Model, simulate, predict → computational chemistry integrated with machine learning
Paraza’s computer-aided drug design (CADD) group is equipped with state-of-the-art tools for in silico drug design. Our experienced, highly innovative CADD scientists employ computational chemistry and machine learning (ML) methods to support and accelerate the process of drug discovery and development. Our capabilities include structure-based, ligand-based, and fragment-based drug design (SBDD, LBDD, FBDD), molecular dynamics (MD), quantum mechanics (QM), virtual screening and protein modeling, all tailored to meet your project’s specific needs. We seamlessly integrate machine learning with computational chemistry to provide useful insights and predictions of activity, selectivity, and molecular properties. We also collaborate with Paraza’s AI partners to conduct pilot study and assess state-of-art ML platforms that could facilitate drug discovery projects.
Client
Testimonial
"... this extra work is a direct result of the extraordinary service that Paraza Pharma has delivered to us on this project. Please accept our deepest appreciation of the heroic efforts that you have displayed in the last few weeks meeting."
Collaborative in silico drug design support
Our CADD group works closely with clients as well as Paraza’s chemistry, biology and DMPK teams to provide in silico insights that help improve potency, selectivity and ADME properties. We are committed to leveraging the power of rational drug design, and we are constantly exploring new computational methods to effectively support drug discovery projects. We offer both FTE and FFS CADD services covering hit identification, lead identification and lead optimization.
Hit Identification
- Homology modeling
- Binding site prediction
- Structure-based virtual screening
- Ligand-based virtual screening
- Docking model generation
Lead Identification
- Structure/ligand/fragment-based design
- Similarity search-based screening
- Combinatorial library enumeration
- Docking/induced-fit docking
- Pharmacophore elucidation and screening
Lead Optimization
- Molecular dynamics simulation
- Quantum mechanics simulation
- SAR rationalization
- QSAR/QSPR modeling
- Selectivity modeling
Machine learning/deep learning
- ADME property prediction
- ML for activity/property predictions
- Generative molecule design
- Neural network potential for energy evaluation
