Abstract: Methods for index hopping sequence read filtering are provided. Each read in a plurality of reads from a multiplexed reaction comprises an insert portion, and first (molecular identifier) and second (sample index) non-insert portions. For each of a plurality of hashes, a hash data structure is formed with a representation of each read. Each representation comprises a hash of the first non-insert portion of the corresponding read. Read pairs are identified in the hash data structures. Each pair includes a first and second read sharing a common hash value but differing index values. An entry is added into a heterogeneous data structure, for each such pair, that includes the first and second non-insert portions of the first and second reads of the pair. Reads with first non-insert portion values appearing more than a threshold number of times in the heterogeneous data structure are removed from the plurality of reads.

Abstract: The disclosure relates to computer technology for precision diagnosis of various states of genetic material such as a gene sequenced from cell-free DNA in a sample. The state may include a somatic homozygous deletion, a somatic heterozygous deletion, a copy number variation, or other states. A computer system may generate competing probabilistic models that each output a probability that the genetic material is in a certain state. Each model may be trained on a training sample set to output a probability that the genetic material is in a respective state. In some embodiments, the computer system may use various probabilistic distributions to generate the models. For example, the computer system may use a beta-binomial distribution, a binomial distribution, a normal (also referred to as “Gaussian”) distribution, or other type of probabilistic modeling techniques.

Abstract: The present invention provides a method for producing a peptide for the treatment (in particular, immunotherapy), monitoring, or diagnosis of a disease in a subject. This method is achieved by obtaining information pertaining to a genome read, for example an exome read, of the subject and a mutation thereof, and, as necessary, information regarding the RNA sequence of the subject and information regarding the MHC type of the subject, analyzing an epitope related to the mutation on the basis of the information pertaining to the genome read (for example, the exome read) and the mutation, arbitrary information from the RNA sequence, the MHC type information, and information regarding the disease, and producing a peptide, as necessary, on the basis of information regarding the epitope.

Abstract: Techniques are described and relate to anisotropic pooling for contextual embedding of a protein sequence. In an example, a system receives a first biological sequence and determines a sequence arrangement that comprises a component of the first biological sequence and a second biological sequence of components. By using an artificial intelligence (AI) model, the system determines a third sequence that comprises a contextual embedding vector corresponding to the component of the first biological sequence. The AI model generates the third sequence based at least in part on the sequence arrangement and by at least using a convolution and anisotropic pooling.

Abstract: Embodiments for storing digital data in DNA storage by receiving input file data, encoding the input file data into an oligonucleotide sequence to produce sequence data through a transformation of text to binary to Base_3 encoding, organizing the Base_3 sequence data into chunks of a defined chunk size, and storing the chunks in a block of a blockchain. The oligonucleotide sequence may comprise metadata for the input file data that refers to actual data stored in the DNA storage, where the actual data is formed by synthesizing the oligonucleotide sequence in a DNA synthesis process. The chunks may be stored in the blockchain only if the block agrees with a smart contract defined for the oligonucleotide sequence.

Abstract: Methods and systems for processing a plurality of sample reads for genome sequencing include, for each sample read of the plurality of sample reads, comparing substring sequences from the sample read to reference sequences representing different portions of a reference genome. One or more reference sequences are identified that match one or more of the compared substring sequences, and a probabilistic location within the reference genome is determined for the sample read based on the one or more identified reference sequences. The plurality of sample reads is sorted into a plurality of sample groups based on the determined probabilistic locations of the respective sample reads.

Abstract: An apparatus for genome sequence alignment attempts a search for the hash tables to align a target nucleotide sequence, from a hash table having a large seed size to a hash table having a small seed size, and when there is at least one matched seed to the target nucleotide sequence on a hash table, aligns the target nucleotide sequence by using candidate positions from the hash table without further hash table searching.

Abstract: Methods comprising an integrated, multiscale artificial intelligence-based system that reconstructs drug-specific pharmacogenomic networks and their constituent functional sub-networks are described. The system uses features of the functional topology of the three-dimensional architecture of drug-modulated spatial contacts in chromatin space. Discovery of a drug pharmacogenomic network is made through the selection of candidate SNPs by imputation, determination of the predicted causality of the SNPs using machine learning and deep learning, use of the causal SNPs to probe the spatial genome as determined by chromosome conformation capture analysis, combining targeted genes controlled by the same cell and tissue-specific enhancers, and reconstruction of the pharmacogenomic network using diverse data sources and metrics based on the results of genome-wide association studies.

Abstract: In accordance with embodiments, a computing device of a processing system performs a seed search of a short read (SR) against a reference sequence using a Burrows Wheeler Transform (BWT) algorithm to determine a seed. During the seed search one or more seed candidates in the reference sequence are determined. If the number of matches is less than or equal to a predefined threshold value the seed search using the BWT algorithm is stopped. Each seed candidate is extended to a respective extended seed candidate equal in length to the SR. bp-to-bp comparisons are performed between a remaining bp sequence of the SR after the matching bp and a corresponding remaining bp sequence in each extended seed candidate. An extended seed candidate that exactly matches the SR in the bp-to-bp comparisons is outputted as the seed.

Abstract: The present invention provide a method of constructing a ligand-receptor protein complex to determine the binding activity of different PBDEs derivatives to an enoyl-ACP reductase. The method comprises providing a ligand-receptor binding complex, molecular docking and performing molecular dynamic simulation. The present invention is able to determine the binding activity of PBDEs derivatives to the enoyl-ACP reductase comparable to the results obtained in vitro.

Abstract: Methods and systems for processing a plurality of sample reads for genome sequencing include, for each sample read of the plurality of sample reads, comparing substring sequences from the sample read to reference sequences representing different portions of a reference genome. One or more reference sequences are identified that match one or more of the compared substring sequences, and a probabilistic location within the reference genome is determined for the sample read based on the one or more identified reference sequences. The reference genome is partitioned for reference-aligned genome sequencing based on the determined probabilistic locations of the respective sample reads.

Abstract: The present invention provides a powerful tool to identify personalized therapeutic strategies. In particular, the invention provides methods for determining therapeutically targetable dominant signaling pathways in a cancer sample from a subject affected with a solid cancer, determining a treatment protocol for the subject, selecting a subject for a therapy, determining whether the subject is susceptible to benefit from a therapy, predicting clinical outcome of the subject, treating the subject and/or predicting the sensitivity of a solid cancer to a therapy.

Abstract: Technologies are provided for an improved classifier apparatus and processes for improving the accuracy of classification technology including example applications of such classifiers. A process includes applying clustering to variables contributing to the classification task. The clusters may be represented in a 1-dimensional, 2-dimensional, or 3-dimensional matrix that is a spatial abstraction of the interrelationships. A convolutional transformation may be applied to the matrix so as to reduce the effective dimensionality of the classification problem and improve the signal-to-noise ration. A deep learning neural network method may be applied to the transformed network to generate an improved classification model, which may be utilized by a decision support tool. One embodiment comprises a decision support tool for detecting risk of venous thrombosis and venous thromboembolism (VTE) in a patient, based on phenotype and genomics information.