6 results about "Negative selection" patented technology

The invention discloses a cleaning robot autonomous path planning control method based on deep learning, and the method comprises the following steps: obtaining the pose and obstacle information of a cleaning robot, and generating a data packet containing obstacle distribution and blocked coordinates when detecting that a path is blocked; activating a reconnaissance granulocyte antibody family, generating a plurality of micro-paths constrained by curvature, evaluating the accessibility, and outputting safety direction information; encoding the path data and the safety direction to form an antigen vector, and generating a candidate antibody set; executing cloning, variation, concentration inhibition and negative selection according to the matching degree, and screening an optimal antibody path as a repair segment for output; and performing phagocytic recovery on the invalid antibody and updating variation prior, and performing closed-loop splicing on the repair path and the original path to generate an executable track. According to the invention, a reconnaissance granulocyte antibody family and a phagocytosis-recovery mechanism are introduced into an artificial immune algorithm, so that the path continuity and the operation stability in a complex environment are remarkably improved.

The present invention provides novel engineered polypeptides having structural and / or kinetic similarities to CD25 or a portion thereof, such as engineered polypeptides designed to mimic an epitope outside the IL-2 binding site. [Solution] Manipulated polypeptides comprising a combination of spatially related topological constraints in which at least one constraint originates from the CD25 reference target, and methods for selecting such manipulated polypeptides are provided herein. Further provided are methods for using manipulated polypeptides, including positive and / or negative selection molecules, in a method for screening a library of binding molecules such as antibodies. CD25 antibodies selected using these manipulated polypeptides are further provided herein.

Provided herein are methods for selectively depleting a target nucleic acid comprising a sequence that does not comprise a nucleotide variant of interest. In some embodiments, a concentration of the target nucleic acid comprising the variant sequence is increased relative to a concentration of the target nucleic acid comprising the wild-type sequence, a concentration of the target nucleic acid comprising a converted nucleotide is increased relative to a concentration of the target nucleic acid that does not comprise the converted nucleotide, or a concentration of the target nucleic acid that does not comprise the converted nucleotide is increased relative to a concentration of the target nucleic acid comprising the converted nucleotide. In some embodiments, the target nucleic acids are sequenced.

Disclosed herein is a method of identifying an L-RNA aptamer specific for a target nucleic acid. According to some embodiments of the present disclosure, the method comprises, in vitro transcribing the DNAs of the DNA library into D-RNAs, followed by identifying target-specific D-RNAs via negative and positive selections, and then producing the L-RNA aptamer based on the identified D-RNA. Also disclosed herein are two aptamers identified by the present method. According to some embodiments of the present disclosure, the two aptamers respectively comprise the nucleotide sequences of SEQ ID NOs: 1 and 2.

The invention discloses a negative selection adaptive optimization method for unbalanced data resampling, and the method comprises the steps: constructing a parameter adaptive optimization model, and dynamically calculating and optimizing the radius r and neighborhood k value of a detector; an oversampling negative selection multi-point cross evolution model is constructed, and high-quality minority class samples are generated through a steady-state evolution strategy, multi-point cross evolution and negative selection; constructing an under-sampling negative selection optimization model, and adjusting the under-sampling negative selection optimization model through negative selection; through dynamic similarity measurement, a multi-point cross evolution dictionary, an information entropy weighted local outlier factor and differentiation feature weight calculation, a fitness evaluation function is guaranteed and designed through diversity tradeoff and convergence, parameter adaptive optimization is carried out, the quality of generated samples is improved, sample feature diversity is reserved, boundary confusion in a multi-label scene is eliminated, and the quality of the generated samples is improved. And the problems of information loss, overfitting and noise amplification of a resampling method can be solved.