### Generate Responses on SMolInstruct Dataset

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Command to run LlaSMol models for generating responses on the SMolInstruct dataset. Supports specifying tasks or generating for all.

```bash
python generate_on_dataset.py --model_name osunlp/LlaSMol-Mistral-7B --output_dir eval/LlaSMol-Mistral-7B/output
```

--------------------------------

### Compute Metrics for SMolInstruct Tasks

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Command to compute evaluation metrics for LlaSMol model predictions on the SMolInstruct dataset. Skips tasks with missing output files.

```bash
python compute_metrics.py --prediction_dir eval/LlaSMol-Mistral-7B/prediction
```

--------------------------------

### Generate Chemistry Answers with LlaSMol

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Python code to initialize the LlaSMol generation model and query it with specific questions, using tags for input types like SMILES.

```python
from generation import LlaSMolGeneration

generator = LlaSMolGeneration('osunlp/LlaSMol-Mistral-7B')
generator.generate('Can you tell me the IUPAC name of <SMILES> C1CCOC1 </SMILES> ?')
```

--------------------------------

### Fine-tune LlaSMol Model

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Command to fine-tune a base model on SMolInstruct using accelerate and LoRA. Ensure to adjust LoRA settings for different base models.

```bash
MODELNAME=LlaSMol-Mistral-7B && CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch finetune.py --data_path osunlp/SMolInstruct --base_model mistralai/Mistral-7B-v0.1 --wandb_project LlaSMol --wandb_run_name $MODELNAME --wandb_log_model true --output_dir checkpoint/$MODELNAME
```

--------------------------------

### Extract Predicted Answers from Model Outputs

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Command to extract predicted answers from LlaSMol model outputs for evaluation. Handles missing or incomplete tags by assigning empty answers.

```bash
python extract_prediction.py --output_dir eval/LlaSMol-Mistral-7B/output --prediction_dir eval/LlaSMol-Mistral-7B/prediction
```

--------------------------------

### Chemical Reaction: Forward Synthesis

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Suggests a possible product given reactants and reagents in SMILES format. This is used for predicting the outcome of a chemical reaction.

```text
Query: <SMILES> NC1=CC=C2OCOC2=C1.O=CO </SMILES> Based on the reactants and reagents given above, suggest a possible product.

Response: A possible product can be <SMILES> O=CNC1=CC=C2OCOC2=C1 </SMILES> .
```

--------------------------------

### Chemical Reaction: Retrosynthesis

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Identifies possible reactants from a given product in SMILES format. This is useful for planning chemical synthesis pathways.

```text
Query: Identify possible reactants that could have been used to create the specified product. <SMILES> CC1=CC=C(N)N=C1N </SMILES>

Response: <SMILES> CC(C#N)CCC#N.N </SMILES>
```

--------------------------------

### Name Conversion: IUPAC to SMILES

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Translates an IUPAC name into its SMILES representation. Useful for converting systematic names into a machine-readable format.

```text
Query: Could you provide the SMILES for <IUPAC> 4-ethyl-4-methyloxolan-2-one </IUPAC> ?

Response: Of course. It's <SMILES> CCC1(C)COC(=O)C1 </SMILES> .
```

--------------------------------

### Molecule Description: Molecule Captioning

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Generates a descriptive text for a molecule provided in SMILES format. This includes its properties and potential uses.

```text
Query: Describe this molecule: <SMILES> CCOC(=O)C1=CN=CN1[C@H](C)C1=CC=CC=C1 </SMILES>

Response: The molecule is an imidazole derivative with short-acting sedative, hypnotic, and general anesthetic properties. Etomidate appears to have gamma-aminobutyric acid (GABA) like effects, mediated through GABA-A receptor. The action enhances the inhibitory effect of GABA on the central nervous system by causing chloride channel opening events which leads to membrane hyperpolarization.
```

--------------------------------

### LlaSMol Citation

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

BibTeX entry for citing the LlaSMol paper.

```bibtex
@article{yu2024llasmol,
    title={LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset},
    author={Botao Yu and Frazier N. Baker and Ziqi Chen and Xia Ning and Huan Sun},
    journal={arXiv preprint arXiv:2402.09391},
    year={2024}
}
```

--------------------------------

### Property Prediction: Clintox

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Assesses the toxicity of a molecule based on its SMILES string. Returns a boolean indicating whether the molecule is toxic.

```text
Query: Is <SMILES> COC[C@@H](NC(C)=O)C(=O)NCC1=CC=CC=C1 </SMILES> toxic?

Response: <BOOLEAN> No </BOOLEAN>
```

--------------------------------

### Name Conversion: SMILES to Molecular Formula

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Derives the molecular formula from a given SMILES string. This is helpful for determining the elemental composition from a structural representation.

```text
Query: Given the SMILES representation <SMILES> S=P1(N(CCCl)CCCl)NCCCO1 </SMILES>, what would be its molecular formula?

Response: It is <MOLFORMULA> C7H15Cl2N2OPS </MOLFORMULA> .
```

--------------------------------

### Name Conversion: SMILES to IUPAC

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Converts a SMILES string into its IUPAC name. Use this to obtain the systematic chemical name from a structural representation.

```text
Query: Translate the given SMILES formula of a molecule <SMILES> CCC(C)C1CNCCCNC1 </SMILES> into its IUPAC name.

Response: <IUPAC> 3-butan-2-yl-1,5-diazocane </IUPAC>
```

--------------------------------

### Molecule Description: Molecule Generation

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Generates a SMILES representation of a molecule based on a textual description of its properties and class. Useful for creating novel molecular structures from requirements.

```text
Query: Give me a molecule that satisfies the conditions outlined in the description: The molecule is a member of the class of tripyrroles that is a red-coloured pigment with antibiotic properties produced by Serratia marcescens. It has a role as an antimicrobial agent, a biological pigment, a bacterial metabolite, an apoptosis inducer and an antineoplastic agent. It is a tripyrrole, an aromatic ether and a ring assembly.

Response: Here is a potential molecule: <SMILES> CCCCCC1=C(C)NC(/C=C2\N=C(C3=CC=CN3)C=C2OC)=C1 </SMILES>
```

--------------------------------

### Property Prediction: HIV

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Predicts whether a molecule, given by its SMILES string, can act as an inhibitor of HIV replication. Returns a boolean.

```text
Query: Can <SMILES> CC1=CN(C2C=CCCC2O)C(=O)NC1=O </SMILES> serve as an inhibitor of HIV replication?

Response: <BOOLEAN> No </BOOLEAN>
```

--------------------------------

### Name Conversion: IUPAC to Molecular Formula

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Converts an IUPAC name to its corresponding molecular formula. Use this when you need to find the chemical formula from a systematic chemical name.

```text
Query: What is the molecular formula of the compound with this IUPAC name <IUPAC> 2,5-diphenyl-1,3-oxazole </IUPAC> ?

Response: <MOLFORMULA> C15H11NO </MOLFORMULA>
```

--------------------------------

### Property Prediction: ESOL

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Predicts the ESOL (Estimated Solubilities) value (log solubility in mol/L) for a given molecule represented by its SMILES string. Useful for estimating aqueous solubility.

```text
Query: How soluble is <SMILES> CC(C)Cl </SMILES> ?

Response: Its log solubility is <NUMBER> -1.41 </NUMBER> mol/L.
```

--------------------------------

### Property Prediction: LIPO

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Predicts the octanol/water distribution coefficient (logD) at pH 7.4 for a molecule given its SMILES string. This is used to estimate lipophilicity.

```text
Query: Predict the octanol/water distribution coefficient logD under the circumstance of pH 7.4 for <SMILES> NC(=O)C1=CC=CC=C1O </SMILES> .

Response: <NUMBER> 1.090 </NUMBER>
```

--------------------------------

### Property Prediction: SIDER

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Checks for known side effects, specifically those affecting the heart, for a molecule represented by its SMILES string. Returns a boolean.

```text
Query: Are there any known side effects of <SMILES> CC1=CC(C)=C(NC(=O)CN(CC(=O)O)CC(=O)O)C(C)=C1Br </SMILES> affecting the heart?

Response: <BOOLEAN> No </BOOLEAN>
```

--------------------------------

### Property Prediction: BBBP

Source: https://github.com/osu-nlp-group/llm4chem/blob/main/README.md

Determines if a molecule, represented by its SMILES string, exhibits blood-brain barrier permeability. Returns a boolean value.

```text
Query: Is blood-brain barrier permeability (BBBP) a property of <SMILES> CCNC(=O)/C=C/C1=CC=CC(Br)=C1 </SMILES> ?

Response: <BOOLEAN> Yes </BOOLEAN>
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.