CodonBert large language model for mRNA vaccines.

mRNA-based vaccines and therapeutics are gaining popularity and usage across a wide range of conditions. One of the critical issues when designing such mRNAs is sequence optimization. Even small proteins or peptides can be encoded by an enormously large number of mRNAs. The actual mRNA sequence can have a large impact on several properties including expression, stability, immunogenicity, and more. To enable the selection of an optimal sequence, we developed CodonBERT, a large language model (LLM) for mRNAs. Unlike prior models, CodonBERT uses codons as inputs which enables it to learn better representations. CodonBERT was trained using more than 10 million mRNA sequences from a diverse set of organisms. The resulting model captures important biological concepts. CodonBERT can also be extended to perform prediction tasks for various mRNA properties. CodonBERT outperforms previous mRNA prediction methods including on a new flu vaccine dataset.

Symbolic recording of signalling and cis-regulatory element activity to DNA.

Measurements of gene expression or signal transduction activity are conventionally performed using methods that require either the destruction or live imaging of a biological sample within the timeframe of interest. Here we demonstrate an alternative paradigm in which such biological activities are stably recorded to the genome. Enhancer-driven genomic recording of transcriptional activity in multiplex (ENGRAM) is based on the signal-dependent production of prime editing guide RNAs that mediate the insertion of signal-specific barcodes (symbols) into a genomically encoded recording unit. We show how this strategy can be used for multiplex recording of the cell-type-specific activities of dozens to hundreds of cis-regulatory elements with high fidelity, sensitivity and reproducibility. Leveraging signal transduction pathway-responsive cis-regulatory elements, we also demonstrate time- and concentration-dependent genomic recording of WNT, NF-κB and Tet-On activities. By coupling ENGRAM to sequential genome editing via DNA Typewriter1, we stably record information about the temporal dynamics of two orthogonal signalling pathways to genomic DNA. Finally we apply ENGRAM to integratively record the transient activity of nearly 100 transcription factor consensus motifs across daily windows spanning the differentiation of mouse embryonic stem cells into gastruloids, an in vitro model of early mammalian development. Although these are proof-of-concept experiments and much work remains to fully realize the possibilities, the symbolic recording of biological signals or states within cells, to the genome and over time, has broad potential to complement contemporary paradigms for how we make measurements in biological systems.

Representations of lipid nanoparticles using large language models for transfection efficiency prediction.

MOTIVATION: Lipid nanoparticles (LNPs) are the most widely used vehicles for mRNA vaccine delivery. The structure of the lipids composing the LNPs can have a major impact on the effectiveness of the mRNA payload. Several properties should be optimized to improve delivery and expression including biodegradability, synthetic accessibility, and transfection efficiency. RESULTS: To optimize LNPs, we developed and tested models that enable the virtual screening of LNPs with high transfection efficiency. Our best method uses the lipid Simplified Molecular-Input Line-Entry System (SMILES) as inputs to a large language model. Large language model-generated embeddings are then used by a downstream gradient-boosting classifier. As we show, our method can more accurately predict lipid properties, which could lead to higher efficiency and reduced experimental time and costs. AVAILABILITY AND IMPLEMENTATION: Code and data links available at: https://github.com/Sanofi-Public/LipoBART.

How DNA encodes the start of transcription.

A deep-learning model reveals the rules that define transcription initiation.

Coronary bypass surgery guided by computed tomography in a low-risk population.

BACKGROUND AND AIMS: In patients with three-vessel disease and/or left main disease, selecting revascularization strategy based on coronary computed tomography angiography (CCTA) has a high level of virtual agreement with treatment decisions based on invasive coronary angiography (ICA). METHODS: In this study, coronary artery bypass grafting (CABG) procedures were planned based on CCTA without knowledge of ICA. The CABG strategy was recommended by a central core laboratory assessing the anatomy and functionality of the coronary circulation. The primary feasibility endpoint was the percentage of operations performed without access to the ICA. The primary safety endpoint was graft patency on 30-day follow-up CCTA. Secondary endpoints included topographical adequacy of grafting, major adverse cardiac and cerebrovascular (MACCE), and major bleeding events at 30 days. The study was considered positive if the lower boundary of confidence intervals (CI) for feasibility was ≥75% (NCT04142021). RESULTS: The study enrolled 114 patients with a mean (standard deviation) anatomical SYNTAX score and Society of Thoracic Surgery score of 43.6 (15.3) and 0.81 (0.63), respectively. Unblinding ICA was required in one case yielding a feasibility of 99.1% (95% CI 95.2%-100%). The concordance and agreement in revascularization planning between the ICA- and CCTA-Heart Teams was 82.9% with a moderate kappa of 0.58 (95% CI 0.50-0.66) and between the CCTA-Heart Team and actual treatment was 83.7% with a substantial kappa of 0.61 (95% CI 0.53-0.68). The 30-day follow-up CCTA in 102 patients (91.9%) showed an anastomosis patency rate of 92.6%, whilst MACCE was 7.2% and major bleeding 2.7%. CONCLUSIONS: CABG guided by CCTA is feasible and has an acceptable safety profile in a selected population of complex coronary artery disease.

How to assess nonresponsiveness to vasodilator stress.

Myocardial perfusion imaging (MPI) is a powerful tool for the functional assessment of ischemia in patients with suspected or known coronary artery disease (CAD). Given that the diagnostic accuracy and prognostic value of MPI and post-test management are highly dependent on achieving an adequate stress vasodilatory response, it is critical to identify those who may not have adequately responded to vasodilator pharmacological stress agents such as adenosine, dipyridamole, and regadenoson. Caffeine, a potent inhibitor of the adenosine receptor, is a compound that can affect vasodilatory hemodynamics, result in false negative studies, and potentially alter management in cases of inaccurate test results. Vasodilator non-responsiveness can be suspected by examining hemodynamics, quantitative positron emission tomography (PET) metrics such as myocardial flow reserve (MFR), and splenic response to stress. Quantitative MFR values of 1-1.2 should raise suspicion for nonresponsiveness in the setting of normal perfusion, along with the absence of a splenic switch off. Newer metrics, such as splenic response ratio, can be used to aid in the identification of potential nonresponders to pharmacologic vasodilators.

Analytical Characterization of Heterogeneities in mRNA-Lipid Nanoparticles Using Sucrose Density Gradient Ultracentrifugation.

Rational design and robust formulation processes are critical for optimal delivery of mRNA by lipid nanoparticles (LNPs). Varying degrees of heterogeneity in mRNA-LNPs can affect their biophysical and functional properties. Given the profound complexity of mRNA-LNPs, it is critical to develop comprehensive and orthogonal analytical techniques for a better understanding of these formulations. To this end, we developed a robust ultracentrifugation method for density-based separation of subpopulations of mRNA-LNPs. Four LNP formulations encapsulating human erythropoietin (hEPO) with varying functionalities were synthesized using two ionizable lipids, A and B, and two helper lipids, 1,2-dioleoyl-sn-glycero-3-phosphoethanolamine (DOPE) and 1,2-dierucoyl-sn-glycero-3-phosphoethanolamine (DEPE), along with cholesterol and DMG-PEG-2K. Upon ultracentrifugation on a sucrose gradient, a distinct pattern of "fractions" was observed across the gradient, from the less dense topmost fraction to the increasingly denser bottom fractions, which were harvested for comprehensive analyses. Parent LNPs, A-DOPE and B-DOPE, were resolved into three density-based fractions, each differing significantly in the hEPO expression following intravenous and intramuscular routes of administration. Parent B-DEPE LNPs resolved into two density-based fractions, with most of the payload and lipid content being attributed to the topmost fraction compared to the lower one, indicating some degree of heterogeneity, while parent A-DEPE LNPs showed remarkable homogeneity, as indicated by comparable in vivo potency, lipid numbers, and particle count among the three density-based fractions. This study is the first to demonstrate the application of density gradient-based ultracentrifugation (DGC) for a head-to-head comparison of heterogeneity as a function of biological performance and biophysical characteristics of parent mRNA-LNPs and their subpopulations.

Quantifying cardiac dysfunction and valvular heart disease associated with subretinal drusenoid deposits in age-related macular degeneration.

BACKGROUND/AIMS: Demonstrate through objective multidisciplinary imaging that subretinal drusenoid deposits (SDDs) in age-related macular degeneration (AMD) are linked to both coexistent valvular heart disease (VHD) and reduced systemic perfusion via cardiac index (CI). METHODS: Post-hoc analysis of cross-sectional study. 200 intermediate AMD (iAMD) subjects were assigned by masked readers to two groups: SDD (with or without drusen) and drusen (only) based on multimodal ophthalmic imaging. 65 transthoracic echocardiograms (TTEs) reports were available for cardiologist evaluation of VHD severity of the four cardiac valves and the presences of precursor lesions of aortic sclerosis (ASc) and mitral annular calcification (MAC). Necessary parameters to calculate CI were also obtained. Univariate testing was performed using Fisher's Exact test and t-test. RESULTS: 82.6% (19/23) of the iAMD subjects with at least one moderate/severe VHD had concurrent SDDs (p = 0.0040). All cases of aortic regurgitation (6/6, p = 0.0370) and mitral regurgitation (13/13, p = 0.0004) were found with coexisting SDDs. Stenotic VHD was not significantly associated with SDDs, however 70.7% of subjects with ASc (29/41, p = 0.0108) and 76.0% of subjects with MAC (19/25, 0.0377) had coexisting SDDs. CI was available in 48 subjects and was significantly below normal levels in the SDD cohort (mean CI SDD 1.95 ± 0.60 L/min/m2, non-SDD 2.71 ± 0.73 L/min/m2, p = 0.0004). CONCLUSIONS: Several specific VHDs have been found associated with the SDD form of AMD. Decreased systemic perfusion as measured by CI was also associated with SDDs, which supports a perfusion hypothesis of SDD pathogenesis. Further research is warranted to understand the relationship between cardiovascular disease and SDDs.

Changes in use of preventive medications after assessment of chest pain by coronary computed tomography angiography: A meta-analysis.

BACKGROUND: Coronary computed tomography angiogram (CCTA) is a crucial tool for diagnosing CAD, but its impact on altering preventive medications is not well-documented. This systematic review aimed to compare changes in aspirin and statin therapy following CCTA and functional stress testing in patients with suspected CAD, and in those underwent CCTA when stratified by the presence/absence of plaque. RESULTS: Eight studies involving 42,812 CCTA patients and 64,118 cardiac stress testing patients were analyzed. Compared to functional testing, CCTA led to 66 â€‹% more changes in statin therapy (pooled RR, 95 â€‹% CI [1.28-2.15]) and a 74 â€‹% increase in aspirin prescriptions (pooled RR, 95 â€‹% CI [1.34-2.26]). For medication modifications based on CCTA results, 13 studies (47,112 patients with statin data) and 11 studies (12,089 patients with aspirin data) were included. Patients with any plaque on CCTA were five times more likely to use or intensify statins compared to those without CAD (pooled RR, 5.40, 95 â€‹% CI [4.16-7.00]). Significant heterogeneity remained, which decreased when stratified by diabetes rates. Aspirin use increased eightfold after plaque detection (pooled RR, 8.94 [95 â€‹% CI, 4.21-19.01]), especially with obstructive plaque findings (pooled RR, 9.41, 95 â€‹% CI [2.80-39.02]). CONCLUSION: In conclusion, CCTA resulted in higher changes in statin and aspirin therapy compared to cardiac stress testing. Detection of plaque by CCTA significantly increased statin and aspirin therapy.

MPRAbase: A Massively Parallel Reporter Assay Database.

Massively parallel reporter assays (MPRAs) represent a set of high-throughput technologies that measure the functional effects of thousands of sequences/variants on gene regulatory activity. There are several different variations of MPRA technology and they are used for numerous applications, including regulatory element discovery, variant effect measurement, saturation mutagenesis, synthetic regulatory element generation or characterization of evolutionary gene regulatory differences. Despite their many designs and uses, there is no comprehensive database that incorporates the results of these experiments. To address this, we developed MPRAbase, a manually curated database that currently harbors 129 experiments, encompassing 17,718,677 elements tested across 35 cell types and 4 organisms. The MPRAbase web interface (http://www.mprabase.com) serves as a centralized user-friendly repository to download existing MPRA data for independent analysis and is designed with the ability to allow researchers to share their published data for rapid dissemination to the community.

CCTA-based CABG SYNTAX Score: a tool to evaluate completeness of coronary segment revascularization after bypass surgery.

To describe the updated coronary computed tomographic angiography (CCTA)-based coronary artery bypass graft (CABG) anatomic SYNTAX Score (aSS) and assess its utility and reproducibility for assessing the completeness of revascularization after CABG. The CCTA-CABG aSS is a visual assessment using CCTA post-CABG which quantifies the failure in effectively grafting stenotic coronary segments, and therefore assesses the completeness of surgical revascularization. It is calculated by subtracting the aSS of successfully anastomosed coronary segments from the aSS of the native coronary tree. The inter-observer reproducibility of the CCTA-CABG aSS was evaluated in 45 consecutive patients with three-vessel disease with or without left main disease who underwent a CCTA 30 days (± 7 days) after CABG. The CCTA-CABG aSS was evaluated in 45 consecutive patients with 117 bypass grafts and 152 anastomoses. The median native coronary aSS was 35.0 [interquartile range (IQR) 27.0-41.0], whilst the median CCTA-CABG aSS was 13.0 (IQR 9.0-20.5). The inter-observer level of agreement for the native coronary aSS and the CCTA-CABG aSS were both substantial with respective Kappas of 0.67 and 0.61. The CCTA-CABG aSS was feasible in all patients who underwent CABG for complex coronary artery disease with substantial inter-observer reproducibility, and therefore can be used to quantify the completeness of revascularization after CABG.

Drug Reaction With Eosinophilia and Systemic Symptoms-Associated Perimyocarditis After Initiation of Anti-tuberculosis Therapy: A Case Report.

A 34-year-old female who was recently placed on anti-tuberculosis medication with rifampin, isoniazid, pyrazinamide, and levofloxacin therapy for suspected tuberculosis reinfection presented with subjective fevers, rash, and generalized fatigue. Labs showed signs of end-organ damage with eosinophilia and leukocytosis. One day later, the patient became hypotensive with a worsening fever, and an electrocardiogram showed new diffuse ST segment elevations with an elevated troponin. An echocardiogram revealed a reduction in ejection fraction with diffuse hypokinesis, and cardiac magnetic resonance imaging (MRI) showed circumferential myocardial edema with subepicardial and pericardial inflammation. Prompt diagnosis of drug reaction with eosinophilia and systemic symptoms (DRESS) syndrome using the European Registry of Severe Cutaneous Adverse Reaction (RegiSCAR) criteria and discontinuation of therapy was initiated. Due to the hemodynamic instability of the patient, the patient was started on systemic corticosteroids and cyclosporine, with the improvement of her symptoms and rash. A skin biopsy was performed, which revealed perivascular lymphocytic dermatitis, consistent with DRESS syndrome. As the patient's ejection fraction improved spontaneously with corticosteroids, the patient was discharged with oral corticosteroids, and a repeat echocardiogram showed full recovery of ejection fraction. Perimyocarditis is a rare complication of DRESS syndrome that is associated with degranulation and the release of cytotoxic agents into myocardial cells. Early discontinuation of offending agents and initiation of corticosteroids are essential to rapid recovery of ejection fraction and improved clinical outcomes. Multimodality imaging, including MRI, should be used to confirm perimyocardial involvement and guide the necessity for mechanical support or transplant. Further research should be on the mortality of DRESS syndrome with and without myocardial involvement, with an increased emphasis on cardiac evaluation in DRESS syndrome.

Uncommon spectral Doppler findings in patients with heart failure.

Spectral Doppler examination is necessary for full hemodynamic assessment of patients with systolic heart failure. It is fully incorporated into comprehensive echocardiographic examination. In this manuscript, we describe two uncommon findings in patients with established severe left ventricular systolic dysfunction: notched aortic regurgitation and merged mitral regurgitation.

Transcription factor binding site orientation and order are major drivers of gene regulatory activity.

The gene regulatory code and grammar remain largely unknown, precluding our ability to link phenotype to genotype in regulatory sequences. Here, using a massively parallel reporter assay (MPRA) of 209,440 sequences, we examine all possible pair and triplet combinations, permutations and orientations of eighteen liver-associated transcription factor binding sites (TFBS). We find that TFBS orientation and order have a major effect on gene regulatory activity. Corroborating these results with genomic analyses, we find clear human promoter TFBS orientation biases and similar TFBS orientation and order transcriptional effects in an MPRA that tested 164,307 liver candidate regulatory elements. Additionally, by adding TFBS orientation to a model that predicts expression from sequence we improve performance by 7.7%. Collectively, our results show that TFBS orientation and order have a significant effect on gene regulatory activity and need to be considered when analyzing the functional effect of variants on the activity of these sequences.

Massively parallel characterization of transcriptional regulatory elements in three diverse human cell types.

The human genome contains millions of candidate cis-regulatory elements (CREs) with cell-type-specific activities that shape both health and myriad disease states. However, we lack a functional understanding of the sequence features that control the activity and cell-type-specific features of these CREs. Here, we used lentivirus-based massively parallel reporter assays (lentiMPRAs) to test the regulatory activity of over 680,000 sequences, representing a nearly comprehensive set of all annotated CREs among three cell types (HepG2, K562, and WTC11), finding 41.7% to be functional. By testing sequences in both orientations, we find promoters to have significant strand orientation effects. We also observe that their 200 nucleotide cores function as non-cell-type-specific 'on switches' providing similar expression levels to their associated gene. In contrast, enhancers have weaker orientation effects, but increased tissue-specific characteristics. Utilizing our lentiMPRA data, we develop sequence-based models to predict CRE function with high accuracy and delineate regulatory motifs. Testing an additional lentiMPRA library encompassing 60,000 CREs in all three cell types, we further identified factors that determine cell-type specificity. Collectively, our work provides an exhaustive catalog of functional CREs in three widely used cell lines, and showcases how large-scale functional measurements can be used to dissect regulatory grammar.

The genetic and biochemical determinants of mRNA degradation rates in mammals.

BACKGROUND: Degradation rate is a fundamental aspect of mRNA metabolism, and the factors governing it remain poorly characterized. Understanding the genetic and biochemical determinants of mRNA half-life would enable more precise identification of variants that perturb gene expression through post-transcriptional gene regulatory mechanisms. RESULTS: We establish a compendium of 39 human and 27 mouse transcriptome-wide mRNA decay rate datasets. A meta-analysis of these data identified a prevalence of technical noise and measurement bias, induced partially by the underlying experimental strategy. Correcting for these biases allowed us to derive more precise, consensus measurements of half-life which exhibit enhanced consistency between species. We trained substantially improved statistical models based upon genetic and biochemical features to better predict half-life and characterize the factors molding it. Our state-of-the-art model, Saluki, is a hybrid convolutional and recurrent deep neural network which relies only upon an mRNA sequence annotated with coding frame and splice sites to predict half-life (r=0.77). The key novel principle learned by Saluki is that the spatial positioning of splice sites, codons, and RNA-binding motifs within an mRNA is strongly associated with mRNA half-life. Saluki predicts the impact of RNA sequences and genetic mutations therein on mRNA stability, in agreement with functional measurements derived from massively parallel reporter assays. CONCLUSIONS: Our work produces a more robust ground truth for transcriptome-wide mRNA half-lives in mammalian cells. Using these revised measurements, we trained Saluki, a model that is over 50% more accurate in predicting half-life from sequence than existing models. Saluki succinctly captures many of the known determinants of mRNA half-life and can be rapidly deployed to predict the functional consequences of arbitrary mutations in the transcriptome.

High-throughput characterization of the role of non-B DNA motifs on promoter function.

lternative DNA conformations, termed non-B DNA structures, can affect transcription, but the underlying mechanisms and their functional impact have not been systematically characterized. Here, we used computational genomic analyses coupled with massively parallel reporter assays (MPRAs) to show that certain non-B DNA structures have a substantial effect on gene expression. Genomic analyses found that non-B DNA structures at promoters harbor an excess of germline variants. Analysis of multiple MPRAs, including a promoter library specifically designed to perturb non-B DNA structures, functionally validated that Z-DNA can significantly affect promoter activity. We also observed that biophysical properties of non-B DNA motifs, such as the length of Z-DNA motifs and the orientation of G-quadruplex structures relative to transcriptional direction, have a significant effect on promoter activity. Combined, their higher mutation rate and functional effect on transcription implicate a subset of non-B DNA motifs as major drivers of human gene-expression-associated phenotypes.

Effective gene expression prediction from sequence by integrating long-range interactions.

How noncoding DNA determines gene expression in different cell types is a major unsolved problem, and critical downstream applications in human genetics depend on improved solutions. Here, we report substantially improved gene expression prediction accuracy from DNA sequences through the use of a deep learning architecture, called Enformer, that is able to integrate information from long-range interactions (up to 100 kb away) in the genome. This improvement yielded more accurate variant effect predictions on gene expression for both natural genetic variants and saturation mutagenesis measured by massively parallel reporter assays. Furthermore, Enformer learned to predict enhancer-promoter interactions directly from the DNA sequence competitively with methods that take direct experimental data as input. We expect that these advances will enable more effective fine-mapping of human disease associations and provide a framework to interpret cis-regulatory evolution.

Cardiac amyloidosis: diagnostic challenges and recent advancement in the treatment of transthyretin amyloidosis (ATTR).

ATTR-CA is an under-reported cause of congestive heart failure (CHF) and cardiac arrhythmias. Heightened clinical suspicion along with a multimodal investigative approach is often required in diagnosing this potentially fatal condition. Tafamidis and inotersen have shown promising results in terms of progression-free survival by ameliorating CHF symptoms and peripheral neuropathies in clinical trials. In this case series of five patients, we present three wild-type cardiac amyloidosis (ATTRwt-CA), one familial cardiac amyloidosis (ATTRm-CA) and one primary cardiac (AL-CA). The diagnostic modality was different for each patient. ATTRwt-CA, ATTRm-CA and AL-CA patients received tafamidis, inotersen and chemotherapy with bone marrow stem-cell transplantation, respectively.