80:) when a chemical property is modeled as the response variable. "Different properties or behaviors of chemical molecules have been investigated in the field of QSPR. Some examples are quantitative structure–reactivity relationships (QSRRs), quantitative structure–chromatography relationships (QSCRs) and, quantitative structure–toxicity relationships (QSTRs), quantitative structure–electrochemistry relationships (QSERs), and quantitative structure–
232:
the basis of pre-defined chemical rules in case of non-congeneric sets. GQSAR also considers cross-terms fragment descriptors, which could be helpful in identification of key fragment interactions in determining variation of activity. Lead discovery using fragnomics is an emerging paradigm. In this context FB-QSAR proves to be a promising strategy for fragment library design and in fragment-to-lead identification endeavours.
414:
476:. Obtaining a good quality QSAR model depends on many factors, such as the quality of input data, the choice of descriptors and statistical methods for modeling and for validation. Any QSAR modeling should ultimately lead to statistically robust and predictive models capable of making accurate and reliable predictions of the modeled response of new compounds.
269:, rather than experimental constants and is concerned with the overall molecule rather than a single substituent. The first 3-D QSAR was named Comparative Molecular Field Analysis (CoMFA) by Cramer et al. It examined the steric fields (shape of the molecule) and the electrostatic fields which were correlated by means of
231:
Group or fragment-based QSAR is also known as GQSAR. GQSAR allows flexibility to study various molecular fragments of interest in relation to the variation in biological response. The molecular fragments could be substituents at various substitution sites in congeneric set of molecules or could be on
296:
by encoding molecules as sets of data instances, each of which represents a possible molecular conformation. A label or response is assigned to each set corresponding to the activity of the molecule, which is assumed to be determined by at least one instance in the set (i.e. some conformation of the
308:
In this approach, descriptors quantifying various electronic, geometric, or steric properties of a molecule are computed and used to develop a QSAR. This approach is different from the fragment (or group contribution) approach in that the descriptors are computed for the system as whole rather than
235:
An advanced approach on fragment or group-based QSAR based on the concept of pharmacophore-similarity is developed. This method, pharmacophore-similarity-based QSAR (PS-QSAR) uses topological pharmacophoric descriptors to develop QSAR models. This activity prediction may assist the contribution of
516:
Different aspects of validation of QSAR models that need attention include methods of selection of training set compounds, setting training set size and impact of variable selection for training set models for determining the quality of prediction. Development of novel validation parameters for
500:
The success of any QSAR model depends on accuracy of the input data, selection of appropriate descriptors and statistical tools, and most importantly validation of the developed model. Validation is the process by which the reliability and relevance of a procedure are established for a specific
87:
As an example, biological activity can be expressed quantitatively as the concentration of a substance required to give a certain biological response. Additionally, when physicochemical properties or structures are expressed by numbers, one can find a mathematical relationship, or quantitative
227:
of compound can be determined by the sum of its fragments; fragment-based methods are generally accepted as better predictors than atomic-based methods. Fragmentary values have been determined statistically, based on empirical data for known logP values. This method gives mixed results and is
2017:
Manz TA, Phomphrai K, Medvedev G, Krishnamurthy BB, Sharma S, Haq J, Novstrup KA, Thomson KT, Delgass WN, Caruthers JM, Abu-Omar MM (Apr 2007). "Structure-activity correlation in titanium single-site olefin polymerization catalysts containing mixed cyclopentadienyl/aryloxide ligation".
512:
cross-validation generally leads to an overestimation of predictive capacity. Even with external validation, it is difficult to determine whether the selection of training and test sets was manipulated to maximize the predictive capacity of the model being published.
3255:
Fabian
Pedregosa; Gaël Varoquaux; Alexandre Gramfort; Vincent Michel; Bertrand Thirion; Olivier Grisel; Mathieu Blondel; Peter Prettenhofer; Ron Weiss; Vincent Dubourg; Jake Vanderplas; Alexandre Passos; David Cournapeau; Matthieu Perrot; Édouard Duchesnay (2011).
368:
problem (i.e., which structural features should be interpreted to determine the structure-activity relationship). Feature selection can be accomplished by visual inspection (qualitative selection by a human); by data mining; or by molecule mining.
256:
calculations requiring three-dimensional structures of a given set of small molecules with known activities (training set). The training set needs to be superimposed (aligned) by either experimental data (e.g. based on ligand-protein
309:
from the properties of individual fragments. This approach is different from the 3D-QSAR approach in that the descriptors are computed from scalar quantities (e.g., energies, geometric parameters) rather than from 3D fields.
2053:
Manz TA, Caruthers JM, Sharma S, Phomphrai K, Thomson KT, Delgass WN, Abu-Omar MM (2012). "Structure–Activity
Correlation for Relative Chain Initiation to Propagation Rates in Single-Site Olefin Polymerization Catalysis".
2851:
Chirico N, Gramatica P (Sep 2011). "Real external predictivity of QSAR models: how to evaluate it? Comparison of different validation criteria and proposal of using the concordance correlation coefficient".
456:(including desirable therapeutic effect and undesirable side effects) or physico-chemical properties in QSPR models of chemicals (drugs/toxicants/environmental pollutants) with descriptors representative of
41:
or classification models used in the chemical and biological sciences and engineering. Like other regression models, QSAR regression models relate a set of "predictor" variables (X) to the potency of the
484:
1570:
Chirico N, Gramatica P (Aug 2012). "Real external predictivity of QSAR models. Part 2. New intercomparable thresholds for different validation criteria and the need for scatter plot inspection".
1990:
Caruthers JM, Lauterbach JA, Thomson KT, Venkatasubramanian V, Snively CM, Bhan A, Katare S, Oskarsdottir G (2003). "Catalyst design: knowledge extraction from high-throughput experimentation".
3056:
Fioravanzo, E.; Bassan, A.; Pavan, M.; Mostrag-Szlichtyng, A.; Worth, A. P. (2012-04-01). "Role of in silico genotoxicity tools in the regulatory assessment of pharmaceutical impurities".
683:
690:
toxicological assessment of genotoxic impurities. Commonly used QSAR assessment software such as DEREK or CASE Ultra (MultiCASE) is used to genotoxicity of impurity according to ICH M7.
336:
Similarly to string-based methods, the molecular graph can directly be used as input for QSAR models, but usually yield inferior performance compared to descriptor-based QSAR models.
88:
structure-activity relationship, between the two. The mathematical expression, if carefully validated, can then be used to predict the modeled response of other chemical structures.
1812:
Manoharan P, Vijayan RS, Ghoshal N (Oct 2010). "Rationalizing fragment based drug discovery for BACE1: insights from FB-QSAR, FB-QSSR, multi objective (MO-QSPR) and MIF studies".
487:(actually, while extracting data, cross validation is a measure of model robustness, the more a model is robust (higher q2) the less data extraction perturb the original model);
1867:
402:
approaches, apply a similarity matrix based prediction or an automatic fragmentation scheme into molecular substructures. Furthermore, there exist also approaches using
705:, and so is less reliable (on average) than prediction within the applicability domain. The assessment of the reliability of QSAR predictions remains a research topic.
1447:, Gramatica P, Gombar VJ (2003). "The Importance of Being Earnest: Validation is the Absolute Essential for Successful Application and Interpretation of QSPR Models".
300:
On June 18, 2011 the
Comparative Molecular Field Analysis (CoMFA) patent has dropped any restriction on the use of GRID and partial least-squares (PLS) technologies.
364:
Computer SAR models typically calculate a relatively large number of features. Because those lack structural interpretation ability, the preprocessing steps face a
219:"—a measurement of differential solubility and itself a component of QSAR predictions—can be predicted either by atomic methods (known as "XLogP" or "ALogP") or by
2123:
Mayr, Andreas; Klambauer, Günter; Unterthiner, Thomas; Steijaert, Marvin; Wegner, Jörg K.; Ceulemans, Hugo; Clevert, Djork-Arné; Hochreiter, Sepp (20 June 2018).
561:. There is a clear trend in the increase of boiling point with an increase in the number carbons, and this serves as a means for predicting the boiling points of
686:
regulation, where "REACH" abbreviates "Registration, Evaluation, Authorisation and
Restriction of Chemicals". Regulatory application of QSAR methods includes
3310:"Three-dimensional quantitative structure-activity relationship and docking studies in a series of anthocyanin derivatives as cytochrome P450 3A4 inhibitors"
1372:
Nantasenamat C, Isarankura-Na-Ayudhya C, Prachayasittikul V (Jul 2010). "Advances in computational methods to predict the biological activity of compounds".
3389:
3107:
2274:
Jiang, Dejun; Wu, Zhenxing; Hsieh, Chang-Yu; Chen, Guangyong; Liao, Ben; Wang, Zhe; Shen, Chao; Cao, Dongsheng; Wu, Jian; Hou, Tingjun (17 February 2021).
2765:
Put R, Vander Heyden Y (Oct 2007). "Review on modelling aspects in reversed-phase liquid chromatographic quantitative structure-retention relationships".
325:
1345:
Nantasenamat C, Isarankura-Na-Ayudhya C, Naenna T, Prachayasittikul V (2009). "A practical overview of quantitative structure-activity relationship".
2276:"Could graph neural networks learn better molecular representation for drug discovery? A comparison study of descriptor-based and graph-based models"
1174:
3106:
ICH M7 Assessment and control of DNA reactive (mutagenic) impurities in pharmaceuticals to limit potential carcinogenic risk - Scientific guideline
490:
external validation by splitting the available data set into training set for model development and prediction set for model predictivity check;
1302:
Ghasemi, Pérez-Sánchez; Mehri, Pérez-Garrido (2018). "Neural network and deep-learning algorithms used in QSAR studies: merits and drawbacks".
2172:
Merkwirth, Christian; Lengauer, Thomas (1 September 2005). "Automatic
Generation of Complementary Descriptors with Molecular Graph Networks".
3486:
111:
403:
889:
654:
method to reduce the risk for a SAR paradox, especially taking into account that only a finite amount of data is available (see also
496:
data randomization or Y-scrambling for verifying the absence of chance correlation between the response and the modeling descriptors.
1183:
2738:
Roy PP, Leonard JT, Roy K (2008). "Exploring the impact of size of training sets for the development of predictive QSAR models".
1118:
3298:
3040:
3015:
2896:
2601:
2408:
2383:
1947:
1922:
1703:
1286:
1257:
1222:
631:
While many quantitative structure activity relationship analyses involve the interactions of a family of molecules with an
2102:
Bjerrum, Esben Jannik (17 May 2017). "SMILES Enumeration as Data
Augmentation for Neural Network Modeling of Molecules".
1963:
Dietterich TG, Lathrop RH, Lozano-Pérez T (1997). "Solving the multiple instance problem with axis-parallel rectangles".
655:
153:
236:
certain pharmacophore features encoded by respective fragments toward activity improvement and/or detrimental effects.
46:(Y), while classification QSAR models relate the predictor variables to a categorical value of the response variable.
3479:
2933:
2617:
Roy K (Dec 2007). "On some aspects of validation of predictive quantitative structure-activity relationship models".
3643:
3449:
3155:"AZOrange - High performance open source machine learning for QSAR modeling in a graphical programming environment"
2660:
Sahigara, Faizan; Mansouri, Kamel; Ballabio, Davide; Mauri, Andrea; Consonni, Viviana; Todeschini, Roberto (2012).
1029:
1013:
604:
often involves the use of QSAR to identify chemical structures that could have good inhibitory effects on specific
270:
2711:
Leonard JT, Roy K (2006). "On selection of training and test sets for the development of predictive QSAR models".
817:
152:
is that similar molecules have similar activities. This principle is also called
Structure–Activity Relationship (
3407:
1164:
1128:
643:
of proteins. Protein-protein interactions can be quantitatively analyzed for structural variations resulted from
553:
between structure and observed properties. A simple example is the relationship between the number of carbons in
437:
436:
is seen as a "black box", which fails to guide medicinal chemists. Recently there is a relatively new concept of
427:
195:: the generation of hypotheses that fit training data very closely but perform poorly when applied to new data.
1516:"QSAR DataBank repository: open and linked qualitative and quantitative structure–activity relationship models"
1418:
Yousefinejad S, Hemmateenejad B (2015). "Chemometrics tools in QSAR/QSPR studies: A historical perspective".
1112:
1064:
1033:
1017:
2081:
Jastrzębski, Stanisław; Leśniak, Damian; Czarnecki, Wojciech Marian (8 March 2018). "Learning to SMILE(S)".
1239:
3628:
3472:
1025:
959:
708:
The QSAR equations can be used to predict biological activities of newer molecules before their synthesis.
3283:
3206:"Alvascience: A New Software Suite for the QSAR Workflow Applied to the Blood–Brain Barrier Permeability"
2461:"Prediction-driven matched molecular pairs to interpret QSARs and aid the molecular optimization process"
919:
3562:
3425:
625:
577:
293:
2592:
Wold S, Eriksson L (1995). "Statistical validation of QSAR results". In
Waterbeemd, Han van de (ed.).
1138:
701:. Prediction of properties of novel chemicals that are located outside the applicability domain uses
644:
385:
220:
3638:
3118:
Lavecchia A (Mar 2015). "Machine-learning approaches in drug discovery: methods and applications".
1768:
Wildman SA, Crippen GM (1999). "Prediction of physicochemical parameters by atomic contributions".
659:
281:
118:) and observational variability, that is, the variability in observations even on a correct model.
1868:"Pharmacophore-similarity-based QSAR (PS-QSAR) for group-specific biological activity predictions"
3633:
1204:
1123:
636:
538:
440:
or prediction driven MMPA which is coupled with QSAR model in order to identify activity cliffs.
266:
253:
2424:
Dossetter AG, Griffen EJ, Leach AG (2013). "Matched molecular pair analysis in drug discovery".
202:
refers to the fact that it is not the case that all similar molecules have similar activities .
3547:
2207:
Kearnes, Steven; McCloskey, Kevin; Berndl, Marc; Pande, Vijay; Riley, Patrick (1 August 2016).
1037:
1021:
1009:
501:
purpose; for QSAR models validation must be mainly for robustness, prediction performances and
399:
377:
313:
289:
3254:
3567:
1143:
613:
345:
224:
216:
172:, target activity, and so on, might depend on another difference. Examples were given in the
1721:"On the hydrophobicity of peptides: Comparing empirical predictions of peptide log P values"
1274:
2962:
2550:
2230:
1821:
1133:
893:
698:
502:
115:
66:
50:
17:
8:
3582:
3572:
3496:
2125:"Large-scale comparison of machine learning methods for drug target prediction on ChEMBL"
593:
453:
389:
353:
62:
54:
38:
2966:
2951:"Structural modeling extends QSAR analysis of antibody-lysozyme interactions to 3D-QSAR"
2554:
2234:
1825:
3648:
3336:
3309:
3232:
3205:
3181:
3154:
3089:
2983:
2950:
2925:
2828:
2801:
2688:
2661:
2642:
2574:
2487:
2460:
2376:
Algorithms on strings, trees, and sequences: computer science and computational biology
2351:
2326:
2302:
2275:
2251:
2220:
2208:
2149:
2124:
2103:
2082:
1895:
1845:
1745:
1720:
1641:
1542:
1515:
1397:
1344:
1327:
1238:
Mauri, Andrea; Consonni, Viviana; Todeschini, Roberto (2017). "Molecular
Descriptors".
1169:
461:
457:
349:
277:
92:
58:
49:
In QSAR modeling, the predictors consist of physico-chemical properties or theoretical
2974:
2662:"Comparison of Different Approaches to Define the Applicability Domain of QSAR Models"
2003:
1976:
1659:
Patani GA, LaVoie EJ (Dec 1996). "Bioisosterism: A Rational
Approach in Drug Design".
3557:
3460:
Multiscale Conceptual Model Figures for QSARs in Biological and Environmental Science
3341:
3294:
3237:
3186:
3135:
3081:
3073:
3036:
3011:
2988:
2929:
2892:
2869:
2833:
2782:
2693:
2634:
2597:
2566:
2492:
2441:
2404:
2379:
2356:
2307:
2256:
2189:
2154:
2035:
1943:
1918:
1887:
1837:
1750:
1699:
1676:
1633:
1625:
1605:
1587:
1547:
1444:
1389:
1319:
1282:
1253:
1218:
640:
605:
597:
546:
542:
449:
365:
165:
161:
43:
2646:
2578:
1899:
1645:
1401:
1331:
697:
is generated by a particular training set of chemicals is called the training set's
3592:
3587:
3552:
3537:
3397:
3331:
3321:
3227:
3217:
3176:
3166:
3127:
3093:
3065:
2978:
2970:
2921:
2912:
Fraczkiewicz, R (2013). "In Silico Prediction of Ionization". In Reedijk, J (ed.).
2861:
2823:
2813:
2774:
2751:
2747:
2720:
2683:
2673:
2626:
2558:
2523:
2482:
2472:
2433:
2346:
2338:
2297:
2287:
2246:
2238:
2181:
2144:
2136:
2063:
2027:
1999:
1972:
1879:
1849:
1829:
1777:
1740:
1732:
1668:
1617:
1608:(2010). "Best Practices for QSAR Model Development, Validation, and Exploitation".
1579:
1537:
1527:
1494:
1486:
1477:
Gramatica P (2007). "Principles of QSAR models validation: internal and external".
1456:
1427:
1423:
1381:
1354:
1311:
1245:
1210:
1148:
651:
569:
473:
433:
285:
180:
81:
3512:
3453:
3131:
3069:
2437:
1883:
1385:
1371:
1315:
1249:
1179:
1107:
675:
465:
395:
262:
258:
3464:
324:
It has been shown that activity prediction is even possible based purely on the
312:
An example of this approach is the QSARs developed for olefin polymerization by
3577:
3542:
3257:
2630:
2292:
679:
601:
562:
469:
2818:
2778:
2678:
2562:
2477:
2325:
van Tilborg, Derek; Alenicheva, Alisa; Grisoni, Francesca (12 December 2022).
2242:
1833:
1532:
1074:
57:
of the chemicals. QSAR models first summarize a supposed relationship between
3622:
3602:
3527:
3517:
3077:
2527:
2342:
2327:"Exposing the Limitations of Molecular Machine Learning with Activity Cliffs"
1629:
1153:
760:
702:
573:
558:
531:
381:
173:
1989:
344:
In the literature it can be often found that chemists have a preference for
3597:
3402:
3345:
3241:
3190:
3171:
3139:
3085:
2992:
2918:
Reference Module in Chemistry, Molecular Sciences and Chemical Engineering
2873:
2837:
2786:
2724:
2697:
2638:
2570:
2496:
2445:
2360:
2311:
2260:
2193:
2158:
2039:
1891:
1841:
1754:
1736:
1680:
1637:
1621:
1591:
1551:
1490:
1460:
1393:
1323:
1060:
621:
407:
3222:
2914:
Reference Module in Chemistry, Molecular Sciences and Chemical Engineering
1214:
639:
binding site, QSAR can also be used to study the interactions between the
493:
blind external validation by application of model on new external data and
3532:
2459:
Sushko Y, Novotarskyi S, Körner R, Vogt J, Abdelaziz A, Tetko IV (2014).
1499:
1044:
960:"MOA Massive Online Analysis | Real Time Analytics for Data Streams"
818:"Weka 3 - Data Mining with Open Source Machine Learning Software in Java"
694:
550:
373:
192:
3446:
3326:
1358:
866:
130:
Selection of data set and extraction of structural/empirical descriptors
3522:
3419:
A regression program that has dual databases of over 21,000 QSAR models
3055:
2140:
821:
479:
For validation of QSAR models, usually various strategies are adopted:
188:
184:
169:
149:
2865:
2185:
2067:
2031:
1781:
1672:
1583:
1209:. Methods and Principles in Medicinal Chemistry. Vol. 41. Wiley.
3006:
Timmerman H, Todeschini R, Consonni V, Mannhold R, Kubinyi H (2002).
1413:
1411:
284:). The following learning method can be any of the already mentioned
2511:
223:(known as "CLogP" and other variations). It has been shown that the
3459:
3390:"Nature Protocols: Development of QSAR models using C-QSAR program"
3005:
2225:
2108:
2087:
1718:
1070:
Logistic Regression, Naive Bayes, kNN, RF, SVM, GP, ANN, and others
663:
612:(non-specific activity). Of special interest is the prediction of
609:
160:
difference on a molecular level, since each kind of activity, e.g.
2802:"On two novel parameters for validation of predictive QSAR models"
2016:
1866:
Prasanth Kumar S, Jasrai YT, Pandya HA, Rawal RM (November 2013).
1408:
2122:
1158:
963:
890:"TANAGRA - A free DATA MINING software for teaching and research"
554:
3308:
Shityakov S, Puskás I, Roewer N, Förster C, Broscheit J (2014).
923:
799:"RapidMiner | #1 Open Source Predictive Analytics Platform"
413:
228:
generally not trusted to have accuracy of more than ±0.1 units.
106:(physiochemical properties and/or structural properties) + error
1865:
632:
508:
Some validation methodologies can be problematic. For example,
468:, toxicity prediction, and regulatory decisions in addition to
3293:. Vol. 1 (6th ed.). New York: Wiley. pp. 1–48.
2510:
Tong W, Hong H, Xie Q, Shi L, Fang H, Perkins R (April 2005).
1719:
Thompson SJ, Hattotuwagama CK, Holliday JD, Flower DR (2006).
941:
779:
711:
Examples of machine learning tools for QSAR modeling include:
276:
The created data space is then usually reduced by a following
2659:
1962:
589:
530:
One of the first historical QSAR applications was to predict
3307:
3152:
2541:
Dearden JC (2003). "In silico prediction of drug toxicity".
2324:
2052:
741:
588:
The biological activity of molecules is usually measured in
464:. QSARs are being applied in many disciplines, for example:
3507:
3429:
2948:
2458:
2206:
2080:
1102:
443:
3374:
3284:"History of Quantitative Structure-Activity Relationships"
2209:"Molecular graph convolutions: moving beyond fingerprints"
452:
derived from application of statistical tools correlating
3314:
Advances and Applications in Bioinformatics and Chemistry
1565:
1563:
1561:
1417:
1244:. Springer International Publishing. pp. 2065–2093.
847:
678:. QSARS are suggested by regulatory authorities; in the
3360:
2512:"Assessing QSAR Limitations – A Regulatory Perspective"
1811:
1237:
1045:"alvaModel: a software tool to create QSAR/QSPR models"
982:
537:
It is well known for instance that within a particular
156:). The underlying problem is therefore how to define a
2799:
1558:
1443:
1275:"Chapter 1.2: What is QSAR? Definitions and Formulism"
798:
210:
3153:
Stålring JC, Carlsson LA, Almeida P, Boyer S (2011).
2920:. Vol. 5. Amsterdam, the Netherlands: Elsevier.
2423:
978:
Logistic Regression, Naive Bayes, RF, ANN, and others
658:). In general, all QSAR problems can be divided into
620:, which is an important measure used in identifying "
179:
In general, one is more interested in finding strong
2949:
Freyhult EK, Andersson K, Gustafsson MG (Apr 2003).
2889:
Chemical graph theory: introduction and fundamentals
1279:
A primer on QSAR/QSPR modeling: Fundamental Concepts
191:
number of chemicals, so care must be taken to avoid
53:
of chemicals; the QSAR response-variable could be a
2046:
867:"AZCompTox/AZOrange: AstraZeneca add-ons to Orange"
592:to establish the level of inhibition of particular
1937:
1202:
517:judging quality of QSAR models is also important.
421:
121:
3494:
3024:
2999:
2880:
2585:
2392:
2367:
2171:
1931:
1906:
1513:
761:"LIBSVM -- A Library for Support Vector Machines"
65:in a data-set of chemicals. Second, QSAR models
3620:
3456:, Drug Theoretics and Cheminformatics Laboratory
2891:. Tunbridge Wells, Kent, England: Abacus Press.
2850:
2764:
2273:
1915:Molecular modelling: principles and applications
1872:Journal of Biomolecular Structure & Dynamics
1797:
1569:
1472:
1470:
1365:
1338:
265:software. It uses computed potentials, e.g. the
3291:Burger's medicinal Chemistry and Drug Discovery
2740:Chemometrics and Intelligent Laboratory Systems
1420:Chemometrics and Intelligent Laboratory Systems
1281:. New York: Springer-Verlag Inc. pp. 2–6.
1203:Todeschini, Roberto; Consonni, Viviana (2009).
3441:A comprehensive web resource for QSAR modelers
2886:
2509:
2417:
1793:
1791:
1767:
1439:
1437:
432:Typically QSAR models derived from non linear
3480:
3197:
3030:
2800:Pratim Roy P, Paul S, Mitra I, Roy K (2009).
2737:
2653:
2378:. Cambridge, UK: Cambridge University Press.
1861:
1859:
1467:
74:quantitative structure–property relationships
3608:Quantitative structure–activity relationship
3388:Verma, Rajeshwar P.; Hansch, Corwin (2007).
3203:
3146:
3111:
2942:
2911:
2854:Journal of Chemical Information and Modeling
2844:
2758:
2591:
2534:
2331:Journal of Chemical Information and Modeling
2174:Journal of Chemical Information and Modeling
2010:
1712:
1658:
1652:
1572:Journal of Chemical Information and Modeling
1301:
1184:List of predicted structure based properties
742:"R: The R Project for Statistical Computing"
568:A still very interesting application is the
303:
148:The basic assumption for all molecule-based
31:Quantitative structure–activity relationship
3387:
3210:International Journal of Molecular Sciences
2452:
1788:
1598:
1434:
3487:
3473:
3258:"scikit-learn: Machine Learning in Python"
2710:
2543:Journal of Computer-Aided Molecular Design
2213:Journal of Computer-Aided Molecular Design
1856:
1814:Journal of Computer-Aided Molecular Design
1514:Ruusmann, V.; Sild, S.; Maran, U. (2015).
1206:Molecular Descriptors for Chemoinformatics
143:
126:The principal steps of QSAR/QSPR include:
3401:
3335:
3325:
3231:
3221:
3180:
3170:
3117:
2982:
2827:
2817:
2687:
2677:
2503:
2486:
2476:
2350:
2301:
2291:
2250:
2224:
2148:
2107:
2086:
1744:
1541:
1531:
1498:
1476:
1272:
1175:Software for molecular mechanics modeling
3281:
2905:
2793:
2403:. Washington, DC: Taylor & Francis.
2373:
2020:Journal of the American Chemical Society
1917:. Englewood Cliffs, N.J: Prentice Hall.
444:Evaluation of the quality of QSAR models
412:
3248:
3204:Mauri, Andrea; Bertola, Matteo (2022).
2610:
2594:Chemometric methods in molecular design
2540:
2101:
1940:Kernel methods in computational biology
1604:
794:SVM, RF, Naïve Bayes, DT, ANN, and k-NN
359:
14:
3621:
3361:"The Cheminformatics and QSAR Society"
3058:SAR and QSAR in Environmental Research
1938:Vert JP, Schölkopf B, Tsuda K (2004).
3468:
3035:. Chichester: John Wiley & Sons.
2398:
1912:
1693:
176:reviews by Patanie/LaVoie and Brown.
3262:Journal of Machine Learning Research
693:The chemical descriptor space whose
348:(PLS) methods, since it applies the
3031:Duda RO, Hart PW, Stork DG (2001).
2616:
2596:. Weinheim: VCH. pp. 309–318.
1696:Bioisosteres in Medicinal Chemistry
1241:Handbook of Computational Chemistry
1024:and Consensus) and Classification (
211:Fragment based (group contribution)
24:
3275:
2926:10.1016/B978-0-12-409547-2.02610-X
2516:Current Computer-Aided Drug Design
1119:Conformation–activity relationship
848:"KNIME | Open for Innovation"
448:QSAR modeling produces predictive
25:
3660:
3353:
3008:Handbook of Molecular Descriptors
1798:Ajmani S, Jadhav K, Kulkarni SA,
674:(Q)SAR models have been used for
69:the activities of new chemicals.
2713:QSAR & Combinatorial Science
2619:Expert Opinion on Drug Discovery
1374:Expert Opinion on Drug Discovery
1165:QSAR & Combinatorial Science
737:RF, SVM, Naïve Bayesian, and ANN
271:partial least squares regression
3100:
3049:
2731:
2704:
2318:
2267:
2200:
2165:
2116:
2095:
2074:
1983:
1956:
1805:
1761:
1687:
1507:
1129:Matched molecular pair analysis
669:
438:matched molecular pair analysis
428:Matched molecular pair analysis
422:Matched molecular pair analysis
319:
292:. An alternative approach uses
122:Essential steps in QSAR studies
2887:Rouvray DH, Bonchev D (1991).
2752:10.1016/j.chemolab.2007.07.004
1942:. Cambridge, Mass: MIT Press.
1428:10.1016/j.chemolab.2015.06.016
1295:
1266:
1231:
1196:
520:
398:approaches, a special case of
331:
13:
1:
2975:10.1016/S0006-3495(03)75032-2
2004:10.1016/S0021-9517(02)00036-2
1977:10.1016/S0004-3702(96)00034-3
1273:Roy K, Kar S, Das RN (2015).
1190:
1113:Computer-assisted drug design
682:, QSARs are suggested by the
583:
392:a predictive learning model.
252:refers to the application of
3132:10.1016/j.drudis.2014.10.012
3070:10.1080/1062936X.2012.657236
2438:10.1016/j.drudis.2013.03.003
1884:10.1080/07391102.2013.849618
1386:10.1517/17460441.2010.492827
1316:10.1016/j.drudis.2018.06.016
1250:10.1007/978-3-319-27282-5_51
920:"ELKI Data Mining Framework"
885:SVM, RF, Naïve Bayes, and DT
7:
1095:
775:RF, SVM, and Naïve Bayesian
525:
376:based prediction uses e.g.
339:
10:
3665:
3159:Journal of Cheminformatics
2631:10.1517/17460441.2.12.1567
2465:Journal of Cheminformatics
2293:10.1186/s13321-020-00479-8
2280:Journal of Cheminformatics
1520:Journal of Cheminformatics
425:
386:artificial neural networks
294:multiple-instance learning
239:
3503:
2819:10.3390/molecules14051660
2779:10.1016/j.aca.2007.09.014
2679:10.3390/molecules17054791
2478:10.1186/s13321-014-0048-0
2243:10.1007/s10822-016-9938-8
1834:10.1007/s10822-010-9378-9
1800:Group-Based QSAR (G-QSAR)
1770:J. Chem. Inf. Comput. Sci
1533:10.1186/s13321-015-0082-6
1139:Molecular design software
645:site-directed mutagenesis
304:Chemical descriptor based
221:chemical fragment methods
91:A QSAR has the form of a
27:Predictive chemical model
2528:10.2174/1573409053585663
2343:10.1021/acs.jcim.2c01073
1422:. 149, Part B: 177–204.
843:DT, Naïve Bayes, and SVM
813:RF, SVM, and Naïve Bayes
549:, that there are strong
282:dimensionality reduction
205:
84:relationships (QSBRs)."
3644:Computational chemistry
3563:Lipinski's rule of five
3289:. In Abraham DJ (ed.).
3010:. Weinheim: Wiley-VCH.
2563:10.1023/A:1025361621494
1965:Artificial Intelligence
1698:. Weinheim: Wiley-VCH.
1124:Differential solubility
626:Lipinski's Rule of Five
483:internal validation or
404:maximum common subgraph
378:support vector machines
314:half sandwich compounds
290:support vector machines
267:Lennard-Jones potential
144:SAR and the SAR paradox
3447:Chemoinformatics Tools
3403:10.1038/nprot.2007.125
3172:10.1186/1758-2946-3-28
3033:Pattern classification
2767:Analytica Chimica Acta
2725:10.1002/qsar.200510161
1737:10.6026/97320630001237
1622:10.1002/minf.201000061
1491:10.1002/qsar.200610151
1461:10.1002/qsar.200390007
418:
400:structured data mining
72:Related terms include
3568:Lipophilic efficiency
3223:10.3390/ijms232112882
2401:Predictive toxicology
1610:Molecular Informatics
1215:10.1002/9783527628766
1144:Partition coefficient
614:partition coefficient
416:
346:partial least squares
217:partition coefficient
139:Validation evaluation
51:molecular descriptors
3375:"The 3D QSAR Server"
3282:Selassie CD (2003).
3120:Drug Discovery Today
2426:Drug Discovery Today
1304:Drug Discovery Today
1134:Molecular descriptor
862:RT, SVM, ANN, and RF
780:"Orange Data Mining"
699:applicability domain
505:(AD) of the models.
503:applicability domain
360:Data mining approach
3629:Medicinal chemistry
3583:New chemical entity
3573:Mechanism of action
3497:medicinal chemistry
3327:10.2147/AABC.S56478
2967:2003BpJ....84.2264F
2955:Biophysical Journal
2555:2003JCAMD..17..119D
2374:Gusfield D (1997).
2235:2016JCAMD..30..595K
1826:2010JCAMD..24..843M
1359:10.17877/DE290R-690
594:signal transduction
458:molecular structure
454:biological activity
110:The error includes
63:biological activity
59:chemical structures
55:biological activity
3452:2017-07-04 at the
2141:10.1039/c8sc00148k
1998:(1–2): 3776–3777.
1606:Tropsha, Alexander
1170:Scientific journal
650:It is part of the
641:structural domains
598:metabolic pathways
543:chemical compounds
419:
350:feature extraction
278:feature extraction
215:Analogously, the "
187:usually rely on a
136:Model construction
133:Variable selection
93:mathematical model
3616:
3615:
3558:Ligand efficiency
3394:Protocol Exchange
3300:978-0-471-27401-8
3042:978-0-471-05669-0
3017:978-3-527-29913-3
2898:978-0-85626-454-2
2866:10.1021/ci200211n
2603:978-3-527-30044-0
2432:(15–16): 724–31.
2410:978-0-8247-2397-2
2385:978-0-521-58519-4
2337:(23): 5938–5951.
2186:10.1021/ci049613b
2135:(24): 5441–5451.
2068:10.1021/om200884x
2032:10.1021/ja0640849
1949:978-0-262-19509-6
1924:978-0-582-38210-7
1913:Leach AR (2001).
1782:10.1021/ci990307l
1705:978-3-527-33015-7
1673:10.1021/cr950066q
1584:10.1021/ci300084j
1310:(10): 1784–1790.
1288:978-3-319-17281-1
1259:978-3-319-27282-5
1224:978-3-527-31852-0
1093:
1092:
942:"MALLET homepage"
547:organic chemistry
474:lead optimization
366:feature selection
166:biotransformation
44:response variable
16:(Redirected from
3656:
3593:Pharmacokinetics
3588:Pharmacodynamics
3553:Enzyme inhibitor
3538:Drug development
3489:
3482:
3475:
3466:
3465:
3443:
3438:
3437:
3428:. Archived from
3421:
3416:
3415:
3406:. Archived from
3405:
3384:
3382:
3381:
3370:
3368:
3367:
3349:
3339:
3329:
3304:
3288:
3270:
3269:
3252:
3246:
3245:
3235:
3225:
3216:(12882): 12882.
3201:
3195:
3194:
3184:
3174:
3150:
3144:
3143:
3115:
3109:
3104:
3098:
3097:
3064:(3–4): 257–277.
3053:
3047:
3046:
3028:
3022:
3021:
3003:
2997:
2996:
2986:
2946:
2940:
2939:
2909:
2903:
2902:
2884:
2878:
2877:
2848:
2842:
2841:
2831:
2821:
2797:
2791:
2790:
2762:
2756:
2755:
2735:
2729:
2728:
2708:
2702:
2701:
2691:
2681:
2672:(5): 4791–4810.
2657:
2651:
2650:
2614:
2608:
2607:
2589:
2583:
2582:
2538:
2532:
2531:
2507:
2501:
2500:
2490:
2480:
2456:
2450:
2449:
2421:
2415:
2414:
2399:Helma C (2005).
2396:
2390:
2389:
2371:
2365:
2364:
2354:
2322:
2316:
2315:
2305:
2295:
2271:
2265:
2264:
2254:
2228:
2204:
2198:
2197:
2180:(5): 1159–1168.
2169:
2163:
2162:
2152:
2129:Chemical Science
2120:
2114:
2113:
2111:
2099:
2093:
2092:
2090:
2078:
2072:
2071:
2050:
2044:
2043:
2014:
2008:
2007:
1987:
1981:
1980:
1960:
1954:
1953:
1935:
1929:
1928:
1910:
1904:
1903:
1863:
1854:
1853:
1809:
1803:
1802:
1795:
1786:
1785:
1765:
1759:
1758:
1748:
1716:
1710:
1709:
1694:Brown N (2012).
1691:
1685:
1684:
1667:(8): 3147–3176.
1661:Chemical Reviews
1656:
1650:
1649:
1616:(6–7): 476–488.
1602:
1596:
1595:
1567:
1556:
1555:
1545:
1535:
1511:
1505:
1504:
1502:
1474:
1465:
1464:
1441:
1432:
1431:
1415:
1406:
1405:
1369:
1363:
1362:
1342:
1336:
1335:
1299:
1293:
1292:
1270:
1264:
1263:
1235:
1229:
1228:
1200:
1149:Pharmacokinetics
1089:
1087:
1085:
1079:scikit-learn.org
1052:
997:
995:
993:
967:
962:. Archived from
945:
927:
922:. Archived from
904:
902:
901:
892:. Archived from
874:
851:
832:
830:
829:
820:. Archived from
802:
783:
764:
745:
714:
713:
652:machine learning
570:Hammett equation
545:, especially of
485:cross-validation
434:machine learning
286:machine learning
105:
82:biodegradability
21:
3664:
3663:
3659:
3658:
3657:
3655:
3654:
3653:
3639:Cheminformatics
3619:
3618:
3617:
3612:
3513:Bioavailability
3499:
3493:
3454:Wayback Machine
3435:
3433:
3424:
3413:
3411:
3379:
3377:
3373:
3365:
3363:
3359:
3356:
3301:
3286:
3278:
3276:Further reading
3273:
3253:
3249:
3202:
3198:
3151:
3147:
3116:
3112:
3105:
3101:
3054:
3050:
3043:
3029:
3025:
3018:
3004:
3000:
2947:
2943:
2936:
2910:
2906:
2899:
2885:
2881:
2849:
2845:
2812:(5): 1660–701.
2798:
2794:
2763:
2759:
2736:
2732:
2709:
2705:
2658:
2654:
2625:(12): 1567–77.
2615:
2611:
2604:
2590:
2586:
2549:(2–4): 119–27.
2539:
2535:
2508:
2504:
2457:
2453:
2422:
2418:
2411:
2397:
2393:
2386:
2372:
2368:
2323:
2319:
2272:
2268:
2205:
2201:
2170:
2166:
2121:
2117:
2100:
2096:
2079:
2075:
2056:Organometallics
2051:
2047:
2015:
2011:
1988:
1984:
1961:
1957:
1950:
1936:
1932:
1925:
1911:
1907:
1864:
1857:
1810:
1806:
1796:
1789:
1766:
1762:
1717:
1713:
1706:
1692:
1688:
1657:
1653:
1603:
1599:
1568:
1559:
1512:
1508:
1475:
1468:
1442:
1435:
1416:
1409:
1370:
1366:
1343:
1339:
1300:
1296:
1289:
1271:
1267:
1260:
1236:
1232:
1225:
1201:
1197:
1193:
1188:
1180:Chemicalize.org
1108:Cheminformatics
1098:
1083:
1081:
1073:
1049:alvascience.com
1043:
991:
989:
981:
958:
940:
918:
899:
897:
888:
865:
846:
827:
825:
816:
797:
778:
759:
740:
676:risk management
672:
624:" according to
586:
528:
523:
466:risk assessment
446:
430:
424:
396:Molecule mining
362:
342:
334:
322:
306:
263:superimposition
259:crystallography
242:
213:
208:
146:
124:
103:
28:
23:
22:
15:
12:
11:
5:
3662:
3652:
3651:
3646:
3641:
3636:
3634:Drug discovery
3631:
3614:
3613:
3611:
3610:
3605:
3600:
3595:
3590:
3585:
3580:
3578:Mode of action
3575:
3570:
3565:
3560:
3555:
3550:
3548:Drug targeting
3545:
3543:Drug discovery
3540:
3535:
3530:
3525:
3520:
3515:
3510:
3504:
3501:
3500:
3492:
3491:
3484:
3477:
3469:
3463:
3462:
3457:
3444:
3422:
3385:
3371:
3355:
3354:External links
3352:
3351:
3350:
3305:
3299:
3277:
3274:
3272:
3271:
3247:
3196:
3145:
3110:
3099:
3048:
3041:
3023:
3016:
2998:
2961:(4): 2264–72.
2941:
2934:
2904:
2897:
2879:
2860:(9): 2320–35.
2843:
2792:
2757:
2730:
2719:(3): 235–251.
2703:
2652:
2609:
2602:
2584:
2533:
2522:(2): 195–205.
2502:
2451:
2416:
2409:
2391:
2384:
2366:
2317:
2266:
2219:(8): 595–608.
2199:
2164:
2115:
2094:
2073:
2062:(2): 602–618.
2045:
2026:(13): 3776–7.
2009:
1982:
1971:(1–2): 31–71.
1955:
1948:
1930:
1923:
1905:
1855:
1820:(10): 843–64.
1804:
1787:
1776:(5): 868–873.
1760:
1725:Bioinformation
1711:
1704:
1686:
1651:
1597:
1578:(8): 2044–58.
1557:
1506:
1485:(5): 694–701.
1479:QSAR Comb. Sci
1466:
1449:QSAR Comb. Sci
1433:
1407:
1364:
1337:
1294:
1287:
1265:
1258:
1230:
1223:
1194:
1192:
1189:
1187:
1186:
1177:
1172:
1161:
1156:
1151:
1146:
1141:
1136:
1131:
1126:
1121:
1116:
1110:
1105:
1099:
1097:
1094:
1091:
1090:
1075:"SciKit-Learn"
1071:
1068:
1058:
1054:
1053:
1041:
1040:and Consensus)
1006:
1003:
999:
998:
979:
976:
973:
969:
968:
966:on 2017-06-19.
956:
954:
951:
947:
946:
938:
936:
933:
929:
928:
926:on 2016-11-19.
916:
913:
910:
906:
905:
886:
883:
880:
876:
875:
863:
860:
857:
853:
852:
844:
841:
838:
834:
833:
814:
811:
808:
804:
803:
795:
792:
789:
785:
784:
776:
773:
770:
766:
765:
757:
754:
751:
747:
746:
738:
735:
732:
728:
727:
726:External link
724:
721:
718:
680:European Union
671:
668:
602:Drug discovery
585:
582:
578:pKa prediction
563:higher alkanes
559:boiling points
532:boiling points
527:
524:
522:
519:
498:
497:
494:
491:
488:
470:drug discovery
445:
442:
426:Main article:
423:
420:
382:decision trees
361:
358:
341:
338:
333:
330:
321:
318:
305:
302:
288:methods, e.g.
261:) or molecule
241:
238:
212:
209:
207:
204:
145:
142:
141:
140:
137:
134:
131:
123:
120:
108:
107:
26:
9:
6:
4:
3:
2:
3661:
3650:
3647:
3645:
3642:
3640:
3637:
3635:
3632:
3630:
3627:
3626:
3624:
3609:
3606:
3604:
3603:Pharmacophore
3601:
3599:
3596:
3594:
3591:
3589:
3586:
3584:
3581:
3579:
3576:
3574:
3571:
3569:
3566:
3564:
3561:
3559:
3556:
3554:
3551:
3549:
3546:
3544:
3541:
3539:
3536:
3534:
3531:
3529:
3528:Drug delivery
3526:
3524:
3521:
3519:
3518:Chemogenomics
3516:
3514:
3511:
3509:
3506:
3505:
3502:
3498:
3490:
3485:
3483:
3478:
3476:
3471:
3470:
3467:
3461:
3458:
3455:
3451:
3448:
3445:
3442:
3432:on 2009-04-25
3431:
3427:
3423:
3420:
3410:on 2007-05-01
3409:
3404:
3399:
3395:
3391:
3386:
3376:
3372:
3362:
3358:
3357:
3347:
3343:
3338:
3333:
3328:
3323:
3319:
3315:
3311:
3306:
3302:
3296:
3292:
3285:
3280:
3279:
3267:
3263:
3259:
3251:
3243:
3239:
3234:
3229:
3224:
3219:
3215:
3211:
3207:
3200:
3192:
3188:
3183:
3178:
3173:
3168:
3164:
3160:
3156:
3149:
3141:
3137:
3133:
3129:
3126:(3): 318–31.
3125:
3121:
3114:
3108:
3103:
3095:
3091:
3087:
3083:
3079:
3075:
3071:
3067:
3063:
3059:
3052:
3044:
3038:
3034:
3027:
3019:
3013:
3009:
3002:
2994:
2990:
2985:
2980:
2976:
2972:
2968:
2964:
2960:
2956:
2952:
2945:
2937:
2935:9780124095472
2931:
2927:
2923:
2919:
2915:
2908:
2900:
2894:
2890:
2883:
2875:
2871:
2867:
2863:
2859:
2855:
2847:
2839:
2835:
2830:
2825:
2820:
2815:
2811:
2807:
2803:
2796:
2788:
2784:
2780:
2776:
2773:(2): 164–72.
2772:
2768:
2761:
2753:
2749:
2745:
2741:
2734:
2726:
2722:
2718:
2714:
2707:
2699:
2695:
2690:
2685:
2680:
2675:
2671:
2667:
2663:
2656:
2648:
2644:
2640:
2636:
2632:
2628:
2624:
2620:
2613:
2605:
2599:
2595:
2588:
2580:
2576:
2572:
2568:
2564:
2560:
2556:
2552:
2548:
2544:
2537:
2529:
2525:
2521:
2517:
2513:
2506:
2498:
2494:
2489:
2484:
2479:
2474:
2470:
2466:
2462:
2455:
2447:
2443:
2439:
2435:
2431:
2427:
2420:
2412:
2406:
2402:
2395:
2387:
2381:
2377:
2370:
2362:
2358:
2353:
2348:
2344:
2340:
2336:
2332:
2328:
2321:
2313:
2309:
2304:
2299:
2294:
2289:
2285:
2281:
2277:
2270:
2262:
2258:
2253:
2248:
2244:
2240:
2236:
2232:
2227:
2222:
2218:
2214:
2210:
2203:
2195:
2191:
2187:
2183:
2179:
2175:
2168:
2160:
2156:
2151:
2146:
2142:
2138:
2134:
2130:
2126:
2119:
2110:
2105:
2098:
2089:
2084:
2077:
2069:
2065:
2061:
2057:
2049:
2041:
2037:
2033:
2029:
2025:
2021:
2013:
2005:
2001:
1997:
1993:
1986:
1978:
1974:
1970:
1966:
1959:
1951:
1945:
1941:
1934:
1926:
1920:
1916:
1909:
1901:
1897:
1893:
1889:
1885:
1881:
1877:
1873:
1869:
1862:
1860:
1851:
1847:
1843:
1839:
1835:
1831:
1827:
1823:
1819:
1815:
1808:
1801:
1794:
1792:
1783:
1779:
1775:
1771:
1764:
1756:
1752:
1747:
1742:
1738:
1734:
1731:(7): 237–41.
1730:
1726:
1722:
1715:
1707:
1701:
1697:
1690:
1682:
1678:
1674:
1670:
1666:
1662:
1655:
1647:
1643:
1639:
1635:
1631:
1627:
1623:
1619:
1615:
1611:
1607:
1601:
1593:
1589:
1585:
1581:
1577:
1573:
1566:
1564:
1562:
1553:
1549:
1544:
1539:
1534:
1529:
1525:
1521:
1517:
1510:
1501:
1500:11383/1668881
1496:
1492:
1488:
1484:
1480:
1473:
1471:
1462:
1458:
1454:
1450:
1446:
1440:
1438:
1429:
1425:
1421:
1414:
1412:
1403:
1399:
1395:
1391:
1387:
1383:
1380:(7): 633–54.
1379:
1375:
1368:
1360:
1356:
1352:
1348:
1347:Excli Journal
1341:
1333:
1329:
1325:
1321:
1317:
1313:
1309:
1305:
1298:
1290:
1284:
1280:
1276:
1269:
1261:
1255:
1251:
1247:
1243:
1242:
1234:
1226:
1220:
1216:
1212:
1208:
1207:
1199:
1195:
1185:
1181:
1178:
1176:
1173:
1171:
1167:
1166:
1162:
1160:
1157:
1155:
1154:Pharmacophore
1152:
1150:
1147:
1145:
1142:
1140:
1137:
1135:
1132:
1130:
1127:
1125:
1122:
1120:
1117:
1114:
1111:
1109:
1106:
1104:
1101:
1100:
1080:
1076:
1072:
1069:
1066:
1062:
1059:
1056:
1055:
1050:
1046:
1042:
1039:
1035:
1031:
1027:
1023:
1019:
1015:
1011:
1007:
1004:
1001:
1000:
988:
984:
980:
977:
974:
971:
970:
965:
961:
957:
955:
952:
949:
948:
943:
939:
937:
934:
931:
930:
925:
921:
917:
914:
911:
908:
907:
896:on 2017-12-19
895:
891:
887:
884:
881:
878:
877:
873:. 2018-09-19.
872:
868:
864:
861:
858:
855:
854:
849:
845:
842:
839:
836:
835:
824:on 2011-10-28
823:
819:
815:
812:
809:
806:
805:
800:
796:
793:
790:
787:
786:
781:
777:
774:
771:
768:
767:
762:
758:
755:
752:
749:
748:
743:
739:
736:
733:
730:
729:
725:
722:
719:
716:
715:
712:
709:
706:
704:
703:extrapolation
700:
696:
691:
689:
685:
681:
677:
667:
665:
661:
657:
653:
648:
646:
642:
638:
634:
629:
627:
623:
619:
615:
611:
608:and have low
607:
603:
599:
595:
591:
581:
579:
575:
574:Taft equation
571:
566:
564:
560:
556:
552:
548:
544:
540:
535:
533:
518:
514:
511:
510:leave one-out
506:
504:
495:
492:
489:
486:
482:
481:
480:
477:
475:
471:
467:
463:
459:
455:
451:
441:
439:
435:
429:
417:QSAR protocol
415:
411:
409:
408:graph kernels
405:
401:
397:
393:
391:
387:
383:
379:
375:
370:
367:
357:
356:in one step.
355:
351:
347:
337:
329:
327:
317:
315:
310:
301:
298:
295:
291:
287:
283:
279:
274:
272:
268:
264:
260:
255:
251:
247:
237:
233:
229:
226:
222:
218:
203:
201:
196:
194:
190:
186:
182:
177:
175:
174:bioisosterism
171:
167:
163:
159:
155:
151:
138:
135:
132:
129:
128:
127:
119:
117:
113:
102:
98:
97:
96:
94:
89:
85:
83:
79:
75:
70:
68:
64:
60:
56:
52:
47:
45:
40:
37:models) are
36:
32:
19:
3607:
3598:Pharmacology
3440:
3434:. Retrieved
3430:the original
3426:"QSAR World"
3418:
3412:. Retrieved
3408:the original
3393:
3378:. Retrieved
3364:. Retrieved
3317:
3313:
3290:
3268:: 2825–2830.
3265:
3261:
3250:
3213:
3209:
3199:
3162:
3158:
3148:
3123:
3119:
3113:
3102:
3061:
3057:
3051:
3032:
3026:
3007:
3001:
2958:
2954:
2944:
2917:
2913:
2907:
2888:
2882:
2857:
2853:
2846:
2809:
2805:
2795:
2770:
2766:
2760:
2746:(1): 31–42.
2743:
2739:
2733:
2716:
2712:
2706:
2669:
2665:
2655:
2622:
2618:
2612:
2593:
2587:
2546:
2542:
2536:
2519:
2515:
2505:
2468:
2464:
2454:
2429:
2425:
2419:
2400:
2394:
2375:
2369:
2334:
2330:
2320:
2283:
2279:
2269:
2216:
2212:
2202:
2177:
2173:
2167:
2132:
2128:
2118:
2097:
2076:
2059:
2055:
2048:
2023:
2019:
2012:
1995:
1991:
1985:
1968:
1964:
1958:
1939:
1933:
1914:
1908:
1878:(1): 56–69.
1875:
1871:
1817:
1813:
1807:
1799:
1773:
1769:
1763:
1728:
1724:
1714:
1695:
1689:
1664:
1660:
1654:
1613:
1609:
1600:
1575:
1571:
1523:
1519:
1509:
1482:
1478:
1452:
1448:
1419:
1377:
1373:
1367:
1350:
1346:
1340:
1307:
1303:
1297:
1278:
1268:
1240:
1233:
1205:
1198:
1163:
1082:. Retrieved
1078:
1061:scikit-learn
1048:
1008:Regression (
990:. Retrieved
986:
964:the original
924:the original
898:. Retrieved
894:the original
870:
826:. Retrieved
822:the original
710:
707:
692:
687:
673:
670:Applications
649:
630:
622:druglikeness
617:
587:
567:
551:correlations
536:
529:
515:
509:
507:
499:
478:
447:
431:
406:searches or
394:
371:
363:
343:
335:
323:
320:String based
311:
307:
299:
275:
249:
245:
244:The acronym
243:
234:
230:
214:
199:
197:
178:
157:
147:
125:
109:
100:
90:
86:
77:
73:
71:
48:
34:
30:
29:
3533:Drug design
987:deepchem.io
695:convex hull
521:Application
374:data mining
332:Graph based
297:molecule).
254:force field
200:SAR paradox
193:overfitting
112:model error
99:Activity =
3623:Categories
3523:Drug class
3495:Topics in
3436:2009-05-11
3414:2009-05-11
3380:2011-06-18
3366:2009-05-11
2226:1603.00856
2109:1703.07076
2088:1602.06289
1191:References
992:20 October
983:"DeepChem"
900:2016-03-24
828:2016-03-24
791:RapidMiner
723:Algorithms
584:Biological
557:and their
462:properties
372:A typical
280:(see also
185:hypotheses
183:. Created
170:solubility
150:hypotheses
39:regression
3649:Paradoxes
3320:: 11–21.
3078:1062-936X
2806:Molecules
2666:Molecules
2471:(1): 48.
2286:(1): 12.
1630:1868-1743
1455:: 69–77.
1445:Tropsha A
1353:: 74–88.
1084:13 August
1005:alvaModel
975:Deep Chem
688:in silico
580:methods.
354:induction
168:ability,
164:ability,
3450:Archived
3346:24741320
3242:36361669
3191:21798025
3140:25448759
3086:22369620
2993:12668435
2874:21800825
2838:19471190
2787:17933600
2698:22534664
2647:21305783
2639:23488901
2579:21518449
2571:13677480
2497:25544551
2446:23557664
2361:36456532
2312:33597034
2261:27558503
2194:16180893
2159:30155234
2040:17348648
1992:J. Catal
1900:45364247
1892:24266725
1842:20740315
1755:17597897
1681:11848856
1646:23564249
1638:27463326
1592:22721530
1552:26110025
1402:17622541
1394:22823204
1332:49418479
1324:29936244
1096:See also
859:AZOrange
664:learning
637:receptor
610:toxicity
526:Chemical
390:inducing
340:Modeling
328:string.
250:3-D QSAR
162:reaction
33:models (
3337:3970920
3233:9655980
3182:3158423
3094:2714861
2984:1302793
2963:Bibcode
2829:6254296
2689:6268288
2551:Bibcode
2488:4272757
2352:9749029
2303:7888189
2252:5028207
2231:Bibcode
2150:6011237
1850:1171860
1822:Bibcode
1746:1891704
1543:4479250
1159:Q-RASAR
1026:LDA/QDA
882:Tanagra
606:targets
555:alkanes
273:(PLS).
246:3D-QSAR
240:3D-QSAR
104:
67:predict
3344:
3334:
3297:
3240:
3230:
3189:
3179:
3165:: 28.
3138:
3092:
3084:
3076:
3039:
3014:
2991:
2981:
2932:
2895:
2872:
2836:
2826:
2785:
2696:
2686:
2645:
2637:
2600:
2577:
2569:
2495:
2485:
2444:
2407:
2382:
2359:
2349:
2310:
2300:
2259:
2249:
2192:
2157:
2147:
2038:
1946:
1921:
1898:
1890:
1848:
1840:
1753:
1743:
1702:
1679:
1644:
1636:
1628:
1590:
1550:
1540:
1526:: 32.
1400:
1392:
1330:
1322:
1285:
1256:
1221:
1115:(CADD)
1065:Python
1030:PLS-DA
935:MALLET
871:GitHub
772:Orange
753:libSVM
660:coding
633:enzyme
590:assays
539:family
450:models
326:SMILES
189:finite
181:trends
3287:(PDF)
3090:S2CID
2643:S2CID
2575:S2CID
2221:arXiv
2104:arXiv
2083:arXiv
1896:S2CID
1846:S2CID
1642:S2CID
1398:S2CID
1328:S2CID
840:Knime
717:S.No.
684:REACH
206:Types
158:small
3508:ADME
3342:PMID
3295:ISBN
3238:PMID
3187:PMID
3136:PMID
3082:PMID
3074:ISSN
3037:ISBN
3012:ISBN
2989:PMID
2930:ISBN
2893:ISBN
2870:PMID
2834:PMID
2783:PMID
2694:PMID
2635:PMID
2598:ISBN
2567:PMID
2493:PMID
2442:PMID
2405:ISBN
2380:ISBN
2357:PMID
2308:PMID
2257:PMID
2190:PMID
2155:PMID
2036:PMID
1944:ISBN
1919:ISBN
1888:PMID
1838:PMID
1751:PMID
1700:ISBN
1677:PMID
1634:PMID
1626:ISSN
1588:PMID
1548:PMID
1390:PMID
1320:PMID
1283:ISBN
1254:ISBN
1219:ISBN
1103:ADME
1086:2023
1034:k-NN
1018:k-NN
994:2017
915:k-NN
912:Elki
810:Weka
720:Name
662:and
656:MVUE
616:log
576:and
472:and
388:for
352:and
225:logP
198:The
116:bias
78:QSPR
61:and
35:QSAR
18:QSAR
3398:doi
3332:PMC
3322:doi
3228:PMC
3218:doi
3177:PMC
3167:doi
3128:doi
3066:doi
2979:PMC
2971:doi
2922:doi
2862:doi
2824:PMC
2814:doi
2775:doi
2771:602
2748:doi
2721:doi
2684:PMC
2674:doi
2627:doi
2559:doi
2524:doi
2483:PMC
2473:doi
2434:doi
2347:PMC
2339:doi
2298:PMC
2288:doi
2247:PMC
2239:doi
2182:doi
2145:PMC
2137:doi
2064:doi
2028:doi
2024:129
2000:doi
1996:216
1973:doi
1880:doi
1830:doi
1778:doi
1741:PMC
1733:doi
1669:doi
1618:doi
1580:doi
1538:PMC
1528:doi
1495:hdl
1487:doi
1457:doi
1424:doi
1382:doi
1355:doi
1312:doi
1246:doi
1211:doi
1057:14.
1038:SVM
1022:SVM
1014:PLS
1010:OLS
1002:13.
972:12.
953:MOA
950:11.
932:10.
756:SVM
635:or
596:or
541:of
460:or
248:or
154:SAR
3625::
3439:.
3417:.
3396:.
3392:.
3340:.
3330:.
3316:.
3312:.
3266:12
3264:.
3260:.
3236:.
3226:.
3214:23
3212:.
3208:.
3185:.
3175:.
3161:.
3157:.
3134:.
3124:20
3122:.
3088:.
3080:.
3072:.
3062:23
3060:.
2987:.
2977:.
2969:.
2959:84
2957:.
2953:.
2928:.
2916:.
2868:.
2858:51
2856:.
2832:.
2822:.
2810:14
2808:.
2804:.
2781:.
2769:.
2744:90
2742:.
2717:25
2715:.
2692:.
2682:.
2670:17
2668:.
2664:.
2641:.
2633:.
2621:.
2573:.
2565:.
2557:.
2547:17
2545:.
2518:.
2514:.
2491:.
2481:.
2467:.
2463:.
2440:.
2430:18
2428:.
2355:.
2345:.
2335:62
2333:.
2329:.
2306:.
2296:.
2284:13
2282:.
2278:.
2255:.
2245:.
2237:.
2229:.
2217:30
2215:.
2211:.
2188:.
2178:45
2176:.
2153:.
2143:.
2131:.
2127:.
2060:31
2058:.
2034:.
2022:.
1994:.
1969:89
1967:.
1894:.
1886:.
1876:33
1874:.
1870:.
1858:^
1844:.
1836:.
1828:.
1818:24
1816:.
1790:^
1774:39
1772:.
1749:.
1739:.
1727:.
1723:.
1675:.
1665:96
1663:.
1640:.
1632:.
1624:.
1614:29
1612:.
1586:.
1576:52
1574:.
1560:^
1546:.
1536:.
1522:.
1518:.
1493:.
1483:26
1481:.
1469:^
1453:22
1451:.
1436:^
1410:^
1396:.
1388:.
1376:.
1349:.
1326:.
1318:.
1308:23
1306:.
1277:.
1252:.
1217:.
1168:–
1077:.
1067:)
1047:.
1036:,
1032:,
1028:,
1020:,
1016:,
1012:,
985:.
909:9.
879:8.
869:.
856:7.
837:6.
807:5.
788:4.
769:3.
750:2.
731:1.
666:.
647:.
628:.
600:.
572:,
565:.
534:.
410:.
384:,
380:,
316:.
95::
3488:e
3481:t
3474:v
3400::
3383:.
3369:.
3348:.
3324::
3318:7
3303:.
3244:.
3220::
3193:.
3169::
3163:3
3142:.
3130::
3096:.
3068::
3045:.
3020:.
2995:.
2973::
2965::
2938:.
2924::
2901:.
2876:.
2864::
2840:.
2816::
2789:.
2777::
2754:.
2750::
2727:.
2723::
2700:.
2676::
2649:.
2629::
2623:2
2606:.
2581:.
2561::
2553::
2530:.
2526::
2520:1
2499:.
2475::
2469:6
2448:.
2436::
2413:.
2388:.
2363:.
2341::
2314:.
2290::
2263:.
2241::
2233::
2223::
2196:.
2184::
2161:.
2139::
2133:9
2112:.
2106::
2091:.
2085::
2070:.
2066::
2042:.
2030::
2006:.
2002::
1979:.
1975::
1952:.
1927:.
1902:.
1882::
1852:.
1832::
1824::
1784:.
1780::
1757:.
1735::
1729:1
1708:.
1683:.
1671::
1648:.
1620::
1594:.
1582::
1554:.
1530::
1524:7
1503:.
1497::
1489::
1463:.
1459::
1430:.
1426::
1404:.
1384::
1378:5
1361:.
1357::
1351:8
1334:.
1314::
1291:.
1262:.
1248::
1227:.
1213::
1182::
1088:.
1063:(
1051:.
996:.
944:.
903:.
850:.
831:.
801:.
782:.
763:.
744:.
734:R
618:P
114:(
101:f
76:(
20:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.