Search for: All records

The global effort to combat the COVID-19 pandemic faces ongoing uncertainty with the emergence of Variants of Concern featuring numerous mutations on the Spike (S) protein. In particular, the Omicron Variant is distinguished by 32 mutations, including 10 within its receptor-binding domain (RBD). These mutations significantly impact viral infectivity and the efficacy of vaccines and antibodies currently in use for therapeutic purposes. In our study, we employed structure-based computational saturation mutagenesis approaches to predict the effects of Omicron missense mutations on RBD stability and binding affinity, comparing them to the original Wuhan-Hu-1 strain. Our results predict that mutations such as G431W and P507W induce the most substantial destabilizations in the Wuhan-Hu-1-S/Omicron-S RBD. Notably, we postulate that mutations in the Omicron-S exhibit a higher percentage of enhancing binding affinity compared to Wuhan-S. We found that the mutations at residue positions G447, Y449, F456, F486, and S496 led to significant changes in binding affinity. In summary, our findings may shed light on the widespread prevalence of Omicron mutations in human populations. The Omicron mutations that potentially enhance their affinity for human receptors may facilitate increased viral binding and internalization in infected cells, thereby enhancing infectivity. This informs the development of new neutralizing antibodies capable of targeting Omicron’s immune-evading mutations, potentially aiding in the ongoing battle against the COVID-19 pandemic. 

Federated learning (FL) has been emerging as a new distributed machine learning paradigm recently. Although FL can protect the data privacy of participants by keeping their training data on local devices, there are recent works raising new privacy concerns especially when workers or the parameter server of FL are untrustworthy or malicious. One effective way to solve the problem is using hierarchical federated learning (HFL) where a few middle-layer aggregators (or called group leaders) are used to aggregate local model updates from workers and send group model updates to the parameter server. In this paper, we consider the participant selection problem of HFL in an edge cloud with multiple FL models, where each model needs to select one parameter server, a few group leaders and a certain amount of workers from edge servers to jointly perform HFL. We first formulate this problem as a non-linear integer programming, aiming to minimize the total learning cost of all models while satisfying the constrained edge resources. We then design a three-stage algorithm by decoupling the original problem into three sub-problems and solving them iteratively. Simulations with real-world datasets and FL models confirm that our proposed algorithm can efficiently reduce the average total learning cost in edge cloud compared with existing methods. 

Abstract Despite efforts to integrate research across different subdisciplines of biology, the scale of integration remains limited. We hypothesize that future generations of Artificial Intelligence (AI) technologies specifically adapted for biological sciences will help enable the reintegration of biology. AI technologies will allow us not only to collect, connect and analyze data at unprecedented scales, but also to build comprehensive predictive models that span various subdisciplines. They will make possible both targeted (testing specific hypotheses) and untargeted discoveries. AI for biology will be the cross-cutting technology that will enhance our ability to do biological research at every scale. We expect AI to revolutionize biology in the 21st century much like statistics transformed biology in the 20th century. The difficulties, however, are many, including data curation and assembly, development of new science in the form of theories that connect the subdisciplines, and new predictive and interpretable AI models that are more suited to biology than existing machine learning and AI techniques. Development efforts will require strong collaborations between biological and computational scientists. This white paper provides a vision for AI for Biology and highlights some challenges. 

Diverse sets of complete human genomes are required to construct a pangenome reference and to understand the extent of complex structural variation. Here, we sequence 65 diverse human genomes and build 130 haplotype-resolved assemblies (130 Mbp median continuity), closing 92% of all previous assembly gaps and reaching telomere-to-telomere (T2T) status for 39% of the chromosomes. We highlight complete sequence continuity of complex loci, including the major histocompatibility complex (MHC), SMN1/SMN2, NBPF8, and AMY1/AMY2, and fully resolve 1,852 complex structural variants (SVs). In addition, we completely assemble and validate 1,246 human centromeres. We find up to 30-fold variation in α-satellite high-order repeat (HOR) array length and characterize the pattern of mobile element insertions into α-satellite HOR arrays. While most centromeres predict a single site of kinetochore attachment, epigenetic analysis suggests the presence of two hypomethylated regions for 7% of centromeres. Combining our data with the draft pangenome reference significantly enhances genotyping accuracy from short-read data, enabling whole-genome inference to a median quality value (QV) of 45. Using this approach, 26,115 SVs per sample are detected, substantially increasing the number of SVs now amenable to downstream disease association studies.