to fit your needs for knowledge discovery to save time and money

Extract value from your data across various fields of applications

unlimited fields of applications

Our insilico solutions are flexible enough to extract value from your data across various applications.

multiple industries

Biotech, Pharmaceuticals, Nutrition, Cosmetics, Home and Personal Care, Retail, Agritech, Chemicals...

various departments

Research & Development, Sales, Marketing, Logistics, Human Resources, Business Intelligence...

Diverse Use cases

Biomarker Discovery, Structural Alert Detection, Product Claims, Profiling, Chemical Safety...

chemical toxicology:
cosmetics & pharma safety

During the development of novel pharmaceuticals drugs or cosmetical products, the toxic hazard assessment is known as a critical step. The development of chemicals now requires a data gap-filing procedure, which means for the formulator to tackle this problematic using a pluridisciplinary approach (e.g., to fit to the regulation authority guidelines such as ECHA/REACH recommandations). Moreover, animal testing has been strongly reduced and classical investigation (in vitro, in cellulo) are not sufficient by themselves for toxic assessment anymore. Furthermore, because multiplying classical experimentation is time and money consuming, we created a decision-support system named QUIID[CHEM] for toxic hazard assessment.

QUIID[CHEM] aims at optimising your development process by providing a decision-support system, which helps you to shortlist the best chemical candidates and/or during read-across processes. QUIID[CHEM] helps scientists to early predict structural alerts related to toxic properties or any other endpoints (e.g., sensitisation, carcinogenic, mutagenic, or metabolic properties). The targeted properties of queries chemicals are predicted using datamining methodologies applied to chemical databases (public and/or private databases). Our predictions allow you to anticipate toxical issues along the drugdesign phase, leading you to scaled up your productivity.

lab-217043_1280 cropped

Related publications :

Jean-Philippe Métivier, Alban Lepailleur, Aleksey Buzmakov, Guillaume Poezevara, Bruno Crémilleux, Sergei Kuznetsov, Jérémie Le Goff, Amédéo Napoli, Ronan Bureau, Bertrand Cuissart: Discovering structural alerts for mutagenicity using stable emerging molecular patterns. Dans: Journal of Chemical Information and Modeling, 0 (ja), p. null, 2015, (PMID: 25871768).

Bertrand Cuissart, Guillaume Poezevara, Bruno Cremilleux, Alban Lepailleur, Ronan Bureau: Emerging Patterns as Structural Alerts for Computational Toxicology. Dans: Chapman and Hall/CRC, 2012, ISBN: 978-1-4398-5432-7, (0).

Sylvain Lozano, Guillaume Poezevara, Marie-Pierre Halm-Lemeille, Elodie Lescot-Fontaine, Alban Lepailleur, Ryan Bissell-Siders, Bruno Crémilleux, Sylvain Rault, Bertrand Cuissart, Ronan Bureau: Introduction of Jumping Fragments in Combination with QSARs for the Assessment of Classification in Ecotoxicology. Dans: Journal of Chemical Information and Modeling, 50 (8), p. 1330-1339, 2010, (PMID: 20726596).

for chemical toxicology use quiid[chem]


biomarkers identification

Metabolomics, the science of metabolites analysis, is an emerging and promising technology that aims at identifying complex metabolic signatures and pathways. The metabolome profiling contributes towards a better understanding a human physiology by giving us a functional readout of cellular biochemistry. That is why the identification of specific biochemical fingerprints is a key step to tackle common problematics within the (pre)clinical studies and healthcare industry (e.g., biomarkers for diagnostics, treatment’s response, precision medicine…).

Historically, small numbers of metabolites have been used to diagnose complex metabolic diseases as well as monogenic disorders such as inborn errors of metabolism. But, in the last decades the emerging technologies (such as proteomic methodologies or high througtput sequencing) have continuously generated complex and considerable amount of data about the metabolome, meanwhile the solutions for analysing those datasets are not efficient as well.

QUIID understand your needs and provide solutions to tackle metabolomics problematic. We are able to apply our technology on any subset of metabolic data to unveil hidden correlations between variables (e.g., metabolite interactions, dose effect, pronostical model, pathfinding). QUIID help you to deeply analyse your existing metabolomics data, and also provide a heavy support and a fully understandable output. 

Related publications :

Guillaume Poezevara, Sylvain Lozano, Bertrand Cuissart, Ronan Bureau, Pierre Bureau, Vincent Croixmarie, Philippe Vayer, Alban Lepailleur: A Computational Selection of Metabolite Biomarkers Using Emerging Pattern Mining: A Case Study in Human Hepatocellular Carcinoma. Dans: Journal of Proteome Research, 0 (0), p. null, 2017, (PMID: 28447453).

discover our consulting services

make it easier & faster

The main objective of proteomic is to identify and quantify the proteins contained in a biological sample to obtain functional data, in order to localise and/or identify protein partners or protein binding sites. These data allow us to better understand the molecular mechanisms underlying specific cellular functions. Helped with mass spectrometry methologies, the emergence of proteomics large-scale analysis on multiple and various biological specimens, now generate gigantic quantities of data. Moreover, this data rising phenomenon is intensified by the fact that the proteome could be considered as a dynamic and complex entity.

QUIID understand your aims and provide solutions to tackle issues coming from the proteomics field. Indeed, because proteomics studies quickly generate a large volume of data, their analyses require a computational-based support to improve scientist’s efficiency. QUIID understand your needs and provide expert data mining solutions buy identifying new hidden correlations between the different characteristics obtained from your proteomic experiments (redundant protein partners, binding affinity, comparison to treated condition). Our solutions allow you to deeply investigate signaling pathway (linear cascade, crosstalks, etc…), biomarkers validation (early pathological detection) or assess treatment delivering/efficacy.


discover our consulting services

your activity

No matter your industry, activities and applications, do not hesitate to contact us to find out how we can help you exploit the full potential of your data thanks to our in silico solutions.

We’re looking forward to hearing from you!