ABSTRACT
We seek to transform how new and emergent variants of pandemiccausing viruses, specifically SARS-CoV-2, are identified and classified. By adapting large language models (LLMs) for genomic data, we build genome-scale language models (GenSLMs) which can learn the evolutionary landscape of SARS-CoV-2 genomes. By pretraining on over 110 million prokaryotic gene sequences and finetuning a SARS-CoV-2-specific model on 1.5 million genomes, we show that GenSLMs can accurately and rapidly identify variants of concern. Thus, to our knowledge, GenSLMs represents one of the first whole genome scale foundation models which can generalize to other prediction tasks. We demonstrate scaling of GenSLMs on GPU-based supercomputers and AI-hardware accelerators utilizing 1.63 Zettaflops in training runs with a sustained performance of 121 PFLOPS in mixed precision and peak of 850 PFLOPS. We present initial scientific insights from examining GenSLMs in tracking evolutionary dynamics of SARS-CoV-2, paving the path to realizing this on large biological data.
ABSTRACT
Metaldehyde has been detected in drinking water system in relatively high concentration exceeding European water quality standard. In order to address this problem, the aim of this project was to treat metaldehyde aqueous solution by advanced oxidation processes (AOPs) and granular activated carbon (GAC) column. Ten novel materials were tested for degradation rates of metaldehyde under ultraviolet light irradiation (UVC). For treatment of 1 mg/L metaldehyde solution by AOPs, the highest degradation rate is 16.59% under UVC light with the aid of nitrogen doped titanium dioxide coated graphene (NTiO2/Gr). Furthermore, 0.5 mg/L is the optimal concentration for degradation of metaldehyde with N-TiO2/Gr under UVC light. Apart from that, the lifetime of GAC column could be elongated on condition that metaldehyde has been treated by AOPs previously. Hence, combination of AOPs and GAC column is promising in treating water containing metaldehyde.
