Merge pull request #232 from Jhsmit/web_plots

Plot updates

.github/workflows/pytest.yml

@@ -23,8 +23,7 @@ jobs:
         pip install codecov
         pip install pytest
         pip install pytest-cov
-        pip install -r requirements.txt
-        pip install -e .
+        pip install -e .[web,pdf]
     - name: Test with pytest
       run: |
         pytest --cov=./

dev/gui/dev_gui_secB.py

@@ -9,54 +9,58 @@
 import pickle
 from pyhdx.web.apps import main_app
 from pyhdx.web.base import DEFAULT_COLORS, STATIC_DIR
+from pyhdx.web.utils import load_state
 from pyhdx.web.sources import DataSource
 from pyhdx.batch_processing import yaml_to_hdxm
 from pyhdx.fileIO import csv_to_protein
 import panel as pn
 import numpy as np
 from pathlib import Path
 import pandas as pd
+import yaml
 
 ctrl = main_app()
 directory = Path(__file__).parent
 root_dir = directory.parent.parent
-data_dir = root_dir / 'tests' / 'test_data'
+data_dir = root_dir / 'tests' / 'test_data' / 'input'
 test_dir = directory / 'test_data'
 
 fpath_1 = root_dir / 'tests' / 'test_data' / 'ecSecB_apo.csv'
 fpath_2 = root_dir / 'tests' / 'test_data' / 'ecSecB_dimer.csv'
 
-fpaths = [fpath_1, fpath_2]
-files = [p.read_bytes() for p in fpaths]
+yaml_dict = yaml.safe_load(Path(data_dir / 'data_states.yaml').read_text())
 
+# fpaths = [fpath_1, fpath_2]
+# files = [p.read_bytes() for p in fpaths]
+#
+#
+# d1 = {
+#     'filenames': ['ecSecB_apo.csv', 'ecSecB_dimer.csv'],
+#     'd_percentage': 95,
+#     'control': ('Full deuteration control', 0.167),
+#     'series_name': 'SecB WT apo',
+#     'temperature': 30,
+#     'temperature_unit': 'celsius',
+#     'pH': 8.,
+#     'c_term': 165
+# }
+#
+# d2 = {
+#     'filenames': ['ecSecB_apo.csv', 'ecSecB_dimer.csv'],
+#     'd_percentage': 95,
+#     'control': ('Full deuteration control', 0.167),
+#     'series_name': 'SecB his dimer apo',
+#     'temperature': 30,
+#     'temperature_unit': 'celsius',
+#     'pH': 8.,
+#     'c_term': 165
+# }
 
-d1 = {
-    'filenames': ['ecSecB_apo.csv', 'ecSecB_dimer.csv'],
-    'd_percentage': 95,
-    'control': ('Full deuteration control', 0.167),
-    'series_name': 'SecB WT apo',
-    'temperature': 30,
-    'temperature_unit': 'celsius',
-    'pH': 8.,
-    'c_term': 165
-}
-
-d2 = {
-    'filenames': ['ecSecB_apo.csv', 'ecSecB_dimer.csv'],
-    'd_percentage': 95,
-    'control': ('Full deuteration control', 0.167),
-    'series_name': 'SecB his dimer apo',
-    'temperature': 30,
-    'temperature_unit': 'celsius',
-    'pH': 8.,
-    'c_term': 165
-}
-
-yaml_dicts = {'testname_123': d1, 'SecB his dimer apo': d2}
+#yaml_dicts = {'testname_123': d1, 'SecB his dimer apo': d2}
 
 
 def reload_dashboard():
-    data_objs = {k: yaml_to_hdxm(v, data_dir=data_dir) for k, v in yaml_dicts.items()}
+    data_objs = {k: yaml_to_hdxm(v, data_dir=data_dir) for k, v in yaml_dict.items()}
     for k, v in data_objs.items():
         v.metadata['name'] = k
     ctrl.data_objects = data_objs
@@ -96,21 +100,24 @@ def reload_dashboard():
 
 
 def init_dashboard():
-    file_input = ctrl.control_panels['PeptideFileInputControl']
-    file_input.input_files = files
-    file_input.fd_state = 'Full deuteration control'
-    file_input.fd_exposure = 0.167*60
-    file_input.pH = 8
-    file_input.temperature = 273.15 + 30
-    file_input.d_percentage = 90.
-
-    file_input.exp_state = 'SecB WT apo'
-    file_input.dataset_name = 'SecB_tetramer'
-    file_input._action_add_dataset()
-
-    file_input.exp_state = 'SecB his dimer apo'
-    file_input.dataset_name = 'SecB_dimer'  # todo catch error duplicate name
-    file_input._action_add_dataset()
+    for k, v in yaml_dict.items():
+        load_state(ctrl, v, data_dir=data_dir, name=k)
+
+    # file_input = ctrl.control_panels['PeptideFileInputControl']
+    # file_input.input_files = files
+    # file_input.fd_state = 'Full deuteration control'
+    # file_input.fd_exposure = 0.167*60
+    # file_input.pH = 8
+    # file_input.temperature = 273.15 + 30
+    # file_input.d_percentage = 90.
+    #
+    # file_input.exp_state = 'SecB WT apo'
+    # file_input.dataset_name = 'SecB_tetramer'
+    # file_input._action_add_dataset()
+    #
+    # file_input.exp_state = 'SecB his dimer apo'
+    # file_input.dataset_name = 'SecB_dimer'  # todo catch error duplicate name
+    # file_input._action_add_dataset()
 
     # initial_guess = ctrl.control_panels['InitialGuessControl']
     # initial_guess._action_fit()

pyhdx/__init__.py

@@ -1,10 +1,10 @@
-from .models import PeptideMasterTable, PeptideMeasurements, HDXMeasurement, Coverage, HDXMeasurementSet
+from .models import PeptideMasterTable, HDXTimepoint, HDXMeasurement, Coverage, HDXMeasurementSet
 from .fileIO import read_dynamx
-from .fitting_torch import TorchSingleFitResult, TorchBatchFitResult
+from .fitting_torch import TorchFitResult
 from ._version import get_versions
 
 try:
-    from .output import Output, Report
+    from .output import FitReport
 except ModuleNotFoundError:
     pass
 

pyhdx/batch_processing.py

@@ -4,7 +4,8 @@
 
 
 time_factors = {"s": 1, "m": 60., "min": 60., "h": 3600, "d": 86400}
-temperature_offsets = {'C': 273.15, 'celsius': 273.15, 'K': 0, 'kelvin': 0}
+temperature_offsets = {'c': 273.15, 'celsius': 273.15, 'k': 0, 'kelvin': 0}
+
 
 def yaml_to_hdxmset(yaml_dict, data_dir=None, **kwargs):
     """reads files according to `yaml_dict` spec from `data_dir into HDXMEasurementSet"""

pyhdx/config.ini

@@ -5,3 +5,16 @@ n_workers = 10
 [fitting]
 dtype = float64
 device = cpu
+
+[plotting]
+# Sizes are in mm
+ncols = 2
+page_width = 160
+cbar_width = 2.5
+peptide_coverage_aspect = 3
+peptide_mse_aspect = 3
+residue_scatter_aspect = 3
+deltaG_aspect = 2.5
+linear_bars_aspect=30
+loss_aspect = 2.5
+rainbow_aspect = 4

pyhdx/config.py

@@ -74,6 +74,15 @@ def get(self, *args, **kwargs):
         """configparser get"""
         return self._config.get(*args, **kwargs)
 
+    def getint(self, *args, **kwargs):
+        return self._config.getint(*args, **kwargs)
+
+    def getfloat(self, *args, **kwargs):
+        return self._config.getfloat(*args, **kwargs)
+
+    def getboolean(self, *args, **kwargs):
+        return self._config.getboolean(*args, **kwargs)
+
     def set(self, *args, **kwargs):
         """configparser set"""
         self._config.set(*args, **kwargs)

pyhdx/fileIO.py

@@ -18,6 +18,8 @@
 PEPTIDE_DTYPES = {
     'start': int,
     'end': int,
+    '_start': int,
+    '_end': int
 }
 
 
@@ -196,7 +198,7 @@ def csv_to_hdxm(filepath_or_buffer, comment='#', **kwargs):
     if df.columns.nlevels == 2:
         hdxm_list = []
         for state in df.columns.unique(level=0):
-            subdf = df[state].dropna(how='all')
+            subdf = df[state].dropna(how='all').astype(PEPTIDE_DTYPES)
             m = metadata.get(state, {})
             hdxm = pyhdx.models.HDXMeasurement(subdf, **m)
             hdxm_list.append(hdxm)
@@ -343,10 +345,10 @@ def save_fitresult(output_dir, fit_result, log_lines=None):
     dataframe_to_file(output_dir / 'losses.csv', fit_result.losses)
     dataframe_to_file(output_dir / 'losses.txt', fit_result.losses, fmt='pprint')
 
-    if isinstance(fit_result.data_obj, pyhdx.HDXMeasurement):
-        fit_result.data_obj.to_file(output_dir / 'HDXMeasurement.csv')
-    if isinstance(fit_result.data_obj, pyhdx.HDXMeasurementSet):
-        fit_result.data_obj.to_file(output_dir / 'HDXMeasurements.csv')
+    if isinstance(fit_result.hdxm_set, pyhdx.HDXMeasurement):
+        fit_result.hdxm_set.to_file(output_dir / 'HDXMeasurement.csv')
+    if isinstance(fit_result.hdxm_set, pyhdx.HDXMeasurementSet):
+        fit_result.hdxm_set.to_file(output_dir / 'HDXMeasurements.csv')
 
     loss = f'Total_loss {fit_result.total_loss:.2f}, mse_loss {fit_result.mse_loss:.2f}, reg_loss {fit_result.reg_loss:.2f}' \
            f'({fit_result.regularization_percentage:.2f}%)'
@@ -379,12 +381,9 @@ def load_fitresult(fit_dir):
     if pth.is_dir():
         fit_result = csv_to_dataframe(fit_dir / 'fit_result.csv')
         losses = csv_to_dataframe(fit_dir / 'losses.csv')
-        try:
-            data_obj = csv_to_hdxm(fit_dir / 'HDXMeasurement.csv')
-            result_klass = pyhdx.fitting_torch.TorchSingleFitResult
-        except FileNotFoundError:
-            data_obj = csv_to_hdxm(fit_dir / 'HDXMeasurements.csv')
-            result_klass = pyhdx.fitting_torch.TorchBatchFitResult
+
+        data_obj = csv_to_hdxm(fit_dir / 'HDXMeasurements.csv')
+        result_klass = pyhdx.fitting_torch.TorchFitResult
     elif pth.is_file():
         raise DeprecationWarning('`load_fitresult` only loads from fit result directories')
         fit_result = csv_to_dataframe(fit_dir)