Neural network frames. Application to biochemical kinetic diagnosis

Proceedings of the 11th International Electronic Conference on Synthetic Organic Chemistry

2007

Classification algorithms are proposed based on information entropy and applied to 13 human immunodeficiency virus type 1 inhibitors. A number of results are compatible with the data suffering combinatorial explosion. After the equipartition conjecture, entropy production is most uniformly distributed. In ddI the formula is N 4 O 3 S 0 P 0 X 0 , X = F, Cl; it is selected as a reference <11111>. In most cases (ddI, ddC, d4T, novel proposed ligand) the formula is N 3-4 O 3 S 0 P 0 X 0 , while in 3TC the formula is N 3 O 3 S 1 P 0 X 0. The analysis compares well with other classification taken as good.

“…The procedure has been applied in the synthesis of complex flowsheets using of information entropy. 19 From the present results and discussion the folllowing conclusions can be drawn.…”

Section: Hivnexsupporting

confidence: 57%

Periodic Classification of Human Immunodeficiency Virus Inhibitors

Proceedings of the 11th International Electronic Conference on Synthetic Organic Chemistry

2007

“…The splits graph is in general agreement with both partial correlation diagrams, dendrograms and binary trees (Figures 3 and 4). The main difference is the partial fusion of C b 2 classes (1,4,6,7,8,14,17,20,21,22,23) and (3,11,12,13,15,16,18,19,24,25,28). However, the results ( Figure 5) should be taken with care, because the former class includes four compounds with the constant <11111> vector (anaesthetics 4, 6, 20 and 23), for which the null standard deviation causes a Pearson correlation coefficient of r = 1 with any local anaesthetic, which is an artifact.…”

Section: Resultsmentioning

confidence: 99%

“…The result of the algorithm is a set of weights allowing adequate classification. Such a procedure has been applied in the synthesis of complex flowsheets using of information entropy [21].…”

Section: The Equipartition Conjecture Of Entropy Productionmentioning

confidence: 99%

Information entropy and the classification of local anaesthetics

Proceedings of the 11th International Electronic Conference on Synthetic Organic Chemistry

2007

Algorithms for classification and taxonomy based on criteria such as information entropy and its production are proposed. As an example, the feasibility of replacing a given anaesthetic by similar ones in the composition of a complex drug is studied. Some local anaesthetics currently in use are classified using characteristic chemical properties of different portions of their molecules. Many classification algorithms are based on information entropy. When applying the procedures to sets of moderate size, an excessive number of results appear compatible with data, and this number suffers a combinatorial explosion. However, after the equipartition conjecture, one has a selection criterion between different variants resulting from classification between hierarchical trees. According to this conjecture, for a given charge or duty, the best configuration of a flowsheet is the one in which the entropy production is most uniformly distributed. Information entropy and principal component analyses agree.

“…classes (1,4,6,7,8,14,17,20,21,22,23) and (3,11,12,13,15,16,18,19,24,25,28) corresponding to Figure 4. However, the results ( Figure 7) should be taken with care, because the former class includes four compounds with the constant <11111> vector (anaesthetics 4, 6, 20 and 23), for which the null standard deviation causes a correlation coefficient of r = 1 with any local anaesthetic, which is an artifact.…”

Section: Calculation Results and Discussionmentioning

confidence: 99%

“…Such a procedure has been applied in the synthesis of complex flowsheets using of information entropy [22].…”

Section: Learning Proceduresmentioning

confidence: 99%

Periodic Classification of Local Anaesthetics (Procaine Analogues)

2006

IJMS

Algorithms for classification are proposed based on criteria (information entropy and its production). The feasibility of replacing a given anaesthetic by similar ones in the composition of a complex drug is studied. Some local anaesthetics currently in use are classified using characteristic chemical properties of different portions of their molecules. Many classification algorithms are based on information entropy. When applying these procedures to sets of moderate size, an excessive number of results appear compatible with data, and this number suffers a combinatorial explosion. However, after the equipartition conjecture, one has a selection criterion between different variants resulting from classification between hierarchical trees. According to this conjecture, for a given charge or duty, the best configuration of a flowsheet is the one in which the entropy production is most uniformly distributed. Information entropy and principal component analyses agree. The periodic law of anaesthetics has not the rank of the laws of physics: (1) the properties of anaesthetics are not repeated; (2) the order relationships are repeated with exceptions. The proposed statement is: The relationships that any anaesthetic p has with its neighbour p + 1 are approximately repeated for each period.