The drug-maker's guide to the galaxy

Mullard, Asher

doi:10.1038/549445a

Cited by 92 publications

(78 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note that the formalism of the composite method corresponds to a sophisticated extension of the telescoping series in Equation (2). One could also simply rewrite (2) as,…”

Section: A From Pople Diagrams To Cqmlmentioning

confidence: 99%

Boosting Quantum Machine Learning Models with a Multilevel Combination Technique: Pople Diagrams Revisited

Zaspel

Huang

Harbrecht

et al. 2018

J. Chem. Theory Comput.

107

184

View full text Add to dashboard Cite

Inspired by Pople diagrams popular in quantum chemistry, we introduce a hierarchical scheme, based on the multi-level combination (C) technique, to combine various levels of approximations made when calculating molecular energies within quantum chemistry. When combined with quantum machine learning (QML) models, the resulting CQML model is a generalized unified recursive kernel ridge regression which exploits correlations implicitly encoded in training data comprised of multiple levels in multiple dimensions. Here, we have investigated up to three dimensions: Chemical space, basis set, and electron correlation treatment. Numerical results have been obtained for atomization energies of a set of ∼7'000 organic molecules with up to 7 atoms (not counting hydrogens) containing CHONFClS, as well as for ∼6'000 constitutional isomers of C 7 H 10 O 2 . CQML learning curves for atomization energies suggest a dramatic reduction in necessary training samples calculated with the most accurate and costly method. In order to generate milli-second estimates of CCSD(T)/cc-pvdz atomization energies with prediction errors reaching chemical accuracy (∼1 kcal/mol), the CQML model requires only ∼100 training instances at CCSD(T)/cc-pvdz level, rather than thousands within conventional QML, while more training molecules are required at lower levels. Our results suggest a possibly favorable trade-off between various hierarchical approximations whose computational cost scales differently with electron number.

show abstract

“…Note that the formalism of the composite method corresponds to a sophisticated extension of the telescoping series in Equation (2). One could also simply rewrite (2) as,…”

Section: A From Pople Diagrams To Cqmlmentioning

confidence: 99%

Boosting Quantum Machine Learning Models with a Multilevel Combination Technique: Pople Diagrams Revisited

Zaspel

Huang

Harbrecht

et al. 2018

J. Chem. Theory Comput.

107

184

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, this is the first study which compares and contrasts the performance of diverse molecular descriptor sets for bitter-sweet prediction and releases pretrained models. We believe that along with computational strategies for generating realizable small organic molecules 36 , our models would provide the foundation of a framework to span the chemical universe in search of compounds with desirable bitter-sweet taste gradient.…”

Section: Discussionmentioning

confidence: 99%

BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules

Tuwani

Wadhwa

Bagler

2018

Preprint

View full text Add to dashboard Cite

The dichotomy of sweet and bitter tastes is a salient evolutionary feature of human gustatory system with an innate attraction to sweet taste and aversion to bitterness. A better understanding of molecular correlates of bitter-sweet taste gradient is crucial for identification of natural as well as synthetic compounds of desirable taste on this axis. While previous studies have advanced our understanding of the molecular basis of bitter-sweet taste and contributed models for their identification, there is ample scope to enhance these models by meticulous compilation of bitter-sweet molecules and utilization of a wide spectrum of molecular descriptors. Towards these goals, based on structured data compilation our study provides an integrative framework with state-of-the-art machine learning models for bitter-sweet taste prediction (BitterSweet). We compare different sets of molecular descriptors for their predictive performance and further identify important features as well as feature blocks. The utility of BitterSweet models is demonstrated by taste prediction on large specialized chemical sets such as FlavorDB, FooDB, SuperSweet, Super Natural II, DSSTox, and DrugBank. To facilitate future research in this direction, we make all datasets and BitterSweet models publicly available, and also present an end-to-end software for bitter-sweet taste prediction based on freely available chemical descriptors.

show abstract

“…Denn nach wie vor kennen sie erst einen kleinen Bruchteil der theoretisch möglichen Substanzvielfalt. Allein die Zahl der pharmazeutisch möglicherweise interessanten kleinen Moleküle soll bei 10 60 liegen .…”

Section: Abbunclassified

150 Millionen Substanzen

Hübner¹

2019

Chemie in nserer Zeit

View full text Add to dashboard Cite

Am 9. Mai war es so weit: Das Substanzregister des Chemical Abstracts Service (CAS), CAS RegistrySM, erhielt seinen 150millionsten Eintrag: 2‐[[3,3‐Difluoro‐1‐[(2R)‐2‐hydroxy‐1‐oxopropyl]‐4‐piperidinyl]oxy]‐5‐[2‐[[5‐[(2R)‐2,4‐dimethyl‐1‐piperazinyl]‐ 6‐methoxy‐2‐pyridinyl]amino]‐4‐pyrimidinyl]benzonitril heißt die Substanz und ist fortan, vielleicht etwas griffiger, auch mit der CAS‐Nummer 2306877‐20‐1 eindeutig beschrieben.

show abstract

The drug-maker's guide to the galaxy

Cited by 92 publications

References 3 publications

Boosting Quantum Machine Learning Models with a Multilevel Combination Technique: Pople Diagrams Revisited

Boosting Quantum Machine Learning Models with a Multilevel Combination Technique: Pople Diagrams Revisited

BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules

150 Millionen Substanzen

Contact Info

Product

Resources

About