The most recent wave of SARS-CoV-2 Omicron variants descending from BA.2 and BA.2.86 exhibited improved viral growth and fitness due to convergent evolution of functional hotspots. These hotspots operate in tandem to optimize both receptor binding for effective infection and immune evasion efficiency, thereby maintaining overall viral fitness. The lack of molecular details on structure, dynamics and binding energetics of the latest FLiRT and FLuQE variants with the ACE2 receptor and antibodies provides a considerable challenge that is explored in this study. We combined AlphaFold2-based atomistic predictions of structures and conformational ensembles of the SARS-CoV-2 spike complexes with the host receptor ACE2 for the most dominant Omicron variants JN.1, KP.1, KP.2 and KP.3 to examine the mechanisms underlying the role of convergent evolution hotspots in balancing ACE2 binding and antibody evasion. Using the ensemble-based mutational scanning of the spike protein residues and computations of binding affinities, we identified binding energy hotspots and characterized the molecular basis underlying epistatic couplings between convergent mutational hotspots. The results suggested the existence of epistatic interactions between convergent mutational sites at L455, F456, Q493 positions that protect and restore ACE2-binding affinity while conferring beneficial immune escape. To examine immune escape mechanisms, we performed structure-based mutational profiling of the spike protein binding with several classes of antibodies that displayed impaired neutralization against BA.2.86, JN.1, KP.2 and KP.3. The results confirmed the experimental data that JN.1, KP.2 and KP.3 harboring the L455S and F456L mutations can significantly impair the neutralizing activity of class 1 monoclonal antibodies, while the epistatic effects mediated by F456L can facilitate the subsequent convergence of Q493E changes to rescue ACE2 binding. Structural and energetic analysis provided a rationale to the experimental results showing that BD55-5840 and BD55-5514 antibodies that bind to different binding epitopes can retain neutralizing efficacy against all examined variants BA.2.86, JN.1, KP.2 and KP.3. The results support the notion that evolution of Omicron variants may favor emergence of lineages with beneficial combinations of mutations involving mediators of epistatic couplings that control balance of high ACE2 affinity and immune evasion.

In this study, we performed a computational study of binding mechanisms for the SARS-CoV-2 spike Omicron XBB lineages with the host cell receptor ACE2 and a panel of diverse class one antibodies. The central objective of this investigation was to examine the molecular factors underlying epistatic couplings among convergent evolution hotspots that enable optimal balancing of ACE2 binding and antibody evasion for Omicron variants BA.1, BA2, BA.3, BA.4/BA.5, BQ.1.1, XBB.1, XBB.1.5, and XBB.1.5 + L455F/F456L. By combining evolutionary analysis, molecular dynamics simulations, and ensemble-based mutational scanning of spike protein residues in complexes with ACE2, we identified structural stability and binding affinity hotspots that are consistent with the results of biochemical studies. In agreement with the results of deep mutational scanning experiments, our quantitative analysis correctly reproduced strong and variant-specific epistatic effects in the XBB.1.5 and BA.2 variants. It was shown that Y453W and F456L mutations can enhance ACE2 binding when coupled with Q493 in XBB.1.5, while these mutations become destabilized when coupled with the R493 position in the BA.2 variant. The results provided a molecular rationale of the epistatic mechanism in Omicron variants, showing a central role of the Q493/R493 hotspot in modulating epistatic couplings between convergent mutational sites L455F and F456L in XBB lineages. The results of mutational scanning and binding analysis of the Omicron XBB spike variants with ACE2 receptors and a panel of class one antibodies provide a quantitative rationale for the experimental evidence that epistatic interactions of the physically proximal binding hotspots Y501, R498, Q493, L455F, and F456L can determine strong ACE2 binding, while convergent mutational sites F456L and F486P are instrumental in mediating broad antibody resistance. The study supports a mechanism in which the impact on ACE2 binding affinity is mediated through a small group of universal binding hotspots, while the effect of immune evasion could be more variant-dependent and modulated by convergent mutational sites in the conformationally adaptable spike regions.

In 2020, over 250,000 people died from brain and Central Nervous System (CNS) tumors. Brain tumors account for around 85% or more of these. As of 2021, over 16 million people in the United States have been diagnosed with some type of cognitive impairment. The goal of this paper is to find the most effective set of data augmentations to correctly classify cognitive diseases with deep networks, using structural Magnetic Resonance Imaging (MRI) data. This paper demonstrates a Greedy optimization technique to find the most effective sequence of data augmentations out of blurring, distortion, position, and red noise (an overlay augmentation displaying random clouds of noise on the images). We sought to classify 3 tumors: glioma tumors, pituitary tumors, and meningioma tumors, as well as detect if there was no tumor at all. We also classified 3 stages of Alzheimer's disease: not demented, very mildly demented, and mildly demented, to further demonstrate the effectiveness of the data augmentation sequence.

There has been a lot of research done into the implementation of neural networks in the bioinformatics space, specifically with respect to drug discovery. Although there have been many promising steps taken in this direction, there is still a large amount of research yet to be done in this field. In this paper, we design a novel architecture that aims to generate novel molecules that will treat hormone-receptor-positive breast cancer disease. These molecules are aimed to inhibit aromatase, CDK4, CDK6, PI3K, and mTOR proteins. To do this, we used a natural language processor based variational autoencoder. Our model is trained on the ZINC open-source dataset due to its library of 250k drug molecules. To generate our molecules we compiled a test set of about 68 molecules that were already proven to bind to our mentioned target proteins. To measure the initial viability of our generated molecules we used RDKit’s quantitative estimated drug-likeness score, which will help provide insight into the drug-likeness of our generated data. Supplementary models helped predict other properties of our generated molecules, specifically solubility, synthetic accessibility, and toxicity to further heighten our screening process. We used the AutoDock Vina framework to predict the Gibbs Free Energy Score between the molecule and the desired target enzymes. Our experimentation was able to expand and improve upon a previous solubility prediction architecture to procure more accurate results on both solubility and synthetic accessibility of molecules. The goal of our research is to develop a novel high-throughput process to generate and screen for hormone-positive breast cancer drug molecules that can be feasible in the real world. Since the drug discovery space is so large (approximately 10 ⁶⁰ molecules), neural networks are a valuable tool to help cut down the time and cost it takes to find these molecules. Through our experimentation, we were able to add a novel improvement to a working VAE framework by refining certain layers of the network’s decoder, leading to the generation of three molecules that passed our screening process and have high viability to be successful in suppressing hormone-positive breast cancer tumor growth.

The latest wave SARS-CoV-2 Omicron variants displayed a growth advantage and the increased viral fitness through convergent evolution of functional hotspots that work synchronously to balance fitness requirements for productive receptor binding and efficient immune evasion. In this study, we combined AlphaFold2-based structural modeling approaches with all-atom MD simulations and mutational profiling of binding energetics and stability for prediction and comprehensive analysis of the structure, dynamics, and binding of the SARS-CoV-2 Omicron BA.2.86 spike variant with ACE2 host receptor and distinct classes of antibodies. We adapted several AlphaFold2 approaches to predict both structure and conformational ensembles of the Omicron BA.2.86 spike protein in the complex with the host receptor. The results showed that AlphaFold2-predicted conformational ensemble of the BA.2.86 spike protein complex can accurately capture the main dynamics signatures obtained from microscond molecular dynamics simulations. The ensemble-based dynamic mutational scanning of the receptor binding domain residues in the BA.2 and BA.2.86 spike complexes with ACE2 dissected the role of the BA.2 and BA.2.86 backgrounds in modulating binding free energy changes revealing a group of conserved hydrophobic hotspots and critical variant-specific contributions of the BA.2.86 mutational sites R403K, F486P and R493Q. To examine immune evasion properties of BA.2.86 in atomistic detail, we performed large scale structure-based mutational profiling of the S protein binding interfaces with distinct classes of antibodies that displayed significantly reduced neutralization against BA.2.86 variant. The results quantified specific function of the BA.2.86 mutations to ensure broad resistance against different classes of RBD antibodies. This study revealed the molecular basis of compensatory functional effects of the binding hotspots, showing that BA.2.86 lineage may have primarily evolved to improve immune escape while modulating binding affinity with ACE2 through cooperative effect of R403K, F486P and R493Q mutations. The study supports a hypothesis that the impact of the increased ACE2 binding affinity on viral fitness is more universal and is mediated through cross-talk between convergent mutational hotspots, while the effect of immune evasion could be more variant-dependent.

There has been a lot of research done into the implementation of neural networks in the bioinformatics space, specifically with respect to drug discovery. Although there have been many promising steps taken in this direction, there is still a large amount of research yet to be done in this field. In this paper, we design a novel architecture that aims to generate novel molecules that will treat hormone-receptor-positive breast cancer disease. These molecules are aimed to inhibit aromatase, CDK4, CDK6, PI3K, and mTOR proteins. To do this, we used a natural language processor based variational autoencoder. Our model is trained on the ZINC open-source dataset due to its library of 250k drug molecules. To generate our molecules we compiled a test set of about 68 molecules that were already proven to bind to our mentioned target proteins. To measure the initial viability of our generated molecules we used RDKit’s quantitative estimated drug-likeness score, which will help provide insight into the drug-likeness of our generated data. Supplementary models helped predict other properties of our generated molecules, specifically solubility, synthetic accessibility, and toxicity to further heighten our screening process. We used the AutoDock Vina framework to predict the Gibbs Free Energy Score between the molecule and the desired target enzymes. Our experimentation was able to expand and improve upon a previous solubility prediction architecture to procure more accurate results on both solubility and synthetic accessibility of molecules. The goal of our research is to develop a novel high-throughput process to generate and screen for hormone-positive breast cancer drug molecules that can be feasible in the real world. Since the drug discovery space is so large (approximately 1060 molecules), neural networks are a valuable tool to help cut down the time and cost it takes to find these molecules. Through our experimentation, we were able to add a novel improvement to a working VAE framework by refining certain layers of the network’s decoder, leading to the generation of three molecules that passed our screening process and have high viability to be successful in suppressing hormone-positive breast cancer tumor growth.