Summary Brown fat defends against hypothermia and obesity through thermogenesis mediated by mitochondrial UCP1. Recent data suggest that there are two distinct types of brown fat: classical brown fat derived from a myf-5 cellular lineage and UCP1-positive cells that emerge in white fat from a non-myf-5 lineage. Here we report the cloning of “beige” cells from murine white fat depots. Beige cells resemble white fat cells in having extremely low basal expression of UCP1, but like classical brown fat, they respond to cyclic AMP stimulation with high UCP1 expression and respiration rates. Beige cells have a gene expression pattern distinct from either white or brown fat and are preferentially sensitive to the polypeptide hormone irisin. Finally, we show that deposits of brown fat previously observed in adult humans are composed of beige adipose cells. These data illustrate a new cell type with therapeutic potential in mouse and human.

Motivation Drug target interaction (DTI) prediction is a foundational task for in-silico drug discovery, which is costly and time-consuming due to the need of experimental search over large drug compound space. Recent years have witnessed promising progress for deep learning in DTI predictions. However, the following challenges are still open: (1) existing molecular representation learning approaches ignore the sub-structural nature of DTI, thus produce results that are less accurate and difficult to explain; (2) existing methods focus on limited labeled data while ignoring the value of massive unlabelled molecular data. Results We propose a Molecular Interaction Transformer (MolTrans) to address these limitations via: (1) knowledge inspired sub-structural pattern mining algorithm and interaction modeling module for more accurate and interpretable DTI prediction; (2) an augmented transformer encoder to better extract and capture the semantic relations among substructures extracted from massive unlabeled biomedical data. We evaluate MolTrans on real world data and show it improved DTI prediction performance compared to state-of-the-art baselines. Availability The model scripts is available at https://github.com/kexinhuang12345/moltrans. Contact jimeng@illinois.edu Supplementary information Supplementary data are available at Bioinformatics online.

Summary Accurate prediction of drug–target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use DL library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. Availability and implementation https://github.com/kexinhuang12345/DeepPurpose. Contact jimeng@illinois.edu Supplementary information Supplementary data are available at Bioinformatics online.

Clinical notes contain information about patients that goes beyond structured data like lab values and medications. However, clinical notes have been underused relative to structured data, because notes are high-dimensional and sparse. This work develops and evaluates representations of clinical notes using bidirectional transformers (ClinicalBert). Clini-calBert uncovers high-quality relationships between medical concepts as judged by humans. ClinicalBert outperforms baselines on 30-day hospital readmission prediction using both discharge summaries and the first few days of notes in the intensive care unit. Code and model parameters are available. 1

Chemokine (CC motif) receptor-like 2 (CCRL2) binds leukocyte chemoattractant chemerin and can regulate local levels of the attractant, but does not itself support cell migration. In this study, we show that CCRL2 and VCAM-1 are upregulated on cultured human and mouse vascular endothelial cells (EC) and cell lines by proinflammatory stimuli. CCRL2 induction is dependent on NF-κB and JAK/STAT signaling pathways, and activated endothelial cells specifically bind chemerin. In vivo, CCRL2 is constitutively expressed at high levels by lung endothelial cells and at lower levels by liver endothelium; and liver but not lung EC respond to systemic LPS injection by further upregulation of the receptor. Plasma levels of total chemerin are elevated in CCRL2−/− mice and are significantly enhanced after systemic LPS treatment in CCRL2−/− mice compared with wild-type mice. Following acute LPS-induced pulmonary inflammation in vivo, chemokine-like receptor 1 (CMKLR1)+ NK cell recruitment to the airways is significantly impaired in CCRL2−/− mice compared with wild-type mice. In vitro, chemerin binding to CCRL2 on endothelial cells triggers robust adhesion of CMKLR1+ lymphoid cells through an α4β1 integrin/VCAM-1–dependent mechanism. In conclusion, CCRL2 is expressed by EC in a tissue- and activation-dependent fashion, regulates circulating chemerin levels and its bioactivity, and enhances chemerin- and CMKLR1-dependent lymphocyte/EC adhesion in vitro and recruitment to inflamed airways in vivo. Its expression and/or induction on EC by proinflammatory stimuli provide a novel and specific mechanism for the local enrichment of chemerin at inflammatory sites, regulating the recruitment of CMKLR1+ cells.

Cellular response to genetic perturbation is central to numerous biomedical applications from identifying genetic interactions involved in cancer to methods for regenerative medicine. However, the combinatorial explosion in the number of possible multi-gene perturbations severely limits experimental interrogation. Here, we present GEARS, a method that can predict transcriptional response to both single and multi-gene perturbations using single-cell RNA-sequencing data from perturbational screens. GEARS is uniquely able to predict outcomes of perturbing combinations consisting of novel genes that were never experimentally perturbed by leveraging geometric deep learning and a knowledge graph of gene-gene relationships. GEARS has higher precision than existing approaches in predicting five distinct genetic interaction subtypes and can identify the strongest interactions more than twice as well as prior approaches. Overall, GEARS can discover novel phenotypic outcomes to multi-gene perturbations and can thus guide the design of perturbational experiments.

No abstract

BackgroundMonoclonal antibody therapeutics are rapidly gaining in popularity for the treatment of a myriad of diseases, ranging from cancer to autoimmune diseases and neurological diseases. Multiple forms of antibody therapeutics are in use today that differ in the amount of human sequence present in both the constant and variable regions, where antibodies that are more human-like usually have reduced immunogenicity in clinical trials.ResultsHere we present a method to quantify the humanness of the variable region of monoclonal antibodies and show that this method is able to clearly distinguish human and non-human antibodies with excellent specificity. After creating and analyzing a database of human antibody sequences, we conducted an in-depth analysis of the humanness of therapeutic antibodies, and found that increased humanness score is correlated with decreased immunogenicity of antibodies. We further discovered a surprisingly similarity in the immunogenicity of fully human antibodies and humanized antibodies that are more human-like based on their humanness score.ConclusionsOur results reveal that in most cases humanizing an antibody and confirming the humanness of the final form may be sufficient to eliminate immunogenicity issues to the same extent as using fully human antibodies. We created a public website to calculate the humanness score of any input antibody sequence based on our human antibody database. This tool will be of great value during the preclinical drug development process for new monoclonal antibody therapeutics.