Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 6 appraisals
Journal of computer-aided molecular design
Two faces of drug repurposing data in machine learning-driven structure-based virtual screening supported by interaction fingerprints
Ensemble docking is a prominent source of protein-ligand complex structures, which could be conveniently analyzed with interaction fingerprints approach in a machine learning framework. Nevertheless, the chemical nature and provenance of the source data libraries used for model development may influence the predictive ability. We assessed the performance of SARS-CoV-2 main protease (Mpro) inhibitors classification by random forest models trained on different fingerprint implementations using three inhibitor libraries, comprising drug repurposing data or compounds rationally designed as Mpro inhibitors. Models trained on drug repurposing data showed a low prediction performance on their own, while infusion of these data into libraries with specific inhibitors greatly improved applicability domains of the models. Our results highlight the importance of balanced dataset preparation for machine learning applications in medicinal chemistry, especially when relied on drug repurposing experiments.
8 July 2026
Read appraisal →Journal of chemical information and modeling
Machine Learning-Driven Simulations of the SARS-CoV-2 Fitness Landscape from Deep Mutational Scanning Experiments
Predicting protein variant effects is a key challenge in preparing for pathogenic viral strains, understanding mutation-linked diseases, and designing new proteins. Protein sequence-structure-function relationships are difficult to model due to complex allosteric and epistatic effects. To investigate efficient modeling strategies, we trained supervised machine learning (ML) models with deep mutational scanning (DMS) libraries of SARS-CoV-2 receptor binding domain (RBD) sequences labeled with angiotensin converting enzyme 2 (ACE2) binding affinity. These models demonstrate superior performance predicting combinatorial mutation effects compared to adding or averaging the effects of point mutations and exhibit strong extrapolative performance ranking omicron variants when training only near wild type (WT) variants. We characterize the RBD fitness landscape by combining ML with Markov Chain Monte Carlo simulations to predict evolutionary patterns from the WT sequence. These generate comparable sequence profiles to high-fitness sequences in DMS data and predict mutations in unseen omicron variants. These models provide insight into the relationship between RBD sequence elements and offer a new perspective on the use of DMS to predict emerging viral strains, which we anticipate will be applicable to other evolutionary prediction tasks. To facilitate application and future development of this strategy, we introduce Mavenets: https://github.com/SztainLab/mavenets.
27 May 2026
Read appraisal →Clinical infectious diseases : an official publication of the Infectious Diseases Society of America
Dolutegravir Reduces Human T-Cell Lymphotropic Virus Type 1 Proviral Load and Improves Neurological Outcomes in a Phase 2 Controlled Trial
BACKGROUND: No specific therapy is approved for human T-cell lymphotropic virus type 1 (HTLV-1) infection. We tested the effect of dolutegravir (DTG) on clinical outcomes and on HTLV-1 proviral load (PVL) in adults with HTLV-1 infection. METHODS: We conducted an open-label, randomized controlled phase 2 trial in Salvador, Brazil. Symptomatic adults with HTLV-1 infection were randomized 1:1 to DTG 50 mg once daily or vitamin C (VTC) 500 mg once daily for 48 weeks. We evaluated changes in gait performance (timed 10-meter walk test [T10MWT]). Key secondary endpoints included change in PVL and prespecified neurofunctional and urinary outcomes. Primary analyses emphasized intragroup and between-group comparisons; exploratory per-protocol analyses were performed for neurofunctional measures. Asymptomatic participants were included for PVL and immunological evaluations. RESULTS: Eighty-three participants (53 symptomatic) were randomized (DTG, n = 43; VTC, n = 40). At week 48, there was no between-group difference in T10MWT. However, DTG use significantly reduced PVL over 48 weeks compared with VTC (P < .001). Exploratory per-protocol analyses found significant improvements associated with DTG use in lower limb spasticity (P < .001), sensory function (light touch, P = .035; pinprick, P = .001), and median nocturia frequency (P = .012). Network analysis of cytokine expression showed a change in the DTG group from baseline to week 48, with loss of negative correlations and a more balanced pattern. DTG was well tolerated, with no unexpected safety signals. CONCLUSIONS: In this pilot randomized trial, DTG use was associated with significantly reduced PVL and improvement in neurofunctional and immunological characteristics of participants in exploratory analyses. These findings provide evidence supporting the use of integrase inhibitors for HTLV-1 infection. Clinical Trials Registration. Brazilian Clinical Trial Register (ReBEC), code RBR-5x7ccxp.
22 May 2026
Read appraisal →Journal of virology
Is the molecular microenvironment of the latent HIV reservoir predictable using deep learning approaches?
Although current antiretroviral therapy effectively suppresses viral replication in infected individuals, infections remain incurable. One of the main reasons for this is the uncertainty of the molecular microenvironment of the latent HIV reservoir. If this microenvironment can be precisely targeted, the effectiveness of current antiretroviral therapy can be leveraged. To better depict the potent microenvironments of the latent HIV reservoir, it is crucial to first understand the mechanisms that make some viruses transcriptionally active and others silent in the first place. It is currently feasible to predict gene activity from DNA sequence, coupled with epigenetics, using deep learning approaches. Substantial progress has been made in creating multidimensional data sets related to the HIV latent reservoir. The implementation of deep learning to mine potent attributes, enabling the characterization and prediction of the microenvironment of the latent HIV reservoir, is thus imperative. This minireview discusses potent features that can be integrated into deep learning methodologies to predict the likelihood of the potential microenvironment from different tiered levels of the latent HIV reservoir organization, and proposes the principal workflow to tackle this question using deep learning approaches.
20 May 2026
Read appraisal →The Journal of infectious diseases
Cytomegalovirus DNAemia in Hospitalized Adults With SARS-CoV-2 Infection Requiring Supplemental Oxygen: Virologic and Clinical Characteristics and Association With Outcomes
BACKGROUND: Cytomegalovirus (CMV) reactivation occurs in the context of coronavirus disease 2019 (COVID-19); however, the viral kinetics, risk factors, and clinical outcomes are poorly defined. METHODS: We examined the association of CMV DNAemia with clinical outcomes among participants of a randomized trial of remdesivir with or without baricitinib (National Institute of Allergy and Infectious Diseases [NIAID], Adaptive COVID-19 Treatment Trial 2 [ACTT-2]). Plasma CMV DNAemia from CMV-seropositive participants with COVID-19 (NIAID ordinal scale [OS] 5, 6, or 7 at entry) were assessed longitudinally by quantitative polymerase chain reaction. Factors associated with CMV DNAemia, and clinical outcomes were analyzed by Cox regression and proportional odds models. RESULTS: Of 772 trial participants with available samples, 643 (83%) were CMV seropositive. Baseline CMV serostatus was not associated with COVID-19 outcomes. The cumulative incidence of CMV DNAemia among seropositive persons by day 28 was overall 11% (baseline OS 5, 6.3%; OS 6, 16.4%; OS 7, 24.7%), and was associated with older age, baseline OS, male sex, lymphopenia, and systemic corticosteroid use, while remdesivir and baricitinib did not affect risk. CMV DNAemia was associated with a lower probability of improvement by day 29 (adjusted hazard ratio, 0.3 [95% confidence interval, .17-.56]), with a more pronounced delay of recovery with higher CMV viral load. CMV DNAemia was also associated with higher severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) viral load and death. CONCLUSIONS: In hospitalized adults with COVID-19 requiring oxygen, CMV viremia occurs within well-defined clinical risks and is independently associated with delayed recovery from illness, higher SARS-CoV-2 viral load, and increased mortality.
16 May 2026
Read appraisal →Journal of medicinal chemistry
Rational Design of Broad-Spectrum Non-Nucleoside Reverse Transcriptase Inhibitors via Pharmacophore-Oriented Generative Artificial Intelligence
Guided by the pharmacophore-oriented molecular generation platform PhoreGen, we employed rilpivirine (RPV) as a lead compound to generate 300 structurally diverse analogs that preserve key pharmacophoric features. Subsequent drug-likeness evaluation, molecular docking score, and synthetic feasibility led to the identification of compound No.102 (A19), which displayed potent inhibition activity against WT HIV-1 (EC50 = 3.15 nM) and low cytotoxicity (CC50 > 335 μM). Subsequent structure-activity relationship optimization identified A24, which demonstrated robust activity against clinically relevant drug-resistant HIV-1 mutants (EC50 = 2.07-28.8 nM). Notably, compared to RPV, A24 exhibited significantly reduced cytotoxicity (CC50 = 82.3 μM vs. 3.98 μM) and enhanced potency against the Y188L (EC50 = 28.8 nM vs. 79.4 nM) and F227L + V106A (EC50 = 19.0 nM vs. 81.6 nM) mutants. Pharmacokinetic evaluations revealed that A24 exhibited attenuated CYP enzyme inhibition (IC50 ≥ 1.88 μM), reduced hERG-related toxicity (IC50 = 2.633 μM), and improved metabolic stability (human t1/2 = 39.1 min). Collectively, these favorable properties position A24 as a promising NNRTI for further development.
10 Apr 2026
Read appraisal →