A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

A method of generating a chemical structure performed by a neural network device includes receiving a target property value and a target structure characteristic value; selecting first generation descriptors; generating second generation descriptors; determining, using a first neural network of the neural network device, property values of the second generation descriptors; determining, using a second neural network of the neural network device, structure characteristic values of the second generation descriptors; selecting, from the second generation descriptors, candidate descriptors that satisfy the target property value and the target structure characteristic value; and generating, using the second neural network of the neural network device, chemical structures for the selected candidate descriptors.

Systems and methods for scoring and visualizing the effects of variants in biological sequences. Variants may include substitutions, insertions and deletions. The method comprises encoding biological sequences as vector sequences and then operating a neural network in the forward-propagation mode and possibly in the back-propagation mode to compute variant scores. Variant scores are determined by normalizing the gradients. Variant scores may be used to select a subset of variants, which are then used to produce modified vector sequences which are analyzed by the neural network operating in forward-propagation mode, to determine improved variant scores. The variant scores may be visualized using black and white, greyscale or colored elements that are arranged in blocks with dimensions corresponding to different possible symbols and the length of the sequence. These blocks are aligned with the biological sequence, which is illustrated by a symbol sequence arranged in a line.

A method for automatically generating a universal set of stereoisomers of an organic molecule. The method includes: (1) segmenting an input molecule into a group of fragments; (2) matching the obtained isomer fragments with fragment templates in a fragment template library; (3) generating all isomers of the corresponding fragments according to fragment template information; and (4) traversing all the isomer fragments and sites thereof, and assembling the fragments at the two ends of a broken bond in the step (1) according to all possible sites of a broken-bond atom to obtain all stereoisomers; and if filtering is needed, performing filtering according to a specified filtering rule.

A method for automatically generating a universal set of stereoisomers of an organic molecule. The method includes: (1) segmenting an input molecule into a group of fragments; (2) matching the obtained isomer fragments with fragment templates in a fragment template library; (3) generating all isomers of the corresponding fragments according to fragment template information; and (4) traversing all the isomer fragments and sites thereof, and assembling the fragments at the two ends of a broken bond in the step (1) according to all possible sites of a broken-bond atom to obtain all stereoisomers; and if filtering is needed, performing filtering according to a specified filtering rule.

Volatile organic compounds classification by receiving test data associated with detecting volatile organic compounds (VOCs), analyzing the test data according to a set of data features associated with known VOCs, determining a match between each feature of the test data and a corresponding feature of the set of data features, yielding a set of matches, defining a first degree of anomaly for the test data according to the set of matches, and classifying the test data according to the first degree of anomaly.

Volatile organic compounds classification by receiving test data associated with detecting volatile organic compounds (VOCs), analyzing the test data according to a set of data features associated with known VOCs, determining a match between each feature of the test data and a corresponding feature of the set of data features, yielding a set of matches, defining a first degree of anomaly for the test data according to the set of matches, and classifying the test data according to the first degree of anomaly.

In some implementations, the present solution can determine a first structural vector of a first chemical based on a chemical structure of the first chemical. The system can also determine first target vector of the first chemical based on at least one gene target for the first chemical. The system can use the structural vector and the target vector to generate a toxicity predictor score for the first chemical.

In some implementations, the present solution can determine a first structural vector of a first chemical based on a chemical structure of the first chemical. The system can also determine first target vector of the first chemical based on at least one gene target for the first chemical. The system can use the structural vector and the target vector to generate a toxicity predictor score for the first chemical.

A stable structure search system includes one or more processors configured to acquire a plurality of degrees of structure similarity between each of a plurality of kinds of molecules and a first molecule included in a target molecule based on each interaction potential of the plurality of kinds of molecules, acquire a plurality of degrees of charge similarity between each of the plurality of kinds of molecules and the first molecule, acquire a plurality of total degrees of similarity based on sums of each of the plurality of degrees of structure similarity and each of the plurality of degrees of charge similarity, determine a second molecule whose total degree of similarly is largest among the plurality of kinds of molecules, acquire energy of a molecular structure of the target molecule based on an interaction potential of the second molecule, and determine whether the calculated energy satisfies a certain condition.