Leukemia is a deadly disease caused by the overproduction of immature white blood cells (WBS) in the bone marrow. If leukemia is detected at the initial stages, the chances of recovery are better. Typically, morphological analysis for the identification of acute lymphoblastic leukemia (ALL) is performed manually on blood cells by skilled medical personnel, which has several disadvantages, including a lack of medical personnel, sluggish analysis, and prediction that is dependent on the medical personnel’s expertise. Therefore, we proposed the Multi-Attention EfficientNetV2S and EfficientNetB3 state-of-the-art deep learning architectures using transfer learning-based fine-tuning approach to distinguish the normal and blast cells from microscopic blood smear images that both are pretrained on large-scale ImageNet database. We simply modified the last block of both models and added additional layers to both models. After including this Multi-Attention Mechanism, it not only reduces the model’s complexities but also generalizes its network quite well. By using the proposed technique, the accuracy has improved and the overall loss is also minimized. Our Multi-Attention EfficientNetV2S and EfficientNetB3 models achieved 99.73% and 99.25% accuracy, respectively. We have further compared the proposed model’s performance to other individual and ensemble models. Upon comparison, the proposed model outclassed the existing literature and other benchmark models, thus proving its efficiency.

Acute myeloid leukemia (AML) is a quickly aggressive hematopoietic disorder that progress due to the accumulation and clonal expansion of immature myeloid cells. Despite the latest developments in AML treatment, repeated relapses and drug resistance remain one of the major challenges in treatment of leukemia. Currently, it is well known that the components of the tumor microenvironment such as cellular and non-cellular elements play a critical function in treatment failures of AML, also they are most common cause of complications including suppression of hematopoiesis. Exosomes are membrane-bound extracellular vesicles (EVs) that transfer signaling molecules and have attracted a large amount of attention due to their important role in inter-cellular communication in health and disease. Exosomes participate in the survival and chemoresistance of many leukemia through transferring their rich cargos of molecules including miRNAs, growth factors, and cytokines. The key producers of exosomes that mainly participate to AML pathogenesis are bone marrow mesenchymal stem cell (BMSCs) and AML cell themselves. These cells release an enormous number of exosomes that affect several target cells such as natural killer (NK) and hematopoietic stem cells to the development of leukemia proliferation and progression. In the present study, a comprehensive review of the literature has been done to briefly discuss the biology of exosomes and highlight the role of exosomes derived from AML in the progress of acute myeloid leukemia.

Keratoconus (KC) is a serious disease that can affect people of any race or nationality, although the exact etiology and pathogenic mechanism are still unknown. In this study, thirty-two FDA-approved ophthalmic drugs were exposed to virtual screening using docking studies against both the MMP-2 and MMP-9 proteins to find the most promising inhibitors as a proposed computational mechanism to treat keratoconus. Matrix metalloproteinases (MMPs) are zinc-dependent proteases, and MMP inhibitors (MMPIs) are usually designed to interact with zinc ion in the catalytic (CAT) domain, thus interfering with enzymatic activity. In our research work, the FDA-approved ophthalmic medications will be investigated as MMPIs, to explore if they can be repurposed for KC treatment. The obtained findings of the docking study suggest that atenolol and ampicillin are able to accommodate into the active sites of MMP-2 and MMP-9. Additionally, both exhibited binding modes similar to inhibitors used as references, with an ability to bind to the zinc of the CAT. Molecular dynamic simulations and the MM-GBSA binding free-energy calculations revealed their stable binding over the course of 50 ns. An additional pharmacophoric study was carried out on MMP-9 (PDB ID: 1GKC) using the co-crystallized ligand as a reference for the future design and screening of the MMP-9 inhibitors. These promising results open the door to further biological research to confirm such theoretical results.