Detecting anomalous proteins using deep representations.

Many advances in biomedicine can be attributed to identifying unusual proteins and genes. Many of these proteins' unique properties were discovered by manual inspection, which is becoming infeasible at the scale of modern protein datasets. Here, we propose to tackle this challenge using anomaly detection methods that automatically identify unexpected properties. We adopt a state-of-the-art anomaly detection paradigm from computer vision, to highlight unusual proteins. We generate meaningful representations without labeled inputs, using pretrained deep neural network models. We apply these protein language models (pLM) to detect anomalies in function, phylogenetic families, and segmentation tasks. We compute protein anomaly scores to highlight human prion-like proteins, distinguish viral proteins from their host proteome, and mark non-classical ion/metal binding proteins and enzymes. Other tasks concern segmentation of protein sequences into folded and unstructured regions. We provide candidates for rare functionality (e.g. prion proteins). Additionally, we show the anomaly score is useful in 3D folding-related segmentation. Our novel method shows improved performance over strong baselines and has objectively high performance across a variety of tasks. We conclude that the combination of pLM and anomaly detection techniques is a valid method for discovering a range of global and local protein characteristics.

Disentanglement of single-cell data with biolord.

Biolord is a deep generative method for disentangling single-cell multi-omic data to known and unknown attributes, including spatial, temporal and disease states, used to reveal the decoupled biological signatures over diverse single-cell modalities and biological systems. By virtually shifting cells across states, biolord generates experimentally inaccessible samples, outperforming state-of-the-art methods in predictions of cellular response to unseen drugs and genetic perturbations. Biolord is available at https://github.com/nitzanlab/biolord .

Genetika+: precision medicine solutions for mental health.

Genetika+ is developing a precision medicine tool to optimize the treatment of depression by helping physicians find the best drug therapy for their patients. The tool builds on traditional pharmacogenetics, introducing a 'brain-in-a-dish' screening platform for each patient that will overcome the challenge of limited pharmacodynamic knowledge of pharmacogenetics (PGx). In addition to PGx, our platform integrates patient data with innovative blood-derived patient neurons to test all categories of antidepressants and predict the best drug for each patient. This offers patients optimal drug treatment, allowing a faster response, fewer side effects and lower dosing.

Chip-scale atomic wave-meter enabled by machine learning.

The quest for miniaturized optical wave-meters and spectrometers has accelerated the design of novel approaches in the field. Particularly, random spectrometers (RS) using the one-to-one correlation between the wavelength and an output random interference pattern emerged as a promising tool combining high spectral resolution and cost-effectiveness. Recently, a chip-scale platform for RS has been demonstrated with a markedly reduced footprint. Yet, despite the evident advantages of such modalities, they are very susceptible to environmental fluctuations and require an external calibration process. To address these challenges, we demonstrate a paradigm shift in the field, enabled by the integration of atomic vapor with a photonic chip and the use of a machine learning classification algorithm. Our approach provides a random wave-meter on chip device with accurate calibration and enhanced robustness against environmental fluctuations. The demonstrated device is expected to pave the way toward fully integrated spectrometers advancing the field of silicon photonics.

Unified platform for genetic and serological detection of COVID-19 with single-molecule technology.

The COVID-19 pandemic raises the need for diverse diagnostic approaches to rapidly detect different stages of viral infection. The flexible and quantitative nature of single-molecule imaging technology renders it optimal for development of new diagnostic tools. Here we present a proof-of-concept for a single-molecule based, enzyme-free assay for detection of SARS-CoV-2. The unified platform we developed allows direct detection of the viral genetic material from patients' samples, as well as their immune response consisting of IgG and IgM antibodies. Thus, it establishes a platform for diagnostics of COVID-19, which could also be adjusted to diagnose additional pathogens.

Unified platform for genetic and serological detection of COVID-19 with single-molecule technology.

The COVID-19 pandemic raises the need for diverse diagnostic approaches to rapidly detect different stages of viral infection. The flexible and quantitative nature of single-molecule imaging technology renders it optimal for development of new diagnostic tools. Here we present a proof-of-concept for a single-molecule based, enzyme-free assay for detection of SARS-CoV-2. The unified platform we developed allows direct detection of the viral genetic material from patients' samples, as well as their immune response consisting of IgG and IgM antibodies. Thus, it establishes a platform for diagnostics of COVID-19, which could also be adjusted to diagnose additional pathogens.

Resveratrol Enhances mRNA and siRNA Lipid Nanoparticles Primary CLL Cell Transfection.

Chronic lymphocytic leukemia (CLL) is the most common adult leukemia in Western populations. Therapies such as mRNA and siRNA encapsulated in lipid nanoparticles (LNPs) represent a clinically advanced platform and are utilized for a wide variety of applications. Unfortunately, transfection of RNA into CLL cells remains a formidable challenge and a bottleneck for developing targeted therapies for this disease. Therefore, we aimed to elucidate the barriers to efficient transfection of RNA-encapsulated LNPs into primary CLL cells to advance therapies in the future. To this end, we transfected primary CLL patient samples with mRNA and siRNA payloads encapsulated in an FDA-approved LNP formulation and characterized the transfection. Additionally, we tested the potential of repurposing caffeic acid, curcumin and resveratrol to enhance the transfection of nucleic acids into CLL cells. The results demonstrate that the rapid uptake of LNPs is required for successful transfection. Furthermore, we demonstrate that resveratrol enhances the delivery of both mRNA and siRNA encapsulated in LNPs into primary CLL patient samples, overcoming inter-patient heterogeneity. This study points out the important challenges to consider for efficient RNA therapeutics for CLL patients and advocates the use of resveratrol in combination with RNA lipid nanoparticles to enhance delivery into CLL cells.

RNA Structural Determinants of Optimal Codons Revealed by MAGE-Seq.

Synonymous codon choices at the beginning of genes optimize 5' RNA structures for enhanced translation initiation, but less is known about mechanisms that drive codon optimization downstream within the gene. To understand what determines codon choices across a gene, we generated 12,726 in situ codon mutants in the Escherichia coli essential gene infA and measured their fitness by combining multiplex automated genome engineering mutagenesis with amplicon deep sequencing (MAGE-seq). Correlating predicted 5' RNA structure with fitness revealed that codons even far from the start of the gene are deleterious if they disrupt the native 5' RNA conformation. These long-range structural interactions generate context-dependent rules that constrain codon choices beyond intrinsic codon preferences. Genome-wide RNA folding predictions confirm that natural codon choices far from the start codon are optimized in part to prevent disruption of native structures near the 5' UTR. Our results shed light on natural codon distributions and should improve engineering of gene expression for synthetic biology applications.