Abstract：
:Quantitative Structure-Activity Relationship (QSAR) models are critical in various areas of drug discovery, for example in lead optimisation and virtual screening. Recently, the need for models that are not only predictive but also interpretable has been highlighted. In this paper, a new methodology is proposed to build interpretable QSAR models by combining elements of network analysis and piecewise linear regression. The algorithm presented, modSAR, splits data using a two-step procedure. First, compounds associated with a common target are represented as a network in terms of their structural similarity, revealing modules of similar chemical properties. Second, each module is subdivided into subsets (regions), each of which is modelled by an independent linear equation. Comparative analysis of QSAR models across five data sets of protein inhibitors obtained from ChEMBL is reported and it is shown that modSAR offers similar predictive accuracy to popular algorithms, such as Random Forest and Support Vector Machine. Moreover, we show that models built by modSAR are interpretatable, capable of evaluating the applicability domain of the compounds and serve well tasks such as virtual screening and the development of new drug leads.
journal_name
J Comput Aided Mol Desjournal_title
Journal of computer-aided molecular designauthors
Cardoso-Silva J,Papageorgiou LG,Tsoka Sdoi
10.1007/s10822-019-00228-6subject
Has Abstractpub_date
2019-09-01 00:00:00pages
831-844issue
9eissn
0920-654Xissn
1573-4951pii
10.1007/s10822-019-00228-6journal_volume
33pub_type
杂志文章abstract：:Molecular modeling techniques and three-dimensional (3D) pattern analysis have been used to investigate the chemical and steric properties of compounds that inhibit transport of the plant hormone auxin. These compounds bind to a specific site on the plant plasma membrane characterized by its affinity for the herbicide...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/BF00126666
更新日期：1991-08-01 00:00:00
abstract：:The binding mode of (2S)-2-[4-[[(3S)-1-acetimidoyl-3-pyrrolidinyl]oxy]phenyl]-3-(7-ami dino-2- naphthyl)propanoic acid hydrochloride (DX-9065a, 4) to Factor Xa is examined using inhibition data for a series of analogs that have a hydrophobic group as well as basic or dibasic functionality. Comparative molecular field ...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1023/a:1007969517376
更新日期：1998-03-01 00:00:00
abstract：:We apply an atomistic model of passive membrane permeability to a series of weakly basic drugs. The computational model uses conformational sampling in combination with an all-atom force field and implicit solvent model to estimate relative passive membrane permeabilities. The model does not require the use of trainin...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-007-9141-z
更新日期：2007-12-01 00:00:00
abstract：:The complex of adenylate kinase with its transition-state inhibitor has been studied by molecular dynamics simulations in water and in vacuum environments with the GROMOS force field over a period of 300 ps. The adenylate kinase, a member of the nucleotide-binding protein family, was exemplarily chosen for the inspect...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/BF00125373
更新日期：1994-08-01 00:00:00
abstract：:Capacity ratio (log k') values, which are a measure of hydrophobicity, were calculated directly from the three-dimensional structures of 17 furans and 54 triazines using the comparative molecular field analysis approach. The H2O probe and the GRID force field, including hydrogen-bond potentials, yielded excellent corr...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/BF00125172
更新日期：1995-08-01 00:00:00
abstract：:Molecular modeling methodologies such as molecular docking, pharmacophore modeling, and 3D-QSAR, rely on conformational searches of small molecules as a starting point. All of these methodologies seek conformations of the small molecules as they bind to target proteins, i.e., their active conformations. Thus the quest...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1023/a:1016320106741
更新日期：2002-02-01 00:00:00
abstract：:The binding properties of sequence-specific nucleic acids (aptamers) to low-molecular-weight ligands, macromolecules and even cells attract substantial scientific interest. These ligand-DNA complexes found different applications for sensing, nanomedicine, and DNA nanotechnology. Structural information on the aptamer-l...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-015-9844-5
更新日期：2015-07-01 00:00:00
abstract：:Patents from medicinal chemistry represent a rich source of novel compounds and activity data that appear only infrequently in the scientific literature. Moreover, patent information provides a primary focal point for drug discovery. Accordingly, text mining and image extraction approaches have become hot topics in pa...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-017-0061-2
更新日期：2017-09-01 00:00:00
abstract：:Orientation of ten water molecules bound strongly at the contact surface of the dihydrofolate reductase-methotrexate enzyme-inhibitor complex was determined theoretically. To optimize the orientation of the water molecules, a recent method based on a simple electrostatic model was applied. The electrostatic complement...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/BF01532054
更新日期：1988-04-01 00:00:00
abstract：:A new computer program is described, which positions small molecules into clefts of protein structures (e.g. an active site of an enzyme) in such a way that hydrogen bonds can be formed with the enzyme and hydrophobic pockets are filled with hydrophobic groups. The program works in three steps. First it calculates int...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/BF00124387
更新日期：1992-02-01 00:00:00
abstract：:While it may seem intuitive that using an ensemble of multiple conformations of a receptor in structure-based virtual screening experiments would necessarily yield improved enrichment of actives relative to using just a single receptor, it turns out that at least in the p38 MAP kinase model system studied here, a very...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-008-9182-y
更新日期：2008-09-01 00:00:00
abstract：:A new and rigorous method for the fractional description of solvation and transfer free energies is presented. The method is based on the use of the Miertus-Scrocco-Tomasi self-consistent reaction field method (MST-SCRF), and allows for a rigorous partition of the total solvation free energy into surface elements. The...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1023/a:1008036526741
更新日期：1999-03-01 00:00:00
abstract：:We developed a new structure-based in-silico screening method using a negative image of a ligand-binding pocket and a multi-protein-compound interaction matrix. Based on the structure of the ligand pocket of the target protein, we designed a negative image, which consists of virtual atoms whose radii are close to thos...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-006-9047-1
更新日期：2006-04-01 00:00:00
abstract：:In the present work we have modeled the Michaelis complex of the cyclic-Adenosine Monophosphate Dependent (cAMD) Protein Kinase A (PKA) with Mg(2)ATP and the heptapeptide substrate Kemptide by classical molecular dynamics. The chosen synthetic substrate is relevant for its high efficiency and small size, and it has no...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-007-9143-x
更新日期：2007-10-01 00:00:00
abstract：:Non-canonical base pairs contribute immensely to the structural and functional variability of RNA, which calls for a detailed characterization of their spatial conformation. Intra-base pair parameters, namely propeller, buckle, open-angle, stagger, shear and stretch describe structure of base pairs indicating planarit...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-006-9083-x
更新日期：2006-10-01 00:00:00
abstract：:To generate reduced point charge models of proteins, we developed an original approach to hierarchically locate extrema in charge density distribution functions built from the Poisson equation applied to smoothed molecular electrostatic potential (MEP) functions. A charge fitting program was used to assign charge valu...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-011-9471-8
更新日期：2011-10-01 00:00:00
abstract：:All-atom molecular dynamics computer simulations were used to blindly predict the hydration free energies of a range of chloro-organic compounds as part of the SAMPL3 challenge. All compounds were parameterized within the framework of the OPLS-AA force field, using an established protocol to compute the absolute hydra...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-011-9527-9
更新日期：2012-05-01 00:00:00
abstract：:Quantitative Structure-Activity Relationship (QSAR) models are used increasingly to screen chemical databases and/or virtual chemical libraries for potentially bioactive molecules. These developments emphasize the importance of rigorous model validation to ensure that the models have acceptable predictive power. Using...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1023/a:1025386326946
更新日期：2003-02-01 00:00:00
abstract：:Poly(amidoamine) (PAMAM) dendrimers have been extensively studied as delivery vectors in biomedical applications. A limited number of molecular dynamics (MD) simulation studies have investigated the effect of surface chemistry on therapeutic molecules loading, with the aim of providing insights for biocompatibility im...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-017-0091-9
更新日期：2017-12-01 00:00:00
abstract：:During the last few years, we have developed a docking protocol involving two steps: (i) the choice of the most appropriate docking software and parameters for the system of interest using structural and functional information available in public databases (PDB, ChEMBL, PubChem Assay, BindingDB, etc.); (ii) the dockin...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-018-0161-7
更新日期：2019-01-01 00:00:00
abstract：:Leishmania donovani dipeptidylcarboxypeptidsae (LdDCP), an angiotensin converting enzyme (ACE) related metallopeptidase has been identified and characterized as a putative drug target for antileishmanial chemotherapy. The kinetic parameters for LdDCP with substrate, Hip-His-Leu were determined as, Km, 4 mM and Vmax, 1...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-009-9315-y
更新日期：2010-01-01 00:00:00
abstract：:Atomic-resolution structures of the transmembrane 7-alpha-helical domains of 26 G-protein-coupled receptors (GPCRs) (including opsins, cationic amine, melatonin, purine, chemokine, opioid, and glycoprotein hormone receptors and two related proteins, retinochrome and Duffy erythrocyte antigen) were calculated by distan...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章,评审
doi：10.1023/a:1008050821744
更新日期：1999-07-01 00:00:00
abstract：:Fast Fourier transform (FFT) based approaches have been successful in application to modeling of relatively rigid protein-protein complexes. Recently, we have been able to adapt the FFT methodology to treatment of flexible protein-peptide interactions. Here, we report our latest attempt to expand the capabilities of t...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-017-0069-7
更新日期：2018-01-01 00:00:00
abstract：:Babesia bigemina is a protozoan parasite that causes babesiosis, a disease with a world-wide distribution in mammals, principally affecting cattle and man. The unveiling of the genome of B. bigemina is a project in active progress that has already revealed a number of new targets with potential interest for the design...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-013-9682-2
更新日期：2013-09-01 00:00:00
abstract：:This paper describes a new and efficient stochastic conformational sampling method for generating a range of low-energy molecule conformations. Sampling can be tailored to a specific structural domain (e.g., peptides) by extracting torsional profiles from specific datasets and subsequently applying them to target mole...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-007-9156-5
更新日期：2008-09-01 00:00:00
abstract：:Estimation of bioavailability and toxicity at the very beginning of the drug development process is one of the big challenges in drug discovery. Most of the processes involved in ADME are driven by rather unspecific interactions between drugs and biological macromolecules. Within the past decade, drug transport pumps ...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1023/a:1023828527638
更新日期：2002-11-01 00:00:00
abstract：:Steric complementarity is a prerequisite for ligand-receptor recognition; this implies that drugs with a common receptor binding site should possess sterically similar binding surfaces. This principle is used as the basis for an automatic and unbiased method that superposes molecules. One molecule is rotated and trans...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/BF00124319
更新日期：1995-12-01 00:00:00
abstract：:Computational prediction of the effects of residue changes on peptide-protein binding affinities, followed by experimental testing of the top predicted binders, is an efficient strategy for the rational structure-based design of peptide inhibitors. In this study we apply this approach to the discovery of competitive a...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-012-9574-x
更新日期：2012-07-01 00:00:00
abstract：:As part of the fourth statistical assessment of modeling of proteins and ligands (sampl.eyesopen.com) prediction challenge, the strength of association of nine guests (1-9) binding to octa-acid host was determined by a combination of (1)H NMR and isothermal titration calorimetry. Association constants in sodium tetrab...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-013-9690-2
更新日期：2014-04-01 00:00:00
abstract：:Using the X-ray crystal structure of the human topoisomerase I (top1) - DNA cleavable complex and the Sybyl software package, we have developed a general model for the ternary cleavable complex formed with four protoberberine alkaloids differing in the substitution on the terminal phenyl rings and covering a broad ran...
journal_title：Journal of computer-aided molecular design
pub_type： 杂志文章
doi：10.1007/s10822-004-7878-1
更新日期：2004-12-01 00:00:00
