Download full-text PDF

Source
http://dx.doi.org/10.1038/scientificamerican0800-62DOI Listing

Publication Analysis

Top Keywords

universe's unseen
4
unseen dimensions
4
universe's
1
dimensions
1

Similar Publications

Accurate prediction of chlorophyll- (Chl-) concentrations, a key indicator of eutrophication, is essential for the sustainable management of lake ecosystems. This study evaluated the performance of Kolmogorov-Arnold Networks (KANs) along with three neural network models (MLP-NN, LSTM, and GRU) and three traditional machine learning tools (RF, SVR, and GPR) for predicting time-series Chl- concentrations in large lakes. Monthly remote-sensed Chl- data derived from Aqua-MODIS spanning September 2002 to April 2024 were used.

View Article and Find Full Text PDF

A foundation model of transcription across human cell types.

Nature

January 2025

Program of Mathematical Genomics, Department of Systems Biology, Columbia University, New York, NY, USA.

Transcriptional regulation, which involves a complex interplay between regulatory sequences and proteins, directs all biological processes. Computational models of transcription lack generalizability to accurately extrapolate to unseen cell types and conditions. Here we introduce GET (general expression transformer), an interpretable foundation model designed to uncover regulatory grammars across 213 human fetal and adult cell types.

View Article and Find Full Text PDF

Background: Subtle uterine lesions are abnormal intracavitary conditions that, while not causing significant anatomical changes, can adversely impact fertility. Identifying these "subtle" lesions is challenging due to arbitrary interpretation, varied management strategies, unclear clinical significance, and insufficient clinician training in recognizing them. Hysteroscopy offers direct visualization and the capacity to obtain targeted biopsies, making it an invaluable tool for the diagnosis and treatment of these often overlooked conditions.

View Article and Find Full Text PDF

Immunohistochemistry (IHC) is the common companion diagnostics in targeted therapies. However, quantifying protein expressions in IHC images present a significant challenge, due to variability in manual scoring and inherent subjective interpretation. Deep learning (DL) offers a promising approach to address these issues, though current models require extensive training for each cancer and IHC type, limiting the practical application.

View Article and Find Full Text PDF

The SARS-CoV-2 pandemic alerted the potential for significant harm due to future cross-species transmission of various animal coronaviruses to human. There is a significant need of antibody-based drugs to treat patients infected with previously unseen coronaviruses. In this study, we generated CV804, an antibody that binds to the S2 domain of SARS-CoV-2 spike protein, which is highly conserved across the coronavirus family and less susceptible to mutations.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!