Skip to content

Commit

Permalink
test files for dummy nodes + generate_input fixes
Browse files Browse the repository at this point in the history
  • Loading branch information
sumedhars committed Sep 20, 2024
1 parent 8934b4c commit e28d801
Show file tree
Hide file tree
Showing 4 changed files with 1,204 additions and 22 deletions.
30 changes: 17 additions & 13 deletions config/config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,9 @@ container_registry:
# then myAlg will be run on (a=1,b=0.5),(a=1,b=0.75),(a=2,b=0.5), and (a=2,b=0,75). Pretty neat, but be
# careful: too many parameters might make your runs take a long time.

# TODO: where does the dummy node argument go?
# i.e. where do i set dummy_mode = all, etc.

algorithms:
- name: "pathlinker"
params:
Expand All @@ -56,6 +59,7 @@ algorithms:
b: [5, 6]
w: np.linspace(0,5,2)
d: [10]
dummy_mode: ["file"]

- name: "omicsintegrator2"
params:
Expand Down Expand Up @@ -100,24 +104,24 @@ algorithms:
datasets:
-
# Labels can only contain letters, numbers, or underscores
label: data0
node_files: ["node-prizes.txt", "sources.txt", "targets.txt"]
label: hivtest2
node_files: ["modified_prize_05.txt", "dummy.txt"]
# DataLoader.py can currently only load a single edge file, which is the primary network
edge_files: ["network.txt"]
edge_files: ["phosphosite-irefindex13.0-uniprot.txt"]
# Placeholder
other_files: []
# Relative path from the spras directory
data_dir: "input"

gold_standards:
-
# Labels can only contain letters, numbers, or underscores
label: gs0
node_files: ["gs_nodes0.txt"]
# edge_files: [] TODO: later iteration
data_dir: "input"
# List of dataset labels to compare with the specific gold standard dataset
dataset_labels: ["data0"]
# gold_standards:
# -
# # Labels can only contain letters, numbers, or underscores
# label: gs0
# node_files: ["gs_nodes0.txt"]
# # edge_files: [] TODO: later iteration
# data_dir: "input"
# # List of dataset labels to compare with the specific gold standard dataset
# dataset_labels: ["data0"]

# If we want to reconstruct then we should set run to true.
# TODO: if include is true above but run is false here, algs are not run.
Expand Down Expand Up @@ -160,4 +164,4 @@ analysis:
# 'euclidean', 'manhattan', 'cosine'
metric: 'euclidean'
evaluation:
include: true
include: false
55 changes: 55 additions & 0 deletions input/dummy.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
UBAC2_HUMAN
H37_HUMAN
PHF3_HUMAN
DDX52_HUMAN
HNRPK_HUMAN
Q5T5H1_HUMAN
ZC11A_HUMAN
TCPG_HUMAN
2A5E_HUMAN
CPNE2_HUMAN
HEYL_HUMAN
CAMP1_HUMAN
SVEP1_HUMAN
SPRL1_HUMAN
C9JFD3_HUMAN
THAP5_HUMAN
NCOR1_HUMAN
SKIL_HUMAN
A8YXX4_HUMAN
CO4A2_HUMAN
ZBTB3_HUMAN
MORC4_HUMAN
HIPK3_HUMAN
ZN200_HUMAN
TGFR1_HUMAN
Q2TU89_HUMAN
SUMO2_HUMAN
UBC9_HUMAN
AXIN1_HUMAN
RS27_HUMAN
UBP25_HUMAN
RN111_HUMAN
CBX4_HUMAN
B4E127_HUMAN
G4XH65_HUMAN
CPNE1_HUMAN
HDAC1_HUMAN
RNF4_HUMAN
SETB1_HUMAN
SMAD2_HUMAN
TRI62_HUMAN
FAF1_HUMAN
EF1G_HUMAN
AHNK_HUMAN
LRP1_HUMAN
UIMC1_HUMAN
B3KWV4_HUMAN
CDC27_HUMAN
RB_HUMAN
ZMYM2_HUMAN
WWP1_HUMAN
RU17_HUMAN
HIPK1_HUMAN
ZZEF1_HUMAN
SMAD4_HUMAN
Loading

0 comments on commit e28d801

Please sign in to comment.