A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space.

Transformers are widely used deep learning architectures. Existing transformers are mostly designed for sequences (texts or time series), images or videos, and graphs. This paper proposes a novel transformer model for massive (up to a million) point samples in continuous space.

Fusing remote sensing data with spatiotemporal in situ samples for red tide (Karenia brevis) detection.

We present a novel method for detecting red tide (Karenia brevis) blooms off the west coast of Florida, driven by a neural network classifier that combines remote sensing data with spatiotemporally distributed in situ sample data. The network detects blooms over a 1-km grid, using seven ocean color features from the MODIS-Aqua satellite platform (2002-2021) and in situ sample data collected by the Florida Fish and Wildlife Conservation Commission and its partners. Model performance was demonstrably enhanced by two key innovations: depth normalization of satellite features and encoding of an in situ feature.

An optimized purification protocol for enzymatically synthesized S-adenosyl-L-methionine (SAM) for applications in solution state infrared spectroscopic studies.

S-adenosyl-L-methionine (SAM) is an abundant biomolecule used by methyltransferases to regulate a wide range of essential cellular processes such as gene expression, cell signaling, protein functions, and metabolism. Despite considerable effort, there remain many specificity challenges associated with designing small molecule inhibitors for methyltransferases, most of which exhibit off-target effects. Interestingly, NMR evidence suggests that SAM undergoes conformeric exchange between several states when free in solution.

Interpretable HER2 scoring by evaluating clinical guidelines through a weakly supervised, constrained deep learning approach.

The evaluation of the Human Epidermal growth factor Receptor-2 (HER2) expression is an important prognostic biomarker for breast cancer treatment selection. However, HER2 scoring has notoriously high interobserver variability due to stain variations between centers and the need to estimate visually the staining intensity in specific percentages of tumor area. In this paper, focusing on the interpretability of HER2 scoring by a pathologist, we propose a semi-automatic, two-stage deep learning approach that directly evaluates the clinical HER2 guidelines defined by the American Society of Clinical Oncology/ College of American Pathologists (ASCO/CAP).

Measuring the Enthalpy of an Individual Hydrogen Bond in a DNA Duplex with Nucleobase Isotope Editing and Variable-Temperature Infrared Spectroscopy.

The level of interest in probing the strength of noncovalent interactions in DNA duplexes is high, as these weak forces dictate the range of suprastructures the double helix adopts under different conditions, in turn directly impacting the biological functions and industrial applications of duplexes that require making and breaking them to access the genetic code. However, few experimental tools can measure these weak forces embedded within large biological suprastructures in the native solution environment. Here, we develop experimental methods for detecting the presence of a single noncovalent interaction [a hydrogen bond (H-bond)] within a large DNA duplex in solution and measure its formation enthalpy (Δ).

Can AI predict epithelial lesion categories via automated analysis of cervical biopsies: The TissueNet challenge?

The French Society of Pathology (SFP) organized its first data challenge in 2020 with the help of the Health Data Hub (HDH). The organization of this event first consisted of recruiting nearly 5000 cervical biopsy slides obtained from 20 pathology centers. After ensuring that patients did not refuse to include their slides in the project, the slides were anonymized, digitized, and annotated by expert pathologists, and finally uploaded to a data challenge platform for competitors from around the world.

Mitosis domain generalization in histopathology images - The MIDOG challenge.

The density of mitotic figures (MF) within tumor tissue is known to be highly correlated with tumor proliferation and thus is an important marker in tumor grading. Recognition of MF by pathologists is subject to a strong inter-rater bias, limiting its prognostic value. State-of-the-art deep learning methods can support experts but have been observed to strongly deteriorate when applied in a different clinical environment.

Treatment of Hepatitis C Infection in an Internal Medicine Residency Continuity Clinic: Resident Perspectives and Patient Outcomes.

Introduction: Studies have demonstrated that primary care clinicians can achieve the same excellent outcomes in treatment of hepatitis C (HCV) infection as specialist physicians but there is a dearth of literature on experiences and outcomes of treatment of HCV infection in residency clinics. We sought to describe the perspectives of internal medicine resident physicians in one community-based residency program toward treating HCV infection before and after launching treatment of HCV infection within the residency clinic. Further, this study examined outcomes of patients treated by the resident physicians.

Recommendations on compiling test datasets for evaluating artificial intelligence solutions in pathology.

Artificial intelligence (AI) solutions that automatically extract information from digital histology images have shown great promise for improving pathological diagnosis. Prior to routine use, it is important to evaluate their predictive performance and obtain regulatory approval. This assessment requires appropriate test datasets.

A Partial Label-Based Machine Learning Approach For Cervical Whole-Slide Image Classification: The Winning TissueNet Solution.

Cervical cancer is the fourth most common cancer in women worldwide. To determine early treatment for patients, it is critical to accurately classify the cervical intraepithelial lesion status based on a microscopic biopsy. Lesion classification is a 4-class problem, with biopsies being designated as benign or increasingly malignant as class 1-3, with 3 being invasive cancer.

On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types: Chronicles of the MEMENTO challenge.

Diffusion MRI (dMRI) has become an invaluable tool to assess the microstructural organization of brain tissue. Depending on the specific acquisition settings, the dMRI signal encodes specific properties of the underlying diffusion process. In the last two decades, several signal representations have been proposed to fit the dMRI signal and decode such properties.

Probing the Hydrogen-Bonding Environment of Individual Bases in DNA Duplexes with Isotope-Edited Infrared Spectroscopy.

Measuring the strength of the hydrogen bonds between DNA base pairs is of vital importance for understanding how our genetic code is physically accessed and recognized in cells, particularly during replication and transcription. Therefore, it is important to develop probes for these key hydrogen bonds (H-bonds) that dictate events critical to cellular function, such as the localized melting of DNA. The vibrations of carbonyl bonds are well-known probes of their H-bonding environment, and their signals can be observed with infrared (IR) spectroscopy.

Mutations of the Transcriptional Corepressor ZMYM2 Cause Syndromic Urinary Tract Malformations.

Congenital anomalies of the kidney and urinary tract (CAKUT) constitute one of the most frequent birth defects and represent the most common cause of chronic kidney disease in the first three decades of life. Despite the discovery of dozens of monogenic causes of CAKUT, most pathogenic pathways remain elusive. We performed whole-exome sequencing (WES) in 551 individuals with CAKUT and identified a heterozygous de novo stop-gain variant in ZMYM2 in two different families with CAKUT.

Homozygous 15q13.3 microdeletion in a child with hypotonia and impaired vision: A new report and review of the literature.

Although there are numerous reports of heterozygous 15q13.3 microdeletion, homozygous 15q13.3 microdeletion is rare.

The Dmipy Toolbox: Diffusion MRI Multi-Compartment Modeling and Microstructure Recovery Made Easy.

Non-invasive estimation of brain microstructure features using diffusion MRI (dMRI)-known as Microstructure Imaging-has become an increasingly diverse and complicated field over the last decades. Multi-compartment (MC)-models, representing the measured diffusion signal as a linear combination of signal models of distinct tissue types, have been developed in many forms to estimate these features. However, a generalized implementation of MC-modeling as a whole, providing deeper insights in its capabilities, remains missing.

Structural and Functional Characterization of Sulfonium Carbon-Oxygen Hydrogen Bonding in the Deoxyamino Sugar Methyltransferase TylM1.

The N-methyltransferase TylM1 from Streptomyces fradiae catalyzes the final step in the biosynthesis of the deoxyamino sugar mycaminose, a substituent of the antibiotic tylosin. The high-resolution crystal structure of TylM1 bound to the methyl donor S-adenosylmethionine (AdoMet) illustrates a network of carbon-oxygen (CH···O) hydrogen bonds between the substrate's sulfonium cation and residues within the active site. These interactions include hydrogen bonds between the methyl and methylene groups of the AdoMet sulfonium cation and the hydroxyl groups of Tyr14 and Ser120 in the enzyme.

Reducing the number of samples in spatiotemporal dMRI acquisition design.

Purpose: Acquisition time is a major limitation in recovering brain white matter microstructure with diffusion magnetic resonance imaging. The aim of this paper is to bridge the gap between growing demands on spatiotemporal resolution of diffusion signal and the real-world time limitations. The authors introduce an acquisition scheme that reduces the number of samples under adjustable quality loss.

Water-Mediated Carbon-Oxygen Hydrogen Bonding Facilitates S-Adenosylmethionine Recognition in the Reactivation Domain of Cobalamin-Dependent Methionine Synthase.

The C-terminal domain of cobalamin-dependent methionine synthase (MetH) has an essential role in catalyzing the reactivation of the enzyme following the oxidation of its cobalamin cofactor. This reactivation occurs through reductive methylation of the cobalamin using S-adenosylmethionine (AdoMet) as the methyl donor. Herein, we examine the molecular recognition of AdoMet by the MetH reactivation domain utilizing structural, biochemical, and computational approaches.

Non-parametric graphnet-regularized representation of dMRI in space and time.

Effective representation of the four-dimensional diffusion MRI signal - varying over three-dimensional q-space and diffusion time τ - is a sought-after and still unsolved challenge in diffusion MRI (dMRI). We propose a functional basis approach that is specifically designed to represent the dMRI signal in this qτ-space. Following recent terminology, we refer to our qτ-functional basis as "qτ-dMRI".

Diffusion MRI microstructure models with in vivo human brain Connectome data: results from a multi-group comparison.

A large number of mathematical models have been proposed to describe the measured signal in diffusion-weighted (DW) magnetic resonance imaging (MRI). However, model comparison to date focuses only on specific subclasses, e.g.

MAPL: Tissue microstructure estimation using Laplacian-regularized MAP-MRI and its application to HCP data.

The recovery of microstructure-related features of the brain's white matter is a current challenge in diffusion MRI. To robustly estimate these important features from multi-shell diffusion MRI data, we propose to analytically regularize the coefficient estimation of the Mean Apparent Propagator (MAP)-MRI method using the norm of the Laplacian of the reconstructed signal. We first compare our approach, which we call MAPL, with competing, state-of-the-art functional basis approaches.

Sulfur-Oxygen Chalcogen Bonding Mediates AdoMet Recognition in the Lysine Methyltransferase SET7/9.

Recent studies have demonstrated that carbon-oxygen (CH···O) hydrogen bonds have important roles in S-adenosylmethionine (AdoMet) recognition and catalysis in methyltransferases. Here, we investigate noncovalent interactions that occur between the AdoMet sulfur cation and oxygen atoms in methyltransferase active sites. These interactions represent sulfur-oxygen (S···O) chalcogen bonds in which the oxygen atom donates a lone pair of electrons to the σ antibonding orbital of the AdoMet sulfur atom.

Sparse Reconstruction Challenge for diffusion MRI: Validation on a physical phantom to determine which acquisition scheme and analysis method to use?

Diffusion magnetic resonance imaging (dMRI) is the modality of choice for investigating in-vivo white matter connectivity and neural tissue architecture of the brain. The diffusion-weighted signal in dMRI reflects the diffusivity of water molecules in brain tissue and can be utilized to produce image-based biomarkers for clinical research. Due to the constraints on scanning time, a limited number of measurements can be acquired within a clinically feasible scan time.

Improving Fiber Alignment in HARDI by Combining Contextual PDE Flow with Constrained Spherical Deconvolution.

We propose two strategies to improve the quality of tractography results computed from diffusion weighted magnetic resonance imaging (DW-MRI) data. Both methods are based on the same PDE framework, defined in the coupled space of positions and orientations, associated with a stochastic process describing the enhancement of elongated structures while preserving crossing structures. In the first method we use the enhancement PDE for contextual regularization of a fiber orientation distribution (FOD) that is obtained on individual voxels from high angular resolution diffusion imaging (HARDI) data via constrained spherical deconvolution (CSD).