09-01-2020 дата публикации
Номер: US20200013486A1
Принадлежит:
A method for computational drug design using an evolutionary algorithm, comprises evaluating virtual molecules according to vector distance (VD) to at least one achievement objective that defines a desired ideal molecule. In one method the invention comprises defining a set of n achievement objectives (O), where n is at least one; defining a population (P) of at least one molecule; selecting an initial population (P) of at least one molecule (I-I) from the population (P); and evaluating members (I-I) of the initial population (P) against at least one of the n achievement objectives (O), where x is from 1 to n. 1. A method for designing a drug compound having a particular property for a desired use , the method comprising:{'sup': 'A', 'sub': '1-n', 'defining a set of n achievement objectives (O), where n is at least one;'}{'sub': 'G=0', 'defining a population (P) of at least one molecule;'}{'sub': parent', '1', 'n', 'G=0, 'selecting an initial population (P)of at least one molecule (I-I) from the population (P); and'}{'sub': 1', 'n', 'parent', '1-x, 'sup': 'A', 'evaluating members (I-I) of the initial population (P) against at least one of the n achievement objectives (O), where x is from 1 to n;'}{'sub': 1', 'n', '1-x, 'sup': 'A', 'wherein the evaluating comprises the calculation of a linear distance (VD) from the member (I-I) to the at least one achievement objective (O);'}determining whether a stop condition is satisfied;{'sub': G', 'G+1, 'upon determining that a stop condition is not satisfied generating further populations (P; P) of molecules and evaluating each one by an iterative process until a predefined stop condition is satisfied;'} [{'sub': 1', 'n', 'parent', 'G', 'G+1', '1-n, 'sup': 'A', 'ranking members (I-I) of the initial or further evaluated population (PP; P) according to linear distance (VD) and optionally Pareto frontier to the set of n achievement objectives (O); and'}, {'sub': 1', 'n', 'parent', 'G', 'G+1, 'identifying at least the first ranked ...
Подробнее