Starting with Faraday
Your AI Scientist
Starting Point
There are three primary ways to begin exploring Faraday:
1. Ask Faraday an Open-Ended Question
Use plain language to ask Faraday to generate a molecular starting point or explore publicly available literature, biological or chemical data.
Sample prompts:
- Design improved KRAS G12C inhibitors based on sotorasib.
- What are the drug targets for Alzheimer’s disease?
2. Upload Your Own Files
If you have specific data, molecules, or documents you’d like Faraday to analyze, you can upload them directly into the platform or copy the smilestrings of the molecules to the chatbox.
Accepted formats: .pdf
, .csv
, .txt
Sample prompt:
Analyze this compound [insert SMILES string] targeting KRAS G12C, and suggest optimizations to enhance its drug-likeness.
3. Try with Sample Documents
We’ve prepared a set of sample documents to help you quickly understand what Faraday can do.
Sample dataset 1:
Published Kinase Inhibitor Set 2: PKIS2 dataset.xlsx
Source: Drewry, David H., et al. “Progress towards a public chemogenomic set for protein kinases and a call for contributions.” PloS one 12.8 (2017): e0181585.
Description: Composed of 645 small molecule inhibitors representing 86 diverse chemotypes that were published by medicinal chemists at GlaxoSmithKline, Pfizer, and Takeda. PKIS and PKIS2 have only nine chemotypes in common.
Sample dataset 2:
ADME pub set: ADME_public_set_3521.csv
Source: Fang, Cheng, et al. “Prospective validation of machine learning algorithms for absorption, distribution, metabolism, and excretion prediction: An industrial perspective.” Journal of Chemical Information and Modeling 63.11 (2023): 3263-3274.
Description: A collection of 3521 diverse compounds selected from commercially available compound libraries (i.e. Enamine, eMolecules, WuXi LabNetwork, Mcule) and tested against six ADME in vitro assays using the same experimental conditions. The file contains the compound SMILES, vendor and vendor ID, and the experimental log(properties) for six endpoints: HLM, RLM, Solubility, MDR1-MDCK ER, hPPB, and rPPB.
Once uploaded, you can ask Faraday to perform a variety of tasks using the content in these documents.