Sasbdb load

docs/sphinx-docs/source/user/menu_bar.rst

@@ -11,7 +11,8 @@ The File option allows you load data into *SasView* for analysis, or to save the
 Data can be loaded one file at a time, or by selecting multiple files, or by loading an entire folder of 
 files (in which case *SasView* will attempt to make an intelligent guess as to what to load based on the 
 file formats it recognises in the folder!). Data can also be loaded by dragging and dropping files directly
-onto Data Explorer.
+onto Data Explorer. Additionally, datasets can be downloaded directly from the SASBDB (Small Angle Scattering 
+Biological Data Bank) using **File > Load from SASBDB...** (see :ref:`SASBDB_Download` for details).
 
 A *SasView* session can also be saved and reloaded as an 'Analysis' (an individual model fit or invariant 
 calculation, etc), or as a 'Project' (everything you have done since starting your *SasView* session).

docs/sphinx-docs/source/user/tools.rst

@@ -32,3 +32,5 @@ Tools & Utilities
 
    MuMag Tool <qtgui/Utilities/MuMag/mumag_help>
 
+   SASBDB Download <qtgui/Utilities/SASBDB/sasbdb_download_help>
+

src/sas/qtgui/MainWindow/GuiManager.py

@@ -704,6 +704,7 @@ def addTriggers(self):
         # File
         self._workspace.actionLoadData.triggered.connect(self.actionLoadData)
         self._workspace.actionLoad_Data_Folder.triggered.connect(self.actionLoad_Data_Folder)
+        self._workspace.actionLoad_SASBDB.triggered.connect(self.actionLoad_SASBDB)
         self._workspace.actionOpen_Project.triggered.connect(self.actionOpen_Project)
         self._workspace.actionOpen_Analysis.triggered.connect(self.actionOpen_Analysis)
         self._workspace.actionSave.triggered.connect(self.actionSave_Project)
@@ -801,6 +802,238 @@ def actionLoad_Data_Folder(self):
         """
         self.filesWidget.loadFolder()
 
+    def actionLoad_SASBDB(self):
+        """
+        Menu File/Load from SASBDB
+
+        Opens a dialog to download and load a dataset from SASBDB.
+        """
+        from sas.qtgui.Utilities.SASBDB.SASBDBDownloadDialog import SASBDBDownloadDialog
+
+        dialog = SASBDBDownloadDialog(parent=self._workspace)
+        if dialog.exec():
+            # Get the downloaded file path and metadata
+            filepath = dialog.getDownloadedFilepath()
+            dataset_info = dialog.getDatasetInfo()
+
+            if filepath and os.path.exists(filepath):
+                try:
+                    # Load the downloaded file into SasView
+                    # readData returns (output_dict, message)
+                    loaded_data, load_message = self.filesWidget.readData([filepath])
+
+                    # Populate additional metadata from SASBDB into loaded data
+                    if dataset_info and loaded_data:
+                        self._populateSASBDBMetadata(loaded_data, dataset_info)
+
+                    # Log metadata summary
+                    if dataset_info:
+                        entry_id = dataset_info.code or dataset_info.entry_id
+                        logger.info(f"Successfully loaded SASBDB dataset {entry_id} from {filepath}")
+                        if dataset_info.title:
+                            logger.info(f"  Title: {dataset_info.title}")
+                        if dataset_info.rg is not None:
+                            logger.info(f"  Rg: {dataset_info.rg:.2f} Å")
+                        if dataset_info.molecular_weight is not None:
+                            logger.info(f"  MW: {dataset_info.molecular_weight:.1f} kDa")
+                    else:
+                        logger.info(f"Successfully loaded SASBDB dataset from {filepath}")
+
+                except Exception as e:
+                    logger.error(f"Error loading downloaded SASBDB dataset: {e}", exc_info=True)
+                    QMessageBox.warning(
+                        self._workspace,
+                        "Load Error",
+                        f"Failed to load downloaded dataset:\n{str(e)}"
+                    )
+
+    def _populateSASBDBMetadata(self, loaded_data: dict, dataset_info):
+        """
+        Populate SASBDB metadata into loaded data objects.
+
+        Updates the sample, source, and other metadata properties of loaded
+        data with information from SASBDB.
+
+        :param loaded_data: Dictionary of loaded data objects (keyed by id)
+        :param dataset_info: SASBDBDatasetInfo object with parsed metadata
+        """
+        from sasdata.dataloader.data_info import Sample, Source
+
+        for data_id, data in loaded_data.items():
+            try:
+                # Debug: log what we have in dataset_info
+                logger.debug(f"Populating metadata for {data_id}: molecule_name={dataset_info.molecule_name}, "
+                           f"sample_name={dataset_info.sample_name}, temperature={dataset_info.temperature}, "
+                           f"concentration={dataset_info.concentration}, buffer={dataset_info.buffer_description}")
+
+                # Update title
+                if dataset_info.title and not data.title:
+                    data.title = dataset_info.title
+
+                # Update instrument from SASBDB instrument metadata
+                if dataset_info.instrument and not data.instrument:
+                    data.instrument = dataset_info.instrument
+
+                # Update run info with SASBDB code
+                if dataset_info.code:
+                    if not data.run:
+                        data.run = []
+                    if dataset_info.code not in data.run:
+                        data.run.append(dataset_info.code)
+
+                # Populate sample information from Molecule metadata
+                if data.sample is None:
+                    data.sample = Sample()
+
+                # Ensure sample.details is initialized
+                if not hasattr(data.sample, 'details') or data.sample.details is None:
+                    data.sample.details = []
+
+                # Map molecule short name into Sample ID when available.
+                sample_id = ""
+                if dataset_info.molecule_short_name:
+                    sample_id = dataset_info.molecule_short_name
+                elif dataset_info.sample_name:
+                    # Fallback for entries without molecule short name.
+                    sample_id = dataset_info.sample_name
+                elif dataset_info.code:
+                    sample_id = dataset_info.code
+                if sample_id:
+                    data.sample.ID = sample_id
+                    logger.debug(f"Set sample.ID to: {sample_id}")
+
+                # Build human-readable sample details from remaining metadata.
+                sample_details = []
+                if dataset_info.molecule_name:
+                    molecule_str = f"Molecule: {dataset_info.molecule_name}"
+                    if dataset_info.molecule_type:
+                        molecule_str += f" ({dataset_info.molecule_type})"
+                    sample_details.append(molecule_str)
+                elif dataset_info.sample_name:
+                    sample_details.append(f"Sample: {dataset_info.sample_name}")
+
+                if dataset_info.sample_description:
+                    sample_details.append(
+                        f"Description: {dataset_info.sample_description}"
+                    )
+
+                if dataset_info.sequence:
+                    sample_details.append(f"Sequence: {dataset_info.sequence}")
+
+                if dataset_info.uniprot_code:
+                    sample_details.append(f"UniProt: {dataset_info.uniprot_code}")
+
+                oligomerization = (
+                    dataset_info.oligomerization or dataset_info.oligomeric_state
+                )
+                if oligomerization:
+                    sample_details.append(f"Oligomerization: {oligomerization}")
+
+                if dataset_info.number_of_molecules:
+                    sample_details.append(
+                        f"Number of molecules: {dataset_info.number_of_molecules}"
+                    )
+
+                if dataset_info.source_organism:
+                    sample_details.append(
+                        f"Source organism: {dataset_info.source_organism}"
+                    )
+
+                # Set temperature
+                if dataset_info.temperature is not None:
+                    data.sample.temperature = dataset_info.temperature
+                    if dataset_info.temperature_unit:
+                        data.sample.temperature_unit = dataset_info.temperature_unit
+                    logger.debug(f"Set sample.temperature to: {dataset_info.temperature} {dataset_info.temperature_unit}")
+                    temp_unit = dataset_info.temperature_unit or ""
+                    temp_str = f"Temperature: {dataset_info.temperature}"
+                    if temp_unit:
+                        temp_str += f" {temp_unit}"
+                    sample_details.append(temp_str)
+
+                # Store concentration in sample details
+                if dataset_info.concentration is not None:
+                    conc_str = f"Concentration: {dataset_info.concentration}"
+                    if dataset_info.concentration_unit:
+                        conc_str += f" {dataset_info.concentration_unit}"
+                    sample_details.append(conc_str)
+
+                # Add buffer info to sample details
+                if dataset_info.buffer_description:
+                    buffer_str = f"Buffer: {dataset_info.buffer_description}"
+                    if dataset_info.ph is not None:
+                        buffer_str += f" (pH {dataset_info.ph})"
+                    sample_details.append(buffer_str)
+
+                for detail in sample_details:
+                    if detail and detail not in data.sample.details:
+                        data.sample.details.append(detail)
+                        logger.debug(f"Added to sample.details: {detail}")
+
+                # Log sample info for debugging
+                logger.debug(f"Sample populated for {data_id}: name={getattr(data.sample, 'name', None)}, "
+                           f"temperature={getattr(data.sample, 'temperature', None)}, "
+                           f"details={getattr(data.sample, 'details', [])}")
+
+                # Populate source information
+                if data.source is None:
+                    data.source = Source()
+
+                if dataset_info.wavelength is not None:
+                    data.source.wavelength = dataset_info.wavelength
+                    data.source.wavelength_unit = dataset_info.wavelength_unit
+
+                # Store additional SASBDB metadata in meta_data dictionary
+                if not hasattr(data, 'meta_data') or data.meta_data is None:
+                    data.meta_data = {}
+
+                # SASBDB-specific metadata
+                data.meta_data['SASBDB_code'] = dataset_info.code or dataset_info.entry_id
+
+                if dataset_info.rg is not None:
+                    data.meta_data['SASBDB_Rg'] = dataset_info.rg
+                    if dataset_info.rg_error is not None:
+                        data.meta_data['SASBDB_Rg_error'] = dataset_info.rg_error
+
+                if dataset_info.i0 is not None:
+                    data.meta_data['SASBDB_I0'] = dataset_info.i0
+                    if dataset_info.i0_error is not None:
+                        data.meta_data['SASBDB_I0_error'] = dataset_info.i0_error
+
+                if dataset_info.dmax is not None:
+                    data.meta_data['SASBDB_Dmax'] = dataset_info.dmax
+
+                if dataset_info.molecular_weight is not None:
+                    data.meta_data['SASBDB_MW'] = dataset_info.molecular_weight
+                    if dataset_info.molecular_weight_method:
+                        data.meta_data['SASBDB_MW_method'] = dataset_info.molecular_weight_method
+
+                if dataset_info.porod_volume is not None:
+                    data.meta_data['SASBDB_Porod_volume'] = dataset_info.porod_volume
+
+                if dataset_info.molecule_name:
+                    data.meta_data['SASBDB_molecule'] = dataset_info.molecule_name
+
+                if dataset_info.molecule_type:
+                    data.meta_data['SASBDB_molecule_type'] = dataset_info.molecule_type
+
+                if dataset_info.oligomeric_state:
+                    data.meta_data['SASBDB_oligomeric_state'] = dataset_info.oligomeric_state
+
+                if dataset_info.publication_doi:
+                    data.meta_data['SASBDB_DOI'] = dataset_info.publication_doi
+
+                if dataset_info.publication_pmid:
+                    data.meta_data['SASBDB_PMID'] = dataset_info.publication_pmid
+
+                if dataset_info.authors:
+                    data.meta_data['SASBDB_authors'] = ', '.join(dataset_info.authors)
+
+                logger.debug(f"Populated SASBDB metadata for data: {data_id}")
+
+            except Exception as e:
+                logger.warning(f"Error populating metadata for data {data_id}: {e}")
+
     def actionOpen_Project(self):
         """
         Menu Open Project

src/sas/qtgui/MainWindow/UI/MainWindowUI.ui

@@ -33,6 +33,7 @@
     </property>
     <addaction name="actionLoadData"/>
     <addaction name="actionLoad_Data_Folder"/>
+    <addaction name="actionLoad_SASBDB"/>
     <addaction name="separator"/>
     <addaction name="actionOpen_Project"/>
     <addaction name="actionOpen_Analysis"/>
@@ -310,6 +311,18 @@
     <string>Load Data Folder</string>
    </property>
   </action>
+  <action name="actionLoad_SASBDB">
+   <property name="icon">
+    <iconset>
+     <normaloff>:/res/file_send-128.png</normaloff>:/res/file_send-128.png</iconset>
+   </property>
+   <property name="text">
+    <string>Load from SASBDB...</string>
+   </property>
+   <property name="toolTip">
+    <string>Download and load dataset from SASBDB</string>
+   </property>
+  </action>
   <action name="actionOpen_Project">
    <property name="text">
     <string>Open Project</string>