-
Nature sub-journal: Land team development of antibody research models based on artificial intelligence technology
Time of Update: 2023-01-06
。 DeepAAI is different from the classical sequence alignment method, but through the method of deep learning "dynamically and adaptively" learning the relationship between unknown antibodies and known antibodies (Adaptive Relation Graph), thereby avoiding the problem of cold start of unknown antibodies by AI algorithms and effectively predicting the neutralization ability of unknown antibodies 。 In addition, DeepAAI also has good explanatory properties and can provide clues for the binding sites of antigens and antibodies.
-
Nature sub-journal: Land team development of antibody research models based on artificial intelligence technology
Time of Update: 2023-01-06
。 DeepAAI is different from the classical sequence alignment method, but through the method of deep learning "dynamically and adaptively" learning the relationship between unknown antibodies and known antibodies (Adaptive Relation Graph), thereby avoiding the problem of cold start of unknown antibodies by AI algorithms and effectively predicting the neutralization ability of unknown antibodies 。 In addition, DeepAAI also has good explanatory properties and can provide clues for the binding sites of antigens and antibodies.
-
Nature Machine Intelligence: Land teams work together to develop antibody research models based on artificial intelligence technology
Time of Update: 2022-11-25
Predicting unseen antibodies' neutralizability via adaptive graph This study proposed for the first time a deep Ab-Ag interaction algorithm (DeepAAI).
-
Nature: Artificial intelligence AI predicts cancer origin and improves the diagnosis of complex metastatic cancer
Time of Update: 2022-11-04
The research team developed an artificial intelligence (AI) system that uses conventional histological sections to accurately find the origin of metastatic tumors and make differential diagnoses of Cancer of Unknown Primary (CUP).
-
Nature Sub-Journal: Artificial intelligence provides a digital biomarker for the diagnosis of Parkinson's disease
Time of Update: 2022-09-14
In the new study, the team developed a new AI-based neural network model for detecting Parkinson's disease, predicting disease severity, and using nighttime breathing ( that is, breathing characteristics during sleep ) to track the progression of the disease over time.
-
Detecting disease through breathing while sleeping...Nature sub-issue: Artificial intelligence
Time of Update: 2022-09-09
In the new study, the team developed a new artificial intelligence-based neural network model for detecting Parkinson's disease, predicting disease severity and tracking disease progression over time using nocturnal breathing, a characteristic of breathing during sleep progress .
-
Peking University Nature Publishes Breakthrough Research Achievement: Artificial Intelligence
Time of Update: 2022-05-12
Molecular machines of life achieve their special functions through highly complex non-equilibrium kinetic processes and structural changes, which are then precisely regulated by various complex interm
-
Mao Youdong's team at Nature Life Center published breakthrough research results - artificial intelligence ..
Time of Update: 2022-05-12
Molecular machines of life achieve their special functions through highly complex non-equilibrium kinetic processes and structural changes, which are then precisely regulated by various complex inte
-
Nature Medicine research shows artificial intelligence can accurately diagnose prostate cancer
Time of Update: 2022-01-22
Kimmo Kartasalo, researcher at the Department of Medical Epidemiology and Biostatistics at Karolinska Institutet and corresponding author of the study, said: "Hosting the Panda Competition demonstrates how the competition can accelerate the solution of specific problems in healthcare with the help of artificial intelligence.
-
"Nature" cover paper: The field of materials is about to be captured by artificial intelligence
Time of Update: 2022-01-05
Using a more extensive, machine learning model-based, quantum-accurate Gaussian Approximate Potential (GAP) molecular dynamics simulation (GAP-MD), the author analyzed a liquid-amorphous system containing 100,000 silicon atoms (ten-nanometer length scale) The state and the amorphous-amorphous transition process have been studied, and its structure, stability and electronic properties have been predicted at the same time .
-
Nature Sub-Journal: Combining artificial intelligence and brain electrical stimulation to improve human brain function
Time of Update: 2021-12-07
In this study, the research team combined artificial intelligence with targeted brain electrical stimulation, showing that precisely directed electrical stimulation can reliably enhance specific human mental functions related to mental illness, and that there are specific sub-capsules in the brain capsule structure.
-
Nature Sub-Journal: To further understand the structure of protein-sugar based on artificial intelligence model
Time of Update: 2021-11-14
Jon AgirreNew research based on artificial intelligence algorithms enables scientists to create more complete models of human protein structures, paving the way for faster design of treatments and vaccines .
-
Nature Sub-Journal: Using Artificial Intelligence to Detect Colorectal Cancer
Time of Update: 2021-11-13
"But the final study showed that when we use artificial intelligence to diagnose colorectal cancer, in many cases, its performance is comparable to, or even better than, a real pathologist .
-
Nature Sub-Journal: Artificial Intelligence Reveals "Important Genes" in Agriculture and Medicine
Time of Update: 2021-09-28
Image source: New York University Cruze Lab"Our research shows that focusing on genes that are evolutionarily conserved across species expression patterns can improve our ability to learn and predict the'important genes' of major crop growth performance and animal disease outcomes," New York University Department of Biology and Genomics and Systems Professor Carroll and Milton Petrie of the Center for Biology, who are also the senior authors of the paper, explained .
-
Nature Sub-Journal: Artificial Intelligence helps to identify single diseased cells
Time of Update: 2021-09-13
The biggest advantage: "The algorithm does not share raw data between clinics or research centers, but uses transfer learning to compare new data sets from single-cell genomics with existing reference materials, thereby protecting privacy and anonymity .