add label and head

.gitignore

@@ -11,3 +11,4 @@ eval-results/
 eval-queue-bk/
 eval-results-bk/
 logs/
+read_csv.py

app.py

@@ -3,7 +3,7 @@ import base64
 import gradio as gr
 import pandas as pd
 from apscheduler.schedulers.background import BackgroundScheduler
-
+import numpy as np
 from src.about import (
     CITATION_BUTTON_LABEL,
     CITATION_BUTTON_TEXT,
@@ -42,6 +42,13 @@ in-depth evaluation framework for protein foundation models, driving their devel
 ## [Paper](https://www.arxiv.org/pdf/2409.06744) | [Website](https://proteinbench.github.io/)
 """
 
+def convert_to_float(df):
+    columns = df.columns
+    for col in columns[1:]:
+        df[col] = df[col].astype('float')
+    return df
+    
+
 # ### Space initialisation
 
 demo = gr.Blocks(css=custom_css)
@@ -59,10 +66,12 @@ with demo:
         with gr.TabItem("🏆 Inverse Folding Leaderboard", elem_id='inverse-folding-table', id=0,):
             with gr.Row():
                 inverse_folding_csv = pd.read_csv('data/inverse_folding.csv')
+                print(convert_to_float(inverse_folding_csv))
                 inverse_folding_table = gr.components.DataFrame(
-                    inverse_folding_csv,
+                    value=convert_to_float(inverse_folding_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=inverse_folding_csv.columns.to_list(),
                     datatype=['markdown'] + (len(inverse_folding_csv.columns)-1) * ['number'],
                     
                 )
@@ -70,73 +79,81 @@ with demo:
             with gr.Row():
                 structure_design_csv = pd.read_csv('data/structure_design.csv')
                 structure_design_table = gr.components.DataFrame(
-                    structure_design_csv,
+                    value=convert_to_float(structure_design_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=structure_design_csv.columns.to_list(),
                     datatype=['markdown'] + (len(structure_design_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏆 Sequence Design Leaderboard", elem_id='sequence-design-table', id=2,):
             with gr.Row():
-                sequence_design_csv = pd.read_csv('data/sequence_design.csv'),
+                sequence_design_csv = pd.read_csv('data/sequence_design.csv')
                 sequence_design_table = gr.components.DataFrame(
-                    sequence_design_csv,
+                    value=convert_to_float(sequence_design_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=sequence_design_csv.columns.to_list(),
                     datatype=['markdown'] + (len(sequence_design_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏆 Sequence-Structure Co-Design Leaderboard", elem_id='co-design-table', id=3,):
             with gr.Row():
                 co_design_csv = pd.read_csv('data/co_design.csv')
                 co_design_table = gr.components.DataFrame(
-                    co_design_csv,
+                    value=convert_to_float(co_design_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=co_design_csv.columns.to_list(),
                     datatype=['markdown'] + (len(co_design_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏆 Motif Scaffolding Leaderboard", elem_id='motif-scaffolding-table', id=4,):
             with gr.Row():
                 motif_scaffolding_csv = pd.read_csv('data/motif_scaffolding.csv')
                 motif_scaffolding_table = gr.components.DataFrame(
-                    motif_scaffolding_csv,
+                    value=convert_to_float(motif_scaffolding_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=motif_scaffolding_csv.columns.to_list(),
                     datatype=['markdown'] + (len(motif_scaffolding_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏆 Antibody Design Leaderboard", elem_id='antibody-design-table', id=5,):
             with gr.Row():
                 antibody_design_csv = pd.read_csv('data/antibody_design.csv')
                 antibody_design_table = gr.components.DataFrame(
-                    antibody_design_csv,
+                    value=convert_to_float(antibody_design_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=antibody_design_csv.columns.to_list(),
                     datatype=['markdown'] + (len(antibody_design_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏅 Protein Folding Leaderboard", elem_id='protein-folding-table', id=6,):
             with gr.Row():
                 protein_folding_csv = pd.read_csv('data/protein_folding.csv')
                 protein_folding_table = gr.components.DataFrame(
-                    protein_folding_csv,
+                    value=convert_to_float(protein_folding_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=protein_folding_csv.columns.to_list(),
                     datatype=['markdown'] + (len(protein_folding_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏅 Multi-State Prediction Leaderboard", elem_id='multi-state-prediction-table', id=7,):
             with gr.Row():
                 multi_state_prediction_csv = pd.read_csv('data/multi_state_prediction.csv')
                 multi_state_prediction_table = gr.components.DataFrame(
-                    multi_state_prediction_csv,
+                    value=convert_to_float(multi_state_prediction_csv).values,
                     height=99999,
                     interactive=False,
+                    headers=multi_state_prediction_csv.columns.to_list(),
                     datatype=['markdown'] + (len(multi_state_prediction_csv.columns)-1) * ['number'],
                 )
         with gr.TabItem("🏅 Conformation Prediction Leaderboard", elem_id='conformation-prediction-table', id=8,):
             with gr.Row():
-                conformation_prediction = pd.read_csv('data/conformation_prediction.csv')
+                conformation_prediction_csv = pd.read_csv('data/conformation_prediction.csv')
                 conformation_prediction_table = gr.components.DataFrame(
-                    conformation_prediction,
+                    value=convert_to_float(conformation_prediction_csv).values,
                     height=99999,
                     interactive=False,
-                    datatype=['markdown'] + (len(conformation_prediction.columns)-1) * ['number'],
+                    headers=conformation_prediction_csv.columns.to_list(),
+                    datatype=['markdown'] + (len(conformation_prediction_csv.columns)-1) * ['number'],
                 )
 
 

data/antibody_design.csv

@@ -1,9 +1,9 @@
-Model,AAR ↑,RMSD ↓,TM-score ↑,Binding Energy ↓,SeqSim-outer ↓,SeqSim-inner ↑,PHR ↓,CN-score ↑,Clashes-inner ↓,Clashes-outer ↓,SeqNat ↑,Total Energy ↓,scRMSD ↓
-RAbD (natural),100.00%,0.00,1.00,-15.33,0.26,-,45.78%,50.19,0.07,0.00,-1.74,-16.76,1.77
-HERN,33.17%,9.86,0.16,1242.77,0.41,-,39.83%,0.04,0.04,3.25,-1.47,5408.74,9.89
-MEAN,33.47%,1.82,0.25,263.90,0.65,-,40.74%,1.33,11.65,0.29,-1.83,1077.32,2.77
-dyMEAN,40.95%,2.36,0.36,889.28,0.58,-,42.04%,1.49,9.15,0.47,-1.79,1642.65,2.11
-*dyMEAN-FixFR,40.05%,2.37,0.35,612.75,0.60,0.96,43.75%,1.14,8.88,0.48,-1.82,1239.29,2.48
-*DiffAb,35.04%,2.53,0.37,489.42,0.37,0.45,40.68%,2.02,1.84,0.19,-1.88,495.69,2.57
-*AbDPO,31.29%,2.79,0.35,116.06,0.38,0.60,69.69%,1.33,4.14,0.10,-1.99,270.12,2.79
-*AbDPO++,36.25%,2.48,0.35,223.73,0.39,0.54,44.51%,2.34,1.66,0.08,-1.78,338.14,2.50
+Model,AAR ↑,RMSD ↓,TM-score ↑,Binding Energy ↓,SeqSim-outer ↓,SeqSim-inner ↑,PHR (%) ↓,CN-score ↑,Clashes-inner ↓,Clashes-outer ↓,SeqNat ↑,Total Energy ↓,scRMSD ↓
+RAbD (natural),100.00,0.00,1.00,-15.33,0.26,NaN,45.78,50.19,0.07,0.00,-1.74,-16.76,1.77
+HERN,33.17,9.86,0.16,1242.77,0.41,NaN,39.83,0.04,0.04,3.25,-1.47,5408.74,9.89
+MEAN,33.47,1.82,0.25,263.90,0.65,NaN,40.74,1.33,11.65,0.29,-1.83,1077.32,2.77
+dyMEAN,40.95,2.36,0.36,889.28,0.58,NaN,42.04,1.49,9.15,0.47,-1.79,1642.65,2.11
+*dyMEAN-FixFR,40.05,2.37,0.35,612.75,0.60,0.96,43.75,1.14,8.88,0.48,-1.82,1239.29,2.48
+*DiffAb,35.04,2.53,0.37,489.42,0.37,0.45,40.68,2.02,1.84,0.19,-1.88,495.69,2.57
+*AbDPO,31.29,2.79,0.35,116.06,0.38,0.60,69.69,1.33,4.14,0.10,-1.99,270.12,2.79
+*AbDPO++,36.25,2.48,0.35,223.73,0.39,0.54,44.51,2.34,1.66,0.08,-1.78,338.14,2.50

data/co_design.csv

@@ -1,5 +1,5 @@
 Model,scTM (L=100) ↑,scRMSD (L=100) ↓,Max Clust. (L=100) ↑,Max TM (L=100) ↓,scTM (L=200) ↑,scRMSD (L=200) ↓,Max Clust. (L=200) ↑,Max TM (L=200) ↓,scTM (L=300) ↑,scRMSD (L=300) ↓,Max Clust. (L=300) ↑,Max TM (L=300) ↓,scTM (L=500) ↑,scRMSD (L=500) ↓,Max Clust. (L=500) ↑,Max TM (L=500) ↓
-Native PDBs,0.91,2.98,0.75,-,0.88,3.24,0.77,-,0.92,3.94,0.75,-,0.90,9.64,0.80,-
+Native PDBs,0.91,2.98,0.75,NaN,0.88,3.24,0.77,NaN,0.92,3.94,0.75,NaN,0.90,9.64,0.80,NaN
 ProteinGenerator,0.91,3.75,0.24,0.73,0.88,6.24,0.25,0.72,0.81,9.26,0.22,0.71,0.69,17.00,0.18,0.73
 ProtPardelle*,0.56,12.90,0.57,0.66,0.64,13.67,0.10,0.69,0.69,14.91,0.04,0.72,0.44,43.15,0.60,0.69
 Multiflow,0.96,1.10,0.33,0.71,0.95,1.61,0.42,0.71,0.96,2.14,0.58,0.71,0.95,2.71,0.62,0.71

data/conformation_prediction.csv

@@ -1,14 +1,14 @@
 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 % ↓
 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
 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
-EigenFold,5.96,-,-0.04,-,-,-,2.35,7.96,12.2,0.36,0.18,-,-,0.7,9.6,-
+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
 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
 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
 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
-Str2Str-ODE (t=0.1),1.66,-,0.13,-,-,-,2.12,4.42,6.1,0.42,0.17,-,-,0.0,0.1,13.7
-Str2Str-ODE (t=0.3),3.15,-,0.12,-,-,-,2.23,4.75,9.8,0.41,0.17,-,-,0.0,0.1,14.8
-Str2Str-SDE (t=0.1),4.74,-,0.10,-,-,-,2.54,8.84,9.8,0.40,0.13,-,-,1.6,0.2,23.0
-Str2Str-SDE (t=0.3),7.54,-,0.00,-,-,-,3.29,12.28,7.3,0.35,0.13,-,-,1.5,0.2,21.4
+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
+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
+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
+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
 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
 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
 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

data/inverse_folding.csv

@@ -1,5 +1,5 @@
 Model,CASP AAR ↑,CAMEO AAR ↑,scTM (L=100) ↑,pLDDT (L=100) ↑,scTM (L=200) ↑,pLDDT (L=200) ↑,scTM (L=300) ↑,pLDDT (L=300) ↑,scTM (L=400) ↑,pLDDT (L=400) ↑,scTM (L=500) ↑,pLDDT (L=500) ↑
 ProteinMPNN,0.450,0.468,0.962,94.14,0.945,89.34,0.962,90.28,0.875,83.76,0.568,67.09
-ESM-IF1,-,-,0.810,88.83,0.635,69.67,0.336,74.36,0.449,64.59,0.462,58.97
+ESM-IF1,NaN,NaN,0.810,88.83,0.635,69.67,0.336,74.36,0.449,64.59,0.462,58.97
 LM-Design,0.516,0.570,0.834,78.45,0.373,58.41,0.481,69.86,0.565,59.87,0.397,56.35
-ESM3,-,-,0.942,86.60,0.486,60.69,0.632,70.78,0.564,62.63,0.452,59.37
+ESM3,NaN,NaN,0.942,86.60,0.486,60.69,0.632,70.78,0.564,62.63,0.452,59.37

data/multi_state_prediction.csv

@@ -1,5 +1,5 @@
 Model,RMSDens N=10,RMSDens N=100,RMSDens N=500,RMSDens N=1000,RMSD Cluster 3 N=10,RMSD Cluster 3 N=100,RMSD Cluster 3 N=500,RMSD Cluster 3 N=1000,Pairwise RMSD,CA clash (%),CA break (%),PepBond break (%)
-EigenFold,1.56,1.50,1.47,1.46,2.54,2.48,2.46,2.46,0.85,1.4,4.3,-
+EigenFold,1.56,1.50,1.47,1.46,2.54,2.48,2.46,2.46,0.85,1.4,4.3,NaN
 MSA-depth256,1.57,1.54,1.52,1.52,2.51,2.47,2.45,2.45,0.20,0.0,0.0,9.2
 MSA-depth64,1.60,1.54,1.51,1.50,2.48,2.40,2.35,2.33,0.55,0.0,0.0,7.9
 MSA-depth32,1.67,1.53,1.45,1.41,2.39,2.21,1.93,1.87,2.14,0.6,0.0,10.6

data/protein_folding.csv

@@ -3,4 +3,4 @@ AlphaFold2,0.871,3.21,0.860,0.900,0.3,0.0,4.8
 OpenFold,0.870,3.21,0.856,0.895,0.4,0.0,2.0
 RoseTTAFold2,0.859,3.52,0.845,0.888,0.3,0.2,5.5
 ESMFold,0.847,3.98,0.826,0.870,0.3,0.0,4.7
-EigenFold*,0.743,7.65,0.703,0.737,8.0,0.5,-
+EigenFold*,0.743,7.65,0.703,0.737,8.0,0.5,NaN

data/sequence_design.csv

@@ -1,5 +1,5 @@
 Model,ppl (L=100) ↓,pLDDT (L=100) ↑,pairwise TM (L=100) ↓,Max Clust. (L=100) ↑,Max TM (L=100) ↓,ppl (L=200) ↓,pLDDT (L=200) ↑,pairwise TM (L=200) ↓,Max Clust. (L=200) ↑,Max TM (L=200) ↓,ppl (L=300) ↓,pLDDT (L=300) ↑,pairwise TM (L=300) ↓,Max Clust. (L=300) ↑,Max TM (L=300) ↓,ppl (L=500) ↓,pLDDT (L=500) ↑,pairwise TM (L=500) ↓,Max Clust. (L=500) ↑,Max TM (L=500) ↓
-Native Seqs,-,68.46,0.55,0.75,-,-,61.91,0.49,0.78,-,-,61.49,0.51,0.85,-,-,62.95,0.51,0.78,-
+Native Seqs,NaN,68.46,0.55,0.75,NaN,NaN,61.91,0.49,0.78,NaN,NaN,61.49,0.51,0.85,NaN,NaN,62.95,0.51,0.78,NaN
 Progen 2 (700M),8.28,64.00,0.42,0.94,0.64,5.68,69.91,0.40,0.91,0.69,6.25,65.69,0.42,0.93,0.66,4.27,61.45,0.32,0.95,0.68
 EvoDiff,16.89,50.20,0.43,0.98,0.69,17.28,50.66,0.36,1.00,0.71,17.13,45.14,0.31,1.00,0.68,16.51,43.14,0.31,1.00,0.69
 DPLM (650M),6.21,85.38,0.50,0.80,0.74,4.61,93.54,0.54,0.70,0.91,3.47,93.07,0.57,0.63,0.91,3.33,87.73,0.43,0.85,0.85

data/structure_design.csv

@@ -1,5 +1,5 @@
 Model,scTM (L=50) ↑,scRMSD (L=50) ↓,Max TM (L=50) ↓,pairwise TM (L=50) ↓,Max Clust. (L=50) ↑,scTM (L=100) ↑,scRMSD (L=100) ↓,Max TM (L=100) ↓,pairwise TM (L=100) ↓,Max Clust. (L=100) ↑,scTM (L=300) ↑,scRMSD (L=300) ↓,Max TM (L=300) ↓,pairwise TM (L=300) ↓,Max Clust. (L=300) ↑,scTM (L=500) ↑,scRMSD (L=500) ↓,Max TM (L=500) ↓,pairwise TM (L=500) ↓,Max Clust. (L=500) ↑
-Native PDBs,0.91,0.74,-,0.29,0.66,0.96,0.67,-,0.30,0.77,0.97,0.82,-,0.28,0.77,0.97,1.07,-,0.29,0.80
+Native PDBs,0.91,0.74,NaN,0.29,0.66,0.96,0.67,NaN,0.30,0.77,0.97,0.82,NaN,0.28,0.77,0.97,1.07,NaN,0.29,0.80
 RFdiffusion,0.95,0.45,0.65,0.58,0.67,0.98,0.48,0.76,0.41,0.32,0.96,1.03,0.64,0.36,0.65,0.79,5.60,0.62,0.33,0.89
 FrameFlow,0.91,0.58,0.75,0.68,0.39,0.94,0.70,0.72,0.55,0.49,0.92,1.95,0.65,0.43,0.88,0.61,7.92,0.61,0.40,0.92
 Chroma,0.85,1.05,0.59,0.29,0.48,0.89,1.27,0.70,0.35,0.59,0.87,2.47,0.66,0.36,0.67,0.72,6.71,0.60,0.29,0.99