14 results about "Binding drugs" patented technology

This invention discloses a method for drug molecule scaffold replacement and screening based on a deep transfer learning model, belonging to the field of computer-aided drug development. The specific steps include: acquiring source and target domain datasets; extracting the molecular scaffolds of corresponding compounds in the source and target domains, as well as the compounds to be screened; pre-training a graph neural network model based on the source domain dataset; inputting the target domain dataset into the pre-trained network model, fine-tuning the network model parameters to obtain new parameters and the model; obtaining small molecule scaffolds based on comprehensive scoring; and replacing the molecular scaffolds to obtain a series of novel molecules. Based on D-MPNN and FNN, this invention introduces a transfer learning approach, combining a dual upstream and downstream strategy of drug target upstream and downstream and transfer learning task upstream and downstream. It extracts and fine-tunes the feature values ​​of the pre-trained network, achieving better training results on small sample datasets, and helping to establish novel molecular scaffold screening and replacement models for upstream and downstream targets with small sample sizes.

The application provides a drug recommendation method and system with continuous training and drug mutual constraint, relates to the technical field of medical health and artificial intelligence, and the method comprises the following steps: acquiring medical data to construct single-disease and multi-disease samples; a first model distribution of diseases and drugs in a single-disease scenario is obtained through self-attention mechanism pre-training; multi-disease samples are continuously iterated as units, a cross-attention mechanism is used to learn the joint influence of multi-disease and surgery on drugs, a drug interaction graph is introduced to calculate a drug conflict rate as a constraint term to construct a loss function to update the model, and a second model distribution is obtained; multi-disease samples are input into the trained model to output drug combination recommendation, and explanatory content is generated in combination with the drug interaction graph; the application learns single-disease correlation through pre-training, and introduces cross-attention and drug conflict rate constraint in continuous training, so that more accurate and safe drug combination recommendation in a multi-disease coexistence scenario is realized.

The present invention provides a fungal drug carrier comprising an avirulent fungal pathogen cell, for example a Cryptococcus neoformans cell, linked to one or more surface-bound drug-loaded nanoparticles, and methods of making the fungal drug carrier. The invention provides methods of using the fungal drug carrier to deliver a drug to the central nervous system of a patient, wherein the fungal drug carrier is phagocytosed by an immune cell of a patient, transported across the blood-brain barrier, and vomocytosed to allow drug release from the surface-bound nanoparticle into the central nervous system of the patient. The methods involve treating a central nervous system in a patient comprising administering to the patient a pharmaceutical composition comprising a fungal drug carrier.

A conjugate drug formulation in the biopharmaceutical field and its manufacturing method and use. The formulation contains a ligand-drug conjugate, a pH adjuster and a freeze-drying excipient. The pH screening is performed on the above-mentioned formulation containing the ligand-drug conjugate, and the pH adjuster and freeze-drying excipient used are limited. At the same time, the administration order and the liquid distribution environment during drug production are considered, and the freeze-drying process parameters are screened, thereby finally achieving the effect of keeping the properties, water content, impurity content, pH value, etc. of the formulation stable during the storage period.

This invention relates to the fields of bioinformatics and artificial intelligence, and proposes a method and system for predicting drug-target interactions based on multimodal feature fusion. The method includes: segmenting and encoding the acquired drug and target sequences to be identified; extracting sub-sequence features of the drug and target respectively; constructing a two-dimensional molecular graph of the drug and a three-dimensional structural graph of the target, and extracting graph structural features of the drug and target respectively; fusing the sub-sequence features and graph structural features of the drug and target through a cross-attention mechanism; and using a bidirectional collaborative attention mechanism for interactive fusion to obtain the predicted binding affinity of the drug and target. This disclosure, by combining multimodal complementary information of the drug and target, deeply explores the deep interactions between different modal features; simultaneously, by introducing a bidirectional collaborative attention mechanism in the interaction modeling of the drug and target, it effectively improves the accuracy of drug-target binding affinity prediction.

The present invention relates to modular linker compounds for target-binding drug conjugates (TBDCs) and in particular to modular linker compounds for antibody-drug-conjugates (ADCs). The modular linker compounds comprise solubility enhancing groups and self-immolative spacers. The invention further relates to methods of synthesizing the modular linker compound, to target-binding drug conjugates comprising the modular linker compound of the invention as well as to pharmaceutical compositions comprising target-binding drug conjugates compound of the invention. Embodiments of the invention have been particularly developed as target-binding drug conjugates for use in the treatment of cancer and will be described hereinafter with reference to this application. However, it will be appreciated that the invention is not limited to this particular field of use.

The application provides an individualized medication method, device, computing equipment and storage medium, wherein the method comprises: collecting personal information of a patient and collecting gene detection data of the patient; prioritizing gene sites contained in the gene detection data, and generating primary medication information based on a prioritization result and a pre-constructed gene-drug guideline database; constructing a blood drug concentration-time curve based on the personal information and the primary medication information; obtaining precise medication information based on the blood drug concentration-time curve and the primary medication information; collecting actual medication information of the patient, adjusting the precise medication information based on the actual medication information, and obtaining target medication information. The application realizes a precision medicine mode of customizing an exclusive medication scheme for a patient based on individual characteristics of the patient, combining a drug-gene correlation rule and a clinical guideline, and achieving one person, one drug and one dose, so that the efficacy is improved and the risk of adverse reactions is reduced.

The present disclosure relates to the field of pharmacy and medicine, in particular to a method for constructing a drug hepatotoxicity prediction model and its application in predicting drug hepatotoxicity, further relates to a method, system and device for predicting drug hepatotoxicity, and further relates to the use of a combination of cell phenotype parameters in predicting drug hepatotoxicity. The method for predicting drug hepatotoxicity provided by the present disclosure can identify the toxicity of a drug to be tested on hepatocytes by performing high-content analysis test experiments on hepatocytes in at least 3 groups (7 parameters) and at most 6 groups (13 parameters), combined with the drug human body exposure C max value, i.e. the toxicity of the drug to be tested on hepatocytes can be identified, and the accuracy of the method can be up to 87%, and the highest sensitivity and specificity are 84% and 94% respectively, which are significantly higher than the reported prediction methods based on HCA or other technologies.

Disclosed herein are systems and methods for releasing controlled drug doses to cells within fluidic channels. In certain aspects, stimuli such are selectively provided to drug-containing substrates or surface-bound drug libraries to release one or more drugs in time, location, and dose-specific manners.

The present invention relates to modular linker compounds for target binding drug conjugates (TBDCs), and in particular to modular linker compounds for antibody-drug conjugates (ADCs). The modular linker compounds comprise a solubilizing group and a self-immolative spacer. The present invention further relates to methods of synthesizing the modular linker compounds, to target binding drug conjugates comprising the modular linker compounds of the present invention, and to pharmaceutical compositions comprising the target binding drug conjugate compounds of the present invention. Embodiments of the present invention are specifically developed for target binding drug conjugates for use in cancer therapy, and will be described hereinafter with reference to the present application. However, it will be appreciated that the present invention is not limited to this particular field of use.

The present invention relates to a medical implant comprising in its interior a device for electrically controllable ad- and desorption of molecules, said device comprising (a) two electrodes comprising a conductive surface, (b) a stationary phase between said two electrodes, wherein said stationary phase is not in direct contact with said electrodes, (c) a controller functionally associated with a power supply configured for applying and changing a voltage between said electrodes, wherein changing the voltage between said electrodes changes the affinity of molecules so as to adsorb said molecules to said stationary phase or desorb molecules from said stationary phase when said molecules are adsorbed to said stationary phase, and the use of said medical implant in the treatment of a medical condition.

The invention relates to the technical field of medical biological information data processing, in particular to a drug efficacy evaluation data analysis method based on multi-dimensional biochemical indexes. The method comprises the following steps: collecting a real-time multi-dimensional biochemical index sequence of an organism to be detected, constructing a discrete time state estimation model and calculating an observation residual error; identifying non-physiological mutation features according to residual statistical distribution by using a three-section weighting function based on a robust estimation theory, and dynamically generating a signal confidence coefficient weight; the noise covariance matrix is observed through confidence coefficient weight reverse expansion, correction of non-physiological interference on state estimation is blocked, and pure physiological trend data are generated; and finally, in combination with the drug metabolism attenuation factor, calculating a deviation degree relative to a drug efficacy evaluation baseline, and generating a drug efficacy score. According to the method, the problem that in a living animal experiment, drug effect evaluation is not accurate due to stress movement is effectively solved, and accurate restoration of the real physiological state of the to-be-tested organism is achieved.

The present invention relates to a pharmaceutical combination comprising: (C) an anti-LY75 antibody, or an antigen-binding portion thereof, wherein the antibody or antigen-binding portion thereof comprises: (c) a variable heavy chain region comprising: (iv) a first vhCDR comprising SEQ ID NO: 5; (v) a second vhCDR comprising SEQ ID NO: 6, and (vi) a third vhCDR comprising SEQ ID NO: 7; and (d) a variable light chain region comprising: (iv) a first vlCDR comprising SEQ ID NO: 8; (v) a second vlCDR comprising SEQ ID NO: 9, and (vi) a third vlCDR comprising SEQ ID NO: 10; wherein the anti-LY75 antibody or antigen-binding portion thereof further comprises a covalently bound drug, wherein the drug is DM4 or DM1; and (D) Venetoclax a pharmaceutically acceptable salt thereof, for use in the treatment of diffuse large B-cell lymphoma (DLBCL) or non-Hodgkin lymphoma in patients.