Polypeptides are disclosed herein having significantly improved secretion ability from eukaryotic cells, together with fusion proteins, nanoparticles, and uses thereof, and methods for designing such polypeptides.

The disclosure provides genetically engineered C1-fixing microorganisms capable of producing nanobodies. Additionally, the disclosure provides engineered microorganisms comprising one or more disrupted genes to strategically divert carbon flux away from nonessential or undesirable products towards products and/or co-products of interest. The disclosure enables co-production of useful chemicals from gaseous substrates.

The disclosure provides genetically engineered C1-fixing microorganisms capable of producing nanobodies. Additionally, the disclosure provides engineered microorganisms comprising one or more disrupted genes to strategically divert carbon flux away from nonessential or undesirable products towards products and/or co-products of interest. The disclosure enables co-production of useful chemicals from gaseous substrates.

We describe systems and methods for generating and training convolutional neural networks using biological sequences and relevance scores derived from structural, biochemical, population and evolutionary data. The convolutional neural networks take as input biological sequences and additional information and output molecular phenotypes. Biological sequences may include DNA, RNA and protein sequences. Molecular phenotypes may include protein-DNA interactions, protein-RNA interactions, protein-protein interactions, splicing patterns, polyadenylation patterns, and microRNA-RNA interactions, which may be described using numerical, categorical or ordinal attributes. Intermediate layers of the convolutional neural networks are weighted using relevance score sequences, for example, conservation tracks. The resulting molecular phenotype convolutional neural networks may be used in genetic testing, to identify drug targets, to identify patients that respond similarly to a drug, to ascertain health risks, or to connect patients that have similar molecular phenotypes.

We describe systems and methods for generating and training convolutional neural networks using biological sequences and relevance scores derived from structural, biochemical, population and evolutionary data. The convolutional neural networks take as input biological sequences and additional information and output molecular phenotypes. Biological sequences may include DNA, RNA and protein sequences. Molecular phenotypes may include protein-DNA interactions, protein-RNA interactions, protein-protein interactions, splicing patterns, polyadenylation patterns, and microRNA-RNA interactions, which may be described using numerical, categorical or ordinal attributes. Intermediate layers of the convolutional neural networks are weighted using relevance score sequences, for example, conservation tracks. The resulting molecular phenotype convolutional neural networks may be used in genetic testing, to identify drug targets, to identify patients that respond similarly to a drug, to ascertain health risks, or to connect patients that have similar molecular phenotypes.

A system is shown that performs a method that searches for and identifies a genetic condition prodromal of the onset of solid tumors in a healthy subject. The method includes an evaluation cycle of a genetic stability or instability condition and at least one repetition of the evaluation cycle. The repetition cycles are performed periodically on the subject, with the frequency depending on the result of the previous cycle. Each cycle includes taking a sample, verifying the presence of mutations, verifying the frequency of mutations, recording the mutations, defining or updating a genetic instability index of the subject, evaluating, in each repetition cycle, the subject's entry into a prodromal genetic condition upon the onset of one or more solid tumors or groups of solid tumors on the basis of a threshold value (I.sub.TS,I.sub.GS) of the genetic instability index (I.sub.T,I.sub.G), defined for each single gene or group of genes, being exceeded.

A system is shown that performs a method that searches for and identifies a genetic condition prodromal of the onset of solid tumors in a healthy subject. The method includes an evaluation cycle of a genetic stability or instability condition and at least one repetition of the evaluation cycle. The repetition cycles are performed periodically on the subject, with the frequency depending on the result of the previous cycle. Each cycle includes taking a sample, verifying the presence of mutations, verifying the frequency of mutations, recording the mutations, defining or updating a genetic instability index of the subject, evaluating, in each repetition cycle, the subject's entry into a prodromal genetic condition upon the onset of one or more solid tumors or groups of solid tumors on the basis of a threshold value (I.sub.TS,I.sub.GS) of the genetic instability index (I.sub.T,I.sub.G), defined for each single gene or group of genes, being exceeded.

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.

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.

A method of screening a pathogenic uniparental disomy and a use thereof is provided. The method includes the steps as follows: obtaining data: obtaining whole exome sequencing data; screening for sites: screening and obtaining mutations under pre-determined conditions; judging LOH: performing LOH judgement according to the mutations obtained above; and judging UPD: judging UPD according to the LOH judgement, wherein when an amount of chromosomes with LOH exceeds 2, a sample is judged as a consanguineous marriage; when there is a single copy of a region with LOH, a sample is judged as a fragment deletion; and other samples are judged as UPD when there are regions with LOH. In the method, specific mutated sites are screened out to perform LOH judgment, to finally obtain the results for UPD judgment. The method is based on the whole exome sequencing data, indicating the risk of pathogenic UPD alongside conventional screening of pathogenic mutations, without additional experiments and labor cost.