Yeast dataset

configs/dmmm copy.yaml

@@ -0,0 +1,106 @@
+hash_length: 7
+
+containers:
+  registry:
+    base_url: docker.io
+    owner: reedcompbio
+  framework: docker
+  unpack_singularity: false
+
+reconstruction_settings:
+  locations:
+    reconstruction_dir: "output"
+
+analysis:
+  summary:
+    include: true
+  cytoscape:
+    include: false
+  ml:
+    # TODO: we either need at least one non-empty pathway in all algorithm runs,
+    # or we need to get rid of validate_df hard-erroring. The latter seems better.
+    include: false
+    aggregate_per_algorithm: false
+  evaluation:
+    include: false
+
+# Custom settings
+algorithms:
+  - name: "omicsintegrator1"
+    include: true
+    runs:
+      run1:
+        b: 2
+        w: .5
+        d: 10
+        mu: 2
+
+  - name: "omicsintegrator2"
+    include: true
+    runs:
+      run1:
+        b: 4
+        g: 0
+
+  - name: "pathlinker"
+    include: true
+    runs:
+      run1:
+        k: 100
+
+  #- name: "meo"
+  #  include: true
+  #  runs:
+  #    run1:
+  #      max_path_length: 3
+  #      local_search: true
+  #      rand_restarts: 10
+
+  - name: "allpairs"
+    include: true
+
+  - name: "domino"
+    include: true
+    runs:
+      run1:
+        slice_threshold: 0.3
+        module_threshold: 0.05
+
+  - name: "rwr"
+    include: true
+    runs:
+      run1:
+        alpha: 0.85
+        threshold: 100
+
+  - name: "diamond"
+    include: true
+    runs:
+      run1:
+        n: 1
+datasets:
+  - label: dmmmegfr_string
+    data_dir: datasets/egfr
+    edge_files: ["processed/interactome.tsv"]
+    node_files: ["processed/prizes.txt"]
+    other_files: []
+  - label: dmmmegfr_irefindex
+    data_dir: datasets/egfr
+    edge_files: ["processed/phosphosite-irefindex13.0-uniprot.txt"]
+    node_files: ["processed/prizes-uniprot.txt"]
+    other_files: []
+  # Yeast: https://github.com/tristan-f-r/spras-benchmarking/blob/9477d85871024a5e3a4b0b8b9be7e78c0d0ee961/yeast_osmotic_stress/config.yaml
+  - label: dmmmyeast
+    node_files: ["prizes1_dummies.txt"]
+    edge_files: ["network1.txt"]
+    other_files: []
+    data_dir: "datasets/yeast_osmotic_stress/processed"
+gold_standards:
+  - label: gs_egfr_string
+    node_files: ["processed/gold-standard-nodes.txt"]
+    data_dir: datasets/egfr
+    dataset_labels: ["dmmmegfr_string"]
+  - label: gs_egfr_irefindex
+    node_files: ["processed/gold-standard-nodes-uniprot.txt"]
+    data_dir: datasets/egfr
+    dataset_labels: ["dmmmegfr_irefindex"]

configs/dmmm.yaml

@@ -13,14 +13,14 @@ reconstruction_settings:
 
 analysis:
   summary:
-    include: false
+    include: true
   cytoscape:
     include: false
   ml:
     # TODO: we either need at least one non-empty pathway in all algorithm runs,
     # or we need to get rid of validate_df hard-erroring. The latter seems better.
     include: false
-    aggregate_per_algorithm: true
+    aggregate_per_algorithm: false
   evaluation:
     include: false
 
@@ -34,14 +34,28 @@ algorithms:
         w: .5
         d: 10
         mu: 2
-        # TODO: egfr prefers dummy_mode: ["file"] since we manually specify EGF_HUMAN as one.
+
   - name: "omicsintegrator2"
     include: true
     runs:
       run1:
         b: 4
         g: 0
 
+  # domino requires too much memory for dmmmegfr_string (Docker OOM). Disabled.
+  - name: "domino"
+    include: false
+    runs:
+      run1:
+        slice_threshold: 0.3
+        module_threshold: 0.05
+
+  # diamond requires 'active' column, which yeast dataset lacks. Disabled.
+  - name: "diamond"
+    include: false
+    runs:
+      run1:
+        n: 1
 datasets:
   - label: dmmmegfr_string
     data_dir: datasets/egfr