rst

@@ -0,0 +1,4 @@
+Tutorials
+=========
+
+How to use Roodmus utilities

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "roodmus"
-version = "0.0.27"
+version = "0.0.29"
 authors = [
   { name="Joel Greer", email="[email protected]" },
   { name="Maarten Joosten", email="[email protected]" },
@@ -58,6 +58,7 @@ dependencies = [
   "fqdn==1.5.1",
   "fsspec==2023.1.0",
   "gemmi==0.5.4",
+  "gemmi-program==0.6.5",
   "glob2==0.7",
   "guanaco==0.3.0",
   "h5py==3.8.0",

src/roodmus/cli.py

@@ -43,6 +43,7 @@
 import roodmus.heterogeneity.het_metrics
 import roodmus.heterogeneity.latent_clustering
 import roodmus.heterogeneity.het_ensemblecomparison
+import roodmus.heterogeneity.remove_hydrogens
 
 # import analysis.analyse_alignment
 
@@ -84,12 +85,14 @@ def main():
         roodmus.heterogeneity.het_metrics,
         roodmus.heterogeneity.latent_clustering,
         roodmus.heterogeneity.het_ensemblecomparison,
+        roodmus.heterogeneity.remove_hydrogens,
     ]
 
     module_helptext = [
         "Sampling a molecular dynamics trajectory and saving the"
         + " conformations to PDB files.",
         "Simulation of micrograph/tomogram dataset using Parakeet software.",
+        "Write out a particle stack using picked particle coordinates",
         "Plot a comparison between the estimated CTF parameters and the"
         + " true values used in data generation.",
         "Plot statistics from picking analyses and overlays of"
@@ -107,6 +110,7 @@ def main():
         "Calculation of Jensen-Shannon divergence between ensembles"
         + " identified through clustering of MD trajectory(ies)"
         + " and/or clustering of latent spaces representing heterogeneity",
+        "Remove hydrogens from pdb file(s)",
     ]
 
     for helptext, module in zip(module_helptext, modules):

src/roodmus/heterogeneity/het_ensemblecomparison.py

@@ -40,7 +40,10 @@
 import matplotlib.pyplot as plt
 
 from roodmus.analysis.utils import load_data
-from roodmus.heterogeneity.het_metrics import get_pdb_list
+from roodmus.heterogeneity.het_metrics import (
+    get_pdb_list,
+    select_confs,
+)
 
 # import os
 # import pandas as pd
@@ -398,21 +401,21 @@ def __init__(
 
     def compute_ces_stats(self):
         if self.ces:
-            self.ces_avg = np.average(
-                np.array(self.ces, dtype=float), axis=0
-            ).tolist()
-            self.ces_stddev = np.std(
-                np.array(self.ces, dtype=float), axis=0
-            ).tolist()
+            self.ces_avg = np.array(
+                np.average(np.array(self.ces, dtype=float), axis=0)[0][:][:]
+            )
+            self.ces_stddev = np.array(
+                np.std(np.array(self.ces, dtype=float), axis=0)[0][:][:]
+            )
 
     def compute_dres_stats(self):
         if self.dres:
-            self.dres_avg = np.average(
-                np.array(self.dres, dtype=float), axis=0
-            ).tolist()
-            self.dres_stddev = np.std(
-                np.array(self.dres, dtype=float), axis=0
-            ).tolist()
+            self.dres_avg = np.array(
+                np.average(np.array(self.dres, dtype=float), axis=0)[0][:][:]
+            )
+            self.dres_stddev = np.array(
+                np.std(np.array(self.dres, dtype=float), axis=0)[0][:][:]
+            )
 
     def plot_ces_results(self):
         cw = []
@@ -721,36 +724,16 @@ def main(args):
         assert source == "MD" or source == "latent"
 
     # get the conformation filenames
-    conformation_filenames = sorted(get_pdb_list(args.conformations_dir))
-    if args.n_confs and args.contiguous_confs:
-        if args.n_confs > len(conformation_filenames):
-            raise ValueError(
-                "Trying to sample {} confs from {} files!".format(
-                    args.n_confs, len(conformation_filenames)
-                )
-            )
-        conformation_filenames = conformation_filenames[
-            args.first_conf : args.first_conf + args.n_confs
-        ]
-    elif args.n_confs:
-        # get every nth sample depending on n_confs requested
-        if (len(conformation_filenames) - args.first_conf) < args.n_confs:
-            raise ValueError(
-                "Trying to sample {} confs from {} remaining! Error!".format(
-                    args.n_confs,
-                    len(conformation_filenames) - args.first_conf,
-                )
-            )
-        else:
-            sample_indices = np.arange(
-                args.first_conf,
-                len(conformation_filenames),
-                (len(conformation_filenames) - args.first_conf) / args.n_confs,
-            ).astype(int)
-            conformation_filenames = np.array(
-                conformation_filenames, dtype=str
-            )[sample_indices].tolist()
-    assert len(conformation_filenames) > 0
+    conformation_filenames = get_pdb_list(
+        args.conformations_dir,
+        args.file_ext,
+    )
+    conformation_filenames = select_confs(
+        conformation_filenames,
+        args.n_confs,
+        args.first_conf,
+        args.contiguous_confs,
+    )
 
     # TODO replace/update setting of these values
     particle_diameter = 100  # approximate particle diameter in Angstroms