Improvements in documentation

Author: Old-Shatterhand

Diff for: datasail/parsers.py

@@ -25,6 +25,13 @@ def parse_datasail_args(args) -> Dict[str, object]:
                     "clusters within the dataset.",
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
+    parser.add_argument(
+        "--cc",
+        default=False,
+        action='store_true',
+        dest=KW_CC,
+        help="List available clustering algorithms."
+    )
     parser.add_argument(
         "-o",
         "--output",

Diff for: datasail/routine.py

@@ -1,5 +1,5 @@
 import time
-from typing import Dict, Tuple
+from typing import Dict, Tuple, Optional
 
 from datasail.argparse_patch import remove_patch
 from datasail.cluster.clustering import cluster
@@ -8,18 +8,34 @@
 from datasail.report import report
 from datasail.settings import LOGGER, KW_TECHNIQUES, KW_EPSILON, KW_RUNS, KW_SPLITS, KW_NAMES, \
     KW_MAX_SEC, KW_MAX_SOL, KW_SOLVER, KW_LOGDIR, NOT_ASSIGNED, KW_OUTDIR, MODE_E, MODE_F, DIM_2, SRC_CL, KW_DELTA, \
-    KW_E_CLUSTERS, KW_F_CLUSTERS
+    KW_E_CLUSTERS, KW_F_CLUSTERS, KW_CC, CDHIT, INSTALLED, FOLDSEEK, TMALIGN, CDHIT_EST, DIAMOND, MMSEQS, MASH
 from datasail.solver.solve import run_solver
 
 
-def datasail_main(**kwargs) -> Tuple[Dict, Dict, Dict]:
+def list_cluster_algos():
+    """
+    List all available clustering algorithms.
+    """
+
+    print("Available clustering algorithms:", "\tECFP", sep="\n")
+    for algo, name in [(CDHIT, "CD-HIT"), (CDHIT_EST, "CD-HIT-EST"), (DIAMOND, "DIAMOND"), (MMSEQS, "MMseqs, MMseqs2"),
+                       (MASH, "MASH"), (FOLDSEEK, "FoldSeek"), (TMALIGN, "TMalign")]:
+        if INSTALLED[algo]:
+            print("\t", name, sep="")
+
+
+def datasail_main(**kwargs) -> Optional[Tuple[Dict, Dict, Dict]]:
     """
     Main routine of DataSAIL. Here the parsed input is aggregated into structures and then split and saved.
 
     Args:
         **kwargs: Parsed commandline arguments to DataSAIL.
     """
     kwargs = remove_patch(**kwargs)
+    if kwargs[KW_CC]:
+        list_cluster_algos()
+        return None
+
     start = time.time()
     LOGGER.info("Read data")
 

Diff for: datasail/settings.py

@@ -148,6 +148,7 @@ def format2ending(fmt: str) -> str:
 
 KW_CACHE = "cache"
 KW_CACHE_DIR = "cache_dir"
+KW_CC = "cc"
 KW_CLI = "cli"
 KW_DELTA = "delta"
 KW_EPSILON = "epsilon"

Diff for: docs/conf.py

@@ -6,6 +6,7 @@
 import sphinx_rtd_theme
 
 sys.path.insert(0, os.path.abspath("./.."))
+sys.path.insert(0, os.path.abspath("./."))
 
 import datasail
 from datasail.version import __version__
@@ -21,7 +22,7 @@
     "sphinx.ext.githubpages",
     "nbsphinx",
     "nbsphinx_link",
-    "IPython.sphinxext.ipython_console_highlighting"
+    "IPython.sphinxext.ipython_console_highlighting",
 ]
 
 autosummary_generate = True
@@ -45,7 +46,6 @@
 intersphinx_mapping = {
     "python": ("https://docs.python.org/", None),
     "numpy": ("https://numpy.org/doc/stable/", None),
-    # "numpy": ("http://docs.scipy.org/doc/numpy", None),
 }
 
 html_theme_options = {

Diff for: docs/index.rst

@@ -8,35 +8,30 @@ datasets. However, its versatility extends beyond biology, making it applicable
 utilized through its command line interface or integrated as a Python package, DataSAIL stands out for its
 user-friendly design and adaptability. Licensed under the MIT license, it is open source and conveniently accessible on
 `GitHub <https://github.com/kalininalab/datasail>`_. Installation is made simple through
-`conda <https://anaconda.org/kalininalab/datasail>`_, utilizing
-`mamba <https://mamba.readthedocs.io/en/latest/installation.html#existing-conda-install>`_.
+`conda <https://anaconda.org/kalininalab/datasail>`_.
 
-Quick Start
-###########
-
-DataSAIL is available for all modern versions of Pytion (v3.8 or newer). Other than described on the conda-website,
-the command to install DataSAIL within your just created environment is
-
-.. code-block:: shell
+Install
+#######
 
-    mamba install -c kalininalab -c conda-forge -c bioconda datasail
-    pip install grakel
+DataSAIL is available for all modern versions of Pytion (v3.8 or newer).
 
-The second command is necessary to run WLK clustering as the grakel library is not available on conda for python 3.10
-or newer. Alternatively, one can install :code:`DataSAIL-lite` from conda as
+.. note::
+    It is recommended to use `mamba <https://mamba.readthedocs.io/en/latest/installation.html#existing-conda-install>`_
+    for the installation because conda might not be able to resolve the dependencies of DataSAIL successfully.
 
-.. code-block:: shell
+.. raw:: html
+    :file: install.html
 
-    mamba install -c kalininalab -c conda-forge -c bioconda datasail-lite
-    pip install grakel
+DataSAIL vs. DataSAIL-lite
+--------------------------
 
-.. note::
-    It is important to use mamba for the installation because conda might not be able to resolve the dependencies of
-    DataSAIL successfully.
+The difference between :code:`DataSAIL` and :code:`DataSAIL-lite` is that the latter does not include most of the
+clustering algorithms as they are not provide on conda for all OSs. Therefore, the user is required to the user to
+install them manually as needed. DataSAIL will work even if not all clustering are installed. For the installation, is
+it necessary to be able to call them. You can test which are available by running :code:`datasail --cc`.
 
-The difference between :code:`DataSAIL` and :code:`DataSAIL-lite` is that the latter does not include the clustering
-algorithms and requires the user to install them manually as needed. The reason for this is that the clustering
-algorithms are not available for all OS and we want to make DataSAIL available for all OS.
+Quick Start
+###########
 
 Regardless of which installation command was used, DataSAIL can be executed by running
 

Diff for: docs/install.html

@@ -0,0 +1,128 @@
+<style>
+    .quick-start {
+        display: flex;
+        flex-direction: row;
+        flex-wrap: nowrap;
+        margin-bottom: 20px;
+    }
+
+    .title-column {
+        flex-grow: 0;
+    }
+
+    .content-column {
+        flex-grow: 1;
+    }
+
+    .row {
+        display: flex;
+        flex-direction: row;
+        flex-wrap: nowrap;
+    }
+
+    .title-column div, .row div {
+        white-space: nowrap;
+    }
+
+    .title-column div {
+        padding: 14px 10px 12px 0;
+        font-weight: 700;
+    }
+
+    .row div {
+        flex-grow: 1;
+        text-align: center;
+        margin: 2px;
+        padding: 12px 0 10px 0;
+        background: #e3e3e3;
+        cursor: pointer;
+    }
+
+    .row div.selected {
+        background: rgba(59,155,239,0.7);
+        color: #ffffff;
+    }
+
+    #command {
+        margin: 2px;
+        padding: 12px 10px 10px 10px;
+    }
+
+    #command pre {
+        padding: 0;
+        margin: 0;
+        white-space: pre-wrap;
+    }
+</style>
+
+<div class="quick-start">
+    <div class="title-column">
+        <div>OS</div>
+        <div>Package</div>
+        <div>Run:</div>
+    </div>
+    <div class="content-column">
+        <div class="row" id="os">
+            <div id="linux">Linux</div>
+            <div id="osx">OSX</div>
+            <div id="arm">OSX-ARM</div>
+            <div id="win">Windows</div>
+        </div>
+        <div class="row" id="package">
+            <div id="conda">Conda</div>
+            <div id="pip">Pip</div>
+        </div>
+        <div class="row" id="command">
+            <pre id="commandText">Command</pre>
+        </div>
+    </div>
+</div>
+
+<script type="text/javascript">
+    function updateCommand() {
+        // Get the attributes from the #command element
+        var commandElement = document.getElementById("command");
+        var os = commandElement.getAttribute("os");
+        var package = commandElement.getAttribute("package");
+
+        // Get the <pre> element inside the #command element
+        var preElement = commandElement.querySelector("pre");
+
+        // Update the text based on the conditions
+        if (package === "pip") {
+            preElement.textContent = '# datasail is not yet available on pip';
+        }
+        else if (os === "linux" || os === "osx") {
+            preElement.textContent = 'mamba install -c conda-force -c bioconda -c kalininalab datasail  # or datasail-lite\n\npip install grakel<0.1.10';
+        }
+        else {
+            preElement.textContent = `mamba install -c conda-force -c bioconda -c kalininalab datasail-lite\n\npip install grakel<0.1.10`;
+        }
+    }
+
+    document.querySelectorAll(".quick-start .content-column .row div").forEach(function(element) {
+        element.addEventListener("click", function() {
+            // Remove the 'selected' class from all siblings
+            let siblings = this.parentNode.querySelectorAll('div');
+            siblings.forEach(function(sibling) {
+                sibling.classList.remove('selected');
+            });
+
+            // Add the 'selected' class to the clicked element
+            this.classList.add('selected');
+
+            // Get the parent row's id and the clicked element's id
+            let parentId = this.parentNode.id;
+            let elementId = this.id;
+
+            // Set the corresponding attribute on the #command element
+            document.getElementById("command").setAttribute(parentId, elementId);
+
+            // Call the updateCommand function
+            updateCommand();
+        });
+    });
+
+    document.getElementById("os").children[0].click();
+    document.getElementById("package").children[0].click();
+</script>