Node-degree aware edge sampling mitigates inflated classification performance in biomedical random walk-based graph representation learning.

Motivation: Graph representation learning is a family of related approaches that learn low-dimensional vector representations of nodes and other graph elements called embeddings. Embeddings approximate characteristics of the graph and can be used for a variety of machine-learning tasks such as novel edge prediction. For many biomedical applications, partial knowledge exists about positive edges that represent relationships between pairs of entities, but little to no knowledge is available about negative edges that represent the explicit lack of a relationship between two nodes. For this reason, classification procedures are forced to assume that the vast majority of unlabeled edges are negative. Existing approaches to sampling negative edges for training and evaluating classifiers do so by uniformly sampling pairs of nodes. Results: We show here that this sampling strategy typically leads to sets of positive and negative examples with imbalanced node degree distributions. Using representative heterogeneous biomedical knowledge graph and random walk-based graph machine learning, we show that this strategy substantially impacts classification performance. If users of graph machine-learning models apply the models to prioritize examples that are drawn from approximately the same distribution as the positive examples are, then performance of models as estimated in the validation phase may be artificially inflated. We present a degree-aware node sampling approach that mitigates this effect and is simple to implement. Availability and implementation: Our code and data are publicly available at https://github.com/monarch-initiative/negativeExampleSelection.

Overview of the Knowledge Management Center for Illuminating the Druggable Genome.

The Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) project aims to aggregate, update, and articulate protein-centric data knowledge for the entire human proteome, with emphasis on the understudied proteins from the three IDG protein families. KMC collates and analyzes data from over 70 resources to compile the Target Central Resource Database (TCRD), which is the web-based informatics platform (Pharos). These data include experimental, computational, and text-mined information on protein structures, compound interactions, and disease and phenotype associations. Based on this knowledge, proteins are classified into different Target Development Levels (TDLs) for identification of understudied targets. Additional work by the KMC focuses on enriching target knowledge and producing DrugCentral and other data visualization tools for expanding investigation of understudied targets.

Artificial Intelligence for Drug Discovery: Are We There Yet?

Drug discovery is adapting to novel technologies such as data science, informatics, and artificial intelligence (AI) to accelerate effective treatment development while reducing costs and animal experiments. AI is transforming drug discovery, as indicated by increasing interest from investors, industrial and academic scientists, and legislators. Successful drug discovery requires optimizing properties related to pharmacodynamics, pharmacokinetics, and clinical outcomes. This review discusses the use of AI in the three pillars of drug discovery: diseases, targets, and therapeutic modalities, with a focus on small-molecule drugs. AI technologies, such as generative chemistry, machine learning, and multiproperty optimization, have enabled several compounds to enter clinical trials. The scientific community must carefully vet known information to address the reproducibility crisis. The full potential of AI in drug discovery can only be realized with sufficient ground truth and appropriate human intervention at later pipeline stages.

Exploring DrugCentral: from molecular structures to clinical effects.

DrugCentral, accessible at https://drugcentral.org , is an open-access online drug information repository. It covers over 4950 drugs, incorporating structural, physicochemical, and pharmacological details to support drug discovery, development, and repositioning. With around 20,000 bioactivity data points, manual curation enhances information from several major digital sources. Approximately 724 mechanism-of-action (MoA) targets offer updated drug target insights. The platform captures clinical data: over 14,300 on- and off-label uses, 27,000 contraindications, and around 340,000 adverse drug events from pharmacovigilance reports. DrugCentral encompasses information from molecular structures to marketed formulations, providing a comprehensive pharmaceutical reference. Users can easily navigate basic drug information and key features, making DrugCentral a versatile, unique resource. Furthermore, we present a use-case example where we utilize experimentally determined data from DrugCentral to support drug repurposing. A minimum activity threshold t should be considered against novel targets to repurpose a drug. Analyzing 1156 bioactivities for human MoA targets suggests a general threshold of 1 µM: t = 6 when expressed as - log[Activity(M)]). This applies to 87% of the drugs. Moreover, t can be refined empirically based on water solubility (S): t = 3 - logS, for logS < - 3. Alongside the drug repurposing classification scheme, which considers intellectual property rights, market exclusivity protections, and market accessibility, DrugCentral provides valuable data to prioritize candidates for drug repurposing programs efficiently.

Molecular Complexity: You Know It When You See It.

Molecular complexity (MC) lacks a universal definition, but various studies address it in contexts ranging from ligand-receptor interactions to DNA sequencing, with the overarching emphasis being its significance in synthetic organic chemistry and pharmaceutical research. Efforts to quantify MC in drug discovery have been numerous, but a unified approach remains challenging. Strategies based on graph theory, information theory, and substructural feature counts employed to gauge MC are often correlated to molecular weight (MW). Herbert Waldmann and his team introduced a new MC metric called the spacial score (SPS), which is based on factors like atom hybridization and stereoisomeric considerations. While SPS and its normalized version, nSPS, correlate with the natural product likeness score, they do not align with traditional chemical properties. We examined nSPS trends for approved drugs and found no significant changes in MC over eight decades, nor did nSPS capture drug innovation during that period. Furthermore, our analysis indicates that while the majority of approved drugs have an nSPS value between 10 and 20, this metric does not correlate with key drug properties like target bioactivity and oral bioavailability. Mirroring a chemist's intuitive sense of chemical complexity, nSPS addresses the need for a precise empirical tool while a universal definition of MC remains elusive.

Toxicology knowledge graph for structural birth defects.

BACKGROUND: Birth defects are functional and structural abnormalities that impact about 1 in 33 births in the United States. They have been attributed to genetic and other factors such as drugs, cosmetics, food, and environmental pollutants during pregnancy, but for most birth defects there are no known causes. METHODS: To further characterize associations between small molecule compounds and their potential to induce specific birth abnormalities, we gathered knowledge from multiple sources to construct a reproductive toxicity Knowledge Graph (ReproTox-KG) with a focus on associations between birth defects, drugs, and genes. Specifically, we gathered data from drug/birth-defect associations from co-mentions in published abstracts, gene/birth-defect associations from genetic studies, drug- and preclinical-compound-induced gene expression changes in cell lines, known drug targets, genetic burden scores for human genes, and placental crossing scores for small molecules. RESULTS: Using ReproTox-KG and semi-supervised learning (SSL), we scored >30,000 preclinical small molecules for their potential to cross the placenta and induce birth defects, and identified >500 birth-defect/gene/drug cliques that can be used to explain molecular mechanisms for drug-induced birth defects. The ReproTox-KG can be accessed via a web-based user interface available at https://maayanlab.cloud/reprotox-kg . This site enables users to explore the associations between birth defects, approved and preclinical drugs, and all human genes. CONCLUSIONS: ReproTox-KG provides a resource for exploring knowledge about the molecular mechanisms of birth defects with the potential of predicting the likelihood of genes and preclinical small molecules to induce birth defects.

While birth defects are common, for most birth defects there are no known causes. During pregnancy, developing babies are exposed to drugs, cosmetics, food, and environmental pollutants that may cause birth defects. However, exactly how these environmental factors are involved in producing birth defects is difficult to discern. Also, birth defects can be a consequence of the genes inherited from the parents. We combined general data about human genes and drugs with specific data previously implicating genes and drugs in inducing birth defects to create a knowledge graph representation that connects genes, drugs, and birth defects. This knowledge graph can be used to explore new links that may explain why birth defects occur, particularly those that result from a combination of inherited and environmental influences.

Illuminating the druggable genome through patent bioactivity data.

The patent literature is a potentially valuable source of bioactivity data. In this article we describe a process to prioritise 3.7 million life science relevant patents obtained from the SureChEMBL database (https://www.surechembl.org/), according to how likely they were to contain bioactivity data for potent small molecules on less-studied targets, based on the classification developed by the Illuminating the Druggable Genome (IDG) project. The overall goal was to select a smaller number of patents that could be manually curated and incorporated into the ChEMBL database. Using relatively simple annotation and filtering pipelines, we have been able to identify a substantial number of patents containing quantitative bioactivity data for understudied targets that had not previously been reported in the peer-reviewed medicinal chemistry literature. We quantify the added value of such methods in terms of the numbers of targets that are so identified, and provide some specific illustrative examples. Our work underlines the potential value in searching the patent corpus in addition to the more traditional peer-reviewed literature. The small molecules found in these patents, together with their measured activity against the targets, are now accessible via the ChEMBL database.

Pharos 2023: an integrated resource for the understudied human proteome.

The Illuminating the Druggable Genome (IDG) project aims to improve our understanding of understudied proteins and our ability to study them in the context of disease biology by perturbing them with small molecules, biologics, or other therapeutic modalities. Two main products from the IDG effort are the Target Central Resource Database (TCRD) (http://juniper.health.unm.edu/tcrd/), which curates and aggregates information, and Pharos (https://pharos.nih.gov/), a web interface for fusers to extract and visualize data from TCRD. Since the 2021 release, TCRD/Pharos has focused on developing visualization and analysis tools that help reveal higher-level patterns in the underlying data. The current iterations of TCRD and Pharos enable users to perform enrichment calculations based on subsets of targets, diseases, or ligands and to create interactive heat maps and UpSet charts of many types of annotations. Using several examples, we show how to address disease biology and drug discovery questions through enrichment calculations and UpSet charts.

DrugCentral 2023 extends human clinical data and integrates veterinary drugs.

DrugCentral monitors new drug approvals and standardizes drug information. The current update contains 285 drugs (131 for human use). New additions include: (i) the integration of veterinary drugs (154 for animal use only), (ii) the addition of 66 documented off-label uses and iii) the identification of adverse drug events from pharmacovigilance data for pediatric and geriatric patients. Additional enhancements include chemical substructure searching using SMILES and 'Target Cards' based on UniProt accession codes. Statistics of interests include the following: (i) 60% of the covered drugs are on-market drugs with expired patent and exclusivity coverage, 17% are off-market, and 23% are on-market drugs with active patents and exclusivity coverage; (ii) 59% of the drugs are oral, 33% are parenteral and 18% topical, at the level of the active ingredients; (iii) only 3% of all drugs are for animal use only; however, 61% of the veterinary drugs are also approved for human use; (iv) dogs, cats and horses are by far the most represented target species for veterinary drugs; (v) the physicochemical property profile of animal drugs is very similar to that of human drugs. Use cases include azaperone, the only sedative approved for swine, and ruxolitinib, a Janus kinase inhibitor.

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/ .

Interpretable deep learning translation of GWAS and multi-omics findings to identify pathobiology and drug repurposing in Alzheimer's disease.

Translating human genetic findings (genome-wide association studies [GWAS]) to pathobiology and therapeutic discovery remains a major challenge for Alzheimer's disease (AD). We present a network topology-based deep learning framework to identify disease-associated genes (NETTAG). We leverage non-coding GWAS loci effects on quantitative trait loci, enhancers and CpG islands, promoter regions, open chromatin, and promoter flanking regions under the protein-protein interactome. Via NETTAG, we identified 156 AD-risk genes enriched in druggable targets. Combining network-based prediction and retrospective case-control observations with 10 million individuals, we identified that usage of four drugs (ibuprofen, gemfibrozil, cholecalciferol, and ceftriaxone) is associated with reduced likelihood of AD incidence. Gemfibrozil (an approved lipid regulator) is significantly associated with 43% reduced risk of AD compared with simvastatin using an active-comparator design (95% confidence interval 0.51-0.63, p < 0.0001). In summary, NETTAG offers a deep learning methodology that utilizes GWAS and multi-genomic findings to identify pathobiology and drug repurposing in AD.

Agent-based modeling predicts RAC1 is critical for ovarian cancer metastasis.

Experimental and computational studies pinpoint rate-limiting step(s) in metastasis governed by Rac1. Using ovarian cancer cell and animal models, Rac1 expression was manipulated, and quantitative measurements of cell-cell and cell-substrate adhesion, cell invasion, mesothelial clearance, and peritoneal tumor growth discriminated the tumor behaviors most highly influenced by Rac1. The experimental data were used to parameterize an agent-based computational model simulating peritoneal niche colonization, intravasation, and hematogenous metastasis to distant organs. Increased ovarian cancer cell survival afforded by the more rapid adhesion and intravasation upon Rac1 overexpression is predicted to increase the numbers of and the rates at which tumor cells are disseminated to distant sites. Surprisingly, crowding of cancer cells along the blood vessel was found to decrease the numbers of cells reaching a distant niche irrespective of Rac1 overexpression or knockdown, suggesting that sites for tumor cell intravasation are rate limiting and become accessible if cells intravasate rapidly or are displaced due to diminished viability. Modeling predictions were confirmed through animal studies of Rac1-dependent metastasis to the lung. Collectively, the experimental and modeling approaches identify cell adhesion, rapid intravasation, and survival in the blood as parameters in the ovarian metastatic cascade that are most critically dependent on Rac1.

CACHE (Critical Assessment of Computational Hit-finding Experiments): A public-private partnership benchmarking initiative to enable the development of computational methods for hit-finding.

One aspirational goal of computational chemistry is to predict potent and drug-like binders for any protein, such that only those that bind are synthesized. In this Roadmap, we describe the launch of Critical Assessment of Computational Hit-finding Experiments (CACHE), a public benchmarking project to compare and improve small molecule hit-finding algorithms through cycles of prediction and experimental testing. Participants will predict small molecule binders for new and biologically relevant protein targets representing different prediction scenarios. Predicted compounds will be tested rigorously in an experimental hub, and all predicted binders as well as all experimental screening data, including the chemical structures of experimentally tested compounds, will be made publicly available, and not subject to any intellectual property restrictions. The ability of a range of computational approaches to find novel binders will be evaluated, compared, and openly published. CACHE will launch 3 new benchmarking exercises every year. The outcomes will be better prediction methods, new small molecule binders for target proteins of importance for fundamental biology or drug discovery, and a major technological step towards achieving the goal of Target 2035, a global initiative to identify pharmacological probes for all human proteins.

AlphaFold illuminates half of the dark human proteins.

We investigate the use of confidence scores to evaluate the accuracy of a given AlphaFold (AF2) protein model for drug discovery. Prediction of accuracy is improved by not considering confidence scores below 80 due to the effects of disorder. On a set of recent crystal structures, 95% are likely to have accurate folds. Conformational discordance in the training set has a much more significant effect on accuracy than sequence divergence. We propose criteria for models and residues that are possibly useful for virtual screening. Based on these criteria, AF2 provides models for half of understudied (dark) human proteins and two-thirds of residues in those models.

Diseases 2.0: a weekly updated database of disease-gene associations from text mining and data integration.

The scientific knowledge about which genes are involved in which diseases grows rapidly, which makes it difficult to keep up with new publications and genetics datasets. The DISEASES database aims to provide a comprehensive overview by systematically integrating and assigning confidence scores to evidence for disease-gene associations from curated databases, genome-wide association studies (GWAS) and automatic text mining of the biomedical literature. Here, we present a major update to this resource, which greatly increases the number of associations from all these sources. This is especially true for the text-mined associations, which have increased by at least 9-fold at all confidence cutoffs. We show that this dramatic increase is primarily due to adding full-text articles to the text corpus, secondarily due to improvements to both the disease and gene dictionaries used for named entity recognition, and only to a very small extent due to the growth in number of PubMed abstracts. DISEASES now also makes use of a new GWAS database, Target Illumination by GWAS Analytics, which considerably increased the number of GWAS-derived disease-gene associations. DISEASES itself is also integrated into several other databases and resources, including GeneCards/MalaCards, Pharos/Target Central Resource Database and the Cytoscape stringApp. All data in DISEASES are updated on a weekly basis and is available via a web interface at https://diseases.jensenlab.org, from where it can also be downloaded under open licenses. Database URL: https://diseases.jensenlab.org.

State of the Art and Uses for the Biopharmaceutics Drug Disposition Classification System (BDDCS): New Additions, Revisions, and Citation References.

The Biopharmaceutics Drug Disposition Classification system (BDDCS) is a four-class approach based on water solubility and extent of metabolism/permeability rate. Based on the BDDCS class to which a drug is assigned, it is possible to predict the role of metabolic enzymes and transporters on the drug disposition of a new molecular entity (NME) prior to its administration to animals or humans. Here, we report a total of 1475 drugs and active metabolites to which the BDDCS is applied. Of these, 379 are new entries, and 1096 are revisions of former classification studies with the addition of references for the approved maximum dose strength, extent of the systemically available drug excreted unchanged in the urine, and lowest solubility over the pH range 1.0-6.8 when such information is available in the literature. We detail revised class assignments of previously misclassified drugs and the literature analyses to classify new drugs. We review the process of solubility assessment for NMEs prior to drug dosing in humans and approved dose classification, as well as the comparison of Biopharmaceutics Classification System (BCS) versus BDDCS assignment. We detail the uses of BDDCS in predicting, prior to dosing animals or humans, disposition characteristics, potential brain penetration, food effect, and drug-induced liver injury (DILI) potential. This work provides an update on the current status of the BDDCS and its uses in the drug development process.

A Comprehensive COVID-19 Daily News and Medical Literature Briefing to Inform Health Care and Policy in New Mexico: Implementation Study.

BACKGROUND: On March 11, 2020, the New Mexico Governor declared a public health emergency in response to the COVID-19 pandemic. The New Mexico medical advisory team contacted University of New Mexico (UNM) faculty to form a team to consolidate growing information on severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and its disease to facilitate New Mexico's pandemic management. Thus, faculty, physicians, staff, graduate students, and medical students created the "UNM Global Health COVID-19 Intelligence Briefing." OBJECTIVE: In this paper, we sought to (1) share how to create an informative briefing to guide public policy and medical practice and manage information overload with rapidly evolving scientific evidence; (2) determine the qualitative usefulness of the briefing to its readers; and (3) determine the qualitative effect this project has had on virtual medical education. METHODS: Microsoft Teams was used for manual and automated capture of COVID-19 articles and composition of briefings. Multilevel triaging saved impactful articles to be reviewed, and priority was placed on randomized controlled studies, meta-analyses, systematic reviews, practice guidelines, and information on health care and policy response to COVID-19. The finalized briefing was disseminated by email, a listserv, and posted on the UNM digital repository. A survey was sent to readers to determine briefing usefulness and whether it led to policy or medical practice changes. Medical students, unable to partake in direct patient care, proposed to the School of Medicine that involvement in the briefing should count as course credit, which was approved. The maintenance of medical student involvement in the briefings as well as this publication was led by medical students. RESULTS: An average of 456 articles were assessed daily. The briefings reached approximately 1000 people by email and listserv directly, with an unknown amount of forwarding. Digital repository tracking showed 5047 downloads across 116 countries as of July 5, 2020. The survey found 108 (95%) of 114 participants gained relevant knowledge, 90 (79%) believed it decreased misinformation, 27 (24%) used the briefing as their primary source of information, and 90 (79%) forwarded it to colleagues. Specific and impactful public policy decisions were informed based on the briefing. Medical students reported that the project allowed them to improve on their scientific literature assessment, stay current on the pandemic, and serve their community. CONCLUSIONS: The COVID-19 briefings succeeded in informing and guiding New Mexico policy and clinical practice. The project received positive feedback from the community and was shown to decrease information burden and misinformation. The virtual platforms allowed for the continuation of medical education. Variability in subject matter expertise was addressed with training, standardized article selection criteria, and collaborative editing led by faculty.