Supplement of Vitamin D for early-stage Chronic Lymphocytic Leukemia Patients is Associated with a Longer Time to first Treatment.

Low levels of vitamin D are associated with a shorter time to first treatment (TTFT) and inferior overall survival in patients with Chronic Lymphocytic leukemia. But whether vitamin D supplement affects the clinical course of CLL patients, remains an open question. In the current study, we aimed to retrospectively explore the clinical benefit of Vitamin D supplement, or one of its analogues, on TTFT and treatment-free survival (TFS) in a large cohort of patients with asymptomatic CLL, who were under watch and wait approach. Among the 3,474 patients included in the study, 931 patients (26.8%) received either vitamin D supplement or its analogue, for a minimum of 6 months. We found that vitamin D supplement was statistically significant for longer TTFT in the young cohort (age<=65) and was associated with a longer TFS for all ages (p-value=0.004). Among non-vitamin D users, the median TFS was found to be 84 months, while among vitamin D supplement users the median TFS extended to 169 months. In conclusion, our long-term retrospective study demonstrates that the administration of vitamin D to patients with CLL in a watch and wait active surveillance is significantly associated with a longer treatment free survival (in any age) and a longer time to first treatment among young patients (age<=65). A prospective clinical trial is needed to validate results.

Empowering prediction of miRNA-mRNA interactions in species with limited training data through transfer learning.

MicroRNAs (miRNAs) play a crucial role in mRNA regulation. Identifying functionally important mRNA targets of a specific miRNA is essential for uncovering its biological function and assisting miRNA-based drug development. Datasets of high-throughput direct bona fide miRNA-target interactions (MTIs) exist only for a few model organisms, prompting the need for computational prediction. However, the scarcity of data poses a challenge in training accurate machine learning models for MTI prediction. In this study, we explored the potential of transfer learning technique (with ANN and XGB) to address the limited data challenge by leveraging the similarities in interaction rules between species. Furthermore, we introduced a novel approach called TransferSHAP for estimating the feature importance of transfer learning in tabular dataset tasks. We demonstrated that transfer learning improves MTI prediction accuracy for species with limited datasets and identified the specific interaction features the models employed to transfer information across different species.

Machine-learning analysis reveals an important role for negative selection in shaping cancer aneuploidy landscapes.

BACKGROUND: Aneuploidy, an abnormal number of chromosomes within a cell, is a hallmark of cancer. Patterns of aneuploidy differ across cancers, yet are similar in cancers affecting closely related tissues. The selection pressures underlying aneuploidy patterns are not fully understood, hindering our understanding of cancer development and progression. RESULTS: Here, we apply interpretable machine learning methods to study tissue-selective aneuploidy patterns. We define 20 types of features corresponding to genomic attributes of chromosome-arms, normal tissues, primary tumors, and cancer cell lines (CCLs), and use them to model gains and losses of chromosome arms in 24 cancer types. To reveal the factors that shape the tissue-specific cancer aneuploidy landscapes, we interpret the machine learning models by estimating the relative contribution of each feature to the models. While confirming known drivers of positive selection, our quantitative analysis highlights the importance of negative selection for shaping aneuploidy landscapes. This is exemplified by tumor suppressor gene density being a better predictor of gain patterns than oncogene density, and vice versa for loss patterns. We also identify the importance of tissue-selective features and demonstrate them experimentally, revealing KLF5 as an important driver for chr13q gain in colon cancer. Further supporting an important role for negative selection in shaping the aneuploidy landscapes, we find compensation by paralogs to be among the top predictors of chromosome arm loss prevalence and demonstrate this relationship for one paralog interaction. Similar factors shape aneuploidy patterns in human CCLs, demonstrating their relevance for aneuploidy research. CONCLUSIONS: Our quantitative, interpretable machine learning models improve the understanding of the genomic properties that shape cancer aneuploidy landscapes.

Eravacycline, an antibacterial drug, repurposed for pancreatic cancer therapy: insights from a molecular-based deep learning model.

BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) remains a serious threat to health, with limited effective therapeutic options, especially due to advanced stage at diagnosis and its inherent resistance to chemotherapy, making it one of the leading causes of cancer-related deaths worldwide. The lack of clear treatment directions underscores the urgent need for innovative approaches to address and manage this deadly condition. In this research, we repurpose drugs with potential anti-cancer activity using machine learning (ML). METHODS: We tackle the problem by using a neural network trained on drug-target interaction information enriched with drug-drug interaction information, which has not been used for anti-cancer drug repurposing before. We focus on eravacycline, an antibacterial drug, which was selected and evaluated to assess its anti-cancer effects. RESULTS: Eravacycline significantly inhibited the proliferation and migration of BxPC-3 cells and induced apoptosis. CONCLUSION: Our study highlights the potential of drug repurposing for cancer treatment using ML. Eravacycline showed promising results in inhibiting cancer cell proliferation, migration and inducing apoptosis in PDAC. These findings demonstrate that our developed ML drug repurposing models can be applied to a wide range of new oncology therapeutics, to identify potential anti-cancer agents. This highlights the potential and presents a promising approach for identifying new therapeutic options.

Improved Survival of Patients With Chronic Lymphocytic Leukemia Between 1998-2022, Including the Era of Target Therapies With BCL2 and BTK Inhibitors.

BACKGROUND/AIM: The treatment for chronic lymphocytic leukemia (CLL) has changed dramatically over the last two decades. The current study aimed to investigate the impact on overall survival (OS) and time to next treatment (TTT) among CLL patients from 1998 to 2022. PATIENTS AND METHODS: The cohort was based on data obtained from electronic medical records of Maccabi, the second largest healthcare organization in Israel. All included patients were diagnosed with CLL based on the IWCLL criteria and complete clinical, laboratory, and treatment data were available. The study encompassed 3,964 patients diagnosed with CLL during the specified study period. RESULTS: Patients with CLL who required therapy were divided into three eras based on the dominant treatment approach: chemotherapy alone before 2010, therapy with chemotherapy and anti-CD20 between 2010 and 2017, and therapy with targeted agents between 2017 and 2022. Median OS was 4.1 years, 7.5 years, and not reached, respectively. The six-year OS rates were 40%, 55%, and 69%, respectively, (p=0.0001). The median time to the next treatment improved from 5.5 years before 2010, to 8.3 between 2010-2017, to not reached after 2017 (p=0.0021). CONCLUSION: Marked improvements in survival subsequent to fundamental changes in first-line therapy were found in patients with CLL from before 2010 to after 2017.

Improving severity classification of Hebrew PET-CT pathology reports using test-time augmentation.

Classifying medical reports written in Hebrew is challenging due to the ambiguity and complexity of the language. This study proposes Text Test Time Augmentation (TTTA), a novel method to improve the classification accuracy of cancer severity levels from PET-CT diagnostic reports in Hebrew. Hebrew, being a morphologically rich language, often leads to each word having multiple ambiguous interpretations. TTTA leverages test-time augmentation to enhance text information retrieval and model robustness. During training and testing phases, this method generates and evaluates sets of augmentations to enhance the semantics extracted from each report. Experiments utilize a large institutional report repository from Ziv hospital, Israel, where physicians manually labeled the reports. The results demonstrate that the proposed TTTA approach achieves superior performance over baseline models without TTA, improving PR-AUC by 15.18% on classifying cancer severity levels. The study highlights the efficacy of TTTA in extracting essential medical concepts from free text reports and accurately classifying the severity of cancer. The approach addresses the limitations of prior methods and contributes towards improved automated analysis of Hebrew medical reports. TTTA has the potential to assist physicians in cancer diagnosis and treatment planning.

Risk of atrial fibrillation and association with other diseases: protocol of the derivation and international external validation of a prediction model using nationwide population-based electronic health records.

INTRODUCTION: Atrial fibrillation (AF) is a major public health issue and there is rationale for the early diagnosis of AF before the first complication occurs. Previous AF screening research is limited by low yields of new cases and strokes prevented in the screened populations. For AF screening to be clinically and cost-effective, the efficiency of identification of newly diagnosed AF needs to be improved and the intervention offered may have to extend beyond oral anticoagulation for stroke prophylaxis. Previous prediction models for incident AF have been limited by their data sources and methodologies. METHODS AND ANALYSIS: We will investigate the application of random forest and multivariable logistic regression to predict incident AF within a 6-month prediction horizon, that is, a time-window consistent with conducting investigation for AF. The Clinical Practice Research Datalink (CPRD)-GOLD dataset will be used for derivation, and the Clalit Health Services (CHS) dataset will be used for international external geographical validation. Analyses will include metrics of prediction performance and clinical utility. We will create Kaplan-Meier plots for individuals identified as higher and lower predicted risk of AF and derive the cumulative incidence rate for non-AF cardio-renal-metabolic diseases and death over the longer term to establish how predicted AF risk is associated with a range of new non-AF disease states. ETHICS AND DISSEMINATION: Permission for CPRD-GOLD was obtained from CPRD (ref no: 19_076). The CPRD ethical approval committee approved the study. CHS Helsinki committee approval 21-0169 and data usage committee approval 901. The results will be submitted as a research paper for publication to a peer-reviewed journal and presented at peer-reviewed conferences. TRIAL REGISTRATION NUMBER: A systematic review to guide the overall project was registered on PROSPERO (registration number CRD42021245093). The study was registered on ClinicalTrials.gov (NCT05837364).

Vulnerability of pangolin SARS-CoV-2 lineage assignment to adversarial attack.

Pangolin is the most popular tool for SARS-CoV-2 lineage assignment. During COVID-19, healthcare professionals and policymakers required accurate and timely lineage assignment of SARS-CoV-2 genomes for pandemic response. Therefore, tools such as Pangolin use a machine learning model, pangoLEARN, for fast and accurate lineage assignment. Unfortunately, machine learning models are susceptible to adversarial attacks, in which minute changes to the inputs cause substantial changes in the model prediction. We present an attack that uses the pangoLEARN architecture to find perturbations that change the lineage assignment, often with only 2-3 base pair changes. The attacks we carried out show that pangolin is vulnerable to adversarial attack, with success rates between 0.98 and 1 for sequences from non-VoC lineages when pangoLEARN is used for lineage assignment. The attacks we carried out are almost never successful against VoC lineages because pangolin uses Usher and Scorpio - the non-machine-learning alternative methods for VoC lineage assignment. A malicious agent could use the proposed attack to fake or mask outbreaks or circulating lineages. Developers of software in the field of microbial genomics should be aware of the vulnerabilities of machine learning based models and mitigate such risks.

A simplified similarity-based approach for drug-drug interaction prediction.

Drug-drug interactions (DDIs) are a critical component of drug safety surveillance. Laboratory studies aimed at detecting DDIs are typically difficult, expensive, and time-consuming; therefore, developing in-silico methods is critical. Machine learning-based approaches for DDI prediction have been developed; however, in many cases, their ability to achieve high accuracy relies on data only available towards the end of the molecule lifecycle. Here, we propose a simple yet effective similarity-based method for preclinical DDI prediction where only the chemical structure is available. We test the model on new, unseen drugs. To focus on the preclinical problem setting, we conducted a retrospective analysis and tested the models on drugs that were added to a later version of the DrugBank database. We extend an existing method, adjacency matrix factorization with propagation (AMFP), to support unseen molecules by applying a new lookup mechanism to the drugs' chemical structure, lookup adjacency matrix factorization with propagation (LAMFP). We show that using an ensemble of different similarity measures improves the results. We also demonstrate that Chemprop, a message-passing neural network, can be used for DDI prediction. In computational experiments, LAMFP results in high accuracy, with an area under the receiver operating characteristic curve of 0.82 for interactions involving a new drug and an existing drug and for interactions involving only existing drugs. Moreover, LAMFP outperforms state-of-the-art, complex graph neural network DDI prediction methods.

Pretrained transformer models for predicting the withdrawal of drugs from the market.

MOTIVATION: The process of drug discovery is notoriously complex, costing an average of 2.6 billion dollars and taking ∼13 years to bring a new drug to the market. The success rate for new drugs is alarmingly low (around 0.0001%), and severe adverse drug reactions (ADRs) frequently occur, some of which may even result in death. Early identification of potential ADRs is critical to improve the efficiency and safety of the drug development process. RESULTS: In this study, we employed pretrained large language models (LLMs) to predict the likelihood of a drug being withdrawn from the market due to safety concerns. Our method achieved an area under the curve (AUC) of over 0.75 through cross-database validation, outperforming classical machine learning models and graph-based models. Notably, our pretrained LLMs successfully identified over 50% drugs that were subsequently withdrawn, when predictions were made on a subset of drugs with inconsistent labeling between the training and test sets. AVAILABILITY AND IMPLEMENTATION: The code and datasets are available at https://github.com/eyalmazuz/DrugWithdrawn.

The course of patients with hairy cell leukemia during the omicron surge of the Covid-19 pandemic.

In this study, we aim to explore the outcomes of Covid-19 infection in patients with Hairy cell leukemia (HCL). The cohort is based on data obtained from electronic medical records. It includes 218 consecutive patients diagnosed with HCL between 16 June 1998, and 20 September 2022, out of which the coronavirus has infected 85 patients during the Omicron surge. Out of 85 patients with HCL who were infected by Covid-19; 7 patients (8.2%) have been hospitalized, and the mortality rate was 2.3% (two patients). Thirteen of the 85 patients had been infected by Covid-19 in previous waves, including 9/13 after vaccination, and none of them developed a severe disease. Humoral immune response after three doses of the BNT162b2 mRNA vaccination regimen was evaluated in 40 patients and was attained in 67.5%. Based on multivariate analysis: unfavorable outcome was significantly more common in patients with HCL above 65 years old, who had at least one cytopenia, and with comorbidity of cardiovascular disease or asplenia. Our results indicates that the course of COVID-19 in patients with HCL during the Omicron wave has been improved relatively favorable.

Clinical Outcomes of COVID-19 in Mycosis Fungoides and Sezary Syndrome.

INTRODUCTION: Haemato-oncologic patients are more susceptible to severe infections with SARS-CoV-2. We aimed to assess the clinical outcomes of SARS-CoV-2 infection among patients with Mycosis Fungoides and Sezary Syndrome (MF/SS). METHODS: The data were retrieved from anonymized electronic medical records of Maccabi Healthcare Services (MHS), the second-largest healthcare organization in Israel. Patients diagnosed with MF/SS were included in the study. COVID-19 PCR test results together with sociodemographic and clinical data were extracted and analyzed to evaluate the association of COVID-19 with clinical outcomes. RESULTS: In the period of 2020-2022, 1,472 MF/SS patients were included in the study. Among them, 768 (52%) had SARS-CoV-2 infection. The hospitalization rate was 2.9% and infection by the Delta variant was associated with the highest hospitalization rate (7.7%). The hospitalization rate was lower among fully vaccinated patients (p = 0.032) but higher for patients older than 65 (p < 0.001) and patients with SS (vs. MF) (p < 0.001) or COPD (p = 0.024) diagnosis. There was a tendency for decreased hospitalization among patients treated with nirmatrelvir + ritonavir within 5 days of infection, with a 79% risk reduction, although it was not statistically significant (p = 0.164). CONCLUSION: Patients with MF/SS do not necessarily have worse COVID-19 outcomes compared to the general population.

Pregnancy Course of 10 Women Diagnosed with Chronic Lymphocytic Leukemia.

Pregnancies following diagnosis of chronic lymphocytic leukemia (CLL) are rare events, mainly because the disease is typically diagnosed in the elderly. Literature on the topic is based only on case reports, and limited data are available on the influence of pregnancy on CLL course. In this retrospective study, we aimed to summarize the clinical and laboratory course of 10 women with CLL who became pregnant. None of the patients had significant changes in blood count during or after pregnancy or had complications such as infection, autoimmune phenomenon, or preeclampsia. Four out of 10 pregnancies were terminated with an early miscarriage. Following labor, 1 patient started anti-CLL treatment due to preexisting anemia, but none of the women required therapy during CLL progression during the first 2 years of follow-up. We conclude that based on our serial, pregnancy does not negatively impact on CLL course.

The Effectiveness of Bivalent mRNA Omicron Containing Booster Vaccines Among Patients With Hematological Neoplasms.

BACKGROUND/AIM: Last year was characterized by the appearance of novel SARS-CoV-2 virus variants, mainly the omicron sub-lineages BA.2.12.1, BA.4, and BA.5, which have confirmed resistance to the acquired immune response developed following first-generation mRNA vaccines. Given the ability to use mRNA technology to respond quickly to variant strains, novel bivalent vaccines against novel omicron variants were generated. In the current work, we evaluated the efficacy and safety of novel bivalent mRNA Omicron-containing booster vaccines among patients with hematological neoplasms, including both lymphoproliferative and myeloid malignancies. PATIENTS AND METHODS: Cohort patients were obtained from electronic medical records of Maccabi Healthcare Services (MHS), the second-largest healthcare organization in Israel. We analyzed the outcome of all patients with hematological neoplasms, between September 21, 2022, and December 31, 2022, who were identified as having SARS-CoV-2 infection based on polymerase chain reaction (PCR) tests. The Kaplan-Meier method was used to compare the proportion of patients hospitalized for SARS-CoV-2 infection within 30 days among recipients and non-recipients of omicron vaccine. RESULTS: During the study period, 472 patients were infected with Omicron. We compared the outcome of 70 patients who received the bivalent mRNA booster to 402 who did not. Fewer bivalent recipients needed COVID-19-related hospitalization [2 of 70 (2.9%)] in comparison to the non-vaccinated cohort [42 of 402 (10.4%)] (p-value=0.0304). This represents an 89% relative risk reduction in COVID-19-related hospitalization in patients with hematological neoplasms. The median duration of hospitalization was 7 days for the non-vaccinated group and 4 for the vaccinated group. A statistically significant increase in ischemic stroke rates due to bivalent mRNA Omicron-containing booster vaccine was not observed. CONCLUSION: The bivalent Omicron-containing vaccine mRNA booster has a protective effect in preventing and shortening hospitalization in patients with hematological neoplasms with an acceptable safety profile.

Predicting molecular mechanisms of hereditary diseases by using their tissue-selective manifestation.

How do aberrations in widely expressed genes lead to tissue-selective hereditary diseases? Previous attempts to answer this question were limited to testing a few candidate mechanisms. To answer this question at a larger scale, we developed "Tissue Risk Assessment of Causality by Expression" (TRACE), a machine learning approach to predict genes that underlie tissue-selective diseases and selectivity-related features. TRACE utilized 4,744 biologically interpretable tissue-specific gene features that were inferred from heterogeneous omics datasets. Application of TRACE to 1,031 disease genes uncovered known and novel selectivity-related features, the most common of which was previously overlooked. Next, we created a catalog of tissue-associated risks for 18,927 protein-coding genes (https://netbio.bgu.ac.il/trace/). As proof-of-concept, we prioritized candidate disease genes identified in 48 rare-disease patients. TRACE ranked the verified disease gene among the patient's candidate genes significantly better than gene prioritization methods that rank by gene constraint or tissue expression. Thus, tissue selectivity combined with machine learning enhances genetic and clinical understanding of hereditary diseases.

Molecule generation using transformers and policy gradient reinforcement learning.

Generating novel valid molecules is often a difficult task, because the vast chemical space relies on the intuition of experienced chemists. In recent years, deep learning models have helped accelerate this process. These advanced models can also help identify suitable molecules for disease treatment. In this paper, we propose Taiga, a transformer-based architecture for the generation of molecules with desired properties. Using a two-stage approach, we first treat the problem as a language modeling task of predicting the next token, using SMILES strings. Then, we use reinforcement learning to optimize molecular properties such as QED. This approach allows our model to learn the underlying rules of chemistry and more easily optimize for molecules with desired properties. Our evaluation of Taiga, which was performed with multiple datasets and tasks, shows that Taiga is comparable to, or even outperforms, state-of-the-art baselines for molecule optimization, with improvements in the QED ranging from 2 to over 20 percent. The improvement was demonstrated both on datasets containing lead molecules and random molecules. We also show that with its two stages, Taiga is capable of generating molecules with higher biological property scores than the same model without reinforcement learning.

TTANAD: Test-Time Augmentation for Network Anomaly Detection.

Machine learning-based Network Intrusion Detection Systems (NIDS) are designed to protect networks by identifying anomalous behaviors or improper uses. In recent years, advanced attacks, such as those mimicking legitimate traffic, have been developed to avoid alerting such systems. Previous works mainly focused on improving the anomaly detector itself, whereas in this paper, we introduce a novel method, Test-Time Augmentation for Network Anomaly Detection (TTANAD), which utilizes test-time augmentation to enhance anomaly detection from the data side. TTANAD leverages the temporal characteristics of traffic data and produces temporal test-time augmentations on the monitored traffic data. This method aims to create additional points of view when examining network traffic during inference, making it suitable for a variety of anomaly detector algorithms. Our experimental results demonstrate that TTANAD outperforms the baseline in all benchmark datasets and with all examined anomaly detection algorithms, according to the Area Under the Receiver Operating Characteristic (AUC) metric.

Effectiveness of nirmatrelvir plus ritonavir treatment for patients with chronic lymphocytic leukemia during the Omicron surge.

Patients with chronic lymphoid leukemia (CLL), even in the Omicron era and after vaccination, suffer from persistent COVID-19 infection, higher complications, and mortality compared with the general population. In this study, we evaluated retrospectively the effectiveness of nirmatrelvir + ritonavir among 1080 patients with CLL who were infected with severe acute respiratory syndrome coronavirus 2. Nirmatrelvir administration was associated with a reduction in COVID-19-related hospitalization or death by day 35. Specifically, the rate of COVID-19-related hospitalization or death in the treated group compared with the untreated group was 4.8% (14 out of 292) vs 10.2% (75 out of 733), respectively. Moreover, we report a 69% relative risk reduction in COVID-19-related hospitalization or death in patients with CLL at the age of ≥65 years. Multivariate analysis indicates that patients aged >65 years, patients who received heavy treatment (>2 previous treatments), patients with recent hospitalizations, intravenous immunoglobulin (IVIG) treatment, and comorbidity had significant improvement outcomes after treatment with nirmatrelvir.

Predicting drug characteristics using biomedical text embedding.

BACKGROUND: Drug-drug interactions (DDIs) are preventable causes of medical injuries and often result in doctor and emergency room visits. Previous research demonstrates the effectiveness of using matrix completion approaches based on known drug interactions to predict unknown Drug-drug interactions. However, in the case of a new drug, where there is limited or no knowledge regarding the drug's existing interactions, such an approach is unsuitable, and other drug's preferences can be used to accurately predict new Drug-drug interactions. METHODS: We propose adjacency biomedical text embedding (ABTE) to address this limitation by using a hybrid approach which combines known drugs' interactions and the drug's biomedical text embeddings to predict the DDIs of both new and well known drugs. RESULTS: Our evaluation demonstrates the superiority of this approach compared to recently published DDI prediction models and matrix factorization-based approaches. Furthermore, we compared the use of different text embedding methods in ABTE, and found that the concept embedding approach, which involves biomedical information in the embedding process, provides the highest performance for this task. Additionally, we demonstrate the effectiveness of leveraging biomedical text embedding for additional drugs' biomedical prediction task by presenting text embedding's contribution to a multi-modal pregnancy drug safety classification. CONCLUSION: Text and concept embeddings created by analyzing a domain-specific large-scale biomedical corpora can be used for predicting drug-related properties such as Drug-drug interactions and drug safety prediction. Prediction models based on the embeddings resulted in comparable results to hand-crafted features, however text embeddings do not require manual categorization or data collection and rely solely on the published literature.