zhouxiangxin1998 commited on
Commit
a03de21
β€’
1 Parent(s): b63a7bd

update table

Browse files
app.py CHANGED
@@ -43,16 +43,16 @@ in-depth evaluation framework for protein foundation models, driving their devel
43
  ## [Paper](https://www.arxiv.org/pdf/2409.06744) | [Website](https://proteinbench.github.io/)
44
  """
45
 
46
- def convert_to_float(df):
47
  columns = df.columns
48
- for col in columns[2:]:
49
  df[col] = df[col].astype('float')
50
  return df
51
 
52
 
53
  def assign_rank_and_get_sorted_csv(src_csv_path, tag_csv_path, ignore_num=0):
54
  src_csv = pd.read_csv(src_csv_path)
55
- float_csv = convert_to_float(copy.deepcopy(src_csv))
56
  tag_csv = pd.read_csv(tag_csv_path)
57
  rank_csv = pd.DataFrame()
58
 
@@ -170,15 +170,25 @@ with demo:
170
  headers=multi_state_prediction_csv.columns.to_list(),
171
  datatype=['number', 'markdown'] + (len(multi_state_prediction_csv.columns)-1) * ['number'],
172
  )
173
- with gr.TabItem("πŸ… Conformation Prediction Leaderboard", elem_id='conformation-prediction-table', id=8,):
 
 
 
 
 
 
 
 
 
 
174
  with gr.Row():
175
- conformation_prediction_csv = assign_rank_and_get_sorted_csv('data_link/conformation_prediction.csv', 'data_rank/conformation_prediction.csv')
176
- conformation_prediction_table = gr.components.DataFrame(
177
- value=convert_to_float(conformation_prediction_csv).values,
178
  height=99999,
179
  interactive=False,
180
- headers=conformation_prediction_csv.columns.to_list(),
181
- datatype=['number', 'markdown'] + (len(conformation_prediction_csv.columns)-1) * ['number'],
182
  )
183
 
184
 
 
43
  ## [Paper](https://www.arxiv.org/pdf/2409.06744) | [Website](https://proteinbench.github.io/)
44
  """
45
 
46
+ def convert_to_float(df, start_col_idx=2):
47
  columns = df.columns
48
+ for col in columns[start_col_idx:]:
49
  df[col] = df[col].astype('float')
50
  return df
51
 
52
 
53
  def assign_rank_and_get_sorted_csv(src_csv_path, tag_csv_path, ignore_num=0):
54
  src_csv = pd.read_csv(src_csv_path)
55
+ float_csv = convert_to_float(copy.deepcopy(src_csv), start_col_idx=1)
56
  tag_csv = pd.read_csv(tag_csv_path)
57
  rank_csv = pd.DataFrame()
58
 
 
170
  headers=multi_state_prediction_csv.columns.to_list(),
171
  datatype=['number', 'markdown'] + (len(multi_state_prediction_csv.columns)-1) * ['number'],
172
  )
173
+ # with gr.TabItem("πŸ… Conformation Prediction Leaderboard", elem_id='conformation-prediction-table', id=8,):
174
+ # with gr.Row():
175
+ # conformation_prediction_csv = assign_rank_and_get_sorted_csv('data_link/conformation_prediction.csv', 'data_rank/conformation_prediction.csv')
176
+ # conformation_prediction_table = gr.components.DataFrame(
177
+ # value=convert_to_float(conformation_prediction_csv).values,
178
+ # height=99999,
179
+ # interactive=False,
180
+ # headers=conformation_prediction_csv.columns.to_list(),
181
+ # datatype=['number', 'markdown'] + (len(conformation_prediction_csv.columns)-1) * ['number'],
182
+ # )
183
+ with gr.TabItem("πŸ… Distribution Prediction Leaderboard", elem_id='distribution-prediction-table', id=8,):
184
  with gr.Row():
185
+ distribution_prediction_csv = assign_rank_and_get_sorted_csv('data_link/distribution_prediction.csv', 'data_rank/distribution_prediction.csv')
186
+ distribution_prediction_table = gr.components.DataFrame(
187
+ value=convert_to_float(distribution_prediction_csv).values,
188
  height=99999,
189
  interactive=False,
190
+ headers=distribution_prediction_csv.columns.to_list(),
191
+ datatype=['number', 'markdown'] + (len(distribution_prediction_csv.columns)-1) * ['number'],
192
  )
193
 
194
 
data/conformation_prediction.csv CHANGED
@@ -1,21 +1,18 @@
1
- Model,Pairwise RMSD,*RMSF,Pearson r on Pairwise RMSD ↑,Pearson r on *Global RMSF ↑,Pearson r on *Per target RMSF ↑,*RMWD ↓,MD PCA W2 ↓,Joint PCA W2 ↓,PC sim > 0.5% ↑,Weak contacts J ↑,Transient contacts J ↑,*Exposed residue J ↑,*Exposed MI matrix ρ ↑,CA break % ↓,CA clash % ↓,PepBond break % ↓
2
- MD iid,2.76,1.63,0.96,0.97,0.99,0.71,0.76,0.70,93.9,0.90,0.80,0.93,0.56,0.0,0.1,3.4
3
- MD 2.5 ns,1.54,0.98,0.89,0.85,0.85,2.21,1.57,1.93,36.6,0.62,0.45,0.64,0.24,0.0,0.1,3.4
4
- EigenFold,5.96,NaN,-0.04,NaN,NaN,NaN,2.35,7.96,12.2,0.36,0.18,NaN,NaN,0.7,9.6,NaN
5
- MSA-depth256,0.84,0.53,0.25,0.34,0.59,3.63,1.83,2.90,29.3,0.30,0.28,0.33,0.06,0.0,0.2,5.9
6
- MSA-depth64,2.03,1.51,0.24,0.30,0.57,4.00,1.87,3.32,18.3,0.38,0.27,0.38,0.12,0.0,0.2,8.4
7
- MSA-depth32,5.71,7.96,0.07,0.17,0.53,6.12,2.50,5.67,17.1,0.39,0.24,0.36,0.15,0.0,0.5,13.0
8
- Str2Str-ODE (t=0.1),1.66,NaN,0.13,NaN,NaN,NaN,2.12,4.42,6.1,0.42,0.17,NaN,NaN,0.0,0.1,13.7
9
- Str2Str-ODE (t=0.3),3.15,NaN,0.12,NaN,NaN,NaN,2.23,4.75,9.8,0.41,0.17,NaN,NaN,0.0,0.1,14.8
10
- Str2Str-SDE (t=0.1),4.74,NaN,0.10,NaN,NaN,NaN,2.54,8.84,9.8,0.40,0.13,NaN,NaN,1.6,0.2,23.0
11
- Str2Str-SDE (t=0.3),7.54,NaN,0.00,NaN,NaN,NaN,3.29,12.28,7.3,0.35,0.13,NaN,NaN,1.5,0.2,21.4
12
- AlphaFlow-PDB,2.58,1.20,0.27,0.46,0.81,2.96,1.66,2.60,37.8,0.44,0.33,0.42,0.18,0.0,0.2,6.6
13
- AlphaFlow-MD,2.88,1.63,0.53,0.66,0.85,2.68,1.53,2.28,39.0,0.57,0.38,0.50,0.24,0.0,0.2,21.7
14
- ESMFlow-PDB,3.00,1.68,0.14,0.27,0.71,4.20,1.77,3.54,28.0,0.42,0.29,0.41,0.16,0.0,0.6,5.4
15
- ESMFlow-MD,3.34,2.13,0.19,0.30,0.76,3.63,1.54,3.15,25.6,0.51,0.33,0.47,0.21,0.0,0.3,10.9
16
- ConfDiff-Open-ClsFree,3.68,2.12,0.40,0.54,0.83,2.92,1.50,2.54,46.3,0.54,0.33,0.47,0.21,0.0,1.2,5.7
17
- ConfDiff-Open-PDB,2.90,1.43,0.38,0.51,0.82,2.97,1.57,2.51,34.1,0.47,0.34,0.43,0.18,0.0,0.9,5.7
18
- ConfDiff-Open-MD,3.43,2.21,0.59,0.67,0.85,2.76,1.44,2.25,35.4,0.59,0.36,0.50,0.24,0.0,0.8,6.3
19
- ConfDiff-ESM-ClsFree,4.04,2.84,0.31,0.43,0.82,3.82,1.72,3.06,37.8,0.54,0.31,0.47,0.18,0.0,1.8,4.3
20
- ConfDiff-ESM-PDB,3.42,2.06,0.29,0.40,0.80,3.67,1.70,3.17,34.1,0.48,0.31,0.42,0.18,0.0,1.6,3.9
21
- ConfDiff-ESM-MD,3.91,2.79,0.35,0.48,0.82,3.67,1.66,2.89,39.0,0.56,0.34,0.48,0.23,0.0,1.5,4.0
 
1
+ Model,apo-TM ↑,holo-TM ↑,TMens ↑,Pairwise TM,CA clash (%) ↓,CA break (%) ↓,PepBond break (%) ↓
2
+ apo model,1.000,0.790,0.895,N/A,N/A,N/A,N/A
3
+ EigenFold,0.831,0.864,0.847,0.907,3.6,0.3,N/A
4
+ MSA-depth256,0.845,0.889,0.867,0.978,0.2,0.0,4.6
5
+ MSA-depth64,0.844,0.883,0.863,0.950,0.2,0.0,5.7
6
+ MSA-depth32,0.824,0.857,0.841,0.864,0.2,0.0,8.9
7
+ Str2Str-ODE (Tmax=0.1),0.762,0.778,0.770,0.954,0.2,0.0,14.0
8
+ Str2Str-ODE (Tmax=0.3),0.766,0.781,0.774,0.872,0.2,0.0,14.7
9
+ Str2Str-SDE (Tmax=0.1),0.682,0.693,0.688,0.760,0.2,1.5,22.6
10
+ Str2Str-SDE (Tmax=0.3),0.680,0.689,0.684,0.639,0.2,1.4,21.1
11
+ AlphaFlow-PDB,0.855,0.891,0.873,0.924,0.3,0.0,6.6
12
+ AlphaFlow-MD,0.857,0.863,0.860,0.894,0.2,0.0,20.8
13
+ ESMFlow-PDB,0.849,0.882,0.866,0.935,0.3,0.0,4.8
14
+ ESMFlow-MD,0.851,0.864,0.858,0.897,0.1,0.0,10.9
15
+ ConfDiff-Open-ClsFree,0.838,0.879,0.859,0.870,0.8,0.0,5.8
16
+ ConfDiff-Open-MD,0.839,0.874,0.857,0.863,0.4,0.0,6.8
17
+ ConfDiff-ESM-ClsFree,0.837,0.864,0.850,0.846,0.7,0.0,4.6
18
+ ConfDiff-ESM-MD,0.836,0.862,0.849,0.846,0.3,0.0,4.1
 
 
 
data/distribution_prediction.csv ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Model,Pairwise RMSD,*RMSF,Pearson r on Pairwise RMSD ↑,Pearson r on *Global RMSF ↑,Pearson r on *Per target RMSF ↑,*RMWD ↓,MD PCA W2 ↓,Joint PCA W2 ↓,PC sim > 0.5% ↑,Weak contacts J ↑,Transient contacts J ↑,*Exposed residue J ↑,*Exposed MI matrix ρ ↑,CA break % ↓,CA clash % ↓,PepBond break % ↓
2
+ MD iid,2.76,1.63,0.96,0.97,0.99,0.71,0.76,0.70,93.9,0.90,0.80,0.93,0.56,0.0,0.1,3.4
3
+ MD 2.5 ns,1.54,0.98,0.89,0.85,0.85,2.21,1.57,1.93,36.6,0.62,0.45,0.64,0.24,0.0,0.1,3.4
4
+ EigenFold,5.96,NaN,-0.04,NaN,NaN,NaN,2.35,7.96,12.2,0.36,0.18,NaN,NaN,0.7,9.6,NaN
5
+ MSA-depth256,0.84,0.53,0.25,0.34,0.59,3.63,1.83,2.90,29.3,0.30,0.28,0.33,0.06,0.0,0.2,5.9
6
+ MSA-depth64,2.03,1.51,0.24,0.30,0.57,4.00,1.87,3.32,18.3,0.38,0.27,0.38,0.12,0.0,0.2,8.4
7
+ MSA-depth32,5.71,7.96,0.07,0.17,0.53,6.12,2.50,5.67,17.1,0.39,0.24,0.36,0.15,0.0,0.5,13.0
8
+ Str2Str-ODE (t=0.1),1.66,NaN,0.13,NaN,NaN,NaN,2.12,4.42,6.1,0.42,0.17,NaN,NaN,0.0,0.1,13.7
9
+ Str2Str-ODE (t=0.3),3.15,NaN,0.12,NaN,NaN,NaN,2.23,4.75,9.8,0.41,0.17,NaN,NaN,0.0,0.1,14.8
10
+ Str2Str-SDE (t=0.1),4.74,NaN,0.10,NaN,NaN,NaN,2.54,8.84,9.8,0.40,0.13,NaN,NaN,1.6,0.2,23.0
11
+ Str2Str-SDE (t=0.3),7.54,NaN,0.00,NaN,NaN,NaN,3.29,12.28,7.3,0.35,0.13,NaN,NaN,1.5,0.2,21.4
12
+ AlphaFlow-PDB,2.58,1.20,0.27,0.46,0.81,2.96,1.66,2.60,37.8,0.44,0.33,0.42,0.18,0.0,0.2,6.6
13
+ AlphaFlow-MD,2.88,1.63,0.53,0.66,0.85,2.68,1.53,2.28,39.0,0.57,0.38,0.50,0.24,0.0,0.2,21.7
14
+ ESMFlow-PDB,3.00,1.68,0.14,0.27,0.71,4.20,1.77,3.54,28.0,0.42,0.29,0.41,0.16,0.0,0.6,5.4
15
+ ESMFlow-MD,3.34,2.13,0.19,0.30,0.76,3.63,1.54,3.15,25.6,0.51,0.33,0.47,0.21,0.0,0.3,10.9
16
+ ConfDiff-Open-ClsFree,3.68,2.12,0.40,0.54,0.83,2.92,1.50,2.54,46.3,0.54,0.33,0.47,0.21,0.0,1.2,5.7
17
+ ConfDiff-Open-PDB,2.90,1.43,0.38,0.51,0.82,2.97,1.57,2.51,34.1,0.47,0.34,0.43,0.18,0.0,0.9,5.7
18
+ ConfDiff-Open-MD,3.43,2.21,0.59,0.67,0.85,2.76,1.44,2.25,35.4,0.59,0.36,0.50,0.24,0.0,0.8,6.3
19
+ ConfDiff-ESM-ClsFree,4.04,2.84,0.31,0.43,0.82,3.82,1.72,3.06,37.8,0.54,0.31,0.47,0.18,0.0,1.8,4.3
20
+ ConfDiff-ESM-PDB,3.42,2.06,0.29,0.40,0.80,3.67,1.70,3.17,34.1,0.48,0.31,0.42,0.18,0.0,1.6,3.9
21
+ ConfDiff-ESM-MD,3.91,2.79,0.35,0.48,0.82,3.67,1.66,2.89,39.0,0.56,0.34,0.48,0.23,0.0,1.5,4.0
data_link/{conformation_prediction.csv β†’ distribution_prediction.csv} RENAMED
File without changes
data_rank/{conformation_prediction.csv β†’ distribution_prediction.csv} RENAMED
File without changes