Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions (preprint)

Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations. These are all among the core problems in the RNA field. With the rapid growth of sequencing technology, we have accumulated a massive amount of unannotated RNA sequences. On the other hand, expensive experimental observatory results in only limited numbers of annotated data and 3D structures. Hence, it is still challenging to design computational methods for predicting their structures and functions. The lack of annotated data and systematic study causes inferior performance. To resolve the issue, we propose a novel RNA foundation model (RNA-FM) to take advantage of all the 23 million non-coding RNA sequences through self-supervised learning. Within this approach, we discover that the pre-trained RNA-FM could infer sequential and evolutionary information of non-coding RNAs without using any labels. Furthermore, we demonstrate RNA-FM’s effectiveness by applying it to the downstream secondary/3D structure prediction, SARS-CoV-2 genome structure and evolution prediction, protein-RNA binding preference modeling, and gene expression regulation modeling. The comprehensive experiments show that the proposed method improves the RNA structural and functional modelling results significantly and consistently. Despite only being trained with unlabelled data, RNA-FM can serve as the foundational model for the field.

Changes in air pollutants during the COVID-19 lockdown in Beijing: Insights from a machine-learning technique and implications for future control policy

The COVID-19 lockdowns led to abrupt reductions in human-related emissions worldwide and had an unintended impact on air quality improvement. However, quantifying this impact is difficult as meteorological conditions may mask the real effect of changes in emissions on the observed concentrations of pollutants. Based on the air quality and meteorological data at 35 sites in Beijing from 2015 to 2020, a machine learning technique was applied to decouple the impacts of meteorology and emissions on the concentrations of air pollutants. The results showed that the real (“deweathered”) concentrations of air pollutants (expect for O3) dropped significantly due to lockdown measures. Compared with the scenario without lockdowns (predicted concentrations), the observed values of PM2.5, PM10, SO2, NO2 and CO during lockdowns decreased by 39.4%, 50.1%, 51.8%, 43.1% and 35.1%, respectively. In addition, a significant decline for NO2 and CO was found at the background sites (51% and 37.8%) rather than the transport sites (37.1% and 35.5%), which is different from the common belief. While the primary emissions reduced during the lockdown period, episodic haze events still occurred due to unfavorable meteorological conditions. Thus, developing an optimized strategy to tackle air pollution in Beijing is essential in the future. 摘要 基于2015–2020年北京35个环境空气站和20个气象站观测资料, 应用机器学习方法 (随机森林算法) 分离了气象条件和源排放对大气污染物浓度的影响.结果发现, 为应对疫情采取的隔离措施使北京2020年春节期间大气污染物浓度降低了35.1%–51.8%;其中, 背景站氮氧化物和一氧化碳浓度的降幅最大, 超过了以往报道较多的交通站点.同时, 2020年春节期间的气象条件不利于污染物扩散, 导致多次霾污染事件发生.为进一步改善北京空气质量, 未来需要优化减排策略. 关键词 机器学习;大气污染;去气象化;COVID-19;减排策略

Cardiac Troponin I Associated with Poor Prognosis and Death Risk in 726 Severe and Critical COVID-19 Patients: A Retrospective Cohort Study (preprint)

Background: A few patients with coronavirus disease 2019 (COVID-19) may progress into irreparable outcomes. Early identification of patients with serious symptoms who may develop critical illness and even death is of considerable importance for personalizing treatment and balancing medical resources.Methods: In this retrospective study, demographic, clinical characteristics and laboratory tests from 726 patients with serious COVID-19 from Tongji Hospital (Wuhan, China) were analyzed. The standards for the serious type are guided by the Chinese management guideline for COVID-19. Patients were classified into critical group (174 cases) and severe group (552 cases) based on whether the composite endpoint was reached, and the former group was divided into the survivors (47 cases) and non-survivors (127 cases). Univariable and multivariable logistic regression and receiver operating characteristic (ROC) curve analysis were performed to investigate the risk factors associated with poor prognosis and mortality outcomes.Results: Male patients accounted for 62.1% and 51.6% in the critical group and severe group, with a median age of 68 and 65 years, respectively. Among critical cases there was a higher prevalence of chronic obstructive lung disease (p = 0.029) and chest distress (p = 0.040) than in severe cases. In the multivariable analysis, the risk factors associated with poor prognosis in severe cases were advanced age (p = 0.002), high respiratory rate (RR) (p < 0.0001), high lactate dehydrogenase (LDH) level (p = 0.021), high hypersensitive cardiac troponin I (hs-cTnI) level (p < 0.0001), and low platelet counts (p = 0.005) at admission. In the adjusted models, higher mortality outcomes in critical patients were associated with high hs-cTnI level (p = 0.037). By plotting ROC curves of different indices, hs-cTnI and LDH were found to be predictive factors for poor prognosis in patients with severe COVID-19.Conclusions: For the risk assessment of serious COVID-19 patients on admission, advanced age, high level of RR, LDH, hs-cTnI, and low platelet counts, constitute important risk factors for poor prognosis in severe cases, and the hs-cTnI level can be helpful in predicting fatal outcomes in critically ill patients.

Structure of human steroid 5α-reductase 2 with anti-androgen drug finasteride (preprint)

Human steroid 5α-reductase 2 (SRD5α2) as a critical integral membrane enzyme in steroid metabolism catalyzes testosterone to dihydrotestosterone. Mutations on its gene have been linked to 5α-reductase deficiency and prostate cancer. Finasteride and dutasteride as SRD5α2 inhibitors are widely used anti-androgen drugs for benign prostate hyperplasia, which have recently been indicated in the treatment of COVID-19. The molecular mechanisms underlying enzyme catalysis and inhibition remained elusive for SRD5α2 and other eukaryotic integral membrane steroid reductases due to a lack of structural information. Here, we report a crystal structure of human SRD5α2 at 2.8 Å revealing a unique 7-TM structural topology and an intermediate adduct of finasteride and NADPH as NADP-dihydrofinasteride in a largely enclosed binding cavity inside the membrane. Structural analysis together with computational and mutagenesis studies reveals molecular mechanisms for the 5α-reduction of testosterone and the finasteride inhibition involving residues E57 and Y91. Molecular dynamics simulation results indicate high conformational dynamics of the cytosolic region regulating the NADPH/NADP+ exchange. Mapping disease-causing mutations of SRD5α2 to our structure suggests molecular mechanisms for their pathological effects. Our results offer critical structural insights into the function of integral membrane steroid reductases and will facilitate drug development.