diff --git a/docs/api_examples/Download_PRIDE_data.py b/docs/api_examples/Download_PRIDE_data.py
index f029355..9ca219d 100644
--- a/docs/api_examples/Download_PRIDE_data.py
+++ b/docs/api_examples/Download_PRIDE_data.py
@@ -17,7 +17,7 @@
 # This notebook shows how `acore` can be used to download data from
 # the Proteomics Identifications Database - PRIDE -
 # ([ebi.ac.uk/pride/](https://www.ebi.ac.uk/pride/))
-# and parse the data to be used in the analytics core.
+# and parse the data to be used in the analytics core
 # and quickly formated to start analyzing them with the functionality in the analytics core.
 #
 # > based on CKG recipe: [Download PRIDE Data](https://ckg.readthedocs.io/en/latest/notebooks/recipes/Download_PRIDE_data.html)
@@ -36,7 +36,7 @@
 # %% [markdown]
 # ## Parameters
 # Specify the PRIDE identifier and file to be downloaded
-# - and where to store intermediate files.
+# and where to store intermediate files.
 
 # %% tags=["parameters"]
 pxd_id: str = "PXD008541"  # PRIDE identifier
diff --git a/docs/api_examples/enrichment_analysis.ipynb b/docs/api_examples/enrichment_analysis.ipynb
index 17e96d8..12b30fa 100644
--- a/docs/api_examples/enrichment_analysis.ipynb
+++ b/docs/api_examples/enrichment_analysis.ipynb
@@ -8,15 +8,17 @@
    },
    "source": [
     "# Enrichment analysis\n",
+    "requires\n",
+    "- some cluster of proteins/genes (e.g. up- and downregulated proteins/genes)\n",
+    "- functional annotations, i.e. a category summarizing a set of proteins/genes.\n",
     "\n",
-    "- we need some groups of genes to compute clusters\n",
-    "- we need functional annotations, i.e. a category summarizing a set of genes.\n",
-    "-\n",
     "You can start with watching Lars Juhl Jensen's brief introduction to enrichment analysis\n",
     "on [youtube](https://www.youtube.com/watch?v=2NC1QOXmc5o).\n",
     "\n",
-    "Use example data for ovarian cancer\n",
-    "([PXD010372](https://github.com/Multiomics-Analytics-Group/acore/tree/main/example_data/PXD010372))"
+    "Here we use as example data from an ovarian cancer dataset:\n",
+    "[PXD010372](https://github.com/Multiomics-Analytics-Group/acore/tree/main/example_data/PXD010372)\n",
+    "\n",
+    "First make sure you have the required packages installed:"
    ]
   },
   {
@@ -24,14 +26,13 @@
    "execution_count": null,
    "id": "956ed7b7",
    "metadata": {
-    "lines_to_next_cell": 2,
     "tags": [
      "hide-output"
     ]
    },
    "outputs": [],
    "source": [
-    "%pip install acore vuecore"
+    "%pip install acore vuecore 'plotly<6'"
    ]
   },
   {
@@ -49,7 +50,6 @@
     "import acore\n",
     "import acore.differential_regulation\n",
     "import acore.enrichment_analysis\n",
-    "from acore.io.uniprot import fetch_annotations\n",
     "\n",
     "dsp_pandas.format.set_pandas_options(max_colwidth=60)"
    ]
@@ -88,7 +88,9 @@
    "id": "10ed1830",
    "metadata": {},
    "source": [
-    "# Load processed data"
+    "# Load processed data\n",
+    "from our repository. See details on obtaining the data under the example data section on\n",
+    "[this page](nb_ref_ovarian_data)"
    ]
   },
   {
@@ -111,7 +113,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "ax = df_omics.notna().sum().sort_values(ascending=True).plot()"
+    "ax = (\n",
+    "    df_omics.notna()\n",
+    "    .sum()\n",
+    "    .sort_values(ascending=True)\n",
+    "    .plot(xlabel=\"Protein groups\", ylabel=\"Number of non-NaN values (samples)\")\n",
+    ")"
    ]
   },
   {
@@ -120,7 +127,7 @@
    "metadata": {},
    "source": [
     "Keep only features with a certain amount of non-NaN values and select 100 of these\n",
-    "for illustration. Add the ones which were differently regulated in the ANOVA using all\n",
+    "for illustration. Add always four which were differently regulated in the ANOVA using all\n",
     "the protein groups."
    ]
   },
@@ -131,8 +138,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "idx_always_included = [\"Q5HYN5\", \"P39059\", \"O43432\", \"O43175\"]\n",
-    "df_omics[idx_always_included]"
+    "idx_always_included = [\"Q5HYN5\", \"P39059\", \"O43432\", \"O43175\"]"
    ]
   },
   {
@@ -140,7 +146,6 @@
    "execution_count": null,
    "id": "1145a2cd",
    "metadata": {
-    "lines_to_next_cell": 2,
     "tags": [
      "hide-input"
     ]
@@ -162,6 +167,15 @@
     "df_omics"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "ff72465c",
+   "metadata": {},
+   "source": [
+    "And we have the following patient metadata, from which we will use the `Status` column as\n",
+    "our dependent variable and the `PlatinumValue` as a covariate."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -179,7 +193,7 @@
    "id": "4bbf5dc4",
    "metadata": {},
    "source": [
-    "## Compute up and downregulated genes\n",
+    "# ANOVA: Compute up and downregulated genes\n",
     "These will be used to find enrichments in the set of both up and downregulated genes."
    ]
   },
@@ -191,7 +205,6 @@
    "outputs": [],
    "source": [
     "group = \"Status\"\n",
-    "covariates = [\"PlatinumValue\"]\n",
     "diff_reg = acore.differential_regulation.run_anova(\n",
     "    df_omics.join(df_meta[[group]]),\n",
     "    drop_cols=[],\n",
@@ -217,7 +230,8 @@
    "id": "d6c0a225",
    "metadata": {},
    "source": [
-    "## Find functional annotations, here pathways\n"
+    "# Download functional annotations, here pathways, for the protein groups\n",
+    "in our selection of the dataset."
    ]
   },
   {
@@ -227,6 +241,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from acore.io.uniprot import fetch_annotations, process_annotations\n",
+    "\n",
     "fname_annotations = f\"downloaded/annotations_{features_to_sample}.csv\"\n",
     "fname = Path(fname_annotations)\n",
     "try:\n",
@@ -234,32 +250,10 @@
     "    print(f\"Loaded annotations from {fname}\")\n",
     "except FileNotFoundError:\n",
     "    print(f\"Fetching annotations for {df_omics.columns.size} UniProt IDs.\")\n",
-    "    fields = \"go_p,go_c,go_f\"\n",
-    "    annotations = fetch_annotations(df_omics.columns, fields=fields)\n",
-    "    # First column (`From`) is additional to specified fields\n",
-    "    d_fields_to_col = {k: v for k, v in zip(fields.split(\",\"), annotations.columns[1:])}\n",
-    "\n",
-    "    # expand go terms\n",
-    "    to_expand = list()\n",
-    "    for field in d_fields_to_col:\n",
-    "        if \"go_\" in field:\n",
-    "            col = d_fields_to_col[field]\n",
-    "            annotations[col] = annotations[col].str.split(\";\")\n",
-    "            to_expand.append(col)\n",
-    "    for col in to_expand:\n",
-    "        # this is a bit wastefull. Processing to stack format should be done here.\n",
-    "        annotations = annotations.explode(col, ignore_index=True)\n",
-    "    # process other than go term columns\n",
-    "    annotations = (\n",
-    "        annotations.set_index(\"From\")\n",
-    "        .rename_axis(\"identifier\")\n",
-    "        # .drop(\"Entry\", axis=1)\n",
-    "        .rename_axis(\"source\", axis=1)\n",
-    "        .stack()\n",
-    "        .to_frame(\"annotation\")\n",
-    "        .reset_index()\n",
-    "        .drop_duplicates(ignore_index=True)\n",
-    "    )\n",
+    "    FIELDS = \"go_p,go_c,go_f\"\n",
+    "    annotations = fetch_annotations(df_omics.columns, fields=FIELDS)\n",
+    "    annotations = process_annotations(annotations, fields=FIELDS)\n",
+    "    # cache the annotations\n",
     "    fname.parent.mkdir(exist_ok=True, parents=True)\n",
     "    annotations.to_csv(fname, index=True)\n",
     "\n",
@@ -271,7 +265,8 @@
    "id": "d4734452",
    "metadata": {},
    "source": [
-    "See how many protein groups are associated with each annotation."
+    "See how many protein groups are associated with each annotation. We observe that most\n",
+    "functional annotations are associated only to a single protein group in our dataset."
    ]
   },
   {
@@ -285,13 +280,27 @@
    },
    "outputs": [],
    "source": [
-    "_ = (\n",
-    "    annotations.groupby(\"annotation\")\n",
-    "    .size()\n",
-    "    .value_counts()\n",
-    "    .sort_index()\n",
-    "    .plot(kind=\"bar\")\n",
-    ")"
+    "s_count_pg_per_annotation = (\n",
+    "    annotations.groupby(\"annotation\").size().value_counts().sort_index()\n",
+    ")\n",
+    "_ = s_count_pg_per_annotation.plot(\n",
+    "    kind=\"bar\",\n",
+    "    xlabel=\"Number of protein groups associated with annotation\",\n",
+    "    ylabel=\"Number of annotations\",\n",
+    ")\n",
+    "s_count_pg_per_annotation.to_frame(\"number of annotations\").rename_axis(\n",
+    "    \"N protein groups\"\n",
+    ").T"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e04c98d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "annotations.groupby(\"annotation\").size().value_counts(ascending=False)"
    ]
   },
   {
@@ -299,7 +308,7 @@
    "id": "4165bc94",
    "metadata": {},
    "source": [
-    "## Enrichment analysis\n",
+    "# Enrichment analysis\n",
     "Is done separately for up- and downregulated genes as it's assumed that biological\n",
     "processes are regulated in one direction."
    ]
@@ -334,8 +343,10 @@
    "id": "7380a528",
    "metadata": {},
    "source": [
-    "- this additionally sets a fold change cutoff\n",
-    "- and the fore and backgroud populations are changed due to the separation"
+    "Running the enrichment analysis for the up- and down regulated protein groups\n",
+    "separately with the default settings of the function, i.e. a log2 fold change cutoff\n",
+    "of 1 and at least 2 protein groups detected in the set of proteins\n",
+    "defining the functional annotation."
    ]
   },
   {
@@ -348,8 +359,8 @@
     "ret = acore.enrichment_analysis.run_up_down_regulation_enrichment(\n",
     "    regulation_data=diff_reg,\n",
     "    annotation=annotations,\n",
-    "    min_detected_in_set=2,  # ! default is 2, so more conservative\n",
-    "    lfc_cutoff=0.5,  # ! the default is 1\n",
+    "    min_detected_in_set=2,\n",
+    "    lfc_cutoff=1,\n",
     ")\n",
     "ret"
    ]
@@ -359,46 +370,46 @@
    "id": "5cb036be",
    "metadata": {},
    "source": [
-    "here we see differences for the same set of differently regulated protein groups,\n",
-    "which can be reset using lfc_cutoff=0."
+    "we can decrease the cutoff for the log2 fold change to 0.5 and see that we retain\n",
+    "more annotations."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5e5e2b61",
+   "id": "3ea367ca",
    "metadata": {},
    "outputs": [],
    "source": [
     "ret = acore.enrichment_analysis.run_up_down_regulation_enrichment(\n",
     "    regulation_data=diff_reg,\n",
     "    annotation=annotations,\n",
-    "    min_detected_in_set=1,  # ! default is 2, so more conservative\n",
-    "    lfc_cutoff=0.1,  # ! the default is 1\n",
+    "    min_detected_in_set=2,\n",
+    "    lfc_cutoff=0.5,  # ! the default is 1\n",
     ")\n",
     "ret"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "e3530547",
+   "id": "e51bd7e3",
    "metadata": {},
    "source": [
-    "Or restricting the analysis to functional annotation for which we at least found 2\n",
-    "protein groups to be upregulated."
+    "And even more if we do not restrict the analysis of finding at least two proteins\n",
+    "of a functional set in our data set (i.e. we only need to find one match from the set)."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "3ea367ca",
+   "id": "7ede296e",
    "metadata": {},
    "outputs": [],
    "source": [
     "ret = acore.enrichment_analysis.run_up_down_regulation_enrichment(\n",
     "    regulation_data=diff_reg,\n",
     "    annotation=annotations,\n",
-    "    min_detected_in_set=2,\n",
+    "    min_detected_in_set=1,\n",
     "    lfc_cutoff=0.5,  # ! the default is 1\n",
     ")\n",
     "ret"
@@ -409,7 +420,7 @@
    "id": "ecf75e7c",
    "metadata": {},
    "source": [
-    "### Site specific enrichment analysis"
+    "## Site specific enrichment analysis"
    ]
   },
   {
@@ -458,7 +469,7 @@
    "id": "dbc34b7b",
    "metadata": {},
    "source": [
-    "## Single sample GSEA (ssGSEA)\n",
+    "# Single sample GSEA (ssGSEA)\n",
     "Run a gene set enrichment analysis (GSEA) for each sample,\n",
     "see [article](https://www.nature.com/articles/nature08460#Sec3) and\n",
     "the package [`gseapy`](https://gseapy.readthedocs.io/en/latest/run.html#gseapy.ssgsea)\n",
@@ -497,7 +508,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "enrichtments[\"NES\"].plot.hist()"
+    "ax = enrichtments[\"NES\"].plot.hist()"
    ]
   },
   {
@@ -577,13 +588,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from plotly.offline import iplot\n",
+    "import plotly.graph_objects as go\n",
     "from vuecore import viz\n",
     "\n",
-    "args = {\"factor\": 1, \"loadings\": 10}\n",
+    "args = {\"factor\": 2, \"loadings\": 1}  # increase number of loadings or scaling factor\n",
     "#! pca_results has three items, but docstring requests only two -> double check\n",
     "figure = viz.get_pca_plot(data=pca_result, identifier=\"PCA enrichment\", args=args)\n",
-    "iplot(figure)"
+    "figure = go.Figure(data=figure[\"data\"], layout=figure[\"layout\"])\n",
+    "figure.show()"
    ]
   },
   {
@@ -591,7 +603,8 @@
    "id": "4be5a8c8",
    "metadata": {},
    "source": [
-    "## Compare two distributions - KS test\n",
+    "# Compare two distributions - KS test\n",
+    "\n",
     "The Kolmogorov-Smirnov test is a non-parametric test that compares two distributions.\n",
     "- we compare the distributions of the two differently upregulated protein groups\n",
     "This is not the best example for comparing distributions, but it shows how to use the\n",
@@ -643,6 +656,23 @@
    "cell_metadata_filter": "tags,-all",
    "main_language": "python",
    "notebook_metadata_filter": "-all"
+  },
+  "kernelspec": {
+   "display_name": "acore",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.10"
   }
  },
  "nbformat": 4,
diff --git a/docs/api_examples/enrichment_analysis.py b/docs/api_examples/enrichment_analysis.py
index 5f09cd0..1049722 100644
--- a/docs/api_examples/enrichment_analysis.py
+++ b/docs/api_examples/enrichment_analysis.py
@@ -1,19 +1,20 @@
 # %% [markdown]
 # # Enrichment analysis
+# requires
+# - some cluster of proteins/genes (e.g. up- and downregulated proteins/genes)
+# - functional annotations, i.e. a category summarizing a set of proteins/genes.
 #
-# - we need some groups of genes to compute clusters
-# - we need functional annotations, i.e. a category summarizing a set of genes.
-# -
 # You can start with watching Lars Juhl Jensen's brief introduction to enrichment analysis
 # on [youtube](https://www.youtube.com/watch?v=2NC1QOXmc5o).
 #
-# Use example data for ovarian cancer
-# ([PXD010372](https://github.com/Multiomics-Analytics-Group/acore/tree/main/example_data/PXD010372))
+# Here we use as example data from an ovarian cancer dataset:
+# [PXD010372](https://github.com/Multiomics-Analytics-Group/acore/tree/main/example_data/PXD010372)
+#
+# First make sure you have the required packages installed:
 
 
 # %% tags=["hide-output"]
-# %pip install acore vuecore
-
+# %pip install acore vuecore 'plotly<6'
 
 # %%
 from pathlib import Path
@@ -24,7 +25,6 @@
 import acore
 import acore.differential_regulation
 import acore.enrichment_analysis
-from acore.io.uniprot import fetch_annotations
 
 dsp_pandas.format.set_pandas_options(max_colwidth=60)
 
@@ -43,6 +43,8 @@
 
 # %% [markdown]
 # # Load processed data
+# from our repository. See details on obtaining the data under the example data section on
+# [this page](nb_ref_ovarian_data)
 
 # %%
 df_omics = pd.read_csv(omics, index_col=0)
@@ -51,16 +53,20 @@
 df_omics
 
 # %%
-ax = df_omics.notna().sum().sort_values(ascending=True).plot()
+ax = (
+    df_omics.notna()
+    .sum()
+    .sort_values(ascending=True)
+    .plot(xlabel="Protein groups", ylabel="Number of non-NaN values (samples)")
+)
 
 # %% [markdown]
 # Keep only features with a certain amount of non-NaN values and select 100 of these
-# for illustration. Add the ones which were differently regulated in the ANOVA using all
+# for illustration. Add always four which were differently regulated in the ANOVA using all
 # the protein groups.
 
 # %%
 idx_always_included = ["Q5HYN5", "P39059", "O43432", "O43175"]
-df_omics[idx_always_included]
 
 # %% tags=["hide-input"]
 df_omics = (
@@ -77,18 +83,20 @@
 )
 df_omics
 
+# %% [markdown]
+# And we have the following patient metadata, from which we will use the `Status` column as
+# our dependent variable and the `PlatinumValue` as a covariate.
 
 # %%
 df_meta
 
 
 # %% [markdown]
-# ## Compute up and downregulated genes
+# # ANOVA: Compute up and downregulated genes
 # These will be used to find enrichments in the set of both up and downregulated genes.
 
 # %%
 group = "Status"
-covariates = ["PlatinumValue"]
 diff_reg = acore.differential_regulation.run_anova(
     df_omics.join(df_meta[[group]]),
     drop_cols=[],
@@ -102,10 +110,12 @@
 diff_reg.query("rejected")
 
 # %% [markdown]
-# ## Find functional annotations, here pathways
-#
+# # Download functional annotations, here pathways, for the protein groups
+# in our selection of the dataset.
 
 # %%
+from acore.io.uniprot import fetch_annotations, process_annotations
+
 fname_annotations = f"downloaded/annotations_{features_to_sample}.csv"
 fname = Path(fname_annotations)
 try:
@@ -113,51 +123,37 @@
     print(f"Loaded annotations from {fname}")
 except FileNotFoundError:
     print(f"Fetching annotations for {df_omics.columns.size} UniProt IDs.")
-    fields = "go_p,go_c,go_f"
-    annotations = fetch_annotations(df_omics.columns, fields=fields)
-    # First column (`From`) is additional to specified fields
-    d_fields_to_col = {k: v for k, v in zip(fields.split(","), annotations.columns[1:])}
-
-    # expand go terms
-    to_expand = list()
-    for field in d_fields_to_col:
-        if "go_" in field:
-            col = d_fields_to_col[field]
-            annotations[col] = annotations[col].str.split(";")
-            to_expand.append(col)
-    for col in to_expand:
-        # this is a bit wastefull. Processing to stack format should be done here.
-        annotations = annotations.explode(col, ignore_index=True)
-    # process other than go term columns
-    annotations = (
-        annotations.set_index("From")
-        .rename_axis("identifier")
-        # .drop("Entry", axis=1)
-        .rename_axis("source", axis=1)
-        .stack()
-        .to_frame("annotation")
-        .reset_index()
-        .drop_duplicates(ignore_index=True)
-    )
+    FIELDS = "go_p,go_c,go_f"
+    annotations = fetch_annotations(df_omics.columns, fields=FIELDS)
+    annotations = process_annotations(annotations, fields=FIELDS)
+    # cache the annotations
     fname.parent.mkdir(exist_ok=True, parents=True)
     annotations.to_csv(fname, index=True)
 
 annotations
 
 # %% [markdown]
-# See how many protein groups are associated with each annotation.
+# See how many protein groups are associated with each annotation. We observe that most
+# functional annotations are associated only to a single protein group in our dataset.
 
 # %% tags=["hide-input"]
-_ = (
-    annotations.groupby("annotation")
-    .size()
-    .value_counts()
-    .sort_index()
-    .plot(kind="bar")
+s_count_pg_per_annotation = (
+    annotations.groupby("annotation").size().value_counts().sort_index()
 )
+_ = s_count_pg_per_annotation.plot(
+    kind="bar",
+    xlabel="Number of protein groups associated with annotation",
+    ylabel="Number of annotations",
+)
+s_count_pg_per_annotation.to_frame("number of annotations").rename_axis(
+    "N protein groups"
+).T
+
+# %%
+annotations.groupby("annotation").size().value_counts(ascending=False)
 
 # %% [markdown]
-# ## Enrichment analysis
+# # Enrichment analysis
 # Is done separately for up- and downregulated genes as it's assumed that biological
 # processes are regulated in one direction.
 
@@ -176,46 +172,48 @@
 ].sort_values("log2FC")
 
 # %% [markdown]
-# - this additionally sets a fold change cutoff
-# - and the fore and backgroud populations are changed due to the separation
+# Running the enrichment analysis for the up- and down regulated protein groups
+# separately with the default settings of the function, i.e. a log2 fold change cutoff
+# of 1 and at least 2 protein groups detected in the set of proteins
+# defining the functional annotation.
 
 # %%
 ret = acore.enrichment_analysis.run_up_down_regulation_enrichment(
     regulation_data=diff_reg,
     annotation=annotations,
-    min_detected_in_set=2,  # ! default is 2, so more conservative
-    lfc_cutoff=0.5,  # ! the default is 1
+    min_detected_in_set=2,
+    lfc_cutoff=1,
 )
 ret
 
 # %% [markdown]
-# here we see differences for the same set of differently regulated protein groups,
-# which can be reset using lfc_cutoff=0.
+# we can decrease the cutoff for the log2 fold change to 0.5 and see that we retain
+# more annotations.
 
 # %%
 ret = acore.enrichment_analysis.run_up_down_regulation_enrichment(
     regulation_data=diff_reg,
     annotation=annotations,
-    min_detected_in_set=1,  # ! default is 2, so more conservative
-    lfc_cutoff=0.1,  # ! the default is 1
+    min_detected_in_set=2,
+    lfc_cutoff=0.5,  # ! the default is 1
 )
 ret
 
 # %% [markdown]
-# Or restricting the analysis to functional annotation for which we at least found 2
-# protein groups to be upregulated.
+# And even more if we do not restrict the analysis of finding at least two proteins
+# of a functional set in our data set (i.e. we only need to find one match from the set).
 
 # %%
 ret = acore.enrichment_analysis.run_up_down_regulation_enrichment(
     regulation_data=diff_reg,
     annotation=annotations,
-    min_detected_in_set=2,
+    min_detected_in_set=1,
     lfc_cutoff=0.5,  # ! the default is 1
 )
 ret
 
 # %% [markdown]
-# ### Site specific enrichment analysis
+# ## Site specific enrichment analysis
 
 # %% [markdown]
 # The basic example uses a modified peptide sequence to
@@ -240,7 +238,7 @@
 # acore.enrichment_analysis.run_up_down_regulation_enrichment
 
 # %% [markdown]
-# ## Single sample GSEA (ssGSEA)
+# # Single sample GSEA (ssGSEA)
 # Run a gene set enrichment analysis (GSEA) for each sample,
 # see [article](https://www.nature.com/articles/nature08460#Sec3) and
 # the package [`gseapy`](https://gseapy.readthedocs.io/en/latest/run.html#gseapy.ssgsea)
@@ -258,7 +256,7 @@
 enrichtments.iloc[0].to_dict()
 
 # %%
-enrichtments["NES"].plot.hist()
+ax = enrichtments["NES"].plot.hist()
 
 # %% [markdown]
 # The normalised enrichment score (NES) can be used in a PCA plot to see if the samples
@@ -295,16 +293,18 @@
 # for this, which is also developed by the Multiomics Analytics Group.
 
 # %%
-from plotly.offline import iplot
+import plotly.graph_objects as go
 from vuecore import viz
 
-args = {"factor": 1, "loadings": 10}
+args = {"factor": 2, "loadings": 1}  # increase number of loadings or scaling factor
 # #! pca_results has three items, but docstring requests only two -> double check
 figure = viz.get_pca_plot(data=pca_result, identifier="PCA enrichment", args=args)
-iplot(figure)
+figure = go.Figure(data=figure["data"], layout=figure["layout"])
+figure.show()
 
 # %% [markdown]
-# ## Compare two distributions - KS test
+# # Compare two distributions - KS test
+#
 # The Kolmogorov-Smirnov test is a non-parametric test that compares two distributions.
 # - we compare the distributions of the two differently upregulated protein groups
 # This is not the best example for comparing distributions, but it shows how to use the
diff --git a/docs/api_examples/ovarian_cancer.ipynb b/docs/api_examples/ovarian_cancer.ipynb
index 8f35017..ab2a0f7 100644
--- a/docs/api_examples/ovarian_cancer.ipynb
+++ b/docs/api_examples/ovarian_cancer.ipynb
@@ -5,6 +5,7 @@
    "id": "d61c8f55",
    "metadata": {},
    "source": [
+    "(nb_ref_ovarian_data)=\n",
     "# Download from journal (ovarian cancer proteome)\n",
     "Download the ovarian cancer proteome data from the journal's website. It was\n",
     "provided as supplementary data. See the article here:\n",
diff --git a/docs/api_examples/ovarian_cancer.py b/docs/api_examples/ovarian_cancer.py
index 49f6aeb..cf7483e 100644
--- a/docs/api_examples/ovarian_cancer.py
+++ b/docs/api_examples/ovarian_cancer.py
@@ -1,4 +1,5 @@
 # %% [markdown]
+# (nb_ref_ovarian_data)=
 # # Download from journal (ovarian cancer proteome)
 # Download the ovarian cancer proteome data from the journal's website. It was
 # provided as supplementary data. See the article here:
diff --git a/docs/conf.py b/docs/conf.py
index 8cb7971..e935d46 100755
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -104,6 +104,8 @@
 nb_execution_raise_on_error = True
 # Rendering
 nb_merge_streams = True
+# maximum execution time per cell in seconds
+nb_execution_timeout = 120
 
 # https://myst-nb.readthedocs.io/en/latest/authoring/custom-formats.html#write-custom-formats
 # nb_custom_formats = {".py": ["jupytext.reads", {"fmt": "py:percent"}]}
diff --git a/pyproject.toml b/pyproject.toml
index 67d1043..e22a071 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -27,7 +27,7 @@ dependencies = [
     "networkx",
     "biopython",
     "combat",
-    "gseapy",
+    "gseapy!=1.1.5",
     "kmapper",
     "lifelines",
     "pingouin",
diff --git a/src/acore/io/uniprot/__init__.py b/src/acore/io/uniprot/__init__.py
index 96e6002..d8c8ef6 100644
--- a/src/acore/io/uniprot/__init__.py
+++ b/src/acore/io/uniprot/__init__.py
@@ -46,3 +46,47 @@ def fetch_annotations(
     results = [line.split("\t") for line in results]
     df = pd.DataFrame(results, columns=header)
     return df
+
+
+def process_annotations(annotations: pd.DataFrame, fields: str) -> pd.DataFrame:
+    """Process annotations fetched from UniProt API.
+
+    Parameters
+    ----------
+    annotations : pd.DataFrame
+        DataFrame with annotations fetched from UniProt API.
+    fields : str
+        Fields that were fetched from the API. Comma-separated string. Fields
+        needs to match number of columns in annotations.
+
+    Returns
+    -------
+    pd.DataFrame
+        Processed DataFrame with annotations in long-format.
+    """
+    d_fields_to_col = {
+        k: v for k, v in zip(fields.split(","), annotations.columns[1:], strict=True)
+    }
+
+    # expand go terms
+    to_expand = list()
+    for field in d_fields_to_col:
+        if "go_" in field:
+            col = d_fields_to_col[field]
+            annotations[col] = annotations[col].str.split(";")
+            to_expand.append(col)
+    for col in to_expand:
+        # this is a bit wastefull. Processing to stack format should be done here.
+        annotations = annotations.explode(col, ignore_index=True)
+    # process other than go term columns
+    annotations = (
+        annotations.set_index("From")
+        .rename_axis("identifier")
+        # .drop("Entry", axis=1)
+        .rename_axis("source", axis=1)
+        .stack()
+        .to_frame("annotation")
+        .reset_index()
+        .drop_duplicates(ignore_index=True)
+    )
+    return annotations