Abstract: The present disclosure provides a novel machine learning model capable of assisting those of ordinary skill in the art to conduct base editing by, inter alia, facilitating the selection of an appropriate guide RNA and base editor combination which are capable of conducting base editing at a certain level of efficiency and specificity on a given input target DNA sequence desired to be edited to produce an outcome genotype of interest. The disclosure also provides base editors (e.g., ABEs and CBEs), napDNAbps, cytidine deaminases, adenosine deaminases, nucleic acid sequences encoding base editors and components thereof, vectors, and cells. In addition, the disclosure provides methods of making biological or experimental training and/or validation data for training and/or validating the machine learning computational models, as well as, vectors, libraries, and nucleic acid sequences for use in obtaining said experimental training and/or validation data.

Abstract: The disclosure provides methods, base editors, vectors encoding base editors and cognate gRNAs, and compositions and kits comprise said components, for installing nucleobase edits to the SMN2 locus to increase the activity and/or amount and/or stability of SMN2 protein in a cell, thereby treating Spinal Muscular Atrophy. In certain aspect, the disclosure provides compositions and methods to edit C840T of exon 7 of the SMN2 gene, or installing another one or more nucleobase edits which have the effect of removing or inactivating a degron, such as the C-terminal portion of the region encoded by exon 6 or the 4-amino acid region encoded by exon 8 (i.e., the EMLA (SEQ ID NO: 466)-tail) so as to remove or limit their degron activity to reduce, mitigate, or eliminate the intracellular degradation of the SMN2 protein.

Abstract: The specification provides methods for introducing a desired genetic change in a nucleotide sequence using a double-strand break (DSB)-inducing genome editing system, the method comprising: identifying one or more available cut sites in a nucleotide sequence; analyzing the nucleotide sequence and available cut sites with a computational model to identify the optimal cut site for introducing the desired genetic change into the nucleotide sequence; and contacting the nucleotide sequence with a DSB-inducing genome editing system, thereby introducing the desired genetic change in the nucleotide sequence at the cut site.

Abstract: The methods and compositions provided herein improve upon the methods presently used for targeted genomic modification, in part, by removing the requirement for sub-cloning of a sequence complementary to a site selected for genomic modification. The methods and compositions provided herein can be used in place of a standard CRISPR/Cas system to provide simple, fast, and inexpensive targeted modification of a genome. The methods and compositions provided herein can also be used in high-throughput genome editing applications.