SilicoPharm

SilicoPharm has three independent modules based on AI and our innovative compound representations.

SilicoParm enables to arrange a user-defined workflows and polypharmacological profile.

Pharmacoprint module uses an innovative AI-based compression method of our high-resolution pharmacophore representations of compounds, as well as fast affinity prediction using machine learning methods.

Mt-QSAR module uses machine learning models built on our optimized combination of binary molecular fingerprints to provide fast prediction of activity.

Mt-SIFt identifies the interactions profile between the ligand and panel of on- and off-targets using our Structural Interaction Fingerprints (SIFt) and flexible ligand docking. It allows for the de novo design on previously defined structural requirements as well as interaction hot spots.

Two sources of compounds as inputs to the in silico screening for polypharmacological profile

CombLibFP module uses a user-defined polypharmacological profile to encode a binary fingerprint, which can be used to de novo generation of compounds with the desired pharmacological properties.

Our own, manually curated library of commercially available compounds. It contains more than 10M of different structures from the veryfied vendors. Library is constantly updated and expanding.

The main features of the SilicoPharm platform

Databases

in-house databases, veryfied, and updated frequently

SaaS

software as a service platform with no installation required

AI

predictions, and decision making are supported by artificial intelligence

VS Workflow

make your own VS workflow and analyse the results flexible

ON- & OFF-targets

carefully selected on- and off-targets (safety panel)

Target DB

manually curated database of macromolecular drug targets, updated frequently

Ligand DB

manually curated database of bioactive molecules, updated frequently

Results analysis

flexible protocol to a final data analysis and visualization

Our team

Experienced & Professional Team

You can relay on our amazing features list and also our customer services will be great experience for you without doubt and in no-time

Rafał Kurczab, Ph.D.

Ph.D. in chemistry (2013) and habilitation in pharmaceutical science (in 2019). He holds an assistant professor position at the Department of Medicinal Chemistry, Maj Institute of Pharmacology Polish Academy of Sciences. He is developing new methods and algorithms used in the technology of virtual screening of commercial and combinatorial databases. His primary scientific interests are focused on the implementation of methods of artificial intelligence (machine learning) to create innovative tools to support the process of selecting new drug candidates while minimizing the potential side effects (interaction with off-targets).

Marek Śmieja, Ph.D.

He obtained his Ph.D. in Computer Science at the Jagiellonian University. In 2019, he spent three months at Instituto Superior Técnico, University of Lisbon, where he worked as a Post-Doctoral Scholar. Currently, he holds an assistant professor position at the Institute of Computer Science of the Jagiellonian University. He works actively in the area of machine learning and data analysis.

Sabina Podlewska, Ph.D.

She got her professional experience mainly at the Department of Medicinal Chemistry Maj Institute of Pharmacology Polish Academy of Sciences (Ph.D. in 2016). Her scope of research is mainly related to the development and application of computational methods to the search for new biologically active compounds. In her work, she applies mathematical and chemical knowledge, and the core of methodologies used in conducted projects is constituted by machine learning algorithms.

Grzegorz Satała, Ph.D.

Graduate Ph.D. in Pharmaceutical Sciences at the Faculty of Pharmacy (Medical College) at the Jagiellonian University in Cracow. He is employed as an assistant at the Department of Medicinal Chemistry, Maj Institute of Pharmacology Polish Academy of Sciences, where he has gained experience in drug discovery based on high-throughput screening of large compound libraries by in silico and in vitro methods for structure-activity relationship exploration. He participated in numerous research projects and industry internships in Poland and abroad.

Dawid Warszycki, Ph.D.

He graduated Ph.D. in Pharmaceutical Sciences at the Faculty of Pharmacy (Medical College) at the Jagiellonian University in Cracow in 2017. He is employed as a research assistant at the Department of Medicinal Chemistry, Maj Institute of Pharmacology Polish Academy of Sciences where he has been working since 2010. His scientific experience is focused on different approaches of computer-aided drug design including a broad scope of diversified methodologies including ligand and structure-based techniques, machine learning, and data management.

Rafał Kafel, M.Sc.Eng.

He completed studies in the field of Computer Engineering at the Department of Electrical and Computer Engineering at the Cracow University of Technology where he obtained a degree of Master of Science in Engineering. He works at the Maj Institute of Pharmacology Polish Academy of Sciences as a Python developer and DevOps engineer. Rafał has many years of experience in supporting the implementation of computational tasks in the field of molecular modeling mainly using parallel and distributed computing.

Stefan Mordalski, Ph.D.

Holds a Ph.D. in biophysics, defended in 2016. His research interests focus on the structure and function of G Protein-Coupled Receptors (GPCRs). Since 2014 he is a member of the developer team of GPCRdb, a resource gathering sequences, structures, and analysis tools for GPCRs. Stefan has also worked with structure-based drug discovery, utilizing ligand-receptor interactions in virtual screening.

Have any Questions ?

We shows only the best websites, portfolios ans landing pages built completely with passion, simplicity & creativity !

SilicoPharm Polypharmacological in silico screening platform for the next generation drugs