Large-scale chemoproteomics expedites ligand discovery and predicts ligand behavior in cells.

Chemical modulation of proteins enables a mechanistic understanding of biology and represents the foundation of most therapeutics. However, despite decades of research, 80% of the human proteome lacks functional ligands. Chemical proteomics has advanced fragment-based ligand discovery toward cellular systems, but throughput limitations have stymied the scalable identification of fragment-protein interactions. We report proteome-wide maps of protein-binding propensity for 407 structurally diverse small-molecule fragments. We verified that identified interactions can be advanced to active chemical probes of E3 ubiquitin ligases, transporters, and kinases. Integrating machine learning binary classifiers further enabled interpretable predictions of fragment behavior in cells. The resulting resource of fragment-protein interactions and predictive models will help to elucidate principles of molecular recognition and expedite ligand discovery efforts for hitherto undrugged proteins.

Machine Learning Approaches Identify Chemical Features for Stage-Specific Antimalarial Compounds.

Efficacy data from diverse chemical libraries, screened against the various stages of the malaria parasite Plasmodium falciparum, including asexual blood stage (ABS) parasites and transmissible gametocytes, serve as a valuable reservoir of information on the chemical space of compounds that are either active (or not) against the parasite. We postulated that this data can be mined to define chemical features associated with the sole ABS activity and/or those that provide additional life cycle activity profiles like gametocytocidal activity. Additionally, this information could provide chemical features associated with inactive compounds, which could eliminate any future unnecessary screening of similar chemical analogs. Therefore, we aimed to use machine learning to identify the chemical space associated with stage-specific antimalarial activity. We collected data from various chemical libraries that were screened against the asexual (126 374 compounds) and sexual (gametocyte) stages of the parasite (93 941 compounds), calculated the compounds' molecular fingerprints, and trained machine learning models to recognize stage-specific active and inactive compounds. We were able to build several models that predict compound activity against ABS and dual activity against ABS and gametocytes, with Support Vector Machines (SVM) showing superior abilities with high recall (90 and 66%) and low false-positive predictions (15 and 1%). This allowed the identification of chemical features enriched in active and inactive populations, an important outcome that could be mined for essential chemical features to streamline hit-to-lead optimization strategies of antimalarial candidates. The predictive capabilities of the models held true in diverse chemical spaces, indicating that the ML models are therefore robust and can serve as a prioritization tool to drive and guide phenotypic screening and medicinal chemistry programs.

Endothelial transcriptomic analysis identifies biomarkers of severe and cerebral malaria.

Malaria can quickly progress from an uncomplicated infection into a life-threatening severe disease. However, the unspecificity of early symptoms often makes it difficult to identify patients at high risk of developing severe disease. Additionally, one of the most feared malaria complications - cerebral malaria - is challenging to diagnose, often resulting in treatment delays that can lead to adverse outcomes. To identify candidate biomarkers for the prognosis and/or diagnosis of severe and cerebral malaria, we have analyzed the transcriptomic response of human brain microvascular endothelial cells to erythrocytes infected with Plasmodium falciparum. Candidates were validated in plasma samples from a cohort of pediatric patients with malaria from Mozambique, resulting in the identification of several markers with capacity to distinguish uncomplicated from severe malaria, the most potent being the metallopeptidase ADAMTS18. Two other biomarkers, Angiopoietin-like-4 and Inhibin-ßE were able to differentiate children with cerebral malaria within the severe malaria group, showing increased sensitivity after combination in a biomarker signature. The validation of the predicted candidate biomarkers in plasma of children with severe and cerebral malaria underscores the power of this transcriptomic approach and indicates that a specific endothelial response to P. falciparum-infected erythrocytes is linked to the pathophysiology of severe malaria.

First fully-automated AI/ML virtual screening cascade implemented at a drug discovery centre in Africa.

Streamlined data-driven drug discovery remains challenging, especially in resource-limited settings. We present ZairaChem, an artificial intelligence (AI)- and machine learning (ML)-based tool for quantitative structure-activity/property relationship (QSAR/QSPR) modelling. ZairaChem is fully automated, requires low computational resources and works across a broad spectrum of datasets. We describe an end-to-end implementation at the H3D Centre, the leading integrated drug discovery unit in Africa, at which no prior AI/ML capabilities were available. By leveraging in-house data collected over a decade, we have developed a virtual screening cascade for malaria and tuberculosis drug discovery comprising 15 models for key decision-making assays ranging from whole-cell phenotypic screening and cytotoxicity to aqueous solubility, permeability, microsomal metabolic stability, cytochrome inhibition, and cardiotoxicity. We show how computational profiling of compounds, prior to synthesis and testing, can inform progression of frontrunner compounds at H3D. This project is a first-of-its-kind deployment at scale of AI/ML tools in a research centre operating in a low-resource setting.

Xanthine oxidase levels and immune dysregulation are independently associated with anemia in Plasmodium falciparum malaria.

Severe anemia is an important contributor to mortality in children with severe malaria. Anemia in malaria is a multi-factorial complication, since dyserythropoiesis, hemolysis and phagocytic clearance of uninfected red blood cells (RBCs) can contribute to this syndrome. High levels of oxidative stress and immune dysregulation have been proposed to contribute to severe malarial anemia, facilitating the clearance of uninfected RBCs. In a cohort of 552 Ugandan children with severe malaria, we measured the levels of xanthine oxidase (XO), an oxidative enzyme that is elevated in the plasma of malaria patients. The levels of XO in children with severe anemia were significantly higher compared to children with severe malaria not suffering from severe anemia. Levels of XO were inversely associated with RBC hemoglobin (ρ = - 0.25, p < 0.0001), indicating a relation between this enzyme and severe anemia. When compared with the levels of immune complexes and of autoimmune antibodies to phosphatidylserine, factors previously associated with severe anemia in malaria patients, we observed that XO is not associated with them, suggesting that XO is associated with severe anemia through an independent mechanism. XO was associated with prostration, acidosis, jaundice, respiratory distress, and kidney injury, which may reflect a broader relation of this enzyme with severe malaria pathology. Since inhibitors of XO are inexpensive and well-tolerated drugs already approved for use in humans, the validation of XO as a contributor to severe malarial anemia and other malaria complications may open new possibilities for much needed adjunctive therapy in malaria.

Causes of Death Among Infants and Children in the Child Health and Mortality Prevention Surveillance (CHAMPS) Network.

Importance: The number of deaths of children younger than 5 years has been steadily decreasing worldwide, from more than 17 million annual deaths in the 1970s to an estimated 5.3 million in 2019 (with 2.8 million deaths occurring in those aged 1-59 months [53% of all deaths in children aged <5 years]). More detailed characterization of childhood deaths could inform interventions to improve child survival. Objective: To describe causes of postneonatal child deaths across 7 mortality surveillance sentinel sites in Africa and Asia. Design, Setting, and Participants: The Child Health and Mortality Prevention Surveillance (CHAMPS) Network conducts childhood mortality surveillance in sub-Saharan Africa and South Asia using innovative postmortem minimally invasive tissue sampling (MITS). In this cross-sectional study, MITS was conducted in deceased children aged 1 to 59 months at 7 sites in sub-Saharan Africa and South Asia from December 3, 2016, to December 3, 2020. Data analysis was conducted between October and November 2021. Main Outcomes and Measures: The expert panel attributed underlying, intermediate, and immediate conditions in the chain of events leading to death, based on histopathologic analysis, microbiological diagnostics, clinical data, and verbal autopsies. Results: In this study, MITS was performed in 632 deceased children (mean [SD] age at death, 1.3 [0.3] years; 342 [54.1%] male). The 6 most common underlying causes of death were malnutrition (104 [16.5%]), HIV (75 [11.9%]), malaria (71 [11.2%]), congenital birth defects (64 [10.1%]), lower respiratory tract infections (LRTIs; 53 [8.4%]), and diarrheal diseases (46 [7.2%]). When considering immediate causes only, sepsis (191 [36.7%]) and LRTI (129 [24.8%]) were the 2 dominant causes. An infection was present in the causal chain in 549 of 632 deaths (86.9%); pathogens most frequently contributing to infectious deaths included Klebsiella pneumoniae (155 of 549 infectious deaths [28.2%]; 127 [81.9%] considered nosocomial), Plasmodium falciparum (122 of 549 [22.2%]), and Streptococcus pneumoniae (109 of 549 [19.9%]). Other organisms, such as cytomegalovirus (57 [10.4%]) and Acinetobacter baumannii (39 [7.1%]; 35 of 39 [89.7%] considered nosocomial), also played important roles. For the top underlying causes of death, the median number of conditions in the chain of events leading to death was 3 for malnutrition, 3 for HIV, 1 for malaria, 3 for congenital birth defects, and 1 for LRTI. Expert panels considered 494 of 632 deaths (78.2%) preventable and 26 of 632 deaths (4.1%) preventable under certain conditions. Conclusions and Relevance: In this cross-sectional study investigating causes of child mortality in the CHAMPS Network, results indicate that, in these high-mortality settings, infectious diseases continue to cause most deaths in infants and children, often in conjunction with malnutrition. These results also highlight opportunities for action to prevent deaths and reveal common interaction of various causes in the path toward death.

Correction: Evaluation of kidney function among people living with HIV initiating antiretroviral therapy in Zambia.

[This corrects the article DOI: 10.1371/journal.pgph.0000124.].

Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence.

Only around 20% of the human proteome is considered to be druggable with small-molecule antagonists. This leaves some of the most compelling therapeutic targets outside the reach of ligand discovery. The concept of targeted protein degradation (TPD) promises to overcome some of these limitations. In brief, TPD is dependent on small molecules that induce the proximity between a protein of interest (POI) and an E3 ubiquitin ligase, causing ubiquitination and degradation of the POI. In this perspective, we want to reflect on current challenges in the field, and discuss how advances in multiomics profiling, artificial intelligence, and machine learning (AI/ML) will be vital in overcoming them. The presented roadmap is discussed in the context of small-molecule degraders but is equally applicable for other emerging proximity-inducing modalities.

Chemoinformatics and artificial intelligence colloquium: progress and challenges in developing bioactive compounds.

We report the main conclusions of the first Chemoinformatics and Artificial Intelligence Colloquium, Mexico City, June 15-17, 2022. Fifteen lectures were presented during a virtual public event with speakers from industry, academia, and non-for-profit organizations. Twelve hundred and ninety students and academics from more than 60 countries. During the meeting, applications, challenges, and opportunities in drug discovery, de novo drug design, ADME-Tox (absorption, distribution, metabolism, excretion and toxicity) property predictions, organic chemistry, peptides, and antibiotic resistance were discussed. The program along with the recordings of all sessions are freely available at https://www.difacquim.com/english/events/2022-colloquium/ .

Integrating and formatting biomedical data as pre-calculated knowledge graph embeddings in the Bioteque.

Biomedical data is accumulating at a fast pace and integrating it into a unified framework is a major challenge, so that multiple views of a given biological event can be considered simultaneously. Here we present the Bioteque, a resource of unprecedented size and scope that contains pre-calculated biomedical descriptors derived from a gigantic knowledge graph, displaying more than 450 thousand biological entities and 30 million relationships between them. The Bioteque integrates, harmonizes, and formats data collected from over 150 data sources, including 12 biological entities (e.g., genes, diseases, drugs) linked by 67 types of associations (e.g., 'drug treats disease', 'gene interacts with gene'). We show how Bioteque descriptors facilitate the assessment of high-throughput protein-protein interactome data, the prediction of drug response and new repurposing opportunities, and demonstrate that they can be used off-the-shelf in downstream machine learning tasks without loss of performance with respect to using original data. The Bioteque thus offers a thoroughly processed, tractable, and highly optimized assembly of the biomedical knowledge available in the public domain.

IL-4, IL-10, CCL2 and TGF-ß as potential biomarkers for severity in Plasmodium vivax malaria.

Cytokines and chemokines are immune response molecules that display diverse functions, such as inflammation and immune regulation. In Plasmodium vivax infections, the uncontrolled production of these molecules is thought to contribute to pathogenesis and has been proposed as a possible predictor for disease complications. The objective of this study was to evaluate the cytokine profile of P. vivax malaria patients with different clinical outcomes to identify possible immune biomarkers for severe P. vivax malaria. The study included patients with non-severe (n = 56), or severe (n = 50) P. vivax malaria and healthy controls (n = 50). Patient plasma concentrations of IL-4, IL-2, CXCL10, IL-1ß, TNF-α, CCL2, IL-17A, IL-6, IL-10, IFN-γ, IL-12p70, CXCL8 and active TGF-ß1 were determined through flow cytometry. The levels of several cytokines and chemokines, CXCL10, IL-10, IL-6, IL-4, CCL2 and IFN-γ were found to be significantly higher in severe, compared to non-severe P. vivax malaria patients. Severe thrombocytopenia was positively correlated with IL-4, CXCL10, IL-6, IL-10 and IFN-γ levels, renal dysfunction was related to an increase in IL-2, IL-1ß, IL-17A and IL-8, and hepatic impairment with CXCL10, MCP-1, IL-6 and IFN-γ. A Lasso regression model suggests that IL-4, IL-10, CCL2 and TGF-ß might be developed as biomarkers for severity in P. vivax malaria. Severe P. vivax malaria patients present specific cytokine and chemokine profiles that are different from non-severe patients and that could potentially be developed as biomarkers for disease severity.

A community challenge for a pancancer drug mechanism of action inference from perturbational profile data.

The Columbia Cancer Target Discovery and Development (CTD2) Center is developing PANACEA, a resource comprising dose-responses and RNA sequencing (RNA-seq) profiles of 25 cell lines perturbed with ∼400 clinical oncology drugs, to study a tumor-specific drug mechanism of action. Here, this resource serves as the basis for a DREAM Challenge assessing the accuracy and sensitivity of computational algorithms for de novo drug polypharmacology predictions. Dose-response and perturbational profiles for 32 kinase inhibitors are provided to 21 teams who are blind to the identity of the compounds. The teams are asked to predict high-affinity binding targets of each compound among ∼1,300 targets cataloged in DrugBank. The best performing methods leverage gene expression profile similarity analysis as well as deep-learning methodologies trained on individual datasets. This study lays the foundation for future integrative analyses of pharmacogenomic data, reconciliation of polypharmacology effects in different tumor contexts, and insights into network-based assessments of drug mechanisms of action.

Connecting chemistry and biology through molecular descriptors.

Through the representation of small molecule structures as numerical descriptors and the exploitation of the similarity principle, chemoinformatics has made paramount contributions to drug discovery, from unveiling mechanisms of action and repurposing approved drugs to de novo crafting of molecules with desired properties and tailored targets. Yet, the inherent complexity of biological systems has fostered the implementation of large-scale experimental screenings seeking a deeper understanding of the targeted proteins, the disrupted biological processes and the systemic responses of cells to chemical perturbations. After this wealth of data, a new generation of data-driven descriptors has arisen providing a rich portrait of small molecule characteristics that goes beyond chemical properties. Here, we give an overview of biologically relevant descriptors, covering chemical compounds, proteins and other biological entities, such as diseases and cell lines, while aligning them to the major contributions in the field from disciplines, such as natural language processing or computer vision. We now envision a new scenario for chemical and biological entities where they both are translated into a common numerical format. In this computational framework, complex connections between entities can be unveiled by means of simple arithmetic operations, such as distance measures, additions, and subtractions.

Evaluation of kidney function among people living with HIV initiating antiretroviral therapy in Zambia.

As the response to the HIV epidemic in sub-Saharan Africa continues to mature, a growing number of people living with HIV (PLHIV) are aging and risk for non-communicable diseases increases. Routine laboratory tests of serum creatinine have been conducted to assess HIV treatment (ART) suitability. Here we utilize those measures to assess kidney function impairment among those initiating ART. Identification of non-communicable disease (NCD) risks among those in HIV care creates opportunity to improve public health through care referral and/or NCD/HIV care integration. We estimated glomerular filtration rates (eGFR) using routinely collected serum creatinine measures among a cohort of PLHIV with an HIV care visit at one of 113 Centre for Infectious Disease Research Zambia (CIDRZ) supported sites between January 1, 2011 and December 31, 2017, across seven of the ten provinces in Zambia. We used mixed-effect Poisson regression to assess predictors of eGFR <60ml/min/1.73m2 allowing random effects at the individual and facility level. Additionally, we assessed agreement between four eGFR formulae with unadjusted CKD-EPI as a standard using Scott/Fleiss method across five categories of kidney function. A total of 72,933 observations among 68,534 individuals met the inclusion criteria for analysis. Of the 68,534, the majority were female 41,042 (59.8%), the median age was 34 (interquartile range [IQR]: 28-40), and median CD4 cell count was 292 (IQR: 162-435). The proportion of individuals with an eGFR <60ml/min/1.73m2 was 6.9% (95% CI: 6.7-7.1%) according to the unadjusted CKD-EPI equation. There was variation in agreement across eGFR formulas considered compared to unadjusted CKD-EPI (χ2 p-value <0.001). Estimated GFR less than 60ml/min/1.73m2, per the unadjusted CKD-EPI equation, was significantly associated with age, sex, body mass index, and blood pressure. Using routine serum creatinine measures, we identified a significant proportion of individuals with eGFR indicating moderate or great kidney function impairment among PLHIV initiating ART in Zambia. It is possible that differentiated service delivery models could be developed to address this subset of those in HIV care with increased risk of chronic kidney disease.

Identification and drug-induced reversion of molecular signatures of Alzheimer's disease onset and progression in AppNL-G-F, AppNL-F, and 3xTg-AD mouse models.

BACKGROUND: In spite of many years of research, our understanding of the molecular bases of Alzheimer's disease (AD) is still incomplete, and the medical treatments available mainly target the disease symptoms and are hardly effective. Indeed, the modulation of a single target (e.g., ß-secretase) has proven to be insufficient to significantly alter the physiopathology of the disease, and we should therefore move from gene-centric to systemic therapeutic strategies, where AD-related changes are modulated globally. METHODS: Here we present the complete characterization of three murine models of AD at different stages of the disease (i.e., onset, progression and advanced). We combined the cognitive assessment of these mice with histological analyses and full transcriptional and protein quantification profiling of the hippocampus. Additionally, we derived specific Aß-related molecular AD signatures and looked for drugs able to globally revert them. RESULTS: We found that AD models show accelerated aging and that factors specifically associated with Aß pathology are involved. We discovered a few proteins whose abundance increases with AD progression, while the corresponding transcript levels remain stable, and showed that at least two of them (i.e., lfit3 and Syt11) co-localize with Aß plaques in the brain. Finally, we found two NSAIDs (dexketoprofen and etodolac) and two anti-hypertensives (penbutolol and bendroflumethiazide) that overturn the cognitive impairment in AD mice while reducing Aß plaques in the hippocampus and partially restoring the physiological levels of AD signature genes to wild-type levels. CONCLUSIONS: The characterization of three AD mouse models at different disease stages provides an unprecedented view of AD pathology and how this differs from physiological aging. Moreover, our computational strategy to chemically revert AD signatures has shown that NSAID and anti-hypertensive drugs may still have an opportunity as anti-AD agents, challenging previous reports.

Computational Applications in Secondary Metabolite Discovery (CAiSMD): an online workshop.

We report the major conclusions of the online open-access workshop "Computational Applications in Secondary Metabolite Discovery (CAiSMD)" that took place from 08 to 10 March 2021. Invited speakers from academia and industry and about 200 registered participants from five continents (Africa, Asia, Europe, South America, and North America) took part in the workshop. The workshop highlighted the potential applications of computational methodologies in the search for secondary metabolites (SMs) or natural products (NPs) as potential drugs and drug leads. During 3 days, the participants of this online workshop received an overview of modern computer-based approaches for exploring NP discovery in the "omics" age. The invited experts gave keynote lectures, trained participants in hands-on sessions, and held round table discussions. This was followed by oral presentations with much interaction between the speakers and the audience. Selected applicants (early-career scientists) were offered the opportunity to give oral presentations (15 min) and present posters in the form of flash presentations (5 min) upon submission of an abstract. The final program available on the workshop website ( https://caismd.indiayouth.info/ ) comprised of 4 keynote lectures (KLs), 12 oral presentations (OPs), 2 round table discussions (RTDs), and 5 hands-on sessions (HSs). This meeting report also references internet resources for computational biology in the area of secondary metabolites that are of use outside of the workshop areas and will constitute a long-term valuable source for the community. The workshop concluded with an online survey form to be completed by speakers and participants for the goal of improving any subsequent editions.

Bioactivity descriptors for uncharacterized chemical compounds.

Chemical descriptors encode the physicochemical and structural properties of small molecules, and they are at the core of chemoinformatics. The broad release of bioactivity data has prompted enriched representations of compounds, reaching beyond chemical structures and capturing their known biological properties. Unfortunately, bioactivity descriptors are not available for most small molecules, which limits their applicability to a few thousand well characterized compounds. Here we present a collection of deep neural networks able to infer bioactivity signatures for any compound of interest, even when little or no experimental information is available for them. Our signaturizers relate to bioactivities of 25 different types (including target profiles, cellular response and clinical outcomes) and can be used as drop-in replacements for chemical descriptors in day-to-day chemoinformatics tasks. Indeed, we illustrate how inferred bioactivity signatures are useful to navigate the chemical space in a biologically relevant manner, unveiling higher-order organization in natural product collections, and to enrich mostly uncharacterized chemical libraries for activity against the drug-orphan target Snail1. Moreover, we implement a battery of signature-activity relationship (SigAR) models and show a substantial improvement in performance, with respect to chemistry-based classifiers, across a series of biophysics and physiology activity prediction benchmarks.

Cervical cancer screening outcomes in Zambia, 2010-19: a cohort study.

BACKGROUND: Globally, cervical cancer is the fourth leading cause of cancer-related death among women. Poor uptake of screening services contributes to the high mortality. We aimed to examine screening frequency, predictors of screening results, and patterns of sensitisation strategies by age group in a large, programmatic cohort. METHODS: We did a cohort study including 11 government health facilities in Lusaka, Zambia, in which we reviewed routine programmatic data collected through the Cervical Cancer Prevention Program in Zambia (CCPPZ). Participants who underwent cervical cancer screening in one of the participating study sites were considered for study inclusion if they had a screening result. Follow-up was accomplished per national guidelines. We did descriptive analyses and mixed-effects logistic regression for cervical cancer screening results allowing random effects at the individual and clinic level. FINDINGS: Between Jan 1, 2010, and July 31, 2019, we included 183 165 women with 204 225 results for visual inspection with acetic acid and digital cervicography (VIAC) in the analysis. Of all those screened, 21 326 (10·4%) were VIAC-positive, of whom 16 244 (76·2%) received treatment. Of 204 225 screenings, 92 838 (45·5%) were in women who were HIV-negative, 76 607 (37·5%) were in women who were HIV-positive, and 34 780 (17·0%) had an unknown HIV status. Screening frequency increased 65·7% between 2010 and 2019 with most appointments being first-time screenings (n=158 940 [77·8%]). Women with HIV were more likely to test VIAC-positive than women who were HIV-negative (adjusted odds ratio 3·60, 95% CI 2·14-6·08). Younger women (≤29 years) with HIV had the highest predictive probability (18·6%, 95% CI 14·2-22·9) of screening positive. INTERPRETATION: CCPPZ has effectively increased women's engagement in screening since its inception in 2006. Customised sensitisation strategies relevant to different age groups could increase uptake and adherence to screening. The high proportion of screen positivity in women younger than 20 years with HIV requires further consideration. Our data are not able to discern if women with HIV have earlier disease onset or whether this difference reflects misclassification of disease in an age group with a higher sexually transmitted infection prevalence. These data inform scale-up efforts required to achieve WHO elimination targets. FUNDING: US President's Emergency Plan for AIDS Relief.

Personalized cancer therapy prioritization based on driver alteration co-occurrence patterns.

Identification of actionable genomic vulnerabilities is key to precision oncology. Utilizing a large-scale drug screening in patient-derived xenografts, we uncover driver gene alteration connections, derive driver co-occurrence (DCO) networks, and relate these to drug sensitivity. Our collection of 53 drug-response predictors attains an average balanced accuracy of 58% in a cross-validation setting, rising to 66% for a subset of high-confidence predictions. We experimentally validated 12 out of 14 predictions in mice and adapted our strategy to obtain drug-response models from patients' progression-free survival data. Our strategy reveals links between oncogenic alterations, increasing the clinical impact of genomic profiling.