Discovery of new senolytics using machine learning (preprint)

Cellular senescence is a stress response characterised by a permanent cell cycle arrest and a proinflammatory secretome. In addition to its tumour suppressor role, senescence is involved in ageing and promotes many disease processes such as cancer, type 2 diabetes, osteoarthritis, and SARS-CoV-2 infection. There is a growing interest in therapies based on targeted elimination of senescent cells, yet so far only a few such senolytics are known, partly due to the poor grasp of the molecular mechanisms that control the senescence survival programme. Here we report a highly effective machine learning pipeline for the discovery of senolytic compounds. Using solely published data, we trained machine learning algorithms to classify compounds according to their senolytic action. Models were trained on as few as 58 known senolytics against a background of FDA-approved compounds or in late-stage clinical development (2,523 in total). We computationally screened various chemical libraries and singled out top candidates for validation in human lung fibroblasts (IMR90) and lung adenocarcinoma (A549) cell lines. This led to the discovery of three novel senolytics: ginkgetin, oleandrin and periplocin, with potency comparable to current senolytics and a several hundred-fold reduction in experimental screening costs. Our work demonstrates that machine learning can take maximum advantage of existing drug screening data, paving the way for new open science approaches to drug discovery for senescence-associated diseases.

Air Pollutants Reductions During and after the COVID-19 Lockdown and Their Impact on Mortality in China (preprint)

Background: Strict lockdown measurements implemented during the COVID-19 pandemic have dramatically reduced the anthropogenic-based emissions in China. We aimed to comprehensively describe air pollution during and after the COVID-19 lockdown in China, and to estimate the mortality burden related to the air pollution changes.Methods: We analyzed national air quality monitoring and mortality data to describe the changes of air pollutants, and to estimate the health impact from air pollution changes during and after the lockdown periods in 2020 compared with 2018-2019. Changes in number of deaths and years of life lost (YLL) were used as indicators in the estimations.Findings: The mean air quality index (AQI), PM10, PM2·5, NO2, SO2 and CO concentrations during the lockdown period in 2020 across China declined by 18·2 (21·2%), 27·0μg/m3 (28·9%), 10.5μg/m3 (18·3%), 8·4μg/m3 (44·2%), 13·1μg/m3 (38·8%), and 0·3mg/m3 (27·3%) respectively, when compared to the same periods during 2018-2019 . We observed an increase in O3 concentration during the lockdown by 5·5μg/m3 (10·4%), and a slight decrease after the lockdown by 3·4μg/m3 (4·4%). As a result, there were 51·3 (95%CI: 32·2, 70·1) thousand fewer premature deaths (16·2 thousand during and 35·1 thousand after the lockdown), and 1,066·8 (95%CI: 668·7, 1,456·8) thousand fewer YLLs (343·3 thousand during and 723·5 thousand after the lockdown) than these in 2018-2019 in China.Interpretation: The COVID-19 lockdown has caused substantial decrease in air pollutant concentrations except for O3, which has been accompanied by substantial mortality reductions in China.Funding: Key-Area Research and Development Program of Guangdong Province.Declaration of Interests: We declare no competing interests.Ethics Approval Statement: This study was approved by the Ethics Committee of Guangdong Provincial Center for Disease Control and Prevention (W96-027E-2020004).

Clinical, Immunological and Virological Characterization of COVID-19 Patients that Test Re-Positive for SARS-CoV-2 by RT-PCR (preprint)

Background: COVID-19 pandemic is underway. Some COVID-19 cases re-tested positive for SARS-CoV-2 RNA after discharge raising the public concern on their infectivity. Characterization of re-positive cases are urgently needed for designing intervention strategies. Methods: Clinical data were obtained through Guangdong COVID-19 surveillance network. Neutralization antibody titre was determined using a microneutralization assay. Potential infectivity of clinical samples was evaluated after the cell inoculation. SARS-CoV-2 RNA was detected using three different RT-PCR kits and multiplex PCR with nanopore sequencing. Findings: Among 619 discharged COVID-19 cases, 87 were re-tested as SARS-CoV-2 positive in circumstance of social isolation. All re-positive cases had mild or moderate symptoms in initial diagnosis and a younger age distribution (mean, 30·4). Re-positive cases (n=59) exhibited similar neutralization antibodies (NAbs) titre distributions to other COVID-19 cases (n=150) parallel-tested in this study. No infective viral strain could be obtained by culture and none full-length viral genomes could be sequenced for all re-positive cases. Interpretation: Re-positive SARS-CoV-2 was not caused by the secondary infection and was identified in around 14% of discharged cases. A robust Nabs response and a potential virus genome degradation were detected from nearly all re-positive cases suggesting a lower transmission risk, especially through a respiratory route. Funding: This work was supported by grants from Guangdong Provincial Novel Coronavirus Scientific and Technological Project (2020111107001), Science and Technology Planning Project of Guangdong(2018B020207006), National Science and Technology Project(2020YFC0846800).Declaration of Interests: All authors: No reported conflicts of interest.Ethics Approval Statement: This study was reviewed and approved by the Medical Ethical Committee of Guangdong Provincial Center for Disease Control and Prevention. Data collection and analysis of cases were determined by the Health Commission of Guangdong province to be part of a continuing public health outbreak investigation during the emergency response and were thus considered exempt from institutional review board approval.