Maxim V Fedorov

Maxim V Fedorov
Skolkovo Institute of Science and Technology | Skoltech · Centre of Computational and Data-Intensive Science and Engineering

PhD, DSc

About

141
Publications
19,820
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
6,060
Citations
Citations since 2016
48 Research Items
3601 Citations
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
20162017201820192020202120220100200300400500
Introduction
Maxim V Fedorov currently works at the Skolkovo Institute of Science and Technology (aka Skoltech), Skolkovo, Russia. He is Director of Skoltech Centre of Computation and Data-Intensive Science and Engineering. Maxim does research in Parallel Computing, Data Mining and Computing in Mathematics, Natural Science, Engineering and Medicine. Their current project is '3D Convolutional neural networks for drug discovery.'
Additional affiliations
October 2007 - September 2011
Max Planck Institute for Mathematics in the Sciences
Position
  • Group Leader
October 2007 - September 2011
Max Planck Institute for Mathematics
Position
  • Group Leader
October 2005 - September 2008
University of Cambridge
Position
  • Research Associate

Publications

Publications (141)
Article
NMDA (N-methyl-d-aspartate) receptor antagonists are promising tools for the treatment of a wide variety of central nervous system impairments including major depressive disorder. We present here the activity optimization process of a biphenyl-based NMDA negative allosteric modulator (NAM) guided by free energy calculations, which led to a 100 time...
Article
Full-text available
Dissociation induced by the accumulation of internal energy via collisions of ions with neutral molecules is one of the most important fragmentation techniques in mass spectrometry (MS), and the identification of small singly charged molecules is based mainly on the consideration of the fragmentation spectrum. Many research studies have been dedica...
Article
Full-text available
The rise of deep learning in various scientific and technology areas promotes the development of AI‐based tools for information retrieval. Optical recognition of organic structures is a key part of the automated extraction of chemical information. However, this is a challenging task because there is a large variety of representation styles. In this...
Article
Full-text available
Humans prefer visual representations for the analysis of large databases. In this work, we suggest a method for the visualization of the chemical reaction space. Our technique uses the t-SNE approach that is parameterized using a deep neural network (parametric t-SNE). We demonstrated that the parametric t-SNE combined with reaction difference fing...
Article
For interpretation of electroencephalography (EEG) and magnetoencephalography (MEG) data, multiple solutions of the respective forward problems are needed. In this paper, we assess performance of the mixed-hybrid finite element method (MHFEM) applied to EEG and MEG modeling. The method provides an approximate potential and induced currents and resu...
Article
Full-text available
We developed a Transformer-based artificial neural approach to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct. The overall performance level of our model is comparable to the rule-based solutions. We proved that the accuracy and speed of computations as well as the robustness of the model allow to use it in pro...
Preprint
Full-text available
The rise of deep learning in various scientific and technology areas promotes the development of AI-based tools for information retrieval. Optical recognition of organic structures is a key part of the automated extraction of chemical information. However, this is a challenging task because there is a large variety of representation styles. In this...
Article
Full-text available
Background: Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditi...
Preprint
div>Humans prefer visual representations for the analysis of large databases. In this work, we suggest a method for the visualization of the chemical reaction space. Our technique uses the t-SNE approach that is parameterized by a deep neural network (parametric t-SNE). We demonstrated that the parametric t-SNE combined with reaction difference fin...
Preprint
Full-text available
Providing IUPAC chemical names is necessary for chemical information exchange. We developed a Transformer-based artificial neural architecture to translate between SMILES and IUPAC chemical notations: Struct2IUPAC and IUPAC2Struct . Our models demonstrated the performance that is comparable to rule-based solutions. We proved that both accuracy, spe...
Article
Derivation of structure-kinetics relationships can help rational design and development of new small-molecule drug candidates with desired residence times. Efforts are now being directed toward the development of efficient computational methods. Currently, there is a lack of solid, high-throughput binding kinetics prediction approaches on bigger da...
Article
Retention time is an important parameter for identification in untargeted LC-MS screening. Precise retention time prediction facilitates the annotation process and is well known for proteomics. However, the lack of available experimental information for a long time has limited the prediction accuracy for small molecules. Recently introduced large d...
Article
Ionic liquids (IL) are promising electrolytes for electrochemical applications due to their remarkable stability and high charge density. Molecular dynamics simulations are essential for a better understanding of the complex phenomena occurring at the electrode-IL interface. In this work, we have studied the interface between graphene and 1-ethyl-3...
Article
Full-text available
Recommender systems (RSs), which underwent rapid development and had an enormous impact on e-commerce, have the potential to become useful tools for drug discovery. In this paper, we applied RS methods for the prediction of the antiviral activity class (active/inactive) for compounds extracted from ChEMBL. Two main RS approaches were applied: colla...
Article
Ifenprodil-like NMDA receptor negative allosteric modulator based on the biphenyl scaffold has been identified using virtual screening. Docking approach demonstrated that the modulator maintains some characteristic interactions with protein similar to ifenprodil. Electrophysiological and radioligand investigations demonstrated the concentration-dep...
Article
The potential to predict Solvation Free Energies (SFEs) in any solvent using a machine learning (ML) model based on thermodynamic output, extracted exclusively from 3D-RISM simulations in water is investigated. The models on multiple solvents take into account both the solute and solvent description and offer the possibility to predict SFEs of any...
Preprint
Full-text available
Ionic liquids (IL) are promising electrolytes for electrochemical applications due to their remarkable stability and high charge density. Molecular dynamics simulations are essential for better understanding the complex phenomena occurring at the electrode-IL interface. In this work, we have studied the interface between graphene and 1-ethyl-3-meth...
Article
Full-text available
Environment pollutants, especially those from total petroleum hydrocarbons (TPH), have a highly complex chemical, biological and physical impact on soils. Here we study this influence via modelling the TPH acute phytotoxicity effects on eleven samples of soils from Sakhalin island in greenhouse conditions. The soils were contaminated with crude oil...
Article
Full-text available
In this work, we present graph-convolutional neural networks for the prediction of binding constants of protein–ligand complexes. We derived the model using multi task learning, where the target variables are the dissociation constant (Kd), inhibition constant (Ki), and half maximal inhibitory concentration (IC50). Being rigorously trained on the P...
Data
Supporting information to the article: Role of Graphene Edges in the Electron Transfer Kinetics: Insight from Theory and Molecular Modeling DOI: 10.1021/acs.jpcc.8b12531
Poster
Full-text available
Ionotropic glutamate receptors are ligand-gated ion channels responsible for fast synaptic transmission throughout the vertebrate nervous system. Their inhibition is considered to be perspective for the treatment of a wide range of neurological impairments and is currently used against epilepsy. Perampanel is the first drug approved by FDA and acti...
Article
Full-text available
The influence of different types of salts (NaCl, CaCl 2 , MgCl 2 , NaHCO 3 , and Na 2 SO 4 ) on the surface characteristics of unconditioned calcite and dolomite particles, and conditioned with stearic acid, was investigated. This study used zeta potential measurements to gain fundamental understanding of physico-chemical mechanisms involved in sur...
Article
Perampanel approved by FDA in 2012 is a first-in-class antiepileptic drug which inhibits α-amino-3-hydroxy-5-methyl-4-isoxazolepropionic acid (AMPA) receptor currents. It is markedly more active than many of its close analogs, and the reasons for this activity difference are not quite clear. Recent crystallographic studies allowed the authors to id...
Article
Full-text available
We present the novel approach for the increasing reliability of the compound identification for LC-MS and MALDI imaging lipidomics. Our approach is based on the characterization of compounds not only by the elution time, accurate mass and fragmentation spectra, but also by the number of labile hydrogens which can be measured using Hydrogen/Deuteriu...
Article
Full-text available
A parametric t-SNE approach based on deep feed-forward neural networks was applied to the chemical space visualization problem. It is able to retain more information than certain dimensionality reduction techniques used for this purpose (principal component analysis (PCA), multidimensional scaling (MDS)). The applicability of this method to some ch...
Article
Acute toxicity is one of the most challenging properties to predict purely with computational methods due to its direct relationship to biological interactions. Moreover, toxicity can be represented by different endpoints: it can be measured for different species using different types of administration, etc., and it is questionable if the knowledge...
Article
Full-text available
Despite the increasing volume of available data, the proportion of experimentally measured data remains small compared to the virtual chemical space of possible chemical structures. Therefore, there is a strong interest in simultaneously predicting different ADMET and biological properties of molecules, which are frequently strongly correlated with...
Article
Full-text available
Computational modeling is more and more often used in studies of novel ionic liquids. The inevitable side-effect is the growing number of similar computations that require automation. This article introduces NaRIBaS (Nanomaterials and Room Temperature Ionic Liquids in Bulk and Slab)—a scripting framework that combines bash scripts with computationa...
Article
In this work, we present a new method for predicting complex physical-chemical properties of organic molecules. The approach utilizes 3D convolutional neural network (ActivNet4) that uses solvent spatial distributions around solutes as input. These spatial distributions are obtained by a molecular theory called three-dimensional reference interacti...
Article
The maximum density of monolayer packing on a graphene surface is calculated by means of molecular dynamics (MD) for ions of characteristic size and symmetry: 1-butyl-3-methylimidazolium [BMIM]⁺, tetrabutylammonium [TBA]⁺, tetrafluoroborate [BF4]⁻, dicyanamide [DCA]⁻, and bis(trifluoromethane) sulfonimide [TFSI]⁻. The characteristic orientations of...
Article
Full-text available
Temperature dependence of the capacitance of the electrical double layer (EDL) in concentrated electrolytes/ionic liquids has been under debates for decades. To rationalise the capacitance vs temperature dependence, we run molecular dynamics simulations of the EDL at variable temperatures. We show that the dependence is related to the smearing of t...
Article
Full-text available
In this work, we present a new method for predicting bioaccumulation factor of organic molecules. The approach utilizes 3D convolutional neural network (ActivNet4) that uses solvent spatial distributions around solutes as input. These spatial distributions are obtained by a molecular theory called three-dimensional reference interaction site model...
Chapter
Predictive methods for physical–chemical properties are commonly used during the early stage of drug discovery, notably when identifying promising lead structures for development. This article begins with a historical overview of these methods, and background information about the role of physical–chemical properties in medicinal chemistry. Then, a...
Article
Many applications of ionic liquids involve their mixtures with neutral molecular solvents. The chemical physics of these high-concentration electrolytes, in particular at interfaces, still holds many challenges. In this contribution we begin to unravel the relationship between measurements of structural ('solvation') forces in mixtures of ionic liq...
Article
Full-text available
Solvate ionic liquids are a subclass of ionic liquids that have the potential to be used in a range of electrochemical devices. We present molecular dynamics simulations of the interfacial structure of thin films of one such lithium based solvate ionic liquid, [Li(G4)][TFSI], an equimolar solution of tetraglyme and lithium bistriflimide. This solva...
Article
A molecular dynamics study of mixtures of 1-butyl-3-methylimidazolium tetrafluoroborate ([BMIm][BF4]) with magnesium tetrafluoroborate (Mg[BF4]2) confined between two parallel graphene walls is reported. The structure of the system is analyzed by means of ionic density profiles, lateral structure of the first layer close to the graphene surface and...
Article
Full-text available
We demonstrate that using a pressure corrected three-dimensional reference interaction site model one can accurately predict salting-out (Setschenow’s) constants for a wide range of organic compounds in aqueous solutions of NaCl. The approach, based on classical molecular force fields, offers an alternative to more heavily parametrized methods.
Article
We report a method of making biopolymer-based photocatalytic composite materials. The method is based on encapsulation of TiO2 nanoparticles into a porous polymer matrix by mixing the nanoparticles with a biopolymer, iota-carrageenan (CRG), and polyvinyl alcohol (PVA) followed by freezing/thawing cycles; the resulting material makes a stable hydrog...
Article
Full-text available
We present a new approach for predicting solvation free energies in non-aqueous solvents. Utilizing the corresponding states principle, we estimate solvent Lennard-Jones parameters directly from their critical points. Combined with atomic solutes and pressure corrected three-dimensional reference interaction site model (3D-RISM/PC+), the model give...
Article
Full-text available
This work describes the behaviour of water molecules in 1-butyl-3-methylimidazolium tetrafluoroborate ionic liquid under nanoconfinement between graphene sheets. By means of molecular dynamics simulations, an adsorption of water molecules at the graphene surface is studied. A depletion of water molecules in the vicinity of the neutral and negativel...
Chapter
Accurate computational methods to predict the solubility of crystalline organic molecules in aqueous solutions are highly sought after in many fields of the biomolecular sciences and industry. This chapter discusses the different molecular theory and simulation-based approaches that have been used to calculate the intrinsic aqueous solubility of dr...
Article
Fundamental understanding of the wettability of carbonate formations can potentially be applied to the development of oil recovery strategies in a complex carbonate reservoir. In the present study, surface energies of representative carbonate samples were evaluated by direct quantitative force measurements, using scanning force microscopy (SFM) at...
Article
In this paper we present a theoretical/computational framework for accurate calculation of hydration free energies of ionized molecular species. The method is based on a molecular theory, 3D-RISM, combined with a recently developed pressure correction (PC+). The 3D-RISM/PC+ model can provide ≈ 3 kcal/mol hydration free energy accuracy for a large v...
Article
Full-text available
The modern computer simulations of potential green solvents of the future, involving the room temperature ionic liquids, heavily rely on density functional theory (DFT). In order to verify the appropriateness of the common DFT methods, we have investigated the effect of the self-interaction error (SIE) on the results of DFT calculations for 24 ioni...
Article
Full-text available
In this work we study mechanisms of solvent-mediated ion interactions with charged surfaces in ionic liquids by molecular dynamics simulations, in an attempt to reveal the main trends that determine ion-electrode interactions in ionic liquids. We compare the interfacial behaviour of Li(+) and K(+) at a charged graphene sheet in a room temperature i...
Article
Full-text available
We report a molecular dynamics study of the structure and single-particle dynamics of mixtures of a protic (ethylammonium nitrate) and an aprotic (1-butyl-3-methylimidazolium hexaflurophosphate [BMIM][PF6]) room-temperature ionic liquids doped with magnesium and calcium salts with a common anion at 298.15 K and 1 atm. The solvation of these divalen...
Article
We report a method to predict physico-chemical properties of druglike molecules using a classical statistical mechanics based solvent model combined with machine learning. The RISM-MOL-INF method introduced here provides an accurate technique to characterize solvation and desolvation processes based on solute-solvent correlation functions computed...
Article
The integral equation theory (IET) of molecular liquids has been an active area of academic research in theoretical and computational physical chemistry for over 40 years because it provides a consistent theoretical framework to describe the structural and thermodynamic properties of liquid-phase solutions. The theory can describe pure and mixed so...
Chapter
Full-text available
In these lecture notes we will briefly overview current progress in theory and simulations of (room temperature) ionic liquids (ILs) at charged interfaces (CIs). ILs are important highly concentrated electrolyte media for many applications - from energy storage to friction. When a certain IL is to be chosen for a given application, a suitable one h...
Article
Full-text available
We present a new model for computing hydration free energies by 3D reference interaction site model (3D-RISM) that uses an appropriate initial state of the system (as suggested by Sergiievskyi et al.). The new adjustment to 3D-RISM theory significantly improves hydration free energy predictions for various classes of organic molecules at both ambie...
Article
Full-text available
We have investigated the electrical double layer (EDL) structure at an interface between ionic liquid (IL) and charged surface using molecular dynamics simulations. We show that for three different models of ILs the EDL restructuring, driven by surface charging, can be rationalized by the use of two parameters-renormalized surface charge (κ) and ch...
Data
The simulated systems represent model ionic liquid (IL) ions confined between two model electrodes [1–3]. The models represented IL ions as charged Lennard-Jones spheres [1, 3] with the cation-to-anion diameter (d LJ) ratios were chosen to be 1 : 1 (large anion – LA), 1 : 0.8 (medium anion – MA) and 1 : 0.5 (small an-ion – SA) with d LJ (Cation) =...
Article
In this work we use infrared spectroscopy to investigate solubility properties of a bioactive substance in supercritical CO2 (scCO2). By using acetaminophen as a model compound, we show that the method can provide high sensitivity that makes it possible to study solubility at small concentrations, up to 10–6 mol·L–1. This method also allows one to...
Article
In this paper we present a unified view on charge-driven structural transitions in the electrical double layer in ionic liquids and summarise molecular-scale mechanisms of the ionic liquid structural response to the surface charge.
Article
Full-text available
The density, viscosity, electric conductivity, volumetric thermal expansion coefficient, melting point, and refractive index of an aqueous solution of the [Emim][Cl] ionic liquid are measured over wide ranges of temperature and concentrations at standard atmospheric pressure. Analytical dependences of the investigated properties on the concentratio...
Data
We have investigated the screening of solute ion−electrode interactions in two ionic liquids (1-butyl 3-methylimidazolium tetrafluoroborate [BMIm][BF 4 ] and 1,3-dimethylimidazolium chloride [MMIm]Cl) by constructing free energy profiles for dissolved charged probes as a function of distance from a charged surface (graphene). The free energy profil...