Self-supervised deep language modeling has shown unprecedented success across natural language tasks, and has recently been repurposed to biological sequences. However, existing models and pretraining methods are designed and optimized for text analysis. We introduce ProteinBERT, a deep language model specifically designed for proteins. Our pretraining scheme combines language modeling with a novel task of Gene Ontology (GO) annotation prediction. We introduce novel architectural elements that make the model highly efficient and flexible to long sequences. The architecture of ProteinBERT consists of both local and global representations, allowing end-to-end processing of these types of inputs and outputs. ProteinBERT obtains near state-of-the-art performance, and sometimes exceeds it, on multiple benchmarks covering diverse protein properties (including protein structure, post-translational modifications and biophysical attributes), despite using a far smaller and faster model than competing deep-learning methods. Overall, ProteinBERT provides an efficient framework for rapidly training protein predictors, even with limited labeled data. Code and pretrained model weights are available at https://github.com/nadavbra/protein_bert. Supplementary data are available at Bioinformatics online.

Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease. Knowledge of circulating immune cell types and states associated with SLE remains incomplete. We profiled more than 1.2 million peripheral blood mononuclear cells (162 cases, 99 controls) with multiplexed single-cell RNA sequencing (mux-seq). Cases exhibited elevated expression of type 1 interferon–stimulated genes (ISGs) in monocytes, reduction of naïve CD4 ⁺ T cells that correlated with monocyte ISG expression, and expansion of repertoire-restricted cytotoxic GZMH ⁺ CD8 ⁺ T cells. Cell type–specific expression features predicted case-control status and stratified patients into two molecular subtypes. We integrated dense genotyping data to map cell type–specific cis–expression quantitative trait loci and to link SLE-associated variants to cell type–specific expression. These results demonstrate mux-seq as a systematic approach to characterize cellular composition, identify transcriptional signatures, and annotate genetic variants associated with SLE.

A major bottleneck in our understanding of the molecular underpinnings of life is the assignment of function to proteins. While molecular experiments provide the most reliable annotation of proteins, their relatively low throughput and restricted purview have led to an increasing role for computational function prediction. However, assessing methods for protein function prediction and tracking progress in the field remain challenging. We conducted the second critical assessment of functional annotation (CAFA), a timed challenge to assess computational methods that automatically assign protein function. We evaluated 126 methods from 56 research groups for their ability to predict biological functions using Gene Ontology and gene-disease associations using Human Phenotype Ontology on a set of 3681 proteins from 18 species. CAFA2 featured expanded analysis compared with CAFA1, with regards to data set size, variety, and assessment metrics. To review progress in the field, the analysis compared the best methods from CAFA1 to those of CAFA2. The top-performing methods in CAFA2 outperformed those from CAFA1. This increased accuracy can be attributed to a combination of the growing number of experimental annotations and improved methods for function prediction. The assessment also revealed that the definition of top-performing algorithms is ontology specific, that different performance metrics can be used to probe the nature of accurate predictions, and the relative diversity of predictions in the biological process and human phenotype ontologies. While there was methodological improvement between CAFA1 and CAFA2, the interpretation of results and usefulness of individual methods remain context-dependent.

Bacillus Calmette–Guerin (BCG) is a live attenuated form of Mycobacterium bovis that was developed 100 years ago as a vaccine against tuberculosis (TB) and has been used ever since to vaccinate children globally. It has also been used as the first-line treatment in patients with nonmuscle invasive bladder cancer (NMIBC), through repeated intravesical applications. Numerous studies have shown that BCG induces off-target immune effects in various pathologies. Accumulating data argue for the critical role of the immune system in the course of neurodegenerative diseases such as Alzheimer’s disease (AD) and Parkinson’s disease (PD). In this study, we tested whether repeated exposure to BCG during the treatment of NMIBC is associated with the risk of developing AD and PD. We presented a multi-center retrospective cohort study with patient data collected between 2000 and 2019 that included 12,185 bladder cancer (BC) patients, of which 2301 BCG-treated patients met all inclusion criteria, with a follow-up of 3.5 to 7 years. We considered the diagnosis date of AD and nonvascular dementia cases for BC patients. The BC patients were partitioned into those who underwent a transurethral resection of the bladder tumor followed by BCG therapy, and a disjoint group that had not received such treatment. By applying Cox proportional hazards (PH) regression and competing for risk analyses, we found that BCG treatment was associated with a significantly reduced risk of developing AD, especially in the population aged 75 years or older. The older population (≥75 years, 1578 BCG treated, and 5147 controls) showed a hazard ratio (HR) of 0.726 (95% CI: 0.529–0.996; p-value = 0.0473). While in a hospital-based cohort, BCG treatment resulted in an HR of 0.416 (95% CI: 0.203–0.853; p-value = 0.017), indicating a 58% lower risk of developing AD. The risk of developing PD showed the same trend with a 28% reduction in BCG-treated patients, while no BCG beneficial effect was observed for other age-related events such as Type 2 diabetes (T2D) and stroke. We attributed BCG’s beneficial effect on neurodegenerative diseases to a possible activation of long-term nonspecific immune effects. We proposed a prospective study in elderly people for testing intradermic BCG inoculation as a potential protective agent against AD and PD.

The COVID-19 pandemic that started in China has spread within 3 months to the entire globe. We tested the hypothesis that the vaccination against tuberculosis by Bacille Calmette–Guérin vaccine (BCG) correlates with a better outcome for COVID-19 patients. Our analysis covers 55 countries complying with predetermined thresholds on the population size and number of deaths per million (DPM). We found a strong negative correlation between the years of BCG administration and the DPM along with the progress of the pandemic, corroborated by permutation tests. The results from multivariable regression tests with 23 economic, demographic, health-related, and pandemic restriction-related quantitative properties, substantiate the dominant contribution of BCG years to the COVID-19 outcomes. The analysis of countries according to an age-group partition reveals that the strongest correlation is attributed to the coverage in BCG vaccination of the young population (0–24 years). Furthermore, a strong correlation and statistical significance are associated with the degree of BCG coverage for the most recent 15 years, but no association was observed in these years for other broadly used vaccination protocols for measles and rubella. We propose that BCG immunization coverage, especially among the most recently vaccinated population, contribute to attenuation of the spread and severity of the COVID-19 pandemic.

Electronic health records (EHRs) are quickly becoming omnipresent in healthcare, but interoperability issues and technical demands limit their use for biomedical and clinical research. Interactive and flexible software that interfaces directly with EHR data structured around a common data model (CDM) could accelerate more EHR-based research by making the data more accessible to researchers who lack computational expertise and/or domain knowledge. We present PatientExploreR, an extensible application built on the R/Shiny framework that interfaces with a relational database of EHR data in the Observational Medical Outcomes Partnership CDM format. PatientExploreR produces patient-level interactive and dynamic reports and facilitates visualization of clinical data without any programming required. It allows researchers to easily construct and export patient cohorts from the EHR for analysis with other software. This application could enable easier exploration of patient-level data for physicians and researchers. PatientExploreR can incorporate EHR data from any institution that employs the CDM for users with approved access. The software code is free and open source under the MIT license, enabling institutions to install and users to expand and modify the application for their own purposes. PatientExploreR can be freely obtained from GitHub: https://github.com/BenGlicksberg/PatientExploreR. We provide instructions for how researchers with approved access to their institutional EHR can use this package. We also release an open sandbox server of synthesized patient data for users without EHR access to explore: http://patientexplorer.ucsf.edu. Supplementary data are available at Bioinformatics online.