Abstract: The embodiments of present disclosure herein address the inability of existing techniques to fragment both small molecules and substituents of a core scaffold. It addresses generation of lesser number of unique fragments which hinders application of graph propagation approaches to predict properties from molecular datasets. The method and system for extraction of small molecule fragments and their explanation for drug-like properties. A molecular graph representation is used to train graph convolution network (GCN) models for prediction of various absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. The models developed are compared with an existing atom-level graph model trained using a similar architecture. Further, the explanations obtained from the predictive models are validated based on their relevance to the existing knowledgebase of substructure contributions using matched molecular pairs (MMP) analysis.

Abstract: Drug induced gene expression provides information covering various aspects of drug discovery and development. Recent advances in accessibility of open-source drug-induced transcriptomic data along with ability of deep learning algorithms to understand hidden patterns have opened opportunity for designing drug molecules based on desired gene expression signatures. Embodiments herein provide method and system for cell specific model where gene expressions are processed via pretrained Simplified Molecular Input Line Entry System (SMILES) variational autoencoder (s-VAE) to produce new molecules. The model is trained with drug and drug induced gene expression data as input. Both pretrained s-VAE and profile variational autoencoder (p-VAE) are trained jointly. During joint training, difference between newly generated molecules and existing drug molecules is calculated as joint loss function composed of binary cross entropy loss and Kullback-Leibler divergence loss.

Abstract: Traditional drug discovery methods are target-based, time- and resource-intensive, and require a lot of resources for the initial hit molecule identification. Phenotype-based drug screening requires differential gene expression data of a large number of molecules for different combinations of cell-line, time point and dosage. Experimentally obtaining gene expression data for all these combinations is again a heavily resource-intensive process. The technical challenge in conventional methods that use prediction models is that they depend largely on the data processing and representation. The disclosure herein generally relates to drug-like molecule screening, and, more particularly, to a method and system for gene expression and machine learning-based drug screening. The embodiment, thus, provides a mechanism of a small molecule-induced gene expression prediction based on machine learning models.

Abstract: This disclosure relates generally to identifying candidate genome sequences. Next generation sequencing (NGS) is a massively parallel sequencing technique for identifying candidate genome sequences. The current state-of-the-art techniques for identifying candidate genome sequences does not efficiently address the problem of distributing abundance values across several related strains that are present in the reference under the same species. The disclosed technique proposes a technique for identifying candidate genome sequences by estimating coverage. The disclosed technique includes a local search-based optimization to compute maximum likelihood-based estimates using constrains on coverage/cardinality thresholds for identifying candidate genome sequences.

Abstract: This disclosure relates generally to a method and a system for profiling of metagenome samples. Most state of-art techniques for metagenomic profiling use homology-based, curated database of identified marker sequences generated after complex and costly pre-processing. The disclosed method and system for profiling of metagenome samples are a non-homology based, a non-marker based and an alignment free strain level profiling tools for microbe profiling. The disclosure works with a several k-mer based indexing techniques for constructing a compact and comprehensive multi-level indexing, wherein the multi-level indexing includes a L1-Index and a L2-Index. The multi-level indexing is used for profiling metagenomics by abundance estimation, wherein the abundance estimation includes a relative abundance and an absolute abundance.

Abstract: This disclosure relates generally to method and system for structure-based drug design using a multi-modal deep learning model. The method processes a target protein for designing at least one optimized molecule by using a multi-modal deep learning model. The GAT-VAE module obtains a latent vector of at least one active site graph comprising of key amino acid residues from the target protein. The SMILES-VAE module obtains at least one latent vector from the target protein. Further, the conditional molecular generator concatenates the active site graph with the latent vector to generate a set of molecules. The RL framework is iteratively performed on the concatenated latent vector to optimize at least one molecule by using the drug-target affinity (DTA) predictor module to predict an affinity value for the set of molecules towards the target protein. Further, at least one optimized molecule is designed with an affinity of the target protein.

Abstract: The present disclosure provides a neural document embedding based ontology mapping. Conventional methods that map ontology concepts across domains/species extensively take help of bridging ontologies. Initially the system receives a Human Phenotype (HP) Identification number (ID) pertaining to a phenotype. A first HP ID vector is computed from the HP ID using a trained word2vec model. A second HP ID vector is computed from the HP ID using a trained Doc2vec model. An average HP ID vector is computed based on the first HP ID vector and the second HP ID vector. A plurality of cosine similarity scores are computed based on a comparison between the average HP ID vector and a plurality of average MP ID vectors. The plurality of MP IDs are sorted based on the plurality of cosine similarity scores. The plurality of MP IDs corresponding to the HP ID are selected based on a selection threshold.

Abstract: This disclosure relates generally to a method and a system for profiling of metagenome samples. Most state of-art techniques for metagenomic profiling use homology-based, curated database of identified marker sequences generated after complex and costly pre-processing. The disclosed method and system for profiling of metagenome samples are a non-homology based, a non-marker based and an alignment free strain level profiling tools for microbe profiling. The disclosure works with a several k-mer based indexing techniques for constructing a compact and comprehensive multi-level indexing, wherein the multi-level indexing includes a L1-Index and a L2-Index. The multi-level indexing is used for profiling metagenomics by abundance estimation, wherein the abundance estimation includes a relative abundance and an absolute abundance.

Abstract: This disclosure relates generally to method and system for graph convolution based gene prioritization on heterogeneous networks. The method includes obtaining a set of entities for human rare diseases from one or more sources containing rare diseases, genes, phenotypes for rare diseases and biological pathways and constructing an initial heterogeneous network using each of an entity from the set of entities. the initial heterogeneous network applying Graph Convolution-based Association Scoring (GCAS) to the initial heterogeneous network to derive inferred associations and creating a Heterogeneous Association Network for Rare Diseases (HANRD) by adding the inferred associations to the initial heterogeneous network and generating a prioritized set of genes for an input query being received in the HANRD.

Abstract: There is a demand for low-cost efficient robust method for mapping read sequences with genome variation graph in genomic study. This disclosure herein relates to a method and system for mapping read sequences with genome variation graph by constructing a subgraph using a novel combination of graph embedding and graph winnowing techniques. The system processes the obtained plurality of read sequences and a genome variation graph for constructing the subgraph by computing an embedding for the genome variation graph utilizing a graph embedding technique. Further, graph index is generated for the genome variation graph based on the embedding and the genome variation graph utilizing the graph winnowing technique. Then computes gapped alignment score for read sequence (r) with its corresponding subgraph. Thus, enables a reliable method for read sequence with accurate, memory efficient and scalable system for mapping read sequences with genome variation graph.

Abstract: Diagnosis of rare human diseases using DNA sequencing is a fast growing area of research. Conventional methods carries a risk of incorrect phenotype interpretation. However, obtaining a correct genotype and phenotype matching is challenging. A system for matching phenotype descriptions and pathogenic variants provides a one to one mapping of the phenotype and genotypes of a plurality of subjects under test. Initially, a plurality of phenotypes and a plurality of genome sequences are segmented based on metadata. A phenotype driven gene prioritization and a variant prioritization is applied on the segmented data method. A similarity score is calculated between the phenotype driven gene prioritization output and the variant prioritization output. The similarity score is further utilized to obtain a one to one matching of the plurality of phenotypes and the plurality of genotype sequences of the plurality of subjects under test.

Abstract: The present disclosure is generally relates to technique for scoring variants to evaluate an effect of the variants on gene function. The present system and method assigns scores for the plurality of variants that are occurred in a particular transcript corresponding to a protein coding gene comprised in the exome. The plurality of variants including the synonymous variants, the non-synonymous variants, the frameshift indels and the non-frameshift indels, the variants that spans into a coding exonic intronic boundary region, and the splice site variants, considering an interplay between a pair of alleles in order to understand as to what extent the variant may impact the gene, based on number of risk alleles present in the gene. The final score of the variant indicate probable effect of the variant, higher the score more will be the effect of the variant on gene.

Abstract: This disclosure relates generally to method and system for predicting effect of genomic variations on pre-mRNA splicing. The method include receiving genomic position information of at least one candidate variant, gene transcripts and genomic coordinates information of the gene transcripts; classifying the at least one candidate variant into one of a splice acceptor site region and a branch site region based on the coordinates information of the gene transcripts and the genomic position information of at least one candidate variant; evaluating effect of the at least one candidate variant on pre-mRNA splicing, based on a classified region from the classification of the at least one candidate variant and predicting pathogenicity of the at least one candidate variant based on the evaluated effect of the at least one candidate variant on the pre-mRNA splicing.

Abstract: This disclosure relates generally to method and system for graph convolution based gene prioritization on heterogeneous networks. The method includes obtaining a set of entities for human rare diseases from one or more sources containing rare diseases, genes, phenotypes for rare diseases and biological pathways and constructing an initial heterogeneous network using each of an entity from the set of entities. the initial heterogeneous network applying Graph Convolution-based Association Scoring (GCAS) to the initial heterogeneous network to derive inferred associations and creating a Heterogeneous Association Network for Rare Diseases (HANRD) by adding the inferred associations to the initial heterogeneous network and generating a prioritized set of genes for an input query being received in the HANRD.

Abstract: Systems and methods for automated creation of a dictionary of scientific terms are described herein. Initially, input data is filtered to obtain a primary file having a plurality of term-ID pairs with each term-ID pair having a unique term ID and a scientific term. Further, a remove-term file is generated based on one or more term-ID pairs identified from the primary file such that the scientific terms of each term-ID pair corresponds to one of additional terms, frequent scientific terms, and undesirable terms. At least one term-ID pair from among the one or more term-ID pairs is altered to obtain a modified term-ID pair based on modification rules. The modified term-ID pair is added to an add-term file and a modified file is obtained based on the remove-term file and the add-term file. Duplicate term-ID pairs present in the modified file are removed to obtain the dictionary of scientific terms.