Hokkaido University · Materials Science
Professor Pavel Sidorov's research lab specializes in computational chemistry and cheminformatics, focusing on the development and application of machine learning and quantitative structure-property relationship (QSPR) models for drug discovery. The lab investigates drug combination synergy in cancer treatment using large-scale datasets like NCI-ALMANAC, while also exploring antimalarial drug design through physicochemical property modeling and reaction pathway analysis. A key focus is on creating robust data management and modeling tools, such as RePathDB for reaction pathway data and DOPtools for descriptor calculation and model optimization. The lab integrates quantum chemical calculations with machine learning to predict biological activity, mode of action, and molecular properties across diverse chemical spaces.
Figures are computed from collected data and may differ slightly.
Drug combinations are of great interest for cancer treatment. Unfortunately, the discovery of synergistic combinations by purely experimental means is only feasible on small sets of drugs. <i>In silico</i> modeling methods can substantially widen this search by providing tools able to predict which of all possible combinations in a large compound library are synergistic. Here we investigate to which extent drug combination synergy can be predicted by exploiting the largest available dataset to d
3-Benzylmenadiones are potent antimalarial agents that are thought to act through their 3-benzoylmenadione metabolites as redox cyclers of two essential targets: the NADPH-dependent glutathione reductases (GRs) of Plasmodium-parasitized erythrocytes and methemoglobin. Their physicochemical properties were characterized in a coupled assay using both targets and modeled with QSPR predictive tools built in house. The substitution pattern of the west/east aromatic parts that controls the oxidant cha
Presently, quantum chemical calculations are widely used to generate extensive data sets for machine learning applications; however, generally, these sets only include information on equilibrium structures and some close conformers. Exploration of potential energy surfaces provides important information on ground and transition states, but analysis of such data is complicated due to the number of possible reaction pathways. Here, we present RePathDB, a database system for managing 3D structural
Abstract Background Drug combinations are of great interest for cancer treatment. Unfortunately, the discovery of synergistic combinations by purely experimental means is only feasible on small sets of drugs. In silico modeling methods can substantially widen this search by providing tools able to predict which of all possible combinations in a large compound library are synergistic. Here we investigate to which extent drug combination synergy can be predicted by exploiting the largest available
This paper presents the effort of collecting and curating a data set of 15461 molecules tested against the malaria parasite, with robust activity and mode of action annotations. The set is compiled from in-house experimental data and the public ChEMBL database subsets. We illustrate the usefulness of the dataset by building QSAR models for antimalarial activity and QSPR models for modes of actions, as well as by the analysis of the chemical space with the Generative Topographic Mapping method. T
The DOPtools (Descriptors and Optimization tools) platform is a Python library for the calculation of chemical descriptors, hyperparameter optimization, and building and validation of QSPR models.
Machine learning applications in chemistry have come a long way from the simple linear correlations of a property to a handful of descriptors, to complex models built on structural and electronic features of ensembles of molecules or reactions. Nevertheless, models built to predict the enantioselectivity of catalysts in asymmetric reactions are not yet so common. This chapter gives an overview of general approaches to treating reaction data and the recent efforts in enantioselectivity modeling u
This thesis is dedicated to the concept of the analysis of chemical space, and the application of thatconcept to antimalarial compounds. The analysis of the chemical space of antimalarial compoundshere is done with the aid of the Generative Topographic Mapping (GTM) method. A concept ofUniversal GTM maps is developed and discussed in detail in this thesis: these are maps that areable to accommodate different datasets and associated properties. Three types of maps are builtand analyzed: local, gl
The article addresses the essence, features, advantages, associated challenges, and prospects of using artificial intelligence (AI) in managing robotic systems. The relevance of this topic is substantiated by the rapid development of technologies that drive the automation of processes in industries such as manufacturing, medicine, logistics, and other key sectors. The aim of the study is to analyze existing approaches to integrating AI in robotic systems, identify positive effects, systematize t
Open papers in the app to read, cite, and organize with AI.
