Holographic-(V)AE: An end-to-end SO(3)-equivariant (variational) autoencoder in Fourier space.

Group-equivariant neural networks have emerged as an efficient approach to model complex data, using generalized convolutions that respect the relevant symmetries of a system. These techniques have made advances in both the supervised learning tasks for classification and regression, and the unsupervised tasks to generate new data. However, little work has been done in leveraging the symmetry-aware expressive representations that could be extracted from these approaches.

Design of high specificity binders for peptide-MHC-I complexes.

Class I MHC molecules present peptides derived from intracellular antigens on the cell surface for immune surveillance, and specific targeting of these peptide-MHC (pMHC) complexes could have considerable utility for treating diseases. Such targeting is challenging as it requires readout of the few outward facing peptide antigen residues and the avoidance of extensive contacts with the MHC carrier which is present on almost all cells. Here we describe the use of deep learning-based protein design tools to design small proteins that arc above the peptide binding groove of pMHC complexes and make extensive contacts with the peptide.

Loop-Diffusion: an equivariant diffusion model for designing and scoring protein loops.

Predicting protein functional characteristics from structure remains a central problem in protein science, with broad implications from understanding the mechanisms of disease to designing novel therapeutics. Unfortunately, current machine learning methods are limited by scarce and biased experimental data, and physics-based methods are either too slow to be useful, or too simplified to be accurate. In this work, we present Loop-Diffusion, an energy based diffusion model which leverages a dataset of general protein loops from the entire protein universe to learn an energy function that generalizes to functional prediction tasks.

Axon guidance genes are regulated by TDP-43 and RGNEF through long-intron removal.

Rho guanine nucleotide exchange factor (RGNEF) is a guanine nucleotide exchange factor (GEF) mainly involved in regulating the activity of Rho-family GTPases. It is a bi-functional protein, acting both as a guanine exchange factor and as an RNA-binding protein. RGNEF is known to act as a destabilizing factor of neurofilament light chain RNA (NEFL) and it could potentially contribute to their sequestration in nuclear cytoplasmic inclusions.

Hematopoietic and leukemic stem cells homeostasis: the role of bone marrow niche.

The bone marrow microenvironment (BMM) has highly specialized anatomical characteristics that provide a sanctuary place for hematopoietic stem cells (HSCs) that allow appropriate proliferation, maintenance, and self-renewal capacity. Several cell types contribute to the constitution and function of the bone marrow niche. Interestingly, uncovering the secrets of BMM and its interaction with HSCs in health paved the road for research aiming at better understanding the concept of leukemic stem cells (LSCs) and their altered niche.

HERMES: Holographic Equivariant neuRal network model for Mutational Effect and Stability prediction.

Predicting the stability and fitness effects of amino acid mutations in proteins is a cornerstone of biological discovery and engineering. Various experimental techniques have been developed to measure mutational effects, providing us with extensive datasets across a diverse range of proteins. By training on these data, traditional computational modeling and more recent machine learning approaches have advanced significantly in predicting mutational effects.

HERMES: Holographic Equivariant neuRal network model for Mutational Effect and Stability prediction.

Predicting the stability and fitness effects of amino-acid mutations in proteins is a cornerstone of biological discovery and engineering. Various experimental techniques have been developed to measure mutational effects, providing us with extensive datasets across a diverse range of proteins. By training on these data, machine learning approaches have advanced significantly in predicting mutational effects.

H-Packer: Holographic Rotationally Equivariant Convolutional Neural Network for Protein Side-Chain Packing.

Accurately modeling protein 3D structure is essential for the design of functional proteins. An important sub-task of structure modeling is protein side-chain packing: predicting the conformation of side-chains (rotamers) given the protein's backbone structure and amino-acid sequence. Conventional approaches for this task rely on expensive sampling procedures over hand-crafted energy functions and rotamer libraries.

Fms -like tyrosine kinase 3 positive acute myeloid leukemia.

Purpose Of Review: Fms -like tyrosine kinase 3 (FLT3) mutations are common in newly diagnosed patients with acute myeloid leukemia (AML). They are associated with a high risk of relapse. The identification of FLT3 mutations has important implications for the management of AML.

Use of Next Generation Sequencing to Define the Origin of Primary Myelofibrosis.

Primary myelofibrosis (PMF) is a chronic myeloproliferative neoplasm (MPN) characterized by progressive bone marrow sclerosis, extra-medullary hematopoiesis, and possible transformation to acute leukemia. In the last decade, the molecular pathogenesis of the disease has been largely uncovered. Particularly, genetic and genomic studies have provided evidence of deregulated oncogenes in PMF as well as in other MPNs.

Treatment options for acute myeloid leukemia patients aged <60 years.

Treatment of acute myeloid leukemia (AML) has changed over the last few years, after the discovery of new drugs selectively targeting AML blasts. Although 3/7 remains the standard of care for most AML patients, several new targeted agents (such as FLT3 inhibitors, CPX-351, gemtuzumab ozogamicin, BCL-2 inhibitor, and oral azacitidine), either as single agents or combined with standard chemotherapy, are approaching clinical practice, starting a new era in AML management. Moreover, emerging evidence has demonstrated that high-risk AML patients might benefit from both allogeneic stem cell transplant and maintenance therapy, providing new opportunities, as well as new challenges, for treating clinicians.

Venetoclax and idasanutlin in relapsed/refractory AML: a nonrandomized, open-label phase 1b trial.

This phase 1b trial (NCT02670044) evaluated venetoclax-idasanutlin in patients with relapsed/refractory (R/R) acute myeloid leukemia (AML) ineligible for cytotoxic chemotherapy. Two-dimensional dose escalation (DE, n = 50) was performed for venetoclax daily with idasanutlin on days 1 to 5 in 28-day cycles, followed by dosing schedule optimization (n = 6) to evaluate reduced venetoclax schedules (21-/14-day dosing). Common adverse events (occurring in ≥40% of patients) included diarrhea (87.

Prevalence and characteristics of diffuse idiopathic skeletal hyperostosis (DISH) in Italy.

Purpose: Diffuse idiopathic skeletal hyperostosis (DISH) is a benign condition characterized by ossification of the spine and prominent enthesopathies. Highly heterogeneous epidemiological figures have been reported in the literature, while in Italy the largest study has been conducted in 1992. The aim of our research is to contribute updated information about prevalence of DISH in Italy and to describe the clinical and radiographic characteristics associated with the disorder.

Real-life efficacy and safety of idelalisib in 55 double-refractory follicular lymphoma patients.

Idelalisib, a reversible inhibitor of PI3Kδ (phosphoinositide-3 kinase delta), showed remarkable activity in the phase II DELTA trial, leading to its approval by the European Medicines Agency (EMA) in patients with relapsed/refractory (R/R) follicular lymphoma (FL). However, real-life data on idelalisib are scarce. We treated 55 double-refractory FL patients with idelalisib in a real-life setting.

Molecular Profiling of Kenyan Acute Myeloid Leukemia Patients.

Acute myeloid leukemia (AML) is an infrequent disease, and it is associated with high morbidity and mortality. It harbors a unique configuration of cytogenetic abnormalities and molecular mutations that can be detected using microscopic and molecular methods respectively. These genetic tests are core elements of diagnosis and prognostication in high-income countries.

A prognostic model for patients with lymphoma and COVID-19: a multicentre cohort study.

Lymphoma represents a heterogeneous hematological malignancy (HM), which is characterized by severe immunosuppression. Patients diagnosed of coronavirus disease 2019 (COVID-19) during the course of HM have been described to have poor outcome, with only few reports specifically addressing lymphoma patients. Here, we investigated the clinical behavior and clinical parameters of a large multicenter cohort of adult patients with different lymphoma subtypes, with the aim of identifying predictors of death.

Metabolic Switch and Cytotoxic Effect of Metformin on Burkitt Lymphoma.

Altered cellular energetic metabolism has recently emerged as important feature of neoplastic cells. Indeed, interfering with cancer cell metabolism might represent a suitable therapeutic strategy. In this study, we aimed to assess glucose metabolism activation in human lymphomas and evaluate how metformin can exert its action on lymphoma cells.

Immunological Response Against SARS-COV-2 After BNT162b2 Vaccine Administration Is Impaired in Allogeneic but Not in Autologous Stem Cell Transplant Recipients.

The efficacy of Covid-19 vaccine in hematopoietic stem cell transplantation (HSCT) recipients is still unknown. We planned a prospective study to evaluate the immune response after the administration of Covid-19 vaccine in HSCT recipients. Fifty patients previously submitted to HSCT (38 autologous and 12 allogeneic) received the mRNA-based SARS-CoV-2 vaccine BNT162b2 (Pfizer-BioNTech).

COVID-19 elicits an impaired antibody response against SARS-CoV-2 in patients with haematological malignancies.

COVID-19 is associated with high mortality in patients with haematological malignancies (HM) and rate of seroconversion is unknown. The ITA-HEMA-COV project (NCT04352556) investigated patterns of seroconversion for SARS-CoV-2 IgG in patients with HMs. A total of 237 patients, SARS-CoV-2 PCR-positive with at least one SARS-CoV-2 IgG test performed during their care, entered the analysis.

Clinical Relevance of ABCB1, ABCG2, and ABCC2 Gene Polymorphisms in Chronic Myeloid Leukemia Patients Treated With Nilotinib.

Tyrosine kinase inhibitors (TKIs) have radically changed the outcome of chronic myeloid leukemia (CML) patients in the last 20 years. Moreover, the advent of second generation TKIs, namely nilotinib and dasatinib, have largely increased the number of CML patients achieving deep and sustained molecular responses. However, the possible mechanisms capable of influencing the maintenance of the long-term molecular response are not yet fully known and understood.