improve lipophilicity and benchmarking templates

data/tabular/choline_transporter_butkiewicz/meta.yaml

@@ -62,56 +62,56 @@ templates:
   - The polymer with the {compound_name__names__noun} of {compound_name#} has an {Tg_exp__names__noun} of {Tg_exp#} {Tg_exp__units}.
   - The polymer with the {compound_name__names__noun} of {compound_name#} has a {Tg_calc__names__noun} of {Tg_calc#} {Tg_calc__units}.
   - The polymer with the {compound_name__names__noun} of {compound_name#} has a {rho_300K_calc__names__noun} of {rho_300K_calc#} {rho_300K_calc__units}.
-  - What is the {Tg_exp__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}? Answer:<EOI> {Tg_exp#} {Tg_exp__units}.
-  - What is the {Tg_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}? Answer:<EOI> {Tg_calc#} {Tg_calc__units}.
-  - What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}? Answer:<EOI> {rho_300K_calc#} {rho_300K_calc__units}.
-  - What is the {Tg_exp__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}? Answer:<EOI> {Tg_exp#} {Tg_exp__units}.
-  - What is the {Tg_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}? Answer:<EOI> {Tg_calc#} {Tg_calc__units}.
-  - What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}? Answer:<EOI> {rho_300K_calc#} {rho_300K_calc__units}.
+  - What is the {Tg_exp__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}? Answer:<EOI>{Tg_exp#} {Tg_exp__units}.
+  - What is the {Tg_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}? Answer:<EOI>{Tg_calc#} {Tg_calc__units}.
+  - What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}? Answer:<EOI>{rho_300K_calc#} {rho_300K_calc__units}.
+  - What is the {Tg_exp__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}? Answer:<EOI>{Tg_exp#} {Tg_exp__units}.
+  - What is the {Tg_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}? Answer:<EOI>{Tg_calc#} {Tg_calc__units}.
+  - What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}? Answer:<EOI>{rho_300K_calc#} {rho_300K_calc__units}.
   - The polymer with the {PSMILES__description} {PSMILES#} has an {Tg_exp__names__noun} of {Tg_exp#} {Tg_exp__units} and a {Tg_calc__names__noun} of {Tg_calc#} {Tg_calc__units}.
   - The polymer with the {compound_name__names__noun} {compound_name#} has an {Tg_exp__names__noun} of {Tg_exp#} {Tg_exp__units} and a {Tg_calc__names__noun} of {Tg_calc#} {Tg_calc__units}.
-  - Compare the {Tg_exp__names__noun} and {Tg_calc__names__noun} for the polymer with the {PSMILES__description} {PSMILES#}. Answer:<EOI> {Tg_exp#} {Tg_exp__units}, {Tg_calc#} {Tg_calc__units}.
-  - Compare the {Tg_exp__names__noun} and {Tg_calc__names__noun} for the polymer with the {compound_name__names__noun} {compound_name#}. Answer:<EOI> {Tg_exp#} {Tg_exp__units}, {Tg_calc#} {Tg_calc__units}.
-  - What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} at 300K? Answer:<EOI> {rho_300K_calc#} {rho_300K_calc__units}.
-  - What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} at 300K? Answer:<EOI> {rho_300K_calc#} {rho_300K_calc__units}.
-  - What is the {Tg_exp__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} in Kelvin? Answer:<EOI> {Tg_exp#}.
-  - What is the {Tg_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} in Kelvin? Answer:<EOI> {Tg_calc#}.
-  - What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} in g/cm^3? Answer:<EOI> {rho_300K_calc#}.
-  - What is the {Tg_exp__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} in Kelvin? Answer:<EOI> {Tg_exp#}.
-  - What is the {Tg_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} in Kelvin? Answer:<EOI> {Tg_calc#}.
-  - What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} in g/cm^3? Answer:<EOI> {rho_300K_calc#}.
+  - Compare the {Tg_exp__names__noun} and {Tg_calc__names__noun} for the polymer with the {PSMILES__description} {PSMILES#}. Answer:<EOI>{Tg_exp#} {Tg_exp__units}, {Tg_calc#} {Tg_calc__units}.
+  - Compare the {Tg_exp__names__noun} and {Tg_calc__names__noun} for the polymer with the {compound_name__names__noun} {compound_name#}. Answer:<EOI>{Tg_exp#} {Tg_exp__units}, {Tg_calc#} {Tg_calc__units}.
+  - What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} at 300K? Answer:<EOI>{rho_300K_calc#} {rho_300K_calc__units}.
+  - What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} at 300K? Answer:<EOI>{rho_300K_calc#} {rho_300K_calc__units}.
+  - What is the {Tg_exp__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} in Kelvin? Answer:<EOI>{Tg_exp#}.
+  - What is the {Tg_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} in Kelvin? Answer:<EOI>{Tg_calc#}.
+  - What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#} in g/cm^3? Answer:<EOI>{rho_300K_calc#}.
+  - What is the {Tg_exp__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} in Kelvin? Answer:<EOI>{Tg_exp#}.
+  - What is the {Tg_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} in Kelvin? Answer:<EOI>{Tg_calc#}.
+  - What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#} in g/cm^3? Answer:<EOI>{rho_300K_calc#}.
   - The polymer with the {PSMILES__description} {PSMILES#} has an {Tg_exp__names__noun} of {Tg_exp#} {Tg_exp__units} and a {rho_300K_calc__names__noun} of {rho_300K_calc#} {rho_300K_calc__units}.
   - The polymer with the {compound_name__names__noun} {compound_name#} has an {Tg_exp__names__noun} of {Tg_exp#} {Tg_exp__units} and a {rho_300K_calc__names__noun} of {rho_300K_calc#} {rho_300K_calc__units}.
-  - Compare the {Tg_exp__names__noun} and {rho_300K_calc__names__noun} for the polymer with the {PSMILES__description} {PSMILES#}. Answer:<EOI> {Tg_exp#} {Tg_exp__units}, {rho_300K_calc#} {rho_300K_calc__units}.
-  - Compare the {Tg_exp__names__noun} and {rho_300K_calc__names__noun} for the polymer with the {compound_name__names__noun} {compound_name#}. Answer:<EOI> {Tg_exp#} {Tg_exp__units}, {rho_300K_calc#} {rho_300K_calc__units}.
+  - Compare the {Tg_exp__names__noun} and {rho_300K_calc__names__noun} for the polymer with the {PSMILES__description} {PSMILES#}. Answer:<EOI>{Tg_exp#} {Tg_exp__units}, {rho_300K_calc#} {rho_300K_calc__units}.
+  - Compare the {Tg_exp__names__noun} and {rho_300K_calc__names__noun} for the polymer with the {compound_name__names__noun} {compound_name#}. Answer:<EOI>{Tg_exp#} {Tg_exp__units}, {rho_300K_calc#} {rho_300K_calc__units}.
   - |-
     Question: What is the {Tg_exp__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}?
     Constraint: You must pick either {%multiple_choice_enum%3%aA1} without using any other words.
     Options:
     {Tg_exp%}
-    Answer:<EOI> {%multiple_choice_result}
+    Answer:<EOI>{%multiple_choice_result}
   - Question: What is the {Tg_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}?
     Constraint: You must pick either {%multiple_choice_enum%3%aA1} without using any other words.
     Options:
     {Tg_calc%}
-    Answer:<EOI> {%multiple_choice_result}
+    Answer:<EOI>{%multiple_choice_result}
   - Question: What is the {rho_300K_calc__names__noun} of the polymer with the {PSMILES__description} {PSMILES#}?
     Constraint: You must pick either {%multiple_choice_enum%3%aA1} without using any other words.
     Options:
     {rho_300K_calc%}
-    Answer:<EOI> {%multiple_choice_result}
+    Answer:<EOI>{%multiple_choice_result}
   - Question: What is the {Tg_exp__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}?
     Constraint: You must pick either {%multiple_choice_enum%3%aA1} without using any other words.
     Options:
     {Tg_exp%}
-    Answer:<EOI> {%multiple_choice_result}
+    Answer:<EOI>{%multiple_choice_result}
   - Question: What is the {Tg_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}?
     Constraint: You must pick either {%multiple_choice_enum%3%aA1} without using any other words.
     Options:
     {Tg_calc%}
-    Answer:<EOI> {%multiple_choice_result}
+    Answer:<EOI>{%multiple_choice_result}
   - Question: What is the {rho_300K_calc__names__noun} of the polymer with the {compound_name__names__noun} {compound_name#}?
     Constraint: You must pick either {%multiple_choice_enum%3%aA1} without using any other words.
     Options:
     {rho_300K_calc%}
-    Answer:<EOI> {%multiple_choice_result}
+    Answer:<EOI>{%multiple_choice_result}

data/tabular/lipophilicity/meta.yaml

@@ -47,7 +47,7 @@ templates:
     {exp%}
     Answer: {%multiple_choice_result}
   - |-
-    Question: Please estimate the {exp__names__noun} of {SMILES#} by picking one choice of {%multiple_choice_enum%3-6%aA1}.
+    Question: Please {#estimate|guess|predict|provide!} the {exp__names__noun} of {SMILES#} by picking one choice of {%multiple_choice_enum%3-6%aA1}.
     Options:
     {exp%}
     Answer: {%multiple_choice_result}
@@ -57,3 +57,40 @@ templates:
     Options:
     {exp%}
     Answer:<EOI>{%multiple_choice_result}
+  - |-
+    Question: What is the {exp__names__noun} for the {#molecule|chemical|compound!} represented by the {SMILES__description} {SMILES#}?
+
+    Answer:<EOI>{exp}
+  - |-
+    Task: Determine the {exp__names__noun} for the given {SMILES__description}.
+
+    Molecule: {SMILES#}
+
+    Answer:<EOI>{exp}
+  - |-
+    Task: Please {#estimate|guess|predict|provide!} the {exp__names__noun} for the following {SMILES__description}.
+
+    Molecule: {SMILES#}
+
+    Answer:<EOI>{exp}
+  - |-
+    Question: What is the experimental {exp__names__noun} for the molecule with the {SMILES__description} {SMILES#}?
+
+    Answer:<EOI>{exp}
+  - |-
+    Task: Identify the {exp__names__noun} for the given {#molecule|chemical|compound!}.
+
+    Molecule: {SMILES#}
+
+    Answer:<EOI>{exp}
+  - |-
+    Task: Please select the correct {exp__names__noun} for the {#molecule|chemical|compound!} represented by the {SMILES__description} {SMILES#}.
+
+    Options:
+    {exp%}
+
+    Answer:<EOI>{%multiple_choice_result}
+  - |-
+    Task: {#Estimate|Guess|Predict|Provide!} the {exp__names__noun} for the {#molecule|chemical|compound!} with the {SMILES__description} {SMILES#}.
+
+    Answer:<EOI>{exp}

data/tabular/melting_points/meta.yaml

@@ -92,17 +92,17 @@ templates:
 
     Compound: {NAME#}
 
-    Result:<EOI> {mp#} {mp__units}
+    Result:<EOI>{mp#} {mp__units}
   - |-
     Task: Please estimate the {mp_names__noun} of a compound.
 
     {SMILES__description}: {SMILES#}
 
-    Result:<EOI> {mp#} {mp__units}
+    Result:<EOI>{mp#} {mp__units}
   - |-
     Question: What is the {mp_names__noun} of a compound with the {SMILES__description} {SMILES#} in {mp__units}?
 
-    Answer:<EOI> {mp#}
+    Answer:<EOI>{mp#}
   - |-
     Question: Which molecule has a {mp_names__noun} of {mp#} {mp__units}?
     Pick {%multiple_choice_enum%3%aA1}.

data/tabular/mol_repr_transl/transform.py

@@ -46,18 +46,18 @@
         """User: Can you {#tell me|create|generate!} the {IDENTIFIER__names__noun} of the molecule with the {TARGET__names__noun} {TARGET#}?
 Assistant: {#Yes|Of course|Sure|Yes, I'm happy to help!}, this molecule has a {IDENTIFIER__names__noun} of {IDENTIFIER#}.""",  # noqa: E501
         # Benchmarking text templates
-        "The molecule with the {IDENTIFIER__names__noun} {#representation of |!}{IDENTIFIER#} can also be represented with the {TARGET__names__noun}{# representation|!}:<EOI> {TARGET#}.",  # noqa: E501
-        "The molecule with the {TARGET__names__noun} {#representation of |!}{TARGET#} can also be represented with the {IDENTIFIER__names__noun}{# representation|!}:<EOI> {IDENTIFIER#}.",  # noqa: E501
+        "The molecule with the {IDENTIFIER__names__noun} {#representation of |!}{IDENTIFIER#} can also be represented with the {TARGET__names__noun}{# representation|!}:<EOI>{TARGET#}.",  # noqa: E501
+        "The molecule with the {TARGET__names__noun} {#representation of |!}{TARGET#} can also be represented with the {IDENTIFIER__names__noun}{# representation|!}:<EOI>{IDENTIFIER#}.",  # noqa: E501
         """Task: Please {#create|generate!} a molecule representation based on {#the input molecule representation and |!}the description.
 Description: {#Generate|Create!} the {TARGET__names__noun} from the {IDENTIFIER__names__noun}.
 {#Molecule |!}{IDENTIFIER__names__noun}: {IDENTIFIER#}
 Constraint: Even if you are {#uncertain|not sure!}, you must answer with a representation without using any {#other|additional!} words.
-Result:<EOI> {TARGET#}""",  # noqa: E501
+Result:<EOI>{TARGET#}""",  # noqa: E501
         """Task: Please {#create|generate!} a molecule representation based on {#the input molecule representation and |!}the description.
 Description: {#Generate|Create!} the {IDENTIFIER__names__noun} from the {TARGET__names__noun}.
 {#Molecule |!}{TARGET__names__noun}: {TARGET#}
 Constraint: Even if you are {#uncertain|not sure!}, you must answer with a representation without using any {#other|additional!} words.
-Result:<EOI> {IDENTIFIER#}""",  # noqa: E501
+Result:<EOI>{IDENTIFIER#}""",  # noqa: E501
     ],
 }
 

data/tabular/uniprot_binding_single/meta.yaml

@@ -59,9 +59,9 @@ templates:
     Task: {#Find|Identify|Come up with!} a binding site in the {#AA sequence|amino acid sequence|peptide sequence|protein!} for the {#molecule|chemical|compound!}.
     {#AA sequence|Amino acid sequence|Peptide sequence|Protein!}: {sequence#}
     {SMILES__description}{# representation|!}: {SMILES#}
-    {#Output|Result!}:<EOI> {start_binding_site#}
+    {#Output|Result!}:<EOI>{start_binding_site#}
   - |-
     Task: {#Create|Design|Come up with!} a {#molecule|chemical|compound!} that binds to the given {#binding site|site|position|!} in the {#AA sequence|amino acid sequence|peptide sequence|protein!}.
     {#AA sequence|Amino acid sequence|Peptide sequence|Protein!}: {sequence#}
     Binding site{# position|!}: {start_binding_site#}
-    {#Output|Result!}:<EOI> {SMILES#}
+    {#Output|Result!}:<EOI>{SMILES#}

data/tabular/uniprot_binding_sites_multiple/meta.yaml

@@ -64,9 +64,9 @@ templates:
     Task: {#Find|Identify|Come up with!} a binding site in the {#AA sequence|amino acid sequence|peptide sequence|protein!} for the {#molecule|chemical|compound!}.
     {#AA sequence|Amino acid sequence|Peptide sequence|Protein!}: {sequence#}
     {SMILES__description}{# representation|!}: {SMILES#}
-    {#Output|Result!}:<EOI> {start_binding_site#}-{end_binding_site#}
+    {#Output|Result!}:<EOI>{start_binding_site#}-{end_binding_site#}
   - |-
     Task: {#Create|Design|Come up with!} a {#molecule|chemical|compound!} that binds to the given {#binding site|site|position|!} in the {#AA sequence|amino acid sequence|peptide sequence|protein!}.
     {#AA sequence|Amino acid sequence|Peptide sequence|Protein!}: {sequence#}
     Binding site{# position|!}: {start_binding_site#}{#-| to !}{end_binding_site#}
-    {#Output|Result!}:<EOI> {SMILES#}
+    {#Output|Result!}:<EOI>{SMILES#}

data/tabular/uniprot_organisms/meta.yaml

@@ -43,4 +43,4 @@ templates:
   - |-
     Task: {#Predict|Identify!} the organism in which {#the below|this!} {#protein|amino acid sequence|AA sequence|polypeptide!} can be found.
     {#Amino acid sequence|Sequence|AA sequence!}: {other#}
-    Result:<EOI> {organisms#}
+    Result:<EOI>{organisms#}

data/tabular/uniprot_reactions/meta.yaml

@@ -48,8 +48,8 @@ templates:
   - |-
     Task: {#Predict|Identify!} a {#biochemical |chemical |!}reaction that can be catalyzed by {#this|the following!} {#protein|amino acid sequence|AA sequence|polypeptide!}.
     {#Amino acid sequence |Sequence|AA sequence!}: {other#}
-    Result:<EOI> {reactions#}
+    Result:<EOI>{reactions#}
   - |-
     Task: {#Generate|Create|Come up with|Design!} a {#protein|amino acid sequence|AA sequence|polypeptide!} that can catalyze {#a|this!} specific {#biochemical |chemical |!}reaction.
     Reaction: {reactions#}
-    {#Output|Result!}:<EOI> {other#}
+    {#Output|Result!}:<EOI>{other#}

data/tabular/uniprot_sentences/meta.yaml

@@ -48,8 +48,8 @@ templates:
   - |-
     Task: {#Generate|Create|Come up with!} a description {#of a few sentences |!}for the {#protein|amino acid sequence|AA sequence|polypeptide!}{# below|!}.
     {#Protein|Amino acid sequence|AA sequence|Polypeptide!}: {sequence#}
-    {#Output|Result!}:<EOI> {sentences#}
+    {#Output|Result!}:<EOI>{sentences#}
   - |-
     Task: {#Generate|Create|Come up with!} a {#protein|amino acid sequence|AA sequence|polypeptide!} based on the description.
     Description: {sentences#}
-    {#Output|Result!}:<EOI> {sequence#}
+    {#Output|Result!}:<EOI>{sequence#}