International Business Machines Corporation

Leland Stanford Junior University

Shin-etsu Chemical Co., Ltd.

Agency for Science, Technology and Research

Dmitry Zubarev

Nathaniel H Park

James L Hedrick

Victoria A Piunova

Robert M Waymouth

Gavin O Jones

Binhong Lin

Daniel Gruhl

Chandrasekhar Narayan

Alfredo Alba

Linda Ha Kato

Steven R Welch

Chad Eric DeLuca

Petar Ristoski

Anna Lisa Gentile

Yoshio Kawai

Yi Yan Yang

Daniel Sanders

Katsuya Takemura

Masashi Iio

Hiroyuki Urano

Kazuya Honda

Sarathkrishna Swaminathan

Eddy Wei Ping Tan

Mathias B Steiner

Bruce Gordon Elmegreen

Stacey M Gifford

Ronaldo Giro

Kristin Schmidt

David Boaz

Mark Kunitomi

Geeth Ranmal De Mel

Christopher R Gibson

David S Braines

Tim Erdmann

Pedro Luis Arrechea

Flaviu Cipcigan

Mohab Elkaref

Sarath Swaminathan

Maira G De Bayser

Dean Clarke

Lori French

Gowri Nayar

A computational system, which may be an artificial intelligence (AI) system, allows for the electronic representation, modeling, generation, rendering, simulating, and querying of polymeric materials by encoding architectural features as nodes and embedding a directed graph of the polymeric materials within a database system. The embedding of chemical data from multiple nodes within the directed graph data structure enables a scalable data model for containing materials data within computational systems. The computational system may be used for predictive modeling of new polymeric materials and for rendering and/or simulating stochastic polymeric ensembles.

Material representation in computational systems

Candidate material for polymerization can be received. One or more desired features in the candidate material can be identified. A machine learning model can be trained to generate a new material having one or more of the desired features. Permissively, the candidate material can be determined from running a machine learning classification model that ranks a plurality of material as candidates. Permissively, the generated new material can be input to the machine learning classification model, for the machine learning classification model to include in ranking the plurality of material as candidates.

Expert-in-the-loop AI for materials generation

A computer implemented method for generating query results includes generating by a computer processor, a training model through artificial intelligence. The training model is based on annotated data. A knowledge base for a subject matter is generated based on the training model. The knowledge base is based on content from document sources related to the subject matter. A natural language query input is received. An intent and requirements for satisfying the intent is inferred by the computer processor. The knowledge base is referenced to extract information related to the intent and requirements, from documents in the knowledge base. Relationships between the extracted information and the requirements are correlated from the documents in the knowledge base. Query results are displayed to the user. The query results are based on the correlated relationships.

Artificial intelligence based materials discovery building from documents and recommendations

Techniques regarding post polymerization modifications to polycarbonate polymers via a flow reactor are provided. For example, one or more embodiments described herein can comprise a cyclic carbonate monomer that can be employed to facilitate polymerization of one or more polycarbonate platforms susceptible to post polymerization modification. For instance, one or more embodiments can regard a cyclic carbonate molecular backbone covalently bonded to an aryl halide functional group via in accordance with a chemical structure selected from the group consisting of: In the chemical structures, 'R' can be selected from the group consisting of a hydrogen atom and a functional group comprising a first alkyl group; “L” can represent a linkage group, comprising: a second alkyl group and an end group having at least one member selected from the group consisting of an oxygen atom and a nitrogen atom; and “A” can represent the aryl halide functional group.

Post polymerization modification in flow

A set of material candidates expected to yield materials with target properties can be generated. A subject matter expert's decision indicating accepted and rejected material candidates from the set of material candidates can be received. Based on the subject matter expert's input, a machine learning model can be trained to replicate the subject matter expert's decision.

Expert-in-the-loop AI for materials discovery

A method for synthesizing cyclic carbonate monomers using carbon dioxide (CO) is provided. The method also includes combining reagents to synthesize the cyclic carbonate monomer, the reagents including a substrate that is a 1,X-diol, where X is between 2 and 5, a base that is a tertiary amine, a promoter that is a multidentate, bis-tertiary amine base where nitrogens are separated by 2 to 4 carbon atoms, a solvent, and CO.

AI assisted cyclic carbonate monomer synthesis

Techniques regarding the synthesis of one or more polymers through one or more ring-opening polymerizations conducted within a flow reactor and facilitated by one or more anionic catalysts are provided. For example, one or more embodiments can comprise a method, which can comprise polymerizing, via a ring-opening polymerization within a flow reactor, a cyclic monomer in the presence of one or more anionic organocatalysts.

Ring-opening polymerizations using a flow reactor

Techniques regarding the synthesis of one or more polymers of a target polymer class are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a recommendation component that can generate a recommended chemical reactor control setting for inverse synthesis of a polymer based on a target polymer characteristic and reactor training data.

Controlling a chemical reactor for the production of polymer compounds

A method for ranking relevance of documents includes using a set of queries, searching a corpus of documents for a set of candidate documents with information relevant to the set of queries. The method further includes ranking the set of candidate documents by a deep learning processing system according to relevance to respective ones of the set of queries. The method additionally includes responsive to user input, revising the ranked set of candidate documents to produce a revised ranked set of candidate documents. The method further includes using the revised ranked set of candidate documents to retrain the deep learning processing system. The method still further includes performing a categorization of the set of candidate documents by the retrained deep learning processing system.

Cognitive horizon surveillance

A method is described that utilizes non-negative matrix factorization to predict susceptibility of a microorganism to an antimicrobial drug. A sparse adjacency matrix is constructed from existing ground truth datasets that include antibiogram data and other data associated with microorganisms. The rows of the adjacency matrix correspond to biosamples, and the columns correspond to instances of metadata and drugs associated with one or more of the biosamples. The elements of the adjacency matrix are assigned non-zero numerical values or zero depending on whether a known association exists. The adjacency matrix is then factored using a selected number of latent factors, thereby producing a reconstruction matrix approximating the adjacency matrix. The values of the reconstruction matrix are used to predict antimicrobial susceptibility of a biosample ID to a drug when antibiogram data are lacking.

Matrix factorization of antibiogram metadata

Provided is a compound that can be used as a base resin for a photosensitive resin composition. The photosensitive resin can form a fine pattern and can achieve high resolution without impairing mechanical strength and solubility. The compound is represented by the general formula (1): wherein Z represents a linear, branched or cyclic divalent hydrocarbon group having 2 to 30 carbon atoms; Xto Xrepresent any of &#x2014;CO&#x2014;, &#x2014;CONR&#x2014;, &#x2014;O&#x2014;, &#x2014;NR&#x2014;, &#x2014;S&#x2014;, &#x2014;SO&#x2014;, &#x2014;SO&#x2014; and &#x2014;SONR&#x2014; and may be the same as or different from each other, provided that Ris a hydrogen atom or a monovalent hydrocarbon group having 1 to 30 carbon atoms; Ar represents a divalent aromatic group having 2 to 30 carbon atoms; Land Lindependently represent a divalent hydrocarbon group having 1 to 30 carbon atoms; and x and y are each independently 0 or 1.

Compound, polyimide resin and method of producing the same, photosensitive resin composition, patterning method and method of forming cured film, interlayer insulating film, surface protective film, and electronic component

Techniques regarding autonomously controlling one or more chemical reactors using generative machine learning models are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a model component that can build a generative machine learning model based on training data regarding a past chemical reactor operation. The generative machine learning model can generate a recommended chemical reactor control setting for experimental discovery of a polymer.

Generating control settings for a chemical reactor

Techniques regarding post polymerization modifications to polycarbonate polymers via a flow reactor are provided. For example, one or more embodiments described herein can comprise a cyclic carbonate monomer that can be employed to facilitate polymerization of one or more polycarbonate platforms susceptible to post polymerization modification. For instance, one or more embodiments can regard a cyclic carbonate molecular backbone covalently bonded to an aryl halide functional group via in accordance with a chemical structure selected from the group consisting of: In the chemical structures, 'R' can be selected from the group consisting of a hydrogen atom and a functional group comprising a first alkyl group; 'L' can represent a linkage group, comprising: a second alkyl group and an end group having at least one member selected from the group consisting of an oxygen atom and a nitrogen atom; and &#x201c;A&#x201d; can represent the aryl halide functional group.

Provided is a polymer that can be used as a base resin for a positive photosensitive resin composition and a negative photosensitive resin composition, wherein the positive photosensitive resin composition and the negative photosensitive resin composition are soluble in an aqueous alkaline solution, can form a fine pattern, can achieve high resolution, and have good mechanical properties even when they are cured at low temperature. Also provided are a positive photosensitive resin composition and a negative photosensitive resin composition using the polymer. The polymer is represented by general formulas (1) and/or (2): wherein Tand Tmay be the same as, or different from, each other and represent any of &#x2014;CO&#x2014; and &#x2014;SO&#x2014;; Xis a tetravalent organic group; and l is 0 or 1; and Xis a divalent organic group.

Polymer, photosensitive resin composition, patterning method, method of forming cured film, interlayer insulating film, surface protective film, and electronic component

Techniques regarding the synthesis of polyesters and/or polycarbonates through one or more ring-opening polymerizations conducted within a flow reactor and facilitated by a urea anion catalyst and/or a thiourea catalyst are provided. For example, one or more embodiments can comprise a method, which can comprise polymerizing, via a ring-opening polymerization within a flow reactor, a cyclic monomer in the presence an organocatalyst comprising a urea anion.

Growing community of inventors

San Jose, CA, United States of America

Dmitry Zubarev