fix merge conflicts

alphastats/gui/pages/02_Import Data.py

@@ -18,6 +18,7 @@
     sidebar_info,
     empty_session_state,
     init_session_state,
+    StateKeys,
 )
 
 
@@ -27,11 +28,11 @@ def _finalize_data_loading(
     dataset: DataSet,
 ) -> None:
     """Finalize the data loading process."""
-    st.session_state["loader"] = (
+    st.session_state[StateKeys.LOADER] = (
         loader  # TODO: Figure out if we even need the loader here, as the dataset has the loader as an attribute.
     )
-    st.session_state["metadata_columns"] = metadata_columns
-    st.session_state["dataset"] = dataset
+    st.session_state[StateKeys.METADATA_COLUMNS] = metadata_columns
+    st.session_state[StateKeys.DATASET] = dataset
 
     load_options()
     sidebar_info()
@@ -64,7 +65,7 @@ def _finalize_data_loading(
 
 
 st.markdown("### Import Proteomics Data")
-if "dataset" in st.session_state:
+if StateKeys.DATASET in st.session_state:
     st.info(f"DataSet already present.")
     st.page_link("pages/03_Data Overview.py", label="=> Go to data overview page..")
     st.stop()

alphastats/gui/pages/03_Data Overview.py

@@ -7,18 +7,18 @@
     get_intensity_distribution_unprocessed,
     display_loaded_dataset,
 )
-from alphastats.gui.utils.ui_helper import sidebar_info, init_session_state
+from alphastats.gui.utils.ui_helper import sidebar_info, init_session_state, StateKeys
 
 init_session_state()
 sidebar_info()
 
-if "dataset" not in st.session_state:
+if StateKeys.DATASET not in st.session_state:
     st.info("Import Data first")
     st.stop()
 
 st.markdown("### DataSet Info")
 
-display_loaded_dataset(st.session_state["dataset"])
+display_loaded_dataset(st.session_state[StateKeys.DATASET])
 
 st.markdown("## DataSet overview")
 

alphastats/gui/pages/03_Preprocessing.py

@@ -11,13 +11,13 @@
     reset_preprocessing,
     PREPROCESSING_STEPS,
 )
-from alphastats.gui.utils.ui_helper import sidebar_info, init_session_state
+from alphastats.gui.utils.ui_helper import sidebar_info, init_session_state, StateKeys
 
 init_session_state()
 sidebar_info()
 
-if "workflow" not in st.session_state:
-    st.session_state["workflow"] = [
+if StateKeys.WORKFLOW not in st.session_state:
+    st.session_state[StateKeys.WORKFLOW] = [
         PREPROCESSING_STEPS.REMOVE_CONTAMINATIONS,
         PREPROCESSING_STEPS.SUBSET,
         PREPROCESSING_STEPS.LOG2_TRANSFORM,
@@ -27,29 +27,33 @@
 c1, c2 = st.columns([1, 1])
 
 with c2:
-    if "dataset" in st.session_state:
-        settings = configure_preprocessing(dataset=st.session_state["dataset"])
+    if StateKeys.DATASET in st.session_state:
+        settings = configure_preprocessing(dataset=st.session_state[StateKeys.DATASET])
         new_workflow = update_workflow(settings)
-        if new_workflow != st.session_state.workflow:
-            st.session_state.workflow = new_workflow
+        if new_workflow != st.session_state[StateKeys.WORKFLOW]:
+            st.session_state[StateKeys.WORKFLOW] = new_workflow
 
 with c1:
     st.write("#### Flowchart of preprocessing workflow:")
 
-    selected_nodes = draw_workflow(st.session_state.workflow)
+    selected_nodes = draw_workflow(st.session_state[StateKeys.WORKFLOW])
 
-    if "dataset" not in st.session_state:
+    if StateKeys.DATASET not in st.session_state:
         st.info("Import data first to configure and run preprocessing")
 
     else:
         c11, c12 = st.columns([1, 1])
         if c11.button("Run preprocessing", key="_run_preprocessing"):
-            run_preprocessing(settings, st.session_state["dataset"])
+            run_preprocessing(settings, st.session_state[StateKeys.DATASET])
             # TODO show more info about the preprocessing steps
-            display_preprocessing_info(st.session_state["dataset"].preprocessing_info)
+            display_preprocessing_info(
+                st.session_state[StateKeys.DATASET].preprocessing_info
+            )
 
         if c12.button("Reset all Preprocessing steps", key="_reset_preprocessing"):
-            reset_preprocessing(st.session_state["dataset"])
-            display_preprocessing_info(st.session_state["dataset"].preprocessing_info)
+            reset_preprocessing(st.session_state[StateKeys.DATASET])
+            display_preprocessing_info(
+                st.session_state[StateKeys.DATASET].preprocessing_info
+            )
 
 # TODO: Add comparison plot of intensity distribution before and after preprocessing

alphastats/gui/pages/04_Analysis.py

@@ -4,6 +4,7 @@
     sidebar_info,
     init_session_state,
     convert_df,
+    StateKeys,
 )
 from alphastats.gui.utils.analysis_helper import (
     get_analysis,
@@ -24,8 +25,8 @@ def select_analysis():
     load_options()
     method = st.selectbox(
         "Analysis",
-        options=list(st.session_state.plotting_options.keys())
-        + list(st.session_state.statistic_options.keys()),
+        options=list(st.session_state[StateKeys.PLOTTING_OPTIONS].keys())
+        + list(st.session_state[StateKeys.STATISTIC_OPTIONS].keys()),
     )
     return method
 
@@ -50,11 +51,11 @@ def select_analysis():
 st.markdown(styl, unsafe_allow_html=True)
 
 
-if "plot_list" not in st.session_state:
-    st.session_state["plot_list"] = []
+if StateKeys.PLOT_LIST not in st.session_state:
+    st.session_state[StateKeys.PLOT_LIST] = []
 
 
-if "dataset" in st.session_state:
+if StateKeys.DATASET in st.session_state:
     c1, c2 = st.columns((1, 2))
 
     plot_to_display = False
@@ -64,15 +65,16 @@ def select_analysis():
     with c1:
         method = select_analysis()
 
-        if method in st.session_state.plotting_options.keys():
+        if method in st.session_state[StateKeys.PLOTTING_OPTIONS].keys():
             analysis_result = get_analysis(
-                method=method, options_dict=st.session_state.plotting_options
+                method=method, options_dict=st.session_state[StateKeys.PLOTTING_OPTIONS]
             )
             plot_to_display = True
 
-        elif method in st.session_state.statistic_options.keys():
+        elif method in st.session_state[StateKeys.STATISTIC_OPTIONS].keys():
             analysis_result = get_analysis(
-                method=method, options_dict=st.session_state.statistic_options
+                method=method,
+                options_dict=st.session_state[StateKeys.STATISTIC_OPTIONS],
             )
             df_to_display = True
 

alphastats/gui/pages/05_LLM.py

@@ -25,7 +25,6 @@
 
 init_session_state()
 sidebar_info()
-st.session_state[StateKeys.PLOT_DICT] = {}
 
 
 @check_if_options_are_loaded

alphastats/gui/pages/06_Results.py

@@ -6,6 +6,7 @@
     sidebar_info,
     init_session_state,
     convert_df,
+    StateKeys,
 )
 
 
@@ -44,8 +45,8 @@ def download_preprocessing_info(plot, name, count):
 st.markdown("### Results")
 
 
-if "plot_list" in st.session_state:
-    for count, plot in enumerate(st.session_state.plot_list):
+if StateKeys.PLOT_LIST in st.session_state:
+    for count, plot in enumerate(st.session_state[StateKeys.PLOT_LIST]):
         print("plot", type(plot), count)
         count = str(count)
 

alphastats/gui/utils/gpt_helper.py

@@ -9,7 +9,7 @@
 import streamlit as st
 
 from alphastats.plots.DimensionalityReduction import DimensionalityReduction
-
+from alphastats.gui.utils.ui_helper import StateKeys
 
 Entrez.email = "lebedev_mikhail@outlook.com"  # Always provide your email address when using NCBI services.
 
@@ -143,6 +143,10 @@ def get_assistant_functions(
     Returns:
         list[dict]: A list of assistant functions.
     """
+    # TODO figure out how this relates to the parameter `subgroups_for_each_group`
+    subgroups_for_each_group_ = str(
+        get_subgroups_for_each_group(st.session_state[StateKeys.DATASET].metadata)
+    )
     return [
         {
             "type": "function",
@@ -165,7 +169,8 @@ def get_assistant_functions(
                         "subgroups": {
                             "type": "array",
                             "items": {"type": "string"},
-                            "description": f"Specific subgroups within the group to analyze. For each group you need to look up the subgroups in the dict {str(get_subgroups_for_each_group(st.session_state['dataset'].metadata))} or present user with them first if you are not sure what to choose",
+                            "description": f"Specific subgroups within the group to analyze. For each group you need to look up the subgroups in the dict"
+                            f" {subgroups_for_each_group_} or present user with them first if you are not sure what to choose",
                         },
                         "method": {
                             "type": "string",
@@ -302,7 +307,7 @@ def get_assistant_functions(
 
 def perform_dimensionality_reduction(group, method, circle, **kwargs):
     dr = DimensionalityReduction(
-        st.session_state.dataset, group, method, circle, **kwargs
+        st.session_state[StateKeys.DATASET], group, method, circle, **kwargs
     )
     return dr.plot
 
@@ -339,11 +344,11 @@ def get_gene_to_prot_id_mapping(gene_id: str) -> str:
     import streamlit as st
 
     session_state_copy = dict(copy.deepcopy(st.session_state))
-    if "gene_to_prot_id" not in session_state_copy:
-        session_state_copy["gene_to_prot_id"] = {}
-    if gene_id in session_state_copy["gene_to_prot_id"]:
-        return session_state_copy["gene_to_prot_id"][gene_id]
-    for gene, prot_id in session_state_copy["gene_to_prot_id"].items():
+    if StateKeys.GENE_TO_PROT_ID not in session_state_copy:
+        session_state_copy[StateKeys.GENE_TO_PROT_ID] = {}
+    if gene_id in session_state_copy[StateKeys.GENE_TO_PROT_ID]:
+        return session_state_copy[StateKeys.GENE_TO_PROT_ID][gene_id]
+    for gene, prot_id in session_state_copy[StateKeys.GENE_TO_PROT_ID].items():
         if gene_id in gene.split(";"):
             return prot_id
     return gene_id

alphastats/gui/utils/import_helper.py

@@ -11,14 +11,15 @@
 from alphastats.DataSet import DataSet
 from alphastats.gui.utils.options import SOFTWARE_OPTIONS
 from alphastats.loader.MaxQuantLoader import MaxQuantLoader, BaseLoader
+from alphastats.gui.utils.ui_helper import StateKeys
 
 
 def load_options():
     # TODO move import to top
     from alphastats.gui.utils.options import plotting_options, statistic_options
 
-    st.session_state["plotting_options"] = plotting_options(st.session_state)
-    st.session_state["statistic_options"] = statistic_options(st.session_state)
+    st.session_state[StateKeys.PLOTTING_OPTIONS] = plotting_options(st.session_state)
+    st.session_state[StateKeys.STATISTIC_OPTIONS] = statistic_options(st.session_state)
 
 
 def load_proteomics_data(uploaded_file, intensity_column, index_column, software):