Home Services Discovery Services CADD/Artificial Intelligence

CADD/Artificial Intelligence

Computer-Aided Drug Design Selvita’s computer-aided drug design (CADD) centre was created to foster collaborative research between medicinal chemists, biologists, biophysicists, structural biologists and computational scientists. In a drug discovery campaign, CADD is usually used for three major purposes:

  1. Physico-chemical and structural characterization of compounds from various libraries followed by filtering large compound libraries into smaller sets of predicted active compounds that can be tested experimentally;
  2. SAR analysis to guide the optimization of lead compounds, whether to increase its affinity or optimize drug metabolism and pharmacokinetic (DMPK) properties including absorption, distribution, metabolism, excretion, and the potential for toxicity (ADMET);
  3. Design novel compounds with a help of a miscellaneous set of computational tools.

CADD depends on the extent of structure and other information available regarding the target (enzyme/receptor/protein) and the ligands. The latest advancements like AI, QSAR, combinatorial chemistry, different databases and available new software tools provide a basis for designing of ligands and inhibitors that require specificity and novelty.

At hit identification, hit-to-lead or lead optimization stage our CADD can apply the following methods:

  • Ligand-Based Drug Design, LBDD (flexible shape-based and/or field-based alignments with active molecules when 3D structure of target is unknown, pharmacophore modelling)
  • Structure-Based Drug Design, SBDD (ligand-receptor interaction studies with known 3D structure of receptor, docking, molecular dynamics)
  • Homology modelling of proteins
  • Chemoinformatics
  • In silico physico-chemical profiling
  • In silico ADMET profiling
  • Focused libraries design for screening or synthesis (in silico or in collaboration with our medicinal chemists)
  • HTS data analysis (hit confirmation and hit expansion to provide missed starting points for the project)
  • SAR analysis and proposal of new compounds within currently investigated and/or new chemical series (bioisostere replacements, scaffold hopping)
  • Quantitative Structure-Activity Relationship (QSAR) analysis
  • Quantitative Structure-Property Relationship (QSPR) analysis
  • Support to NMR screening for Fragment Based Drug Discovery (FBDD)

Most notably, our computational and medicinal chemists are working seamlessly together in interactive molecular design sessions, in order to rapidly generate hypotheses for molecular drug designs that are immediately assessed in suitable in silico models before molecules are prioritized and selected for syntheses in our laboratories or purchasing. Using a diverse set of available computational chemistry tools that are applicable for a given project, we assist the medical chemists in order to minimize the time, synthetic efforts and detours along the transformation process of a hit compound into a candidate.

AI-driven Drug Discovery

At Selvita not only we use traditional CADD but we also employ methods based on artificial intelligence (AI) or machine learning (ML). Those methods are especially useful for designing focused screening libraries, as a support in properties optimization process or to predict ADMET properties. Since the main task of the AI-based methods is to find associations between seemingly unrelated data, they are also very useful in target deconvolution process. All tasks related to AI and ML are performed in collaboration with ARDIGEN – SELVITA GROUP company specializing in this area.

Ready to partner with us?

Get started