Update examples

app.py

@@ -32,8 +32,8 @@ THEME = gr.themes.Default()
 DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 CACHE = "./cache"
-MAX_ROWS = 500
-BATCH_SIZE = 32
+MAX_ROWS = 1000
+BATCH_SIZE = 16
 HEADER_FILE = os.path.join("sources", "header.md")
 with open("repos.json", "r") as f:
     MODEL_REPOS = json.load(f)
@@ -676,7 +676,7 @@ if __name__ == "__main__":
                         "\n".join(eg["strings"]), 
                         "smiles", 
                         eg["species"], 
-                        list(EXTRA_METRICS)[:2],
+                        list(EXTRA_METRICS)[:3],
                     ] 
                     for eg in EXAMPLES["line input examples"]
                 ],
@@ -732,7 +732,7 @@ if __name__ == "__main__":
                         "smiles",
                         eg["species"],
                         "",
-                        list(EXTRA_METRICS)[:2],
+                        list(EXTRA_METRICS)[:3],
                     ] for eg in EXAMPLES["file examples"]
                 ],
                 example_labels=[

example-data/examples.json

@@ -1,25 +1,47 @@
 {
     "line input examples": [
         {
-            "label": "Y. pestis (plague) vs Ciprofloxacin, Ceftriaxone, Cefiderocol, Linezolid, Gepotidacin",
+            "label": "Y. pestis (plague) vs Ciprofloxacin, Ceftriaxone, Cefiderocol",
             "strings": [
                 "Ciprofloxacin: C1CC1N2C=C(C(=O)C3=CC(=C(C=C32)N4CCNCC4)F)C(=O)O",
                 "Ceftriaxone: CN1C(=NC(=O)C(=O)N1)SCC2=C(N3[C@@H]([C@@H](C3=O)NC(=O)/C(=N\\OC)/C4=CSC(=N4)N)SC2)C(=O)O",
                 "Cefiderocol: CC(C)(C(=O)O)O/N=C(/C1=CSC(=N1)N)\\C(=O)N[C@H]2[C@@H]3N(C2=O)C(=C(CS3)C[N+]4(CCCC4)CCNC(=O)C5=C(C(=C(C=C5)O)O)Cl)C(=O)[O-]",
-                "Linezolid: CC(=O)NC[C@H]1CN(C(=O)O1)C2=CC(=C(C=C2)N3CCOCC3)F",
-                "Gepotidacin: C1CC2=CC(=NC=C2OC1)CNC3CCN(CC3)C[C@@H]4CN5C(=O)C=CC6=C5N4C(=O)C=N6"
             ],
             "species": [
                 "Yersinia pestis"
             ]
         },
         {
-            "label": "S. aureus vs Doxorubicin, Ampicillin, Amoxicillin, Meropenem, Tetracycline, Anhydrotetracycline",
+            "label": "E. coli, K. pneumoniae, & S. aureus vs Ampicillin, Linezolid, Amoxicillin, Meropenem",
             "strings": [
-                "Doxorubicin: C[C@H]1[C@H]([C@H](C[C@@H](O1)O[C@H]2C[C@@](CC3=C2C(=C4C(=C3O)C(=O)C5=C(C4=O)C(=CC=C5)OC)O)(C(=O)CO)O)N)O",
                 "Ampicillin: CC1([C@@H](N2[C@H](S1)[C@@H](C2=O)NC(=O)[C@@H](C3=CC=CC=C3)N)C(=O)O)C",
+                "Linezolid: CC(=O)NC[C@H]1CN(C(=O)O1)C2=CC(=C(C=C2)N3CCOCC3)F",
                 "Amoxicillin: CC1([C@@H](N2[C@H](S1)[C@@H](C2=O)NC(=O)[C@@H](C3=CC=C(C=C3)O)N)C(=O)O)C", 
-                "Meropenem: C[C@@H]1[C@@H]2[C@H](C(=O)N2C(=C1S[C@H]3C[C@H](NC3)C(=O)N(C)C)C(=O)O)[C@@H](C)O",
+                "Meropenem: C[C@@H]1[C@@H]2[C@H](C(=O)N2C(=C1S[C@H]3C[C@H](NC3)C(=O)N(C)C)C(=O)O)[C@@H](C)O"
+            ],
+            "species": [
+                "Escherichia coli", 
+                "Klebsiella pneumoniae",
+                "Staphylococcus aureus"
+            ]
+        },
+        {
+            "label": "E. coli, P. aeruginosa, & S. aureus vs Gepotidacin, Murepavadin, Zosurabalpin, Plazomicin",
+            "strings": [
+                "Murepavadin: CC[C@H](C)[C@H]1C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N2CCC[C@@H]2C(=O)N3CCC[C@H]3C(=O)N[C@H](C(=O)N[C@H](C(=O)N1)CC4=CNC5=CC=CC=C54)[C@@H](C)O)CO)C)CCN)CCN)CC6=CNC7=CC=CC=C76)CCN)CCN)CCCN)CCN",
+                "Gepotidacin: C1CC2=CC(=NC=C2OC1)CNC3CCN(CC3)C[C@@H]4CN5C(=O)C=CC6=C5N4C(=O)C=N6",
+                "Zosurabalpin: CN1[C@H](C(=O)NCC2=C(C=CC=C2SC3=C(CN[C@H](C(=O)N[C@H](C1=O)CCCCN)CCCN)C=CC=N3)C4=CC=C(C=C4)C(=O)O)CC5=CNC6=CC=CC=C65", 
+                "Plazomicin: C[C@@]1(CO[C@@H]([C@@H]([C@H]1NC)O)O[C@H]2[C@@H](C[C@@H]([C@H]([C@@H]2O)O[C@@H]3[C@@H](CC=C(O3)CNCCO)N)N)NC(=O)[C@H](CCN)O)O"
+            ],
+            "species": [
+                "Escherichia coli", 
+                "Pseudomonas aeruginosa",
+                "Staphylococcus aureus"
+            ]
+        },
+        {
+            "label": "S. aureus vs Tetracycline, Anhydrotetracycline",
+            "strings": [
                 "Tetracycline: C[C@@]1([C@H]2C[C@H]3[C@@H](C(=O)C(=C([C@]3(C(=O)C2=C(C4=C1C=CC=C4O)O)O)O)C(=O)N)N(C)C)O",
                 "Anhydrotetracycline: CC1=C2C=CC=C(C2=C(C3=C1C[C@H]4[C@@H](C(=O)C(=C([C@]4(C3=O)O)O)C(=O)N)N(C)C)O)O"
             ],
@@ -28,43 +50,70 @@
             ]
         },
         {
-            "label": "E. coli and A. baumannii vs Halicin, Abaucin, Trimethoprim, Sulfamethoxazole, Amikacin, Isoniazid",
+            "label": "E. coli & A. baumannii vs Trimethoprim, Sulfamethoxazole",
             "strings": [
-                "Halicin: C1=C(SC(=N1)SC2=NN=C(S2)N)[N+](=O)[O-]",
-                "Abaucin: C1CN(CCC12C3=CC=CC=C3NC(=O)O2)CCC4=CC=C(C=C4)C(F)(F)F",
                 "Trimethoprim: COC1=CC(=CC(=C1OC)OC)CC2=CN=C(N=C2N)N",
-                "Amikacin: CC1=CC(=NO1)NS(=O)(=O)C2=CC=C(C=C2)N",
                 "Sulfamethoxazole: C1[C@@H]([C@H]([C@@H]([C@H]([C@@H]1NC(=O)[C@H](CCN)O)O[C@@H]2[C@@H]([C@H]([C@@H]([C@H](O2)CO)O)N)O)O)O[C@@H]3[C@@H]([C@H]([C@@H]([C@H](O3)CN)O)O)O)N", 
-                "Isoniazid: C1=CN=CC=C1C(=O)NN"
             ],
             "species": [
-                "Escherichia coli", 
-                "Acinetobacter baumannii"
+                "Escherichia coli"
             ]
         },
         {
-            "label": "A. baumannii vs Murepavadin, Vancomycin, Zosurabalpin, Plazomicin, Gentamicin, Rifampicin",
+            "label": "E. coli, A. baumannii, & S. aureus vs Halicin, Abaucin, Compound 1 (from Wong, 2024)",
             "strings": [
-                "Murepavadin: CC[C@H](C)[C@H]1C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N[C@H](C(=O)N2CCC[C@@H]2C(=O)N3CCC[C@H]3C(=O)N[C@H](C(=O)N[C@H](C(=O)N1)CC4=CNC5=CC=CC=C54)[C@@H](C)O)CO)C)CCN)CCN)CC6=CNC7=CC=CC=C76)CCN)CCN)CCCN)CCN",
-                "Vancomycin: C[C@H]1[C@H]([C@@](C[C@@H](O1)O[C@@H]2[C@H]([C@@H]([C@H](O[C@H]2OC3=C4C=C5C=C3OC6=C(C=C(C=C6)[C@H]([C@H](C(=O)N[C@H](C(=O)N[C@H]5C(=O)N[C@@H]7C8=CC(=C(C=C8)O)C9=C(C=C(C=C9O)O)[C@H](NC(=O)[C@H]([C@@H](C1=CC(=C(O4)C=C1)Cl)O)NC7=O)C(=O)O)CC(=O)N)NC(=O)[C@@H](CC(C)C)NC)O)Cl)CO)O)O)(C)N)O",
-                "Zosurabalpin: CN1[C@H](C(=O)NCC2=C(C=CC=C2SC3=C(CN[C@H](C(=O)N[C@H](C1=O)CCCCN)CCCN)C=CC=N3)C4=CC=C(C=C4)C(=O)O)CC5=CNC6=CC=CC=C65", 
-                "Plazomicin: C[C@@]1(CO[C@@H]([C@@H]([C@H]1NC)O)O[C@H]2[C@@H](C[C@@H]([C@H]([C@@H]2O)O[C@@H]3[C@@H](CC=C(O3)CNCCO)N)N)NC(=O)[C@H](CCN)O)O",
-                "Gentamicin: CC(C1CCC(C(O1)OC2C(CC(C(C2O)OC3C(C(C(CO3)(C)O)NC)O)N)N)N)NC",
-                "Rifampicin: C[C@H]1/C=C/C=C(\\C(=O)NC2=C(C(=C3C(=C2O)C(=C(C4=C3C(=O)[C@](O4)(O/C=C/[C@@H]([C@H]([C@H]([C@@H]([C@@H]([C@@H]([C@H]1O)C)O)C)OC(=O)C)C)OC)C)C)O)O)/C=N/N5CCN(CC5)C)/CC"
+                "Halicin: C1=C(SC(=N1)SC2=NN=C(S2)N)[N+](=O)[O-]",
+                "Abaucin: C1CN(CCC12C3=CC=CC=C3NC(=O)O2)CCC4=CC=C(C=C4)C(F)(F)F",
+                "Compound 1: ClC1=CC(Cl)=CC=C1OCC(NC2=C(C(O)=O)C=CC(Cl)=C2)=O"
             ],
             "species": [
-                "Acinetobacter baumannii"
+                "Escherichia coli", 
+                "Acinetobacter baumannii",
+                "Staphylococcus aureus"
+
             ]
         },
         {
-            "label": "E. coli vs Debio-1452, Debio-1452-NH3, Fabimycin, 5-FU, Carmofur, Etoposide",
+            "label": "E. coli, P. aeruginosa & S. aureus vs Debio-1452, Debio-1452-NH3, Fabimycin",
             "strings": [
                 "Debio-1452: CC1=C(OC2=CC=CC=C12)CN(C)C(=O)/C=C/C3=CC4=C(NC(=O)CC4)N=C3",
                 "Debio-1452-NH3: CC1=C(OC2=CC=CC=C12)CN(C)C(=O)/C=C/C3=CC4=C(NC(=O)[C@@H](C4)N)N=C3",
-                "Fabimycin: CC1=C(OC2=CC=CC=C12)CN(C)C(=O)/C=C/C3=CC4=C(NC(=O)[C@H](CC4)[NH3+])N=C3.[Cl-]",
+                "Fabimycin: CC1=C(OC2=CC=CC=C12)CN(C)C(=O)/C=C/C3=CC4=C(NC(=O)[C@H](CC4)[NH3+])N=C3.[Cl-]"
+            ],
+            "species": [
+                "Escherichia coli", 
+                "Pseudomonas aeruginosa",
+                "Staphylococcus aureus"
+            ]
+        },
+        {
+            "label": "E. coli, A. baumannii, K. pneumoniae, P. aeruginosa & S. aureus vs 6NDM, 6NDM-NH3",
+            "strings": [
+                "6NDM: CN1C(C=C(C)C2=CC3=C(N4C(C=C3C)=O)C(OCC4)=C12)=O",
+                "6NDM-NH3: CN1C(C=C(C)C2=CC3=C(N4C(C=C3C)=O)C(OCC4C[NH3+])=C12)=O",
+            ],
+            "species": [
+                "Escherichia coli", 
+                "Acinetobacter baumannii",
+                "Klebsiella pneumoniae",
+                "Pseudomonas aeruginosa",
+                "Staphylococcus aureus"
+            ]
+        },
+        {
+            "label": "E. coli vs Doxorubicin, 5-FU, Carmofur, Etoposide, Bleomycin, Cyclophosphamide, Vincristine, Procarbazine, Oxaliplatin, Docetaxel, Gemcitabine",
+            "strings": [
+                "Doxorubicin: C[C@H]1[C@H]([C@H](C[C@@H](O1)O[C@H]2C[C@@](CC3=C2C(=C4C(=C3O)C(=O)C5=C(C4=O)C(=CC=C5)OC)O)(C(=O)CO)O)N)O",
                 "5-FU: C1=C(C(=O)NC(=O)N1)F",
                 "Carmofur: CCCCCCNC(=O)N1C=C(C(=O)NC1=O)F",
-                "Etoposide: C[C@@H]1OC[C@@H]2[C@@H](O1)[C@@H]([C@H]([C@@H](O2)O[C@H]3[C@H]4COC(=O)[C@@H]4[C@@H](C5=CC6=C(C=C35)OCO6)C7=CC(=C(C(=C7)OC)O)OC)O)O"
+                "Etoposide: C[C@@H]1OC[C@@H]2[C@@H](O1)[C@@H]([C@H]([C@@H](O2)O[C@H]3[C@H]4COC(=O)[C@@H]4[C@@H](C5=CC6=C(C=C35)OCO6)C7=CC(=C(C(=C7)OC)O)OC)O)O",
+                "Bleomycin: CC1=C(N=C(N=C1N)[C@H](CC(=O)N)NC[C@@H](C(=O)N)N)C(=O)N[C@@H]([C@H](C2=CN=CN2)OC3C(C(C(C(O3)CO)O)O)OC4C(C(C(C(O4)CO)O)OC(=O)N)O)C(=O)N[C@H](C)[C@H]([C@H](C)C(=O)N[C@@H]([C@@H](C)O)C(=O)NCCC5=NC(=CS5)C6=NC(=CS6)C(=O)NCCC[S+](C)C)O",
+                "Cyclophosphamide: C1CNP(=O)(OC1)N(CCCl)CCCl  ",
+                "Vincristine: CC[C@@]1(C[C@@H]2C[C@@](C3=C(CCN(C2)C1)C4=CC=CC=C4N3)(C5=C(C=C6C(=C5)[C@]78CCN9[C@H]7[C@@](C=CC9)([C@H]([C@@]([C@@H]8N6C=O)(C(=O)OC)O)OC(=O)C)CC)OC)C(=O)OC)O ",
+                "Procarbazine: CC(C)NC(=O)C1=CC=C(C=C1)CNNC",
+                "Oxaliplatin: C1CC[C@H]([C@@H](C1)[NH-])[NH-].C(=O)(C(=O)O)O.[Pt+2]",
+                "Docetaxel: CC1=C2[C@H](C(=O)[C@@]3([C@H](C[C@@H]4[C@]([C@H]3[C@@H]([C@@](C2(C)C)(C[C@@H]1OC(=O)[C@@H]([C@H](C5=CC=CC=C5)NC(=O)OC(C)(C)C)O)O)OC(=O)C6=CC=CC=C6)(CO4)OC(=O)C)O)C)O",
+                "Gemcitabine: C1=CN(C(=O)N=C1N)[C@H]2C([C@@H]([C@H](O2)CO)O)(F)F"
             ],
             "species": [
                 "Escherichia coli"
@@ -85,7 +134,7 @@
             ]
         },
         {
-            "label": "K. pneumoniae vs CHIR-090, SCH79797, DBeQ, Tenovin-6, Pyrimethamine, Aminopterin",
+            "label": "E. coli & K. pneumoniae vs CHIR-090, SCH79797, DBeQ, Tenovin-6, Pyrimethamine, Aminopterin",
             "strings": [
                 "CHIR-090: C[C@H]([C@@H](C(=O)NO)NC(=O)C1=CC=C(C=C1)C#CC2=CC=C(C=C2)CN3CCOCC3)O",
                 "SCH79797: CC(C)C1=CC=C(C=C1)CN2C=CC3=C2C=CC4=C3C(=NC(=N4)NC5CC5)N",
@@ -95,6 +144,7 @@
                 "Aminopterin: C1=CC(=CC=C1C(=O)N[C@@H](CCC(=O)O)C(=O)O)NCC2=CN=C3C(=N2)C(=NC(=N3)N)N"
             ],
             "species": [
+                "Escherichia coli", 
                 "Klebsiella pneumoniae"
             ]
         }
@@ -102,20 +152,20 @@
     "file examples": [
         {
             "label": "E. coli training data from Stokes J. et al., Cell (2020)",
-            "file": "example-data/stokes2020-eco.csv", 
-            "column": "SMILES", 
+            "file": "example-data/stokes2020-eco-1000.csv", 
+            "column": "smiles", 
             "species": "Escherichia coli"
         },
         {
-            "label": "A. baumannii training data from Liu (2023)",
-            "file": "example-data/liu23-abau.csv", 
-            "column": "SMILES", 
+            "label": "A. baumannii training data from Liu G., Nature Chemical Biology (2023)",
+            "file": "example-data/liu23-abau-1000.csv", 
+            "column": "smiles", 
             "species": "Acinetobacter baumannii"
         },
         {
-            "label": "S. aureus training data from Wong (2024)",
-            "file": "example-data/wong24-sau-tox-5000.csv", 
-            "column": "SMILES", 
+            "label": "S. aureus training data from Wong F., Nature (2024)",
+            "file": "example-data/wong24-sau-tox-1000.csv", 
+            "column": "smiles", 
             "species": "Staphylococcus aureus"
         }
     ]