NCE/NBE Drug Discovery - Leverage our In Silico Solutions for NCE/NBE Drug Discovery & Development

NCE/NBE

In today’s pharmaceutical industry, developing new chemical and biological entities is a complex, lengthy, and expensive process, taking decades and billions of dollars to bring a drug to market. Our AI and in silico solutions enhance the success and efficiency of your drug development programs.

Our validated computational models replicate drug-protein interactions and predict a drug’s ability to bind to its target. We identify disease-related proteins and pathways, offering insights into candidate drug efficacy and safety prior to clinical trials. Our validated disease models optimize clinical trial design, protocol, sample size, and outcome predictions, reducing time and cost. Regulatory agencies may grant waivers based on our in silico trial data. We help our clients provide quantitative in silico evidence to regulators which helps support regulatory decision-making and approvals for IND/NDA submissions.

Model Informed Generic Drug Development

Our AI, Modeling & Simulation experts work closely with our clients to understand their unique scientific questions of interest and challenges. We then leverage our expertise in in silico modeling and simulation to provide the correct approach to address our customer requests.

Pharmaceutical Digitization

We have extensive expertise in modeling and simulation for a wide range of applications, including pharmaceuticals, API, and process simulations. We are skilled in developing custom models and simulations to meet specific client needs. Our team is committed to staying up-to-date with the latest developments in the field and applying cutting-edge techniques to drive innovation and optimization.

We are skilled in developing custom validated models

Drug Repurposing

Our in silico solution predicts putative biological targets and corresponding bioactivity of a query compound based on a large database covering a chemical space of more than 600,000 molecules and 1,000,000 activity records.

Molecular Docking

Our in silico solution explores the interactions between a ligand towards a biological target at the molecular level. It evaluates potential target-ligand combinations and quantifies target-ligand binding affinities.

Target Identification

Our in silico solution enables, for a given small molecule chemical structure, the putative drug target finishing via reverse ligand-based screening. It is built on the similarity principle and on a collection of > 600,000 compounds known to be experimentally active on > 6,000 protein targets from ChEMBL. Apart from the identified targets, the tool also provides information on the most similar bioactive ligands to the small molecule along with the best activity experimental values.

Bioactivity Prediction

Our in silico solution enables, for any given small molecule chemical structure, quantitative bioactivity predictions (Ki, EC50, IC50, Kd) towards the identified putative protein targets and corresponding estimate precisions.

Pharmacological Profile

Our in silico solution enables, starting from a given small molecule chemical structure, the evaluation of (poly-) pharmacological activities of compounds either acting on individual targets or acting simultaneously on multiple disease-relevant targets.

Nonclinical Tox

Our in silico solution enables, starting from a given small molecule chemical structure, the prediction of potential toxicity for several toxicological endpoints based on in vitro and acute-chronic in vivo data.

Target Deconvolution

Our in silico solution enables phenotypic deconvolution and pathways analysis of data obtained through screening of a compound or of a library of compounds in in vitro 3D-cells disease models. Pathways predicted to be affected by individuals or groups of biological activities are identified and the phenotypic response rationalized, whenever possible.

Hit Generation

Our in silico solution, using the known target protein as input, enables the design of bioactive small molecules for orthosteric and allosteric binding sites through a protein surface scan to identify protein environments compatible with chemical fragments.

Hit-to-Lead

Our in silico solution enables the generation of in silico libraries of novel bioactive compounds around the identified hits through exclusion of ligand-protein interactions that violate established principles of physical chemistry, particularly as it concerns the exposure to solvent of charged protein and ligand groups.

Lead Optimization

Our in silico solution enables the structure optimization of a lead compound and binding affinities determinations through a protein−ligand docking method. The tool accurately accounts for both ligand and receptor flexibility by iteratively combining rigid receptor docking with protein structure prediction techniques.

Epitopes Identification

Our in silico solution is Deep Learning-based. Predicts protein-protein interactions probability through 2D maps

PhysChem Properties

Our in silico solution quantifies Blood-Brain-Barrier (BBB) permeability to predict whether a compound will cross the BBB. In addition, the tool also predicts a whole range of molecular PhysChem properties.

Macrophages Polarization

Our in silico solution predicts phenotype changes towards M1 and M2 phenotypes (M1 and M2 scores) in an in vitro polarization experiment with customizable experimental conditions.

Chemotoxicity

Our in silico solution evaluates a compound’s toxicological profile by in silico assessment of the major toxicological endpoints (e.g. genotoxicity, neurotoxicity, carcinogenicity, skin irritation, etc.).

Mutagenicity

Our in silico tool assesses a compound’s mutagenicity potential by combining two complementary quantitative structure-activity methodologies, as per the ICH M7 guidelines.

Immunogenicity Risk Screen

Our in silico solution enables an early immunogenicity risk screen which emulates the CD4+ T-cells proliferation assay to determine the potential immunogenicity risk of new protein sequence.

Cardiac Drug Safety Suite (QT/TdP Risk Screen)

Our machine learning-based in silico tool predicts a compound’s proarrhythmic risk using electrophysiology and machine learning.

Cardiac Drug Safety Suite (STrhiPS)

Our tool enables in silico safety trials on a population of human-induced pluripotential stem cells.

Cardiac Drug Safety Suite (CipA InSilico)

Our in silico tool estimates the safety marker qNet based on up to 7 ion channels in vitro data at different concentrations, as per FDA recommendations.

ADME Properties

In Silico Prediction of ADME properties of a compound (absorption, distribution, metabolism and elimination). Our in silico solution provides insights into potential safety issues, optimizes pharmacokinetic properties, and reduces cost and time required for R&D.

Hemochromatosis

Our in silico solution predicts the iron distribution and elimination pathway in a virtual hemochromatosis mouse based on a validated system-biology model.

Mammary Carcinoma

Our in silico tool predicts the immunotherapy treatment effect in a virtual population of mice with mammary carcinoma.

Insulin Injection

Our in silico tool estimates insulin injection, skin absorption, and residual volume in an injection port device over time via Computational Fluid Dynamics.

Population PK/PD Modeling

Our in silico solution that entails a mechanistic modeling approach used for the assessment of therapeutic intervention on a disease by linking descriptions of the molecular and cellular mechanisms of the disease and drug to system-wide dynamics, bridging biomarkers and clinical endpoints relevant for the disease. It supports target selection & validation, biomarker selection & evaluation, proof of concept & proof of mechanism evaluations, experimental & trial design, and in silico clinical trials.

QSP Modeling

Our in silico solution that entails the study of variability in drug concentrations and responses between individuals (healthy volunteers or patients). It comprises the assessment of variability within the population and to account for the variability in terms of patient characteristics such as age, renal function or disease state. The efficacy and safety of a new chemical entity (NCE) / new biological entity (NBE) is generally characterized in phase III studies in a well-defined restricted patient population. The pharmacokinetic (PK) information is used to extrapolate the safety and efficacy findings to the wider patient population who may receive the NCE/NBE in question.

PBPK/PD Modeling

Our in silico solution that uses modeling and simulation that combines physiology, population, and drug characteristics to mechanistically describe the pharmacokinetic (PK) and/or pharmacodynamic (PD) behaviors of a drug. Throughout a drug’s life cycle, PBPK/PD model predictions can be used to support decisions on whether, when, and how to conduct certain clinical pharmacology studies. It also helps support dosing recommendations in product labeling.

PCa GnRH Agonists Simulator

Our in silico tool enables simulations of clinical trials on a virtual population of prostate cancer patients being treated with a gonadotropin GnRH agonist.

CT x NeutroSim

Our tool performs in silico clinical trials to assess the neutropenic effects of a chemotherapeutic agent in a virtual population of cancer patients.

MS TreatSim

Our tool generates in silico trials and personalized therapeutic effect predictions in relapsing-remitting multiple sclerosis, by predicting disease activity and treatment effects in virtual patients.

Amyotrophic Lateral Sclerosis

Our in silico tool generates synthetic control arms for amyotrophic lateral sclerosis (ALS) clinical trials by predicting disease progression with virtual patients.

Infertility Virtual Patients

Our in silico tool simulates the (dys)functional hormonal system guiding the menstrual cycle and treatment effects in female virtual patients in assisted reproduction clinical trials.

Polycystic Ovary Syndrome

Our in silico tool simulates disease progression and treatment effects in polycystic ovary syndrome (PCOS) virtual patients.

Diabetes Virtual Populations

Our in silico tool predicts the effect of anti-diabetic drugs and therapies in a virtual population.

Intra-Articular Injection

Analyzes dissolution, diffusion and transfer of drug from intra-articular knee space to the plasma, based on physiologically-based pharmacokinetic modeling.

SimTabletCoater

Virtually experiment tablet coating process for pharmaceutical applications, in order to establish the desired setup in terms of coater rotation speed, mass of tablets in the coater, amount and composition of the spray applied over time.

XPS

XPS (eXtended Particle Simulation) is a highly efficient simulation solution to better understand, control and predict pharmaceutical fluid-granular processes, to enhance efficiency and improve product quality

Clinical-Postmarket Safety

Solution that enables - for a given small molecule hit, lead or drug candidate - to predict the compound clinical and/or post-marketing safety profile in a given indication and therapeutic area and to compare it with standards of care.

Value of in silico modeling and simulation
in NCE/NBE.

Optimize Drug Formulations

Identify the optimal formulation and dosage forms that leads to improved drug efficacy and patient outcomes

Reduce Cost and Time to Market

Reduce the time and costs associated with clinical trials and drug development

Improve Regulatory Submissions

Help in streamlining the approval process and reduce the risk of regulatory rejection

De-risk
R&D

In silico allows informed decision-making early, de-risking R&D

Enhance Product Lifecycle Management

Identifying opportunities for reformulation or repurposing

NCE/NBE

Model Informed Generic Drug Development​