Knowledge- and Statistics-Based QSAR Software - Free Trial
Fujifilm Corporation offers a QSAR software package that combines both knowledge-based and statistical-based models.
Software Features
Knowledge-based model
- Equipped with a metabolic reaction simulator, it reproduces the metabolic reactions of chemicals under Ames test conditions, reducing the risk of false positives.
- For each metabolite generated by the metabolic reaction simulator, the mutagenicity is predicted using the knowledge-based model.
- If any metabolite has a positive structure, the compound is judged as positive.
Statistical-based model
- Includes more than 6,000 high-quality test data cases, which were acquired from GLP facilities.
- In addition to pharmaceuticals, a wide variety of structural data for applications like dyes, liquid crystals, and dispersed materials are also suitable, and accurate prediction of new compounds can be expected.
User Interface
- The software is a web application that does not require installation, so it can be used immediately from a browser.
- Intuitive and lightweight operation of the UI.
- Prediction of 1,000 chemical substances can be done in about 10 minutes.
- Prediction results can easily be exported to csv files.
Confidentiality of information
- Compound data (structural formula) is handled only within the cloud system.
- To protect confidentiality, the system is isolated from third parties, including Fujifilm Corporation, the software developer.
Two Types of QSAR Models: Knowledge-Based and Statistical-Based
The ICH-M7 guidelines recommend the use of two complementary QSAR models (knowledge-based and statistical).
FUJIFILM Corporation has developed an unprecedented QSAR software that combines two QSAR models: a knowledge-based model that incorporates a proprietary metabolic reaction simulator and a statistical-based model that incorporates various compound information cultivated through product development to date.
Knowledge-based model
Common to all positive chemicals
- Substructure (toxicity-causing structures)
- Rule-based physicochemical parameters
Statistical-based model (AI)
By machine learning,
- Estimated values of physical properties (descriptors)
- Models are trained based on features such as the presence or absence of specific structures (fingerprints)
*Presented at the 50th Annual Meeting of the Japanese Society of Toxicology (June 2023)
「Design and development of compound safety prediction system including AMES prediction considering metabolism」
Knowledge-Based Model: The Importance of Considering Metabolic Reactions
Because Ames tests are also performed in the presence of the S9 enzyme, the structure that a chemical substance can take in the test is not only the input structure itself.
By taking metabolic reactions into account, “false negatives,” which imply an incorrectly predicted negative result for a substance that is actually positive, can be reduced.
Knowledge-Based Model: Prediction Example
Knowledge-Based Model: Considering Metabolic Reactions — Evaluation of Prediction Performance
Comparison of prediction performance with and without considering metabolic reactions
•Validated using about n=300 public data (Annual Meeting of the Japanese Society for Environmental Mutagenomics, 2023)
| Indicators | When S9 metabolism is not taken into account | When S9 metabolism is taken into account |
|---|---|---|
| Positive substances are judged as positive | 64% | 77% |
| Negative substance is judged as negative | 88% | 85% |
Statistical-Based Model: Characteristics of Ames Test Data Used In This Prediction Model
Includes more than 6,000 cases of high-quality test data, which were acquired from GLP facilities.
Various structural data including dyes, liquid crystals, dispersion materials, etc., in addition to pharmaceuticals
⇒Compared to public data sets, the chemical space is large.
- Calculation of chemical fingerprints and compare distributions using t-SNE (nonlinear dimensionality reduction algorithm)
- This training data includes public chemical substance data.
● Public chemical substance data (NTP, J-CHECK, workplace safety sites, etc.)
● Training data of FUJIFILM model
For research use or further manufacturing use only. Not for use in diagnostic procedures.
Product content may differ from the actual image due to minor specification changes etc.
If the revision of product standards and packaging standards has been made, there is a case where the actual product specifications and images are different.