986results about "Molecular design" patented technology

In various embodiments, the systems and methods described herein relate to generative models. The generative models may be trained using machine learning approaches, with training sets comprising chemical compounds and biological or chemical information that relate to the chemical compounds. Deep learning architectures may be used. In various embodiments, the generative models are used to generate chemical compounds that have desired characteristics, e.g. activity against a selected target. The generative models may be used to generate chemical compounds that satisfy multiple requirements.

A system for analyzing a vast amount of data representative of chemical structure and activity information and concisely providing conclusions about structure-to-activity relationships. A computer may adaptively learn new substructure descriptors based on its analysis of the input data. The computer may then apply each substructure descriptor as a filter to establish new groups of molecules that match the descriptor. From each new group of molecules, the computer may in turn generate one or more additional new groups of molecules. A result of the analysis in an exemplary arrangement is a tree structure that reflects pharmacophoric information and efficiently establishes through lineage what effect on activity various chemical substructures are likely to have. The tree structure can then be applied as a multi-domain classifier, to help a chemist classify test compounds into structural subclasses.

A crystalline composition comprising a crystal of the IL-6 receptor I chain is provided. Also provided are methods of using the crystal and related structural information to screen for and design compounds that interact with IL-6R, or variants thereof. Also provided arc methods of modulating an IL-6 receptor comprising contacting the IL-6 receptor with a compound identified by the screening method of the invention.

Combinations of 5-HT2A inverse agonists or antagonists such as pimavanserin with antipsychotics such as risperidone are shown to induce a rapid onset of antipsychotic action and increase the number of responders when compared to therapy with the antipsychotic alone. These effects can be achieved at a low dose of the antipsychotic, thereby reducing the incidence of side effects. The combinations are also effective at decreases the incidence of weight gain and increased glucose or prolactin levels caused by the antipsychotic.

The present invention relates to enzyme inhibitors. More specifically, the present invention relates to ligand-directed covalent modification of proteins; method of designing same; pharmaceutical formulation of same; and method of use.

Methods for treating cancer using compounds that inhibit human DNA ligases. Methods for using compounds that inhibit human DNA ligases to provide insights into the reaction mechanisms of human DNA ligases, for example to identify the human DNA ligase involved in different DNA repair pathways. Screening methods for compounds that inhibit human DNA ligases.

The invention is an algorithm and method for designing an inhibitor that covalently binds a target polypeptide. The algorithm and method can be used to rapidly and efficiently convert reversible inhibitors into irreversible inhibitors.

The present invention relates to peptides, proteins, nucleic acids and cells for use in immunotherapeutic methods. In particular, the present invention relates to the immunotherapy of cancer. The present invention furthermore relates to tumor-associated T-cell peptide epitopes, alone or in combination with other tumor-associated peptides that can for example serve as active pharmaceutical ingredients of vaccine compositions that stimulate anti-tumor immune responses, or to stimulate T cells ex vivo and transfer into patients. Peptides bound to molecules of the major histocompatibility complex (MHC), or peptides as such, can also be targets of antibodies, soluble T-cell receptors, and other binding molecules.

The present invention provides for the first time a quantum mechanics-based method for scoring protein-ligand interactions and binding affinity predictions, using quantum mechanical Hamiltonians and/or a combined quantum mechanical/molecular mechanical approach, and Poisson-Boltzmann (PB)-based solvation methods. Also provided is a method for using quantum mechanics to describe the enthalpic and solvation effects of binding. The method comprises comparing the calculated binding affinities to experimental values in order to measure the success of the method. The methods disclosed herein may further be used to score protein and drug or protein and inhibitor interactions. The present method can predict the free energy of binding of protein-ligand complexes with high accuracy so as to enable lead optimization, thus serving as a powerful tool in computational drug design.

A computer-based method and system of evolving a virtual molecule with a set of desired properties is described that begins with extracting fragments from existing molecules and labeling those fragments. Connectivity rules existing between the fragments in the existing molecules are determined followed by combining these fragments according to the connectivity rules. The molecules generated by the combination are evaluated and some are selected for modification. The evaluation and modification steps are repeated for the selected molecules until either 1) a target evaluation value is achieved or 2) the evaluation step has been performed a predefined number of times.

A method of designing a material by optimising values for design variables includes the steps of: (i) providing one or more property models that produce a prediction for a value of a respective property of the material as a function of the design variables and produce a value for the uncertainty in the prediction, (ii) setting a specification target for a desired value for each property and a probability for that specification target to be met or exceeded, (iii) determining a probabilistic target for a value for each property, the probabilistic target being based on the specification target and the probability, and defining a merit index factor based on the degree to which a given prediction satisfies the probabilistic target, (iv) constructing an overall merit factor from the individual merit index factors of the properties, and (v) determining a set of optimal design variables that optimise the overall merit factor.

The invention discloses a drug repositioning method based on multi-information fusion and a random walk model. According to the method, disease-target-drug heterogeneous network is constructed through integrating existing disease data, drug data, target data, disease-drug associated data, disease-gene associated data and drug-target associated data; the basic random walk model is extended to the constructed heterogeneous network; and candidate therapeutic drugs are recommended for diseases through effectively utilizing global network information. The method disclosed by the invention is simple and effective; and compared with other methods and proved by tests on a standard data set, the method has good prediction performance in the aspect of drug repositioning.

A method for partitioning a molecular subset is described. The partitioning method takes into account molecular structure and its manner of storage and transmission, transformations to be applied to the molecular subset and their implementation, and constraints imposed by the implementation of the partitioning method. Using this method, a molecular subset can be stored, transmitted, and processed more efficiently. The resulting efficiency makes it possible to design and run applications which require complex molecular processing, such as rational drug discovery, virtual library design, etc.

The present invention relates to methods and antagonist compounds for modulating androgen receptor activity. The invention includes a method for identifying molecules that bind to a coactivator binding site of a receptor in the androgen receptor family. Also included is a cocrystal of an androgen receptor ligand binding domain complexed with a ligand and a coactivator. The invention further includes a method for inhibiting androgen receptor activity in a mammal, thereby facilitating treatment of diseases such as prostate cancer.

Methods of identifying targets for designing a therapeutic agent are disclosed. These methods comprise: determining an amino acid sequence of one or more polypeptides of each isolate of a plurality of isolates of a biological system; identifying covariance pairs of amino acid residues; establishing a network comprising the covariance pairs; and identifying one or more hub residue positions, wherein a hub residue position comprises a target for designing a therapeutic agent if the hub residue position has a rank order in the 40^th percentile or greater. In other aspects, methods are disclosed for selecting a therapy for an infectious disorder. In various configurations, these methods comprise: determining amino acids occupying a plurality of diagnostic amino acid residue positions comprised by one or more polypeptides encoded by an infectious agent infecting a subject; and assigning the infectious agent infecting the subject to one covariance network selected from a plurality of covariance networks, wherein each network comprises a unique rank order of hubs with respect to the other networks, and whereby the therapy is selected on the basis of the covariance network assignment.

The invention discloses a small molecule drug virtual screening method based on deep migration learning and application thereof. A source domain is used as an input to be trained, converged and derived to obtain a weight matrix; a target domain is input into an improvement tool to serve as the initialization weight of the target domain; fine adjustment, training and convergence are conducted on the initialization weight and data in the target domain sequentially; a biological activity value of interaction of a lead compound and a drug target in the target domain is predicted, a target domain molecular fingerprint and a predicted value are obtained, and an evaluation index root mean square error and a correlation coefficient of a predicted result are output; the target domain is subjected to fine adjustment by repeating above steps, and the weight matrix of the source domain helps the target domain build a model. According to the small molecule drug virtual screening method and the application thereof, the effective virtual screening model can still be obtained under the condition that the information of a known active ligand sample is insufficient, and does not need to rely on a large number of data samples.

Business methods for the commercialization of antimicrobial and cytotoxic compounds, including antibiotics and chemotherapeutic agents, are disclosed. According to one embodiment of the invention, drugs that are found to be effective but unsafe at therapeutic dosages are rescued by way of the use of an inhibitor of DNA repair, recombination, or replication, which sensitized microorganisms and cells, thereby permitting their use at a lower and safe dosage. In another embodiment, drugs that are found to be effective but cost prohibitive are rescued by way of the use of an inhibitor of DNA repair, recombination, or replication, thereby permitting their use at lower dosages and costs. A biopharmaceutical company may then, commercialize or charge royalties on such drugs.

Disclosed are pharmacophores for developing and screening compounds having G-protein-coupled receptor antagonist activity, including LPA₁, LPA₂, LPA₃ and S1P antagonists. These compositions have therapeutic benefit in the fields of cancer chemotherapy, cardiovascular disease prevention, and fertility protective agents during radiation and chemotherapy.

The computerized method, software, and product of this invention implements a process for computationally designing proteins and/or associated molecular targets with desired quantitative stability/flexibility relationships (QSFR). QSFR is an innovative, high dimensional metric calculated using an improved Distance Constraint Model (DCM). This invention includes three distinct aspects: (i.) utilizing QSFR in computational molecular design of protein sequences, or variations of molecular structures, to have specific stability and flexibility relationships deemed important for biochemical function for specified thermodynamic and solvent conditions; (ii.) utilizing QSFR to optimize thermodynamic and/or solvent conditions necessary for a specified molecular system to exhibit protein function characteristics, such as improved catalytic efficiency; and (iii.) utilizing QSFR to computationally screen or design small molecules and/or design its putative receptor so as to exhibit a desired affect on protein function.

A method and apparatus for analysis of molecular combinations featuring two or more molecular subsets is described. The method computes the shape complementarity of the system utilizing a basis expansion representing molecular shapes of the first and second molecular subsets in a coordinate system. The precomputed sets of translated expansion coefficients for the first molecular subset are first constructed via application of a translation operator to a reference set of expansion coefficients and then stored on a computer recordable medium for later retrieval. Then a shape complementarity score, representing a correlation of the first and second molecular subsets, is computed via suitable application of rotation operators to both the stored translated expansion coefficients of the first molecular subset, and the reference expansion coefficients for the second molecular subset, over the sequence of different sampled configurations for the molecular combination. The application of a translation operator prior to one or more rotation operator(s) has significant and beneficial implications for hardware-based implementations of the method, embodiments of which in the context of a hardware apparatus will also be described.

The present invention relates to a system and method for engineering and designing a macromolecule. An experimentally determined or de novo atomic structure that corresponds to the macromolecule is identified. The atomic structure is composed of building blocks. When the macromolecule is a peptide or a protein, the building blocks are amino acid residues. A target subset of the building blocks in the atomic structure to be optimized is identified. The coordinates of those building blocks that are not in the target subset are fixed. For each building block in the target subset, a large number of potential conformers is sample d. Each conformer to be sampled is substituted into the atomic structure and tested against an energy function that includes the equivalent energy of the conformer in a reference state. Combinations of conformers that best satisfy an interaction energy function are identified.

A forward synthetic method is described that utilizes recursive application of established organic chemical reactions to derive more complex synthons from available reagents than are available from the reagent synthons themselves. The product of each reaction serves as the starting point for further reactions thereby permitting the generation of multiple complex molecular structures. This synthon generation procedure typically yields 20 ? 30 new structures within the limits of easily accessible syntheses based upon each starting reagent. More complex syntheses yield even more structures. The generated synthons are characterized with a molecular structural descriptor possessing a neighborhood property and can be further characterized with features. The synthons are searched for three dimensional shape and feature similarity to molecular fragments derived from query molecules, typically pharmacological molecules of interest. Identified synthons can be assembled into molecules possessing the same three dimensional shape and likely activity as the molecule of interest.