Automated Medical Diagnosis of Alzheimer´s Disease Using an Efficient Net Convolutional Neural Network.

Alzheimer's disease (AD) poses an enormous challenge to modern healthcare. Since 2017, researchers have been using deep learning (DL) models for the early detection of AD using neuroimaging biomarkers. In this paper, we implement the EfficietNet-b0 convolutional neural network (CNN) with a novel approach-"fusion of end-to-end and transfer learning"-to classify different stages of AD. 245 T1W MRI scans of cognitively normal (CN) subjects, 229 scans of AD subjects, and 229 scans of subjects with stable mild cognitive impairment (sMCI) were employed. Each scan was preprocessed using a standard pipeline. The proposed models were trained and evaluated using preprocessed scans. For the sMCI vs. AD classification task we obtained 95.29% accuracy and 95.35% area under the curve (AUC) for model training and 93.10% accuracy and 93.00% AUC for model testing. For the multiclass AD vs. CN vs. sMCI classification task we obtained 85.66% accuracy and 86% AUC for model training and 87.38% accuracy and 88.00% AUC for model testing. Based on our experimental results, we conclude that CNN-based DL models can be used to analyze complicated MRI scan features in clinical settings.

Minimizing the Entropy Penalty for Ligand Binding: Lessons from the Molecular Recognition of the Histo Blood-Group Antigens by Human Galectin-3.

Ligand conformational entropy plays an important role in carbohydrate recognition events. Glycans are characterized by intrinsic flexibility around the glycosidic linkages, thus in most cases, loss of conformational entropy of the sugar upon complex formation strongly affects the entropy of the binding process. By employing a multidisciplinary approach combining structural, conformational, binding energy, and kinetic information, we investigated the role of conformational entropy in the recognition of the histo blood-group antigens A and B by human galectin-3, a lectin of biomedical interest. We show that these rigid natural antigens are pre-organized ligands for hGal-3, and that restriction of the conformational flexibility by the branched fucose (Fuc) residue modulates the thermodynamics and kinetics of the binding process. These results highlight the importance of glycan flexibility and provide inspiration for the design of high-affinity ligands as antagonists for lectins.

Lactose binding to human galectin-7 (p53-induced gene 1) induces long-range effects through the protein resulting in increased dimer stability and evidence for positive cooperativity.

The product of p53-induced gene 1 is a member of the galectin family, i.e., galectin-7 (Gal-7). To move beyond structural data by X-ray diffraction, we initiated the study of the lectin by nuclear magnetic resonance (NMR) and circular dichroism spectroscopies, and molecular dynamics (MD) simulations. In concert, our results indicate that lactose binding to human Gal-7 induces long-range effects (minor conformational shifts and changes in structural dynamics) throughout the protein that result in stabilization of the dimer state, with evidence for positive cooperativity. Monte Carlo fits of (15)N-Gal-7 HSQC titrations with lactose using a two-site model yield K1 = 0.9 ± 0.6 × 10(3) M(-1) and K2 = 3.4 ± 0.8 × 10(3) M(-1). Ligand binding-induced stabilization of the Gal-7 dimer was supported by several lines of evidence: MD-based calculations of interaction energies between ligand-loaded and ligand-free states, gel filtration data and hetero-FRET spectroscopy that indicate a highly reduced tendency for dimer dissociation in the presence of lactose, CD-based thermal denaturation showing that the transition temperature of the lectin is significantly increased in the presence of lactose, and saturation transfer difference (STD) NMR using a molecular probe of the monomer state whose presence is diminished in the presence of lactose. MD simulations with the half-loaded ligand-bound state also provided insight into how allosteric signaling may occur. Overall, our results reveal long-range effects on Gal-7 structure and dynamics, which factor into entropic contributions to ligand binding and allow further comparisons with other members of the galectin family.

Triazolopyrimidines Are Microtubule-Stabilizing Agents that Bind the Vinca Inhibitor Site of Tubulin.

Microtubule-targeting agents (MTAs) are some of the clinically most successful anti-cancer drugs. Unfortunately, instances of multidrug resistances to MTA have been reported, which highlights the need for developing MTAs with different mechanistic properties. One less explored class of MTAs are [1,2,4]triazolo[1,5-a]pyrimidines (TPs). These cytotoxic compounds are microtubule-stabilizing agents that inexplicably bind to vinblastine binding site on tubulin, which is typically targeted by microtubule-destabilizing agents. Here we used cellular, biochemical, and structural biology approaches to address this apparent discrepancy. Our results establish TPs as vinca-site microtubule-stabilizing agents that promote longitudinal tubulin contacts in microtubules, in contrast to classical microtubule-stabilizing agents that primarily promote lateral contacts. Additionally we observe that TPs studied here are not affected by p-glycoprotein overexpression, and suggest that TPs are promising ligands against multidrug-resistant cancer cells.

(1)H, (13)C, and (15)N backbone and side-chain chemical shift assignments for the 36 proline-containing, full length 29 kDa human chimera-type galectin-3.

Galectin-3, an adhesion/growth regulatory lectin, has a unique trimodular design consisting of the canonical carbohydrate recognition domain, a collagen-like tandem-repeat section, and an N-terminal peptide with two sites for Ser phosphorylation. Structural characterization of the full length protein with its non-lectin part (115 of 250 residues total) will help understand the multi functionality of this potent cellular effector. Here, we report (1)H, (13)C, and (15)N chemical shift assignments as determined by heteronuclear NMR spectroscopy .

Protein-carbohydrate interactions studied by NMR: from molecular recognition to drug design.

Diseases that result from infection are, in general, a consequence of specific interactions between a pathogenic organism and the cells. The study of host-pathogen interactions has provided insights for the design of drugs with therapeutic properties. One area that has proved to be promising for such studies is the constituted by carbohydrates which participate in biological processes of paramount importance. On the one hand, carbohydrates have shown to be information carriers with similar, if not higher, importance than traditionally considered carriers as amino acids and nucleic acids. On the other hand, the knowledge on molecular recognition of sugars by lectins and other carbohydrate-binding proteins has been employed for the development of new biomedical strategies. Biophysical techniques such as X-Ray crystallography and NMR spectroscopy lead currently the investigation on this field. In this review, a description of traditional and novel NMR methodologies employed in the study of sugar-protein interactions is briefly presented in combination with a palette of NMR-based studies related to biologically and/or pharmaceutically relevant applications.

1H, 13C, and 15N backbone and side-chain chemical shift assignments for the 31 kDa human galectin-7 (p53-induced gene 1) homodimer, a pro-apoptotic lectin.

Galectins are multifunctional proteins with carbohydrate/protein-binding properties and distinct expression profiles. Homodimeric galectin-7 (p53-induced gene 1) is a potent pro-apoptotic effector with clinical relevance. Here, we report (1)H, (13)C, and (15)N chemical shift assignments for human galectin-7 dimer as determined by using heteronuclear, triple resonance NMR spectroscopy.