查看更多>>摘要：2024 FEB 22 (NewsRx) – By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – A patent by the inventors Honnavara-Prasad, Sushma (San Jose, CA, US), filed on November 18, 2020, was published online on February 6, 2024, according to news reporting originating from Alexandria, Virginia, by NewsRx correspondents. Patent number 11892896 is assigned to Groq Inc. (Mountain View, California, United States). The following quote was obtained by the news editors from the background information supplied by the inventors: "The present disclosure relates to optimizing power, and in particular, to power optimization in an artificial intelligence processor. "Power and performance are two critical factors that impact integrated circuits. Achieving higher performance, such as faster processing speeds and lower latencies, for example, are a constant goal. However, higher performance typically comes with a price-increased power consumption. Increased power consumption can lead to a wide range of problems, including heat generation, (in the aggregate) increased costs for electricity, or in extreme cases, system failure.
查看更多>>摘要：2024 FEB 22 (NewsRx) – By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – According to news reporting based on a preprint abstract, our journalists obtained the following quote sourced from biorxiv.org: "Predicting whether a compound can cause drug-induced liver injury (DILI) is difficult due to the complexity of its mechanism. The production of reactive metabolites is one of the major causes of DILI, particularly idiosyncratic DILI. The cysteine trapping assay is one of the methods to detect reactive metabo- lites which bind to microsomes covalently. "However, it is cumbersome to use 35S isotope-labeled cysteine for this assay. Therefore, we constructed an in silico classification model for predicting a positive/negative outcome in the cysteine trapping assay to accelerate the drug discovery process. "In this study, we collected 475 compounds (436 in-house compounds and 39 publicly available drugs). Using a Message Passing Neural Network (MPNN) and Random Forest (RF) with extended connectivity fingerprint (ECFP) 4, we built machine learning models to predict the covalent binding risk of compounds. The 5-fold cross-validation (CV) and hold-out test were evaluated in random- and time-split trials. Ad- ditionally, we investigated the substructures that contributed to positive results in the cysteine trapping assay through the framework of the MPNN model.
NETL
NSTL