Skip to main content

Chemoinformatics

The computational techniques are exclusively based on the knowledge
of the chemical structures of compounds with a certain activity, and not
on the structure of a particular target:

Calculation of molecular descriptors

That is, numerical values associated with the structural features of chemical compounds, so that different sets of these descriptors encode different chemical information. We can calculate more than a thousand of these indices, covering simple structural data (number of atoms, bonds, rings, etc.), topological information (shape, size, molecular branching), physicochemical properties (hydrophilicity/hydrophobicity, polarizability, etc.), or descriptors dependent on molecular conformation.

Filtering of chemical compounds according to pre-fixed rules

In the initial stages of medical chemistry projects it is common to determine certain standardized rules such as the well-known “Lipinski rules” (for the selection of drug-like compounds), “Oprea rules” (for the selection of lead-like compounds) or the “rule of three” (for the selection of fragments). In ProtoQSAR we have the means to calculate standard parameters (such as molecular weight, number of proton donors/acceptors, cLogP, number of rotatable bonds, polar surface area (PSA), etc.), which allow us to classify compounds according to these rules.

Analysis of chemical similarity and/or diversity

In ProtoQSAR we can characterize the molecules by using molecular descriptors such as the “MACCS keys” and standard algorithms such as the Tanimoto coefficient, as well as selecting subsets of compounds based on their structural similarity/diversity.

Alignment of small molecules

3D superposition of potential and known ligands -after a conformational sampling of both types of structures- in order to deduce structural requirements for a given biological activity.

QSAR

Construction of mathematical models relating the in silico structure of molecules with a biological property or activity, through the use of statistical tools. Once a correlation has been established, it can be used later to predict the property or biological effect of new structures.

Read-across (aka “neighborhood behavior”)

When there is not enough data to build QSAR models, this method is a simpler alternative based on the well-known principle of “chemical similarity”: chemicals with common structural features usually exhibit similar physico-chemical and biological properties. Therefore, compounds that share structural similarities can be grouped into a chemical category, and it is possible to use data information from members of this group to estimate properties of other members of the same group.

Try our computational prediction platform for chemical compounds

ProtoPRED uses its own QSAR (Quantitative Structure-Activity Relationships) models,  widely applied in sectors such as cosmetics, pharmaceuticals and chemicals. This tool allows the prediction of a wide spectrum of properties of industrial and regulatory interest, ensuring the obtaining of valid documents in accordance with regulations such as REACH and ICH. With ProtoPRED, companies can efficiently comply with current regulations and optimize their registration processes

Computational toxicology

Computational evaluation of the properties required by different regulations in force

Design and optimization

"Drug discovery", virtual screening, drug repositioning, ADME-T properties prediction, etc.

Training

Training courses on the application and development of our techniques

Collaborative projects

We participate in projects on REACH, biocides, nanomaterials, endocrine disruptors, etc.

Frequently asked questions

Is ProtoQSAR a consultancy company or a vendor of specialized software on molecular modeling and chemoinformatics?

ProtoQSAR is a company that conducts studies for its clients and collaborators, currently we do not sell molecular simulation programs, nor our QSAR models. We provide our services to groups and entities that for the most part do not have specific training in chemistry-computing and molecular modeling -or it is very limited- and therefore our expertise can represent a greater added value for them.

How long does it take for a client to get the results of their project?

The projects in which we work are very different from each other, and prior to their execution we make an evaluation of the time necessary. The great advantage of computer studies compared to experimental tests is that we can obtain results in a much shorter time. For example, the prediction of the profile of a compound by QSAR methods is very fast (few days), since we already have models for this kind of evaluation. The virtual screening of a database to search for a candidate interacting with a particular target can represent 1 week to 2 months, depending on the number of chemicals filtered (a few thousands or hundreds of thousands).

Can I propose a collaborative project to ProtoQSAR? How?

At ProtoQSAR we are very interested in the development of new collaborative projects in which chemoinformatics and molecular modeling can provide an added value to our collaborators. If you have any idea to raise, please contact us explaining your proposal, and in a very short time we will give you an answer.

How much do ProtoQSAR services cost? How are the costs estimated?

Costs vary depending on the type of service we provide and the time we spend on a project. Since computing allows results to be obtained in a much shorter time than experimental tests, our services are also much cheaper.

What software does ProtoQSAR use to develop its models?

In ProtoQSAR we work with the whole palette of molecular modeling and chemoinformatics techniques, and therefore we have all the necessary programs for the execution of our projects. We systematically use standardized programs that are well referenced in the scientific literature, and sometimes we carry out our own software developments for specific needs. In any case, these developments remain the property of ProtoQSAR, and are not for sale.

What degree of confidence do the computer models have?

Computational studies are not an “exact science” and a certain degree of uncertainty is expected, as is the case with experimental tests (both in vitro and in vivo) to a certain extent. We conduct our studies according to scientifically recognized quality guidelines, and our extensive experience (demonstrable through our scientific and technical publications) makes our studies as accurate as possible. Before conducting a study, we inform our clients about the reasonable results’ expectations. At the time of providing the results, we also contribute our expert evaluation and inform the customer of the potential limitations of the obtained models.

How much time is needed to do a virtual screening? And how many compounds can be filtered?

Both questions are linked: the execution time of a virtual screening depends essentially on the number of compounds that are screened. To give a general idea, an already developed QSAR model allows the user to evaluate tens of thousands of compounds in a single day. Screening by docking (in a therapeutic target with known 3D structure) requires a longer period of time, but we can also evaluate thousands of compounds in a few days.

Can computational models be applied at the regulatory level?

Chemoinformatic models are recognized as a valid alternative at a the regulatory level, and the international regulations themselves increasingly encourage their use. For example, in the case of REACH, ECHA systematically requests companies to demonstrate that they have fully considered the use of alternative methods before concluding that a new test with vertebrates is necessary.

Can computer models replace the experimental tests required by legislation (e.g. REACH)?

Yes, in a lot of cases our models make it unnecessary to perform additional assays. This is particularly common when there is already some bibliographic information on the studied compounds, or when the products are of natural origin. In other cases the computational studies do not completely replace the experimental tests, but it is usually possible to reduce them (and therefore reduce time and costs). Another factor to consider is the credibility of the company in front of the authorities, which is clearly favored when presenting a complete dossier including the evaluation by alternative methods.

What type of model do I need for the registration/authorization of my substance: QSAR or read-across?

The type of model depends on the baseline information and on the substance to be evaluated. In principle, QSAR models are technically more robust and reliable, but they cannot always be used (for example, if the compound to be evaluated does not fall within the domain of applicability of the compounds that have been used to generate the models). In that case read-across is a good alternative, since this technique has the same validity at the regulatory level when properly executed by an experienced professional.

What is the “Applicability Domain”? How does it affect the prediction of my substance at the regulatory level?

Applicability domain is the “chemical space” to which a specific compound belongs in relation to the compounds that have served as the basis for developing a QSAR model. One of the parameters required by the OECD (and therefore necessary from a regulatory point of view) when determining whether a QSAR is valid on a given compound is the characterization of that space.

How are QSAR models validated?

All our models are subjected to a double validation, internal and external, and when possible we perform an experimental validation with independent structures belonging to the same chemical space or “domain of applicability”.

Contact us and our team will advise you on everything you need

We are here to help you. Do not hesitate to contact us to receive personalized advice and resolve any questions you may have. Our team is available to offer you the best care.

Address

ProtoQSAR SL - CEEI Valencia

Technological Park of Paterna (Valencia)

Avda. Benjamin Franklin 12, Desp. 28
46980 Paterna (Valencia)

Skip to content