The Java computer language was developed at Oracle Corporation, in California, USA. The Java software package CDK stands for Chemoinformatics Developer Kit and can be used for analysing molecular information. A derived package rcdk by Rajarshi Guha and others makes the functionality of the CDK available to users of the R language. Although advanced commercial systems are being used at the Pharmaceutical companies, these packages can be used by interested researchers, in the search for the present-day holy grail – an effective antivirus for COVID-19.
An example of predicting boiling point for various compounds from their molecular structure is quite astounding. In the plot in Figure 1, one can see the regression line and a narrow band of a point around it. This gives one hope, that many other important properties, including disease-fighting characteristics, can be predicted from chemical informatics.
Artificial Intelligence and machine learning culminate in Deep Learning algorithms. A neural network is presented with a training set of molecular descriptors and the output is matched with the correct boiling points of the compounds. An iterative error correction makes the neural network quite good at predicting the correct boiling point. This training may take many hours, but with current day processors, time is not likely to be an issue. What is more important is to decide which molecular descriptors are important, and the parameters of the neural network. In the table below the 277 compounds and the associate, boiling points are displayed. Training sets for drug design are much larger and may have thousands of rows, and multiple outputs to predict correctly.
Table 1 – 277 Compounds with their Boiling Point
| Compound Name | SMILES notation | Boiling Point (Kelvin scale) |
|---|---|---|
| bromo-trichloro-methane | C(Br)(Cl)(Cl)Cl | 378 |
| chloro-trifluoro-methane | ClC(F)(F)F | 191.7 |
| carbon tetrachloride | C(Cl)(Cl)(Cl)Cl | 349.8 |
| tetrafluoromethane | C(F)(F)(F)F | 145.1 |
| bromoform | BrC(Br)Br | 422.3 |
| chloro-difluoro-methane | C(Cl)(F)F | 232.3 |
| dichloro-fluoro-methane | C(Cl)(Cl)F | 282 |
| chloroform | C(Cl)(Cl)Cl | 334.3 |
| fluoroform | C(F)(F)F | 191 |
| dibromomethane | C(Br)Br | 370.1 |
| dichloromethane | C(Cl)Cl | 312.9 |
| difluoromethane | C(F)F | 221.5 |
| diiodomethane | C(I)I | 455.2 |
| formaldehyde | O=C | 254 |
| formic acid | C(=O)O | 373.7 |
| bromomethane | CBr | 276.7 |
| chloromethane | CCl | 248.9 |
| fluoromethane | CF | 194.8 |
| iodomethane | CI | 315.6 |
| methanol | CO | 337.8 |
| methanethiol | CS | 279.1 |
| 1,1-dichloro-1,2,2,2-tetrafluoro-ethane | C(C(F)(F)F)(Cl)(Cl)F | 276.2 |
| 1,1,1,2,2,2-hexafluoroethane | C(C(F)(F)F)(F)(F)F | 194.9 |
| 2,2-dichloro-1,1,1-trifluoro-ethane | C(C(Cl)Cl)(F)(F)F | 301 |
| 1,1,2-trichloroethylene | C(=C(Cl)Cl)Cl | 360.1 |
| 2,2,2-trichloroacetaldehyde | C(C=O)(Cl)(Cl)Cl | 370.8 |
| 1,1,1,2,2-pentachloroethane | C(C(Cl)(Cl)Cl)(Cl)Cl | 433 |
| 1,1,1,2,2-pentafluoroethane | C(C(F)(F)F)(F)F | 225.1 |
| 1,1,2,2-tetrabromoethane | C(C(Br)Br)(Br)Br | 516.7 |
| 1,1,1,2-tetrachloroethane | C(CCl)(Cl)(Cl)Cl | 403.7 |
| 1,1,2,2-tetrachloroethane | C(C(Cl)Cl)(Cl)Cl | 418.3 |
| 1,1-difluoroethylene | C=C(F)F | 187.5 |
| 1,1,2,2-tetrafluoroethane | C(C(F)F)(F)F | 250.1 |
| bromoethylene | C=CBr | 288.9 |
| acetyl chloride | CC(=O)Cl | 323.9 |
| 1,1,1-trichloroethane | CC(Cl)(Cl)Cl | 347.2 |
| 1,1,2-trichloroethane | C(CCl)(Cl)Cl | 387 |
| fluoroethylene | C=CF | 200.9 |
| 1,1,1-trifluoroethane | CC(F)(F)F | 225.8 |
| 1,1-dibromoethane | CC(Br)Br | 381.1 |
| 1,2-dibromoethane | C(CBr)Br | 404.5 |
| 1,1-dichloroethane | C(C)(Cl)Cl | 330.4 |
| 1,2-dichloroethane | C(CCl)Cl | 356.6 |
| 1,1-difluoroethane | CC(F)F | 247.4 |
| 1,2-difluoroethane | C(CF)F | 283.6 |
| acetic acid | CC(=O)O | 391.1 |
| formic acid methyl ester | COC=O | 304.9 |
| bromoethane | CCBr | 311.5 |
| chloroethane | CCCl | 285.4 |
| fluoroethane | CCF | 235.4 |
| iodoethane | CCI | 345.4 |
| methoxymethane | COC | 248.3 |
| ethanol | CCO | 351.4 |
| ethylene glycol | OCCO | 470.5 |
| (methylthio)methane | CSC | 310.5 |
| ethanethiol | CCS | 308.2 |
| methyldisulfanylmethane | CSSC | 382.9 |
| ethane-1,2-dithiol | SCCS | 419.2 |
| 2-chloroprop-1-ene | CC(=C)Cl | 295.8 |
| 1,2,3-trichloropropane | C(C(CCl)Cl)Cl | 430 |
| (2R)-1,2-dichloropropane | C(C(C)Cl)Cl | 369.5 |
| acetone | CC(=O)C | 329.4 |
| propionaldehyde | CCC=O | 321.1 |
| (2R)-2-methyloxirane | CC1CO1 | 307.6 |
| formic acid ethyl ester | CCOC=O | 327.5 |
| acetic acid methyl ester | CC(=O)OC | 330.1 |
| propionic acid | CCC(=O)O | 414.3 |
| 1-bromopropane | C(CC)Br | 344.1 |
| 2-chloropropane | CC(C)Cl | 308.8 |
| 1-chloropropane | CCCCl | 319.7 |
| 2-iodopropane | CC(C)I | 362.6 |
| 1-iodopropane | CCCI | 375.6 |
| propan-2-ol | CC(C)O | 355.4 |
| methoxyethane | CCOC | 280.5 |
| propan-1-ol | CCCO | 370.4 |
| (2R)-propane-1,2-diol | CC(O)CO | 460.8 |
| propane-1,3-diol | C(CCO)O | 487.6 |
| propane-2-thiol | CC(C)S | 325.7 |
| propane-1-thiol | CCCS | 340.9 |
| furan | c1ccco1 | 304.5 |
| thiophene | c1cccs1 | 357.3 |
| 2,5-dihydrofuran | C1C=CCO1 | 339 |
| methacrylic acid | CC(=C)C(=O)O | 434.2 |
| (2R)-1,2-dichlorobutane | C(C(CC)Cl)Cl | 397.1 |
| (2S,3R)-2,3-dichlorobutane | CC(C(C)Cl)Cl | 392.6 |
| butyraldehyde | C(=O)CCC | 348 |
| butan-2-one | CCC(=O)C | 352.8 |
| 2-methylpropionaldehyde | CC(C)C=O | 337.3 |
| tetrahydrofuran | O1CCCC1 | 339.1 |
| butyric acid | CCCC(=O)O | 436.4 |
| acetic acid ethyl ester | CCOC(=O)C | 350.2 |
| isobutyric acid | CC(C)C(=O)O | 427.7 |
| propionic acid methyl ester | COC(=O)CC | 352.6 |
| formic acid propyl ester | CCCOC=O | 354 |
| tetrahydrothiophene | S1CCCC1 | 394.3 |
| 1-bromobutane | C(CCC)Br | 374.8 |
| (2S)-2-bromobutane | CC(CC)Br | 364.4 |
| 1-chlorobutane | CCCCCl | 351.6 |
| (2S)-2-chlorobutane | CC(CC)Cl | 341.3 |
| 2-chloro-2-methyl-propane | CC(C)(C)Cl | 323.8 |
| 1-chloro-2-methyl-propane | CC(C)CCl | 342 |
| butan-1-ol | CCCCO | 390.8 |
| (2S)-butan-2-ol | CC(CC)O | 372.7 |
| ethoxyethane | CCOCC | 307.6 |
| 2-methylpropan-1-ol | C(C(C)C)O | 380.8 |
| 2-methylpropan-2-ol | CC(C)(C)O | 355.6 |
| 1-methoxypropane | CCCOC | 312.2 |
| (3R)-butane-1,3-diol | OCCC(C)O | 480.2 |
| butane-1,4-diol | OCCCCO | 501.2 |
| (2R,3S)-butane-2,3-diol | CC(O)C(O)C | 453.9 |
| 2-methylpropane-1,3-diol | C(C(CO)C)O | 487.2 |
| butane-1-thiol | CCCCS | 371.6 |
| (2S)-butane-2-thiol | CCC(S)C | 358.1 |
| 2-methylpropane-2-thiol | CC(C)(C)S | 337.4 |
| 2-methylpropane-1-thiol | CC(C)CS | 361.6 |
| 1-(methylthio)propane | CSCCC | 368.7 |
| 2-methylthiophene | c1cc(sc1)C | 385.7 |
| 3-methylbutan-2-one | CC(C)C(=O)C | 367.5 |
| valeraldehyde | CCCCC=O | 376.1 |
| pentan-2-one | CCCC(=O)C | 375.5 |
| pentan-3-one | CCC(=O)CC | 375.1 |
| formic acid butyl ester | CCCCOC=O | 379.3 |
| formic acid sec-butyl ester | CC(CC)OC=O | 366.5 |
| formic acid tert-butyl ester | CC(C)(C)OC=O | 356 |
| propionic acid ethyl ester | CCOC(=O)CC | 372.3 |
| formic acid isobutyl ester | CC(C)COC=O | 371.2 |
| acetic acid isopropyl ester | CC(=O)OC(C)C | 361.6 |
| butyric acid methyl ester | CCCC(=O)OC | 375.9 |
| 3-methylbutyric acid | CC(C)CC(=O)O | 448.3 |
| 2,2-dimethylpropionic acid | CC(C)(C)C(=O)O | 437 |
| valeric acid | CCCCC(=O)O | 458.9 |
| acetic acid propyl ester | CCCOC(=O)C | 374.6 |
| 1-chloropentane | CCCCCCl | 381.5 |
| 2,2-dimethylpropan-1-ol | C(C(C)(C)C)O | 386.3 |
| 2-ethoxypropane | CCOC(C)C | 326.1 |
| 1-ethoxypropane | CCOCCC | 337 |
| (2R)-2-methylbutan-1-ol | C(C(CC)C)O | 401.9 |
| 2-methylbutan-2-ol | CC(CC)(C)O | 375.1 |
| 3-methylbutan-1-ol | C(CC(C)C)O | 404.4 |
| (2S)-3-methylbutan-2-ol | CC(C(C)C)O | 384.6 |
| 1-methoxybutane | CCCCOC | 343.4 |
| (2R)-2-methoxybutane | CCC(C)OC | 332.1 |
| 2-methoxy-2-methyl-propane | CC(C)(C)OC | 328.4 |
| pentan-1-ol | C(CCCC)O | 410.9 |
| (2S)-pentan-2-ol | CC(CCC)O | 392.1 |
| pentan-3-ol | CCC(CC)O | 388.4 |
| pentane-1,5-diol | OCCCCCO | 512.2 |
| 1-(methylthio)butane | CSCCCC | 396.6 |
| 2-methyl-2-(methylthio)propane | CSC(C)(C)C | 372 |
| pentane-1-thiol | CCCCCS | 399.8 |
| 1,2,3,4,5,6-hexachlorobenzene | c1(c(c(c(c(c1Cl)Cl)Cl)Cl)Cl)Cl | 582.6 |
| 1,2,3,4,5,6-hexafluorobenzene | c1(c(c(c(c(c1F)F)F)F)F)F | 353.4 |
| 1,2,4-trichlorobenzene | c1cc(c(cc1Cl)Cl)Cl | 486.2 |
| 1,3-dichlorobenzene | c1c(cccc1Cl)Cl | 446.2 |
| 1,2-dichlorobenzene | c1(ccccc1Cl)Cl | 453.6 |
| 1,4-dichlorobenzene | c1(ccc(cc1)Cl)Cl | 447.2 |
| 3-chlorophenol | c1ccc(cc1O)Cl | 487 |
| 2-chlorophenol | c1cccc(c1O)Cl | 447.5 |
| 4-chlorophenol | c1cc(ccc1O)Cl | 493.1 |
| phenol | c1(ccccc1)O | 455 |
| pyrocatechol | c1(ccccc1O)O | 518.7 |
| resorcinol | c1(cccc(c1)O)O | 549.7 |
| hydroquinone | c1cc(ccc1O)O | 558.2 |
| cyclohexanone | C1CCC(=O)CC1 | 428.9 |
| 3-ketobutyric acid ethyl ester | CC(=O)CC(=O)OCC | 454 |
| oxalic acid diethyl ester | CCOC(=O)C(=O)OCC | 458.9 |
| cyclohexanol | C1CCC(CC1)O | 434 |
| pinacolone | CC(=O)C(C)(C)C | 379.4 |
| 2-methylpentan-3-one | CC(C)C(=O)CC | 386.5 |
| hexanal | CCCCCC=O | 401.5 |
| hexan-2-one | CC(=O)CCCC | 400.9 |
| hexan-3-one | CCC(=O)CCC | 396.6 |
| 4-methylpentan-2-one | CC(=O)CC(C)C | 389.6 |
| (3S)-3-methylpentan-2-one | CC(=O)C(C)CC | 390.6 |
| acetic acid butyl ester | CC(=O)OCCCC | 399.1 |
| acetic acid sec-butyl ester | CC(=O)OC(C)CC | 385.1 |
| acetic acid tert-butyl ester | CC(=O)OC(C)(C)C | 369.1 |
| butyric acid ethyl ester | CCCC(=O)OCC | 394.6 |
| 2-ethylbutyric acid | CCC(CC)C(=O)O | 466.9 |
| 2-methylpropionic acid ethyl ester | CCOC(=O)C(C)C | 383 |
| hexanoic acid | CCCCCC(=O)O | 478.8 |
| acetic acid isobutyl ester | CC(=O)OCC(C)C | 389.8 |
| formic acid amyl ester | CCCCCOC=O | 405.5 |
| propionic acid propyl ester | CCCOC(=O)CC | 395.6 |
| 1-ethoxybutane | CCOCCCC | 365.3 |
| 2-ethoxy-2-methyl-propane | CCOC(C)(C)C | 346 |
| 2-isopropoxypropane | CC(C)OC(C)C | 341.5 |
| 2-ethylbutan-1-ol | CCC(CC)CO | 419.7 |
| hexan-1-ol | CCCCCCO | 430.6 |
| (2S)-hexan-2-ol | CC(CCCC)O | 413 |
| (2R)-2-methylpentan-1-ol | C(C(CCC)C)O | 421.2 |
| (2S)-4-methylpentan-2-ol | CC(CC(C)C)O | 404.9 |
| 1-methoxypentane | CCCCCOC | 372 |
| hexane-1,6-diol | OCCCCCCO | 516.2 |
| (4R)-2-methylpentane-2,4-diol | CC(CC(C)O)(C)O | 470.6 |
| 1-(propylthio)propane | CCCSCCC | 416 |
| 2-(ethylthio)-2-methyl-propane | CCSC(C)(C)C | 393.6 |
| hexane-1-thiol | CCCCCCS | 425.8 |
| 1-propyldisulfanylpropane | CCCSSCCC | 469 |
| trichloromethylbenzene | c1ccccc1C(Cl)(Cl)Cl | 486.7 |
| dichloromethylbenzene | c1(ccccc1)C(Cl)Cl | 487 |
| benzoic acid | c1ccccc1C(=O)O | 522.4 |
| 4-hydroxybenzaldehyde | c1cc(ccc1O)C=O | 583.2 |
| 2-hydroxybenzaldehyde | c1(ccccc1O)C=O | 469.7 |
| chloromethylbenzene | c1ccccc1CCl | 452.6 |
| phenylmethanol | c1(ccccc1)CO | 477.9 |
| m-cresol | c1ccc(cc1O)C | 475.4 |
| o-cresol | c1cccc(c1O)C | 464.2 |
| p-cresol | c1cc(ccc1O)C | 475.1 |
| malonic acid diethyl ester | CCOC(=O)CC(=O)OCC | 472 |
| 2,4-dimethylpentan-3-one | CC(C)C(=O)C(C)C | 397.6 |
| enanthaldehyde | CCCCCCC=O | 426 |
| heptan-2-one | CC(=O)CCCCC | 424 |
| heptan-4-one | CCCC(=O)CCC | 417.2 |
| 1-methylcyclohexan-1-ol | C1(CCCCC1)(C)O | 441.2 |
| 5-methylhexan-2-one | CC(=O)CCC(C)C | 418 |
| propionic acid butyl ester | CCCCOC(=O)CC | 419.8 |
| 3-methylbutyric acid ethyl ester | CC(C)CC(=O)OCC | 407.5 |
| enanthic acid | CCCCCCC(=O)O | 496.2 |
| formic acid hexyl ester | CCCCCCOC=O | 428.6 |
| butyric acid propyl ester | CCCC(=O)OCCC | 416.5 |
| heptan-1-ol | CCCCCCCO | 449.5 |
| (2S)-heptan-2-ol | CC(CCCCC)O | 432.4 |
| 5-methylhexan-1-ol | C(CCCC(C)C)O | 445.2 |
| heptane-1-thiol | CCCCCCCS | 450.1 |
| 4-hydroxy-3-methoxy-benzaldehyde | c1cc(c(cc1C=O)OC)O | 558 |
| 4-ethylphenol | c1cc(ccc1CC)O | 491.1 |
| 2,3-xylenol | c1(c(cccc1C)O)C | 490.1 |
| 2,4-xylenol | c1cc(cc(c1O)C)C | 484.1 |
| 2,5-xylenol | c1c(ccc(c1O)C)C | 484.3 |
| 2,6-xylenol | c1c(c(c(cc1)C)O)C | 474.2 |
| 3,4-xylenol | c1(cc(ccc1C)O)C | 500.2 |
| 3,5-xylenol | c1c(cc(cc1O)C)C | 494.9 |
| (Z)-but-2-enedioic acid diethyl ester | CCOC(=O)C=CC(=O)OCC | 498.2 |
| caprylaldehyde | CCCCCCCC=O | 447.2 |
| octan-2-one | CCCCCCC(=O)C | 445.8 |
| butyric acid butyl ester | CCCCOC(=O)CCC | 438.2 |
| formic acid heptyl ester | CCCCCCCOC=O | 451.3 |
| acetic acid hexyl ester | CCCCCCOC(=O)C | 444.7 |
| 2-methylpropionic acid isobutyl ester | CC(C)COC(=O)C(C)C | 420.6 |
| (2R)-2-sec-butoxybutane | CCC(C)OC(C)CC | 394.2 |
| (2R)-2-ethylhexan-1-ol | C(C(CCCC)CC)O | 457.8 |
| octan-1-ol | C(CCCCCCC)O | 468.3 |
| (2S)-octan-2-ol | CC(CCCCCC)O | 453 |
| octane-1-thiol | CCCCCCCCS | 472.2 |
| benzoic acid ethyl ester | c1(ccccc1)C(=O)OCC | 486.6 |
| ethoxymethylbenzene | c1cccc(c1)COCC | 458.1 |
| 3,5,5-trimethylcyclohex-2-en-1-one | C1(CC(=O)C=C(C1)C)(C)C | 488.4 |
| 2,6-dimethylheptan-4-one | CC(C)CC(=O)CC(C)C | 441.4 |
| nonan-2-one | CCCCCCCC(=O)C | 467.5 |
| nonan-5-one | CCCCC(=O)CCCC | 461.6 |
| acetic acid heptyl ester | CCCCCCCOC(=O)C | 465.6 |
| pelargonic acid | CCCCCCCCC(=O)O | 528.8 |
| formic acid octyl ester | CCCCCCCCOC=O | 472 |
| 2,6-dimethylheptan-4-ol | CC(C)CC(CC(C)C)O | 451 |
| nonan-1-ol | CCCCCCCCCO | 486.3 |
| (2R)-nonan-2-ol | CCCCCCCC(C)O | 471.7 |
| nonane-1-thiol | CCCCCCCCCS | 493 |
| benzene-1,2-dicarboxylic acid dimethyl ester | c1cccc(c1C(=O)OC)C(=O)OC | 556.8 |
| anethole | CC=Cc1ccc(cc1)OC | 508.5 |
| 4-tert-butylphenol | c1(ccc(cc1)C(C)(C)C)O | 512.9 |
| capric acid | CCCCCCCCCC(=O)O | 543.2 |
| 3-methylbutyric acid isoamyl ester | CC(C)CCOC(=O)CC(C)C | 467.2 |
| acetic acid octyl ester | CCCCCCCCOC(=O)C | 484.5 |
| decan-1-ol | CCCCCCCCCCO | 504.1 |
| decane-1-thiol | CCCCCCCCCCS | 512.3 |
| acrylic acid [(2R)-2-ethylhexyl] ester | C=CC(=O)OCC(CCCC)CC | 489.2 |
| undecanoic acid | CCCCCCCCCCC(=O)O | 557.4 |
| capric acid methyl ester | CCCCCCCCCC(=O)OC | 505 |
| undecan-1-ol | CCCCCCCCCCCO | 518.2 |
| benzene-1,2-dicarboxylic acid diethyl ester | c1cccc(c1C(=O)OCC)C(=O)OCC | 567.2 |
| acetic acid decyl ester | CCCCCCCCCCOC(=O)C | 517.2 |
| lauric acid | CCCCCCCCCCCC(=O)O | 571.9 |
| 1-hexoxyhexane | CCCCCCOCCCCCC | 498.9 |
| tridecanoic acid | CCCCCCCCCCCCC(=O)O | 585.3 |
| 9,10-anthraquinone | c1cccc2c1C(=O)c3c(cccc3)C2=O | 653.1 |
| 4-(1,1,3,3-tetramethylbutyl)phenol | c1cc(ccc1C(C)(C)CC(C)(C)C)O | 563.6 |
Author:
Dr. Badri Toppur
Associate Professor, Rajalakshmi School of Business, Chennai
Email – badri.toppur@rsb.edu.in