updated the example directory (#337)

* updated the example directory

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

example/example_download.py

@@ -0,0 +1,30 @@
+import os
+import os.path as osp
+import pathlib
+import shutil
+import time
+
+import numpy as np
+
+import geneplexus
+
+# Set up data directory
+homedir = pathlib.Path(__file__).absolute().parent
+datadir = osp.join(homedir, "data")
+os.makedirs(datadir, exist_ok=True)
+
+
+"""
+each file is separated by the species. Can select all by using
+species = ["Human", "Mouse", "Fly", "Worm", "Zebrafish", "Yeast"]
+or
+species = "All"
+
+for a subset just include desired species (example for just Mouse and Human)
+species = ["Human", "Mouse"]
+"""
+
+geneplexus.download.download_select_data(
+    datadir,
+    species=["Human", "Mouse", "Fly", "Worm", "Zebrafish", "Yeast"],
+)

example/example_run.py

@@ -38,23 +38,19 @@
 # Get the data from URL
 geneplexus.download.download_select_data(
     datadir,
-    tasks="All",
-    networks="STRING",
-    features="SixSpeciesN2V",
-    sp_trn="Human",
-    sp_tst="Mouse",
-    gsc="GO",
+    species=["Human", "Mouse"],
 )
 
 # Run through the pipeline
 # First initialize the geneplexus object
 myclass = geneplexus.GenePlexus(
-    file_loc=fp_data,
-    gsc="Combined",
-    features="SixSpeciesN2V",
+    file_loc=datadir,
     net_type="STRING",
+    features="SixSpeciesN2V",
     sp_trn="Human",
-    sp_tst="Mouse",
+    sp_res="Mouse",
+    gsc_trn="Combined",
+    gsc_res="Combined",
 )
 
 # Load the input genes into the class and set up positives/negatives
@@ -65,7 +61,7 @@
 
 # The makes the tables that have the model weight similarity to other models
 # trained on known GO and DisGeNet sets
-df_sim_GO, df_sim_Dis, weights_GO, weights_Dis = myclass.make_sim_dfs()
+df_sim, sim_weights = myclass.make_sim_dfs()
 
 # Return an edgelist
 df_edge, isolated_genes, df_edge_sym, isolated_genes_sym = myclass.make_small_edgelist(num_nodes=50)
@@ -75,5 +71,5 @@
 
 # Save a few things for checking
 df_probs.to_csv(osp.join(outdir, "df_probs.tsv"), sep="\t", header=True, index=False)
-df_sim_GO.to_csv(osp.join(outdir, "df_sim_GO.tsv"), sep="\t", header=True, index=False)
+df_sim.to_csv(osp.join(outdir, "df_sim_GO.tsv"), sep="\t", header=True, index=False)
 df_convert_out_subset.to_csv(osp.join(outdir, "df_convert_out_subset.tsv"), sep="\t", header=True, index=False)

geneplexus/geneplexus.py

@@ -382,20 +382,19 @@ def fit_and_predict(
 
         :attr:`GenePlexus.mdl_weights` (array of float)
             Trained model parameters.
-        :attr:`GenePlexus.probs` (array of float)
-            Genome-wide gene prediction scores. A high value indicates the
-            relevance of the gene to the input gene list.
-        :attr:`GenePlexus.avgps` (array of float)
-            Cross validation results. Performance is measured using
-            log2(auprc/prior).
         :attr:`GenePlexus.df_probs` (DataFrame)
             A table with 7 columns: **Entrez** (the gene Entrez ID), **Symbol**
             (the gene Symbol), **Name** (the gene Name), **Probability** (the
             probability of a gene being part of the input gene list),
             **Known/Novel** (whether the gene is in the input gene list),
             **Class-Label** (positive, negative, or neutral), **Rank** (rank of
             relevance of the gene to the input gene list).
-
+        :attr:`GenePlexus.avgps` (array of float)
+            Cross validation results. Performance is measured using
+            log2(auprc/prior).
+        :attr:`GenePlexus.probs` (array of float)
+            Genome-wide gene prediction scores. A high value indicates the
+            relevance of the gene to the input gene list.
         """
         self._get_pos_and_neg_genes()
         self.mdl_weights, self.probs, self.avgps = _geneplexus._run_sl(