iSafeRat® is the High Accuracy QSAR (HA-QSAR) platform produced by KREATiS. Initially designed to fulfill endpoints of regulatory dossiers to meet the REACH requirements, iSafeRat® aims to be the most reliable and accurate in silico approach to replace all kinds of experimental studies related to human health, physico-chemistry et environment.
At KREATiS we believe in our models, and together we can find accurate answers to your questions without resorting to unnecessary experimentation.
To provide a fully validated endpoint value which is at least as accurate as that of the best experimental technique available for that endpoint following OECD Guideline methods but for a fraction of the price of a laboratory study and in a fraction of the time.
Each endpoint value that you order for successful regulatory submission will include a full QSAR Model Report (QMRF) and QSAR Prediction Report (QPRF).
iSafeRat® uses coded chemical structures (SMILES : Simplified Molecular Input Line Entry System) of organic chemicals to:
- Predict critical physico-chemical parameters
- Define structural alerts within the chemical structure and fit them within a highly structured, published classification scheme (Mechanisms of Toxic Action or MechoAs)
- Quantify their (eco)toxicity from the physico-chemical parameters and the MechoA
iSafeRat® is available as a downloadable desktop version. The predictions come with:
- Applicability domain information* to immediately provide upfront information on the regulatory acceptance status of the prediction
- Confidence interval calculations allowing you to judge the model performance
*3 options are proposed, “inside applicability domain”, “outside applicability domain” or “extrapolated”. “Extrapolated” means we believe in the result but statistically it is not currently completely within domain. The prediction can still be very useful and may be submitted to competent authorities as a weight of evidence.
Besides our intention to cover standard regulatory endpoints, KREATiS also offers tailor-made in silico services to meet your specific requirements.
Just as our existing HA-QSARs have been developed and validated (following the latest regulatory guidelines notably R6 and QAF), each of our tailored models are treated with the same level of attention to detail, data verification and statistical model validation.
Depending on your request, we can also prepare a validation report to justify the robustness and, if possible, a mechanistic interpretation for your models.
iSafeRat® KOW C2SM study can test the hydrophobicity (as log KOW) of a substance
As accurate as an OECD 107 or 123 study
iSafeRat® WatSol study can test the water solubility (in mg/L, at 25°C) of a substance
As accurate as a modified OECD 105 slow stirring study (Thomas & Burosse, 2012, see downloads)
95%-Confidence Intervals available
iSafeRat® VP study can test the vapour pressure (in Pa, at 25°C) of a substance
As accurate as an OECD 104 study
95%-Confidence Intervals available
iSafeRat® fishLC50 study can accurately predict 96h-acute toxicity to fish (in mg/L) effectively replacing Guideline studies for multiple types of structural groups
Currently, the ecotoxicity module of the iSafeRat® QSAR models can reliably predict the acute toxicity to fish for chemicals with the following mechanisms of toxic action (MechoA):
for substances with a log KOW between 0 and ca. 5 (and possibly higher), i.e. the solubility/toxicity cut-off point at which acute toxicity is no longer observed below the limit of solubility.
As accurate as an experimental OECD 203 study (in terms of finding true toxicity)
95%-Confidence Intervals
See QMRF for details
iSafeRat® daphEC50 study can acurately predict experimental Guideline 48h-acute toxicity to daphnids (in mg/L) based on immobilisation for wide range of structural groups
Currently, the ecotoxicity module of the iSafeRat® HA-QSAR models can reliably predict the acute toxicity to daphnids for chemicals with the following mechanisms of toxic action (MechoA):
for substances with a log KOW between 0 and ca. 5 (and possibly higher), i.e. the solubility/toxicity cut-off point at which acute toxicity is no longer observed below the limit of solubility.
As accurate as an experimental OECD 202 study (in terms of finding true toxicity)
95%-Confidence Intervals
iSafeRat® algEC50 and iSafeRat® algNOEC studies can test 72h-toxicity (as inhibition of growth) on algae (in mg/L) of a substance
Currently, the ecotoxicity module of the iSafeRat® HA-QSAR models can reliably predict the toxicity to algae (AlgErC10 and AlgErC50) for chemicals with the following mechanisms of action of toxicity (MechoA):
Soft-electrophile reactivity (MechoA 3.2)
for substances with a log KOW between 0 and ca. 5 (and possibly higher), i.e. the solubility/toxicity cut-off point at which acute toxicity is no longer observed below the limit of solubility.
Note: iSafeRat® algNOEC is only available for compounds with MechoA 1.1, 2.1, 3.1 and 3.2
*Currently only available for AlgErC50 predictions
As accurate as an experimental OECD 201 study (in terms of finding true toxicity)
95%-Confidence Intervals
Note: In certain studies on algae the test substance may be lost due to metabolisation, volatility of the test substance or adsorption by the algal cells. The iSafeRat® value will equate to the ErC50 (or NOEC) value obtained in a study where the substance is maintained over the whole study period whether or not this can be achieved experimentally.
iSafeRat® fishEC10 study can accurately predict the experiemntal result obtained from a Guideline 32d-chronic toxicity on fish (in mg/L) for multiple structural groups
Note: The iSafeRat® fishEC10 study will provide a calculated EC10 value (QSAR based on the most senstive endpoints*: growth/overall survival further to a 32-day study on fish using measured concentrations).
*internal study based on validated data
Currently, the ecotoxicity module of the iSafeRat® HA-QSAR models can reliably predict the chronic toxicity to fish for chemicals with the following mechanisms of action of toxicity (MechoA):
for substances with a log KOW between 0 and ca. 5.5 (and higher for certain MechoA sub-classes), .i.e. the solubility/toxicity cut-off point at which chronic toxicity is no longer observed below the limit of solubility.
As accurate as a well run experimental OECD 210 study (in terms of finding true toxicity)
95%-Confidence Intervals (see QMRF for details)
iSafeRat® daphEC10 study can predict 21d-chronic toxicity to daphnids (in mg/L) of a substance
Note: The iSafeRat® daphEC10 study will provide a calculated EC10 value (QSAR based on the most senstive endpoint*: reproduction effects further to a 21-day study on daphnids using measured concentrations).
*internal study on validated data
with log KOW between 0 and ca. 6 (and possibly higher), i.e. the point at which toxicity is no longer found below the limit of solubility.
As accurate as an OECD 211 study (in terms of finding true toxicity)
95%-Confidence Intervals
As opposed to the other High Accuracy-QSAR models this is a multistep calculation method requiring knowledge of the toxicity properties of each constituent. These can initially be calculated using one of the above ecotoxicity acute modules. Currently KREATiS can accurately predict mixture toxicity (e.g. Natural Complex Substances) for up to 29 constituents. Even if your mixture contains more, it may be possible to get a high quality prediction based on the major constituents and those expected to have the highest toxicity.
iSafeRat® fishLL50 WAF, daphEL50 WAF or algErL50 WAF study can test the acute toxicity on fish, daphnid or agae (in mg/L) of the Water Accommodated Fraction (WAF) of a substance (expressed as the lethal or effective loading rate, L/EL50, in mg/L)
Note. The calculation method is also available to get the chronic result (based on the loading rate once again).
using WAF method (following OECD Guidance No. 23 Guidance on Aquatic testing of difficult substances and mixtures)
The toxicity of mixtuures to aquatic organisms was determined using a calculation method based on toxic additivity principle. That means the toxic parts of each constituent are added up. Therefore the constituents considered within the mixture should act with a similar MechoA. To maximise accuracy of the prediction, the concentration of each constituent in the mixture should be known and is used as inputs into the model.
This method has been validated internally on a dozen of Natural Complex Substances for acute exposure with non-polar narcosis constituents. The methodology will soon be available in literature (Bicherel and Thomas, in prep).
As accurate as a WAF experimental study following the specific guideline
(no confidence limits available)
iSafeRat® asritEC50 study can test the toxicity to microorganisms of activated sludge (as EC50) of a substance
Currently, the ecotoxicity module of the iSafeRat® HA-QSAR models can reliably predict the toxicity to microorganisms for chemicals with the following mechanisms of action of toxicity (MechoA):
with log KOW between 0 and ca. 3 (and possibly higher), i.e. the point at which toxicity is no longer found below the limit of solubility
As accurate as an OECD 209 study (in terms of finding true toxicity)
95%-Confidence Intervals
iSafeRat® iSafeRabbit Skin study can predict the irritant potential to the skin of a substance
The iSafeRat Skin Irritation/Corrosion prediction model determines whether the applied dose of a chemical substance causes cytotoxicity, thereby responsible for erythema and/or oedema as both lesions are driving the classification according to CLP and GHS. The dose applied and the physico-chemical properties of the test substance are the input of a series of algorithms to determine the substance concentration in the viable epidermis to establish if this concentration reaches a cytotoxic concentration for the keratinocytes.
Goodness-of-fit & predictive performance: Accuracy: 84%
Predictive capacity for:
iSafeRat® iSafeRabbit Eye study can predict the irritant potential to the eyes of a substance
The iSafeRat Eye Irritation/Corrosion prediction model determines whether the applied dose of a chemical substance causes cytotoxicity, thereby responsible for corneal opacity and/or conjunctival redness as both lesions are driving the classification according to CLP and GHS. The dose applied and the physico-chemical properties of the test substance are the input of a series of algorithms to determine the substance concentration in the viable epidermis to establish if this concentration reaches a cytotoxic concentration in the eye tissue.
iSafeRat® CLASS (Classification & Labelling Assessment for Skin Sensitisation) v1.5 model can predict the skin sensitization potential of a substance as assessed by the Local Lymph Node Assay.
OECD 492A & 492B (in vitro)
Skin sensitiser
Not skin sensitiser
Not skin sensitiser (surfactant properties, risk of +ve in LLNA studies only)
An additional analogue search is implemented to allow the user to have better confidence in the predictions.
The innovative, mechanistic model iSafeRat® CLASS (Classification & Labelling Assessment for Skin Sensitisation) is designed to predict skin sensitisation of organic chemical substances. It is based on Local Lymph Node Assay (LLNA) conducted according to the OECD Guidelines 429, 442A and 442B (OECD, 2010a; OECD, 2010b; OECD, 2018).
The model is an expert-based decision tree generating a final outcome result based on the results of four independent sub-models:
· Hapten/prohapten detection (based on MechoA) v1.2 (hereafter referred as Hapt v1.2)
· Autoxidation (prehapten detection) v2.0 (hereafter referred as AutOx v2.0)
· Skin penetration v1.0 (hereafter referred as SkinAbs v2.0)
· Expected LLNA positive LLNA+ v1.1 (hereafter referred as LLNA+ v1.1)
These sub-models are either based on structural alerts or physicochemical property thresholds.
Skin sensitisation is predicted through 3 sub-models: pre-hapten detection through autoxidation (AutOx v2.0), skin penetration (SkinAbs v2.0), hapten & pro-hapten detection (Hapt v1.2). Additional information is provided based on the results of LLNA+ v1.1. Based on those, a final outcome is given to predict skin sensitisation potency of the substance.
For iSafeRat® CLASS v1.5 in iSafeRat Desktop v5.2.5 performance of the overall training set of 838 substances (training set and internal validation set) and the external validation set of 237 substances, is:
- Docking tools
- Log Kow: extension of applicability domain and development of another model based on machine learning (iSafeRat® ALPS)
- Solubility: extension of applicability domain
- Vapour Pressure: extension of applicability domain
KREATiS is continuously retrieving data to develop new in silico models and to improve the applicability domain of existing ones in ecotoxicology.
Among others, here are the currently on-going tasks:
- update of the acute and chonic toxicity to fish, daphnids and algae for non-polar narcotic compounds (i.e. MechoA 1.1) taking into account main categories of colorants such as anthraquinones, sulfonates, azo and nitro compounds
- update of the acute and chonic toxicity to fish, daphnids and algae for polar narcotic compounds (i.e. MechoA 1.2) taking into account anilines
- update of the acute and chronic toxicity to fish, daphnids and algae for reactive compounds (i.e. MechoA 3.1 and 3.2) like aldehydes, epoxides and acrylates
- new model of the chronic toxicity to fish, daphnids and algae for carboxylic acids (i.e. MechoA 5.2)
KREATiS is currently working on development of new in silico models to predict these following endpoints in toxicology:
KREATiS is currently working on development of new in silico models to predict these following endpoints :
- Molecular Dynamics
- Further development of ED SAR and SESAME-3D as a part of an NC3Rs project.
Get in touch with the KREATiS team today to benefit from our tailored services. Let us know your requirements and one of our team members will contact you to discuss it further.
Contact us