From 91a1fd15dcaee48f90eaad9638adb0a9427f7a47 Mon Sep 17 00:00:00 2001 From: maykcaldas Date: Wed, 12 Nov 2025 13:10:01 -0800 Subject: [PATCH 01/11] added phoenix guidelines --- docs/phoenix_guidelines.md | 41 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) create mode 100644 docs/phoenix_guidelines.md diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md new file mode 100644 index 0000000..16d0074 --- /dev/null +++ b/docs/phoenix_guidelines.md @@ -0,0 +1,41 @@ +# Best Practices for Interacting with Phoenix + +Phoenix is a chemistry-focused discovery agent. To get the most out of each Phoenix run, follow these guidelines for formulating effective queries: + +## 1. Be specific about molecular inputs. +When asking about molecules, provide SMILES strings, CAS numbers, IUPAC names, or molecular formulas explicitly. Phoenix can work with multiple representation types, but being explicit helps ensure accurate results. A chemist familiar with your field should be able to unambiguously identify the molecule(s) you're asking about. + +## 2. Specify desired outputs clearly. +Clearly state what you need from Phoenix. It can be a synthesis route, molecular property prediction, safety assessment, literature-backed answer, or a combination of these. The more specific you are about the outputs you need, the better Phoenix can select appropriate tools and provide actionable results. + +## 3. Use proper chemical terminology and notation. +Employ standard chemical nomenclature and notation. For example, use SMILES representation for reactions: `reactants>reagents>products`. Use standard property names (e.g., ADMET properties like HIA_Hou, BBB_Martins, AMES) when requesting specific molecular properties. This helps Phoenix understand your intent and select the most appropriate computational tools. + +## 4. Break down complex queries. +For multi-part questions, structure them logically so Phoenix can create an effective execution plan. While Phoenix can handle multi-step queries and will plan longer workflows, clearly organizing your query helps ensure all components are addressed systematically. + +## 5. Provide context when relevant. +Include background information about your use case (e.g., "for drug development" or "for a research synthesis") to help Phoenix select appropriate tools and safety considerations. Context about your constraints, goals, or specific requirements enables Phoenix to provide more targeted and useful responses. + +## 6. Request specific properties or analyses. +Instead of asking vaguely about a molecule, specify what you need. For example, request specific ADMET properties, synthetic accessibility scores, solubility predictions, or toxicity data. This allows Phoenix to use the most appropriate computational tools and provide quantitative, actionable results. + +## 7. Ask actionable questions that leverage Phoenix's toolset. +Frame queries that can be answered using Phoenix's computational capabilities rather than pure theoretical discussions without computational support. Phoenix excels at property prediction, synthesis planning, reaction analysis, database searches, and literature-enhanced discovery. + +Here are some examples of ways to improve Phoenix queries: + +| Insufficient queries | More detailed queries | +|---------------------|--------------| +| Tell me about aspirin. | What are the ADMET properties (HIA_Hou, BBB_Martins, and AMES) for aspirin? Also, what are its GHS classification and LD50 value? | +| Modify quercetin to make it more soluble in water. | Suggest three different substitution modifications to quercetin to make its aqueous solubility (logS) higher. Show me the suggested molecules in your final answer and base your answer in evidence from the literature. | +| How do I make aspirin? | Design a retrosynthesis route for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. Please identify starting materials and propose reaction steps. | +| Can you synthesize caffeine? | Propose a synthesis route for caffeine (SMILES: CN1C=NC2=C1C(=O)N(C(=O)N2C)C), including retrosynthetic analysism reactants pricing, and reaction conditions where possible. | +| What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | +| What drugs treat diabetes? | Find small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | +| Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions (AMES, ClinTox). | +| Find similar molecules to `CC(=O)OC1=CC=CC=C1C(=O)O`. | Search the ChEMBL database for molecules similar to aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for drug repurposing. Return the top 10 candidates with their development phases and bioactivity data. | +| What's the latest on green chemistry? | Using literature search, find recent advances in green chemistry methods for esterification reactions. Focus on catalysts and reaction conditions that minimize environmental impact. | + +## 8. Iterate. +Take some time to write your first Phoenix query so you can avoid the common caveats listed above. However, trial and error will be your best guide to develop a deep intuition on how to best use the system. Start with familiar molecules or reactions. While Phoenix can handle complex multi-step workflows, begin with simpler queries for faster results and quicker iteration can help you refine your queries and get the most out of Phoenix. From 008ff1200eebc597862c93ec985db8f6f182d2a8 Mon Sep 17 00:00:00 2001 From: maykcaldas Date: Wed, 12 Nov 2025 13:15:13 -0800 Subject: [PATCH 02/11] Fixed typos --- docs/phoenix_guidelines.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 16d0074..c1c283c 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -30,7 +30,7 @@ Here are some examples of ways to improve Phoenix queries: | Tell me about aspirin. | What are the ADMET properties (HIA_Hou, BBB_Martins, and AMES) for aspirin? Also, what are its GHS classification and LD50 value? | | Modify quercetin to make it more soluble in water. | Suggest three different substitution modifications to quercetin to make its aqueous solubility (logS) higher. Show me the suggested molecules in your final answer and base your answer in evidence from the literature. | | How do I make aspirin? | Design a retrosynthesis route for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. Please identify starting materials and propose reaction steps. | -| Can you synthesize caffeine? | Propose a synthesis route for caffeine (SMILES: CN1C=NC2=C1C(=O)N(C(=O)N2C)C), including retrosynthetic analysism reactants pricing, and reaction conditions where possible. | +| Can you synthesize caffeine? | Propose a synthesis route for caffeine (SMILES: CN1C=NC2=C1C(=O)N(C(=O)N2C)C), including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | | What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | | What drugs treat diabetes? | Find small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | | Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions (AMES, ClinTox). | @@ -38,4 +38,4 @@ Here are some examples of ways to improve Phoenix queries: | What's the latest on green chemistry? | Using literature search, find recent advances in green chemistry methods for esterification reactions. Focus on catalysts and reaction conditions that minimize environmental impact. | ## 8. Iterate. -Take some time to write your first Phoenix query so you can avoid the common caveats listed above. However, trial and error will be your best guide to develop a deep intuition on how to best use the system. Start with familiar molecules or reactions. While Phoenix can handle complex multi-step workflows, begin with simpler queries for faster results and quicker iteration can help you refine your queries and get the most out of Phoenix. +Take some time to write your first Phoenix query so you can avoid the common pitfalls listed above. However, trial and error will be your best guide to develop a deep intuition on how to best use the system. Start with familiar molecules or reactions. While Phoenix can handle complex multi-step workflows, begin with simpler queries for faster results and quicker iteration can help you refine your queries and get the most out of Phoenix. From 220248ea22c617185827eafbafff42ee0b95dd43 Mon Sep 17 00:00:00 2001 From: maykcaldas Date: Wed, 12 Nov 2025 13:17:38 -0800 Subject: [PATCH 03/11] Rewording some odd sentences --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index c1c283c..409aaf6 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -38,4 +38,4 @@ Here are some examples of ways to improve Phoenix queries: | What's the latest on green chemistry? | Using literature search, find recent advances in green chemistry methods for esterification reactions. Focus on catalysts and reaction conditions that minimize environmental impact. | ## 8. Iterate. -Take some time to write your first Phoenix query so you can avoid the common pitfalls listed above. However, trial and error will be your best guide to develop a deep intuition on how to best use the system. Start with familiar molecules or reactions. While Phoenix can handle complex multi-step workflows, begin with simpler queries for faster results and quicker iteration can help you refine your queries and get the most out of Phoenix. +Take some time to write your first Phoenix query so you can avoid the common pitfalls listed above. However, trial and error will be your best guide to develop a deep intuition on how to best use the system. Start with familiar molecules or reactions. While Phoenix can handle complex multi-step workflows, begin with simpler queries for faster results. Quicker iteration will help you learn how to use Phoenix more effectively and get the most out of the system. From 42dc8b34084cf5ddc995bd97b0e18b3c8214798f Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:07:53 -0800 Subject: [PATCH 04/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 409aaf6..843a281 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -1,6 +1,6 @@ # Best Practices for Interacting with Phoenix -Phoenix is a chemistry-focused discovery agent. To get the most out of each Phoenix run, follow these guidelines for formulating effective queries: +Phoenix is a chemistry-focused scientific agent. To get the most out of each Phoenix run, follow these guidelines for formulating effective queries: ## 1. Be specific about molecular inputs. When asking about molecules, provide SMILES strings, CAS numbers, IUPAC names, or molecular formulas explicitly. Phoenix can work with multiple representation types, but being explicit helps ensure accurate results. A chemist familiar with your field should be able to unambiguously identify the molecule(s) you're asking about. From 4d3610df0e27b5e9bdd9d941ab1db6a02adb10ab Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:08:00 -0800 Subject: [PATCH 05/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 843a281..94ee3d6 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -12,7 +12,7 @@ Clearly state what you need from Phoenix. It can be a synthesis route, molecular Employ standard chemical nomenclature and notation. For example, use SMILES representation for reactions: `reactants>reagents>products`. Use standard property names (e.g., ADMET properties like HIA_Hou, BBB_Martins, AMES) when requesting specific molecular properties. This helps Phoenix understand your intent and select the most appropriate computational tools. ## 4. Break down complex queries. -For multi-part questions, structure them logically so Phoenix can create an effective execution plan. While Phoenix can handle multi-step queries and will plan longer workflows, clearly organizing your query helps ensure all components are addressed systematically. +Structure multi-part questions logically so Phoenix can create an effective execution plan. While Phoenix can handle multi-step queries and longer workflows, clearly organizing your query helps ensure all components are addressed systematically. ## 5. Provide context when relevant. Include background information about your use case (e.g., "for drug development" or "for a research synthesis") to help Phoenix select appropriate tools and safety considerations. Context about your constraints, goals, or specific requirements enables Phoenix to provide more targeted and useful responses. From 6545ba834101cd7833e2ec16368f3a7eaeed77ef Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:08:07 -0800 Subject: [PATCH 06/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 94ee3d6..2ed8f11 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -9,7 +9,7 @@ When asking about molecules, provide SMILES strings, CAS numbers, IUPAC names, o Clearly state what you need from Phoenix. It can be a synthesis route, molecular property prediction, safety assessment, literature-backed answer, or a combination of these. The more specific you are about the outputs you need, the better Phoenix can select appropriate tools and provide actionable results. ## 3. Use proper chemical terminology and notation. -Employ standard chemical nomenclature and notation. For example, use SMILES representation for reactions: `reactants>reagents>products`. Use standard property names (e.g., ADMET properties like HIA_Hou, BBB_Martins, AMES) when requesting specific molecular properties. This helps Phoenix understand your intent and select the most appropriate computational tools. +Employ standard chemical nomenclature and notation. For example, use SMILES representation for reactions: `reactants>reagents>products`. Use standard property names (e.g., ADMET properties) when requesting specific molecular properties. This helps Phoenix understand your intent and select the most appropriate computational tools. ## 4. Break down complex queries. Structure multi-part questions logically so Phoenix can create an effective execution plan. While Phoenix can handle multi-step queries and longer workflows, clearly organizing your query helps ensure all components are addressed systematically. From c8aa6462c77a3866a2fe08f4fe20eac714dacdd1 Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:08:15 -0800 Subject: [PATCH 07/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 2ed8f11..9b34b89 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -30,7 +30,7 @@ Here are some examples of ways to improve Phoenix queries: | Tell me about aspirin. | What are the ADMET properties (HIA_Hou, BBB_Martins, and AMES) for aspirin? Also, what are its GHS classification and LD50 value? | | Modify quercetin to make it more soluble in water. | Suggest three different substitution modifications to quercetin to make its aqueous solubility (logS) higher. Show me the suggested molecules in your final answer and base your answer in evidence from the literature. | | How do I make aspirin? | Design a retrosynthesis route for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. Please identify starting materials and propose reaction steps. | -| Can you synthesize caffeine? | Propose a synthesis route for caffeine (SMILES: CN1C=NC2=C1C(=O)N(C(=O)N2C)C), including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | +| Can you synthesize caffeine? | Propose a synthesis route for caffeine, including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | | What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | | What drugs treat diabetes? | Find small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | | Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions (AMES, ClinTox). | From e7bbe7d133fd2394b8be9e0adcb03e9744b81912 Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:08:21 -0800 Subject: [PATCH 08/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 9b34b89..f8b216b 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -32,7 +32,7 @@ Here are some examples of ways to improve Phoenix queries: | How do I make aspirin? | Design a retrosynthesis route for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. Please identify starting materials and propose reaction steps. | | Can you synthesize caffeine? | Propose a synthesis route for caffeine, including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | | What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | -| What drugs treat diabetes? | Find small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | +| What drugs treat diabetes? | Propose small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | | Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions (AMES, ClinTox). | | Find similar molecules to `CC(=O)OC1=CC=CC=C1C(=O)O`. | Search the ChEMBL database for molecules similar to aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for drug repurposing. Return the top 10 candidates with their development phases and bioactivity data. | | What's the latest on green chemistry? | Using literature search, find recent advances in green chemistry methods for esterification reactions. Focus on catalysts and reaction conditions that minimize environmental impact. | From a09f41f9a7d4431cc1100ce113c16173e049d70c Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:08:28 -0800 Subject: [PATCH 09/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index f8b216b..dc01803 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -33,7 +33,7 @@ Here are some examples of ways to improve Phoenix queries: | Can you synthesize caffeine? | Propose a synthesis route for caffeine, including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | | What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | | What drugs treat diabetes? | Propose small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | -| Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions (AMES, ClinTox). | +| Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions. | | Find similar molecules to `CC(=O)OC1=CC=CC=C1C(=O)O`. | Search the ChEMBL database for molecules similar to aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for drug repurposing. Return the top 10 candidates with their development phases and bioactivity data. | | What's the latest on green chemistry? | Using literature search, find recent advances in green chemistry methods for esterification reactions. Focus on catalysts and reaction conditions that minimize environmental impact. | From 053be5b332534d9ed998abb3b7d59232d0fd31b3 Mon Sep 17 00:00:00 2001 From: Mayk Caldas Date: Thu, 13 Nov 2025 10:08:47 -0800 Subject: [PATCH 10/11] Update docs/phoenix_guidelines.md Co-authored-by: Sam Cox --- docs/phoenix_guidelines.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index dc01803..5af778d 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -31,7 +31,7 @@ Here are some examples of ways to improve Phoenix queries: | Modify quercetin to make it more soluble in water. | Suggest three different substitution modifications to quercetin to make its aqueous solubility (logS) higher. Show me the suggested molecules in your final answer and base your answer in evidence from the literature. | | How do I make aspirin? | Design a retrosynthesis route for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. Please identify starting materials and propose reaction steps. | | Can you synthesize caffeine? | Propose a synthesis route for caffeine, including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | -| What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | +| What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with reaction SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | | What drugs treat diabetes? | Propose small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | | Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions. | | Find similar molecules to `CC(=O)OC1=CC=CC=C1C(=O)O`. | Search the ChEMBL database for molecules similar to aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for drug repurposing. Return the top 10 candidates with their development phases and bioactivity data. | From 1d48d6bca154fc5d96c64355f6008edb2c56dbb4 Mon Sep 17 00:00:00 2001 From: maykcaldas Date: Thu, 13 Nov 2025 11:55:48 -0800 Subject: [PATCH 11/11] Addressed PR comments --- docs/phoenix_guidelines.md | 72 +++++++++++++++++++++++++++++++------- 1 file changed, 60 insertions(+), 12 deletions(-) diff --git a/docs/phoenix_guidelines.md b/docs/phoenix_guidelines.md index 5af778d..68eea14 100644 --- a/docs/phoenix_guidelines.md +++ b/docs/phoenix_guidelines.md @@ -3,39 +3,87 @@ Phoenix is a chemistry-focused scientific agent. To get the most out of each Phoenix run, follow these guidelines for formulating effective queries: ## 1. Be specific about molecular inputs. -When asking about molecules, provide SMILES strings, CAS numbers, IUPAC names, or molecular formulas explicitly. Phoenix can work with multiple representation types, but being explicit helps ensure accurate results. A chemist familiar with your field should be able to unambiguously identify the molecule(s) you're asking about. +When asking about molecules, provide explicit identifiers such as: +- SMILES strings +- CAS numbers +- IUPAC names + +Phoenix can handle multiple representations, but being explicit reduces ambiguity. A chemist familiar with your field should be able to unambiguously identify the molecule(s) from your query. + +| Insufficient queries | More detailed queries | +|---------------------|----------------------| +| Tell me about anti-inflammatory drugs. | What are the ADMET properties for aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O` or CAS: 50-78-2)? | +| What are the functional groups of vitamin C? | List the functional groups available in ascorbic acid (SMILES: `C([C@@H]([C@@H]1C(=C(C(=O)O1)O)O)O)O`). | +| Find compounds to be used as painkillers. | Search for molecules similar to acetaminophen (SMILES: `CC(=O)NC1=CC=C(C=C1)O`) in the ChEMBL database. | ## 2. Specify desired outputs clearly. Clearly state what you need from Phoenix. It can be a synthesis route, molecular property prediction, safety assessment, literature-backed answer, or a combination of these. The more specific you are about the outputs you need, the better Phoenix can select appropriate tools and provide actionable results. +| Insufficient queries | More detailed queries | +|---------------------|----------------------| +| Tell me about `CN1C=NC2=C1C(=O)N(C(=O)N2C)C`. | What are the ADMET properties for `CN1C=NC2=C1C(=O)N(C(=O)N2C)C`? Also, what are its GHS classification and LD50 value? | +| Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions. | +| Can you help me make aspirin? | I need a synthesis route, ADMET property predictions, and a safety assessment for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. | + ## 3. Use proper chemical terminology and notation. Employ standard chemical nomenclature and notation. For example, use SMILES representation for reactions: `reactants>reagents>products`. Use standard property names (e.g., ADMET properties) when requesting specific molecular properties. This helps Phoenix understand your intent and select the most appropriate computational tools. +| Insufficient queries | More detailed queries | +|---------------------|----------------------| +| What happens if I mix ethanol and acetic acid? | Predict the product of the reaction with reaction SMILES: `CCO.CC(=O)O>>CC(=O)OC`. Calculate the reaction enthalpy. | +| How do I make an ester from alcohol and acid? | Design a synthesis route for ethyl acetate using reaction SMILES: `CCO.CC(=O)O>>CC(=O)OC` with appropriate catalysts and conditions. | +| Check the drug properties of quercetin. | Calculate ADMET properties (specifically human intestinal absorption, blood-brain barrier permeability, and cytochrome P450 inhibition) for the molecule with SMILES `C1=CC(=C(C=C1C2=C(C(=O)C3=C(C=C(C=C3O2)O)O)O)O)O`. | + ## 4. Break down complex queries. Structure multi-part questions logically so Phoenix can create an effective execution plan. While Phoenix can handle multi-step queries and longer workflows, clearly organizing your query helps ensure all components are addressed systematically. +| Insufficient queries | More detailed queries | +|---------------------|----------------------| +| Find similar drugs to aspirin. | (1) Analyze aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for ADMET properties. (2) Search ChEMBL for similar anti-inflammatory compounds. (3) Perform safety assessments on the top 5 candidates. (4) Propose modifications to improve solubility while maintaining efficacy. | +| I need everything about caffeine and how to make it and what it does. | I need you to give me information about caffeine. Follow these steps: (1) Calculate molecular properties (logP, logS, QED) for SMILES `CN1C=NC2=C1C(=O)N(C(=O)N2C)C`. (2) Design a retrosynthesis route. (3) Predict biological activity targets. | +| Find drugs for diabetes, check if they work, and make new ones. | (1) Search ChEMBL for approved diabetes drugs targeting INSR. (2) Analyze their binding affinities and ADMET properties. (3) Propose 5 novel small molecule candidates with improved properties. | + ## 5. Provide context when relevant. Include background information about your use case (e.g., "for drug development" or "for a research synthesis") to help Phoenix select appropriate tools and safety considerations. Context about your constraints, goals, or specific requirements enables Phoenix to provide more targeted and useful responses. +| Insufficient queries | More detailed queries | +|---------------------|----------------------| +| Find similar molecules to `CC(=O)OC1=CC=CC=C1C(=O)O`. | Search the ChEMBL database for molecules similar to aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for drug repurposing. Return the top 10 candidates with their development phases and bioactivity data. | + ## 6. Request specific properties or analyses. Instead of asking vaguely about a molecule, specify what you need. For example, request specific ADMET properties, synthetic accessibility scores, solubility predictions, or toxicity data. This allows Phoenix to use the most appropriate computational tools and provide quantitative, actionable results. +| Insufficient queries | More detailed queries | +|---------------------|----------------------| +| Modify quercetin to make it more soluble. | Suggest three different substitution modifications to quercetin to make its aqueous solubility (logS) higher. Show me the suggested molecules in your final answer and base your answer in predicted solubility data. | +| Is aspirin drug-like? | Calculate the drug-likeness score (QED), synthetic accessibility score (SAscore), and Lipinski's Rule of Five violations for `CC(=O)OC1=CC=CC=C1C(=O)O`. | +| What are the properties of caffeine? | Calculate the following properties for caffeine (SMILES: `CN1C=NC2=C1C(=O)N(C(=O)N2C)C`): (1) aqueous solubility (logS), (2) partition coefficient (logP), (3) polar surface area (PSA), and (4) number of rotatable bonds. | + ## 7. Ask actionable questions that leverage Phoenix's toolset. Frame queries that can be answered using Phoenix's computational capabilities rather than pure theoretical discussions without computational support. Phoenix excels at property prediction, synthesis planning, reaction analysis, database searches, and literature-enhanced discovery. -Here are some examples of ways to improve Phoenix queries: - | Insufficient queries | More detailed queries | -|---------------------|--------------| -| Tell me about aspirin. | What are the ADMET properties (HIA_Hou, BBB_Martins, and AMES) for aspirin? Also, what are its GHS classification and LD50 value? | -| Modify quercetin to make it more soluble in water. | Suggest three different substitution modifications to quercetin to make its aqueous solubility (logS) higher. Show me the suggested molecules in your final answer and base your answer in evidence from the literature. | +|---------------------|----------------------| | How do I make aspirin? | Design a retrosynthesis route for the target molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`. Please identify starting materials and propose reaction steps. | -| Can you synthesize caffeine? | Propose a synthesis route for caffeine, including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | -| What happens if I mix ethanol and acetic acid? | Predict the product of the reaction of ethanol and acetic acid with reaction SMILES: `CCO.CC(=O)O>>`. Calculate the reaction enthalpy. | +| Can you synthesize caffeine? | Propose a synthesis route for caffeine (SMILES: `CN1C=NC2=C1C(=O)N(C(=O)N2C)C`), including retrosynthetic analysis, reactants pricing, and reaction conditions where possible. | | What drugs treat diabetes? | Propose small molecule binders for the insulin receptor (INSR gene symbol). Propose up to 10 candidates and analyze their drug-likeness using QED scores. | -| Is CC(=O)OC1=CC=CC=C1C(=O)O safe? | Perform a safety assessment for the molecule with SMILES `CC(=O)OC1=CC=CC=C1C(=O)O`, including GHS classification, LD50 value, chemical weapons screening, and toxicity predictions. | -| Find similar molecules to `CC(=O)OC1=CC=CC=C1C(=O)O`. | Search the ChEMBL database for molecules similar to aspirin (SMILES: `CC(=O)OC1=CC=CC=C1C(=O)O`) for drug repurposing. Return the top 10 candidates with their development phases and bioactivity data. | -| What's the latest on green chemistry? | Using literature search, find recent advances in green chemistry methods for esterification reactions. Focus on catalysts and reaction conditions that minimize environmental impact. | +| Explain how this ethanol reacts with acetic acid. | Predict the product of the reaction with SMILES `CCO.CC(=O)O>>`, calculate the reaction enthalpy, identify the mechanism, and suggest optimal catalysts and conditions. | + ## 8. Iterate. -Take some time to write your first Phoenix query so you can avoid the common pitfalls listed above. However, trial and error will be your best guide to develop a deep intuition on how to best use the system. Start with familiar molecules or reactions. While Phoenix can handle complex multi-step workflows, begin with simpler queries for faster results. Quicker iteration will help you learn how to use Phoenix more effectively and get the most out of the system. +Take some time to write your first Phoenix query so you can avoid the common pitfalls listed above. Starting with simpler queries will give you faster results and allow quicker iteration, helping you learn how to use Phoenix more effectively and get the most out of the system. +Your first query does not have to be perfect. Use Phoenix interactively to refine your query: + +1. Start simple + - Begin with a well-known molecule or reaction and a small set of properties or a basic retrosynthesis. + +2. Inspect the outputs + - Check if the properties, synthesis steps, or hits match your expectations. + +3. Refine your query + - If you need more detail, add explicit properties, constraints, or additional steps. + - Example: "Now also calculate logS and propose modifications to improve solubility." + +4. Repeat + - Use the results of one Phoenix run as input for the next (e.g., take top hits and ask for safety assessments or optimization ideas). + - Phoenix also accepts follow-up questions to the previous run.