Reaction Database Research Articles

HLA-B allele frequencies and implications for pharmacogenetics in the Kuwaiti population.

We utilized the HLA-HD tool to extract, annotate, and analyse HLA-B alleles from the exome data of 561 Kuwaiti individuals, sequenced on the Illumina HiSeq platform. HLA typing was conducted using the HLA-HD tool with a reference panel from the IPD-IMGT/HLA database. The major HLA-B pharmacogenetic markers were obtained from the HLA Adverse Drug Reaction Database, focusing on alleles with significant ADR associations in published literature. The distribution of HLA-B alleles in the Kuwaiti population revealed that the most frequent alleles were HLA-B*50:01 (10.52%), HLA-B*51:01 (9.89%), HLA-B*08:01 (6.06%), HLA-B*52:01 (4.55%), HLA-B*18:01 (3.92%), and HLA-B*41:01 (3.65%). Notably, alleles HLA-B*13:01, HLA-B*13:02, HLA-B*15:02, HLA-B*15:13, HLA-B*35:02, HLA-B*35:05, HLA-B*38:01, HLA-B*40:02, HLA-B*44:03, HLA-B*51:01, HLA-B*57:01 and HLA-B*58:01 were identified with known associations to various ADRs. For example, HLA-B*51:01 was associated with clindamycin, phenobarbital, and phenytoin, and was found in 18% of individuals. Our study enriches the regional genetic landscape by delineating HLA-B allele variations within Kuwait and across the Arabian Peninsula. This genetic insight, along with the identification of markers previously linked to drug hypersensitivity, provides a foundation for future pharmacogenetic research and potential personalized medicine strategies in the region.

Development and validation of a clinical prediction model for osteonecrosis of the jaw in patients receiving zoledronic acid using FAERS and canadian databases.

Osteonecrosis of the jaw (ONJ) stands as a severe complication linked to the use of bisphosphonates, particularly zoledronic acid, which is widely prescribed for managing conditions like osteoporosis and bone metastasis. This study is geared towards the development and validation of a clinical prediction model for ONJ in patients undergoing zoledronic acid treatment. We harnessed data from the FDA Adverse Event Reporting System (FAERS) as our training dataset, while the Canada Vigilance Adverse Reaction (CVAR) database served as the testing dataset. The study encompassed patients treated with zoledronic acid and subsequently diagnosed with ONJ. We analysed a range of predictive factors, including breast cancer, bone metastasis, osteoporosis, vitamin D and calcium levels, comorbidities, the number of concomitant medications, dosage, age, weight, and gender. Logistic regression and nomogram analysis were the chosen methodologies for constructing the predictive model. To evaluate the model's performance, we utilized receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). The study encompassed a total of 2,126 patients in the training cohort, 911 patients in the internal test cohort from the FAERS database, and 121 patients in the external test cohort from the CVAR database. Notable predictors for ONJ included bone metastasis (OR: 1.65, 95% CI: 1.22-2.24), osteoporosis (OR: 0.33, 95% CI: 0.21-0.52), the number of concomitant medications (OR: 1.07, 95% CI: 1.05-1.09), and the dosage of zoledronic acid (OR: 1.24, 95% CI: 1.10-1.39). The nomogram exhibited robust discriminatory power, evidenced by an area under the curve (AUC) of 0.77 in the training cohort, 0.76 in the internal test cohort, and 0.90 in the external test cohort. Calibration plots demonstrated a strong alignment between observed and predicted probabilities. Furthermore, DCA highlighted the prediction model's significant net benefit across various threshold probabilities. By leveraging data from both the FAERS and Canadian databases, this study has successfully developed and validated a clinical prediction model for ONJ in patients receiving zoledronic acid. This model stands as a valuable tool for clinicians, enabling them to pinpoint high-risk patients and make evidence-based treatment decisions to minimize the risk of ONJ.

Ligify: Automated Genome Mining for Ligand-Inducible Transcription Factors.

Prokaryotic transcription factors can be repurposed into biosensors for the ligand-inducible control of gene expression, but the landscape of chemical ligands for which biosensors exist is extremely limited. To expand this landscape, we developed Ligify, a web application that leverages information in enzyme reaction databases to predict transcription factors that may be responsive to user-defined chemicals. Candidate transcription factors are then incorporated into automatically generated plasmid sequences that are designed to express GFP in response to the target chemical. Our benchmarking analyses demonstrated that Ligify correctly predicted 31/100 previously validated biosensors and highlighted strategies for further improvement. We then used Ligify to build a panel of genetic circuits that could induce a 47-fold, 5-fold, 9-fold, and 27-fold change in fluorescence in response to D-ribose, L-sorbose, isoeugenol, and 4-vinylphenol, respectively. Ligify should enhance the ability of researchers to quickly develop biosensors for an expanded range of chemicals and is publicly available at https://ligify.groov.bio.

Transfer learning across different chemical domains: virtual screening of organic materials with deep learning models pretrained on small molecule and chemical reaction data

Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, the scarcity of labeled data for organic materials poses a significant challenge for training advanced machine learning models. This study showcases the potential of utilizing databases of drug-like small molecules and chemical reactions to pretrain the BERT model, enhancing its performance in the virtual screening of organic materials. By fine-tuning the BERT models with data from five virtual screening tasks, the version pretrained with the USPTO–SMILES dataset achieved R2 scores exceeding 0.94 for three tasks and over 0.81 for two others. This performance surpasses that of models pretrained on the small molecule or organic materials databases and outperforms three traditional machine learning models trained directly on virtual screening data. The success of the USPTO–SMILES pretrained BERT model can be attributed to the diverse array of organic building blocks in the USPTO database, offering a broader exploration of the chemical space. The study further suggests that accessing a reaction database with a wider range of reactions than the USPTO could further enhance model performance. Overall, this research validates the feasibility of applying transfer learning across different chemical domains for the efficient virtual screening of organic materials.Scientific contributionThis study verifies the feasibility of applying transfer learning to large language models in different chemical fields to help organic materials perform virtual screening. Through the comparison of transfer learning from different chemical fields to a variety of organic material molecules, the high precision virtual screening of organic materials is realized.

Reaction rebalancing: a novel approach to curating reaction databases

PurposeReaction databases are a key resource for a wide variety of applications in computational chemistry and biochemistry, including Computer-aided Synthesis Planning (CASP) and the large-scale analysis of metabolic networks. The full potential of these resources can only be realized if datasets are accurate and complete. Missing co-reactants and co-products, i.e., unbalanced reactions, however, are the rule rather than the exception. The curation and correction of such incomplete entries is thus an urgent need.MethodsThe SynRBL framework addresses this issue with a dual-strategy: a rule-based method for non-carbon compounds, using atomic symbols and counts for prediction, alongside a Maximum Common Subgraph (MCS)-based technique for carbon compounds, aimed at aligning reactants and products to infer missing entities.ResultsThe rule-based method exceeded 99% accuracy, while MCS-based accuracy varied from 81.19 to 99.33%, depending on reaction properties. Furthermore, an applicability domain and a machine learning scoring function were devised to quantify prediction confidence. The overall efficacy of this framework was delineated through its success rate and accuracy metrics, which spanned from 89.83 to 99.75% and 90.85 to 99.05%, respectively.ConclusionThe SynRBL framework offers a novel solution for recalibrating chemical reactions, significantly enhancing reaction completeness. With rigorous validation, it achieved groundbreaking accuracy in reaction rebalancing. This sets the stage for future improvement in particular of atom-atom mapping techniques as well as of downstream tasks such as automated synthesis planning.Scientific ContributionSynRBL features a novel computational approach to correcting unbalanced entries in chemical reaction databases. By combining heuristic rules for inferring non-carbon compounds and common subgraph searches to address carbon unbalance, SynRBL successfully addresses most instances of this problem, which affects the majority of data in most large-scale resources. Compared to alternative solutions, SynRBL achieves a dramatic increase in both success rate and accurary, and provides the first freely available open source solution for this problem.

OpenChemIE: An Information Extraction Toolkit for Chemistry Literature.

Information extraction from chemistry literature is vital for constructing up-to-date reaction databases for data-driven chemistry. Complete extraction requires combining information across text, tables, and figures, whereas prior work has mainly investigated extracting reactions from single modalities. In this paper, we present OpenChemIE to address this complex challenge and enable the extraction of reaction data at the document level. OpenChemIE approaches the problem in two steps: extracting relevant information from individual modalities and then integrating the results to obtain a final list of reactions. For the first step, we employ specialized neural models that each address a specific task for chemistry information extraction, such as parsing molecules or reactions from text or figures. We then integrate the information from these modules using chemistry-informed algorithms, allowing for the extraction of fine-grained reaction data from reaction condition and substrate scope investigations. Our machine learning models attain state-of-the-art performance when evaluated individually, and we meticulously annotate a challenging dataset of reaction schemes with R-groups to evaluate our pipeline as a whole, achieving an F1 score of 69.5%. Additionally, the reaction extraction results of OpenChemIE attain an accuracy score of 64.3% when directly compared against the Reaxys chemical database. OpenChemIE is most suited for information extraction on organic chemistry literature, where molecules are generally depicted as planar graphs or written in text and can be consolidated into a SMILES format. We provide OpenChemIE freely to the public as an open-source package, as well as through a web interface.

ISTransbase: an online database for inhibitor and substrate of drug transporters

Abstract Drug transporters, integral membrane proteins found throughout the human body, play critical roles in physiological and biochemical processes through interactions with ligands, such as substrates and inhibitors. The extensive and disparate data on drug transporters complicate understanding their complex relationships with ligands. To address this challenge, it is essential to gather and summarize information on drug transporters, inhibitors and substrates, and simultaneously develop a comprehensive and user-friendly database. Current online resources often provide fragmented information and have limited coverage of drug transporter substrates and inhibitors, highlighting the need for a specialized, comprehensive and openly accessible database. ISTransbase addresses this gap by amassing a substantial amount of data from literature, government documents and open databases. It includes 16 528 inhibitors and 4465 substrates of 163 drug transporters from 18 different species, resulting in a total of 93 841 inhibitor records and 51 053 substrate records. ISTransbase provides detailed insights into drug transporters and their inhibitors/substrates, encompassing transporter and molecule structure, transporter function and distribution, as well as experimental methods and results from transport or inhibition experiments. Furthermore, ISTransbase offers three search strategies that allow users to retrieve drugs and transporters based on multiple selectable constraints, as well as perform checks for drug–drug interactions. Users can also browse and download data. In summary, ISTransbase (https://istransbase.scbdd.com/) serves as a valuable resource for accurately and efficiently accessing information on drug transporter inhibitors and substrates, aiding researchers in exploring drug transporter mechanisms and assisting clinicians in mitigating adverse drug reactions Database URL: https://istransbase.scbdd.com/

Reaction Templates: Bridging Synthesis Knowledge and Artificial Intelligence.

ConspectusThe field of chemical research boasts a long history of developing software to automate synthesis planning and reaction prediction. Early software relied heavily on expert systems, requiring significant effort to encode vast amounts of synthesis knowledge into a computer-readable format. However, recent advancements in deep learning have shifted the focus toward AI models, offering improved prediction capabilities. Despite these advancements, current AI models often lack the integration of known synthesis rules and intuitions, creating a gap that hinders interpretability and future development of the models. To bridge them, our research group has been actively working on incorporating reaction templates into deep learning models, achieving promising results across various applications.In this Account, we present our latest works to incorporate the known synthesis knowledge into the deep learning models through the utilization of reaction templates. We begin by highlighting the limitations of early computer programs heavily reliant on hand-coded rules. These programs, while providing a foundation for the field, presented limitations in scalability and adaptability. We then introduce SMARTS (SMILES arbitrary target specification), a popular Python-readable format for representing chemical reactions. This format of reaction encoding facilitates the quick integration of synthesis knowledge into AI models built using the Python language. With the SMARTS-based reaction templates, we introduce our recent efforts of developing an AI model for reaction-based molecule optimization. Subsequently, we discuss the recent efforts to automate the extraction of reaction templates from vast chemical reaction databases. This approach eliminates the previously required manual effort of encoding knowledge, a process that could be time-consuming and prone to error when dealing with large data sets. By customizing the automated extraction algorithm, we have developed powerful AI models for specific tasks such as retrosynthesis (LocalRetro), reaction outcome prediction (LocalTransform), and atom-to-atom mapping (LocalMapper). These models, aligned with the intuition of chemists, demonstrate the effectiveness of incorporating reaction templates into deep learning frameworks.Looking toward the future, we believe that utilizing reaction templates to connect known chemical knowledge and AI models holds immense potential for various applications. Not only can this approach significantly benefit future AI models focused on challenging tasks like reaction mechanism labeling and prediction, but we anticipate it can also extend its reach to the realm of inorganic synthesis. By integrating synthesis knowledge, we can not only achieve improved performance but also enhance the interpretability of AI models, paving the way for further advancements in AI-powered chemical synthesis.

The prevalence of HIV resistance mutations and their influence on the shedding of HIV-1 into peritoneal dialysis effluent.

HIV drug resistance mutations (HIVDRMs) are important determinants of therapeutic effects and outcomes even in end-stage kidney failure (ESKF) people living with HIV (PLWHIV). This study evaluated the prevalence of HIVDRMs and their effect on the shedding of HIV-1 into peritoneal dialysis (PD) effluents. This cross-sectional study of PLWHIV and having ESKF and managed with antiretroviral therapy (ART) and PD,collected enrolled patients' demographic information, clinical and laboratory data, and sequenced HIV-1 RNA in unsuppressed plasma and PD effluent samples. HIV viral load and HIVDRMs were determined using qualitative polymerase chain reaction (qPCR) and Stanford University HIVDRM Database, respectively. There were 60 participants recruited with a median age of 43.0 (interquartilerange [IQR], 38.0-47) years and were predominantly on abacavir (88.3%), lamivudine (98.3%), and efavirenz (70%) for a median duration of 8 (IQR, 5-11) years. Among participants with detectable HIV-1 in PD effluents, the prevalence of HIVDRMs was 62.5% (5/8) compared to 7.7% (4/52) among those with undetectable HIV-1 (p = 0.001) with non-nucleoside reverse transcriptase inhibitor (NNRTI) resistance mutations predominating. On Spearman's correlation analysis, high plasma HIV levels(ρ = 0.649, p < 0.001), T-cell CD4 count (ρ = -0370, p < 0.004), serum creatinine (ρ = -0.396, p < 0.002), and white blood cell count (ρ = -0.294, p < 0.023) levels were significant factors correlated with the detection of HIV-1 in PD effluents. Moreover, HIVDRMs presence (ρ = 0.504, p < 0.001) particularly NNRTI resistance (ρ = 0.504, p < 0.001)were also significantly correlated with detection of HIV-1 in PD effluents. The presence of HIVDRMs, high plasma HIV viral load, and T-cell CD4 count were correlated with HIV-1 shedding into PD effluents.

From the biochemical pieces to the nutritional puzzle: using meta-reactions in teaching and research

We now live in an era where metabolic data are increasingly accessible and available. Analysis of this data can be done using novel techniques (e.g., machine learning and artificial intelligence) but this does not alleviate scientists to use “human intelligence”. The objective of this paper is to combine the information of a large database of biochemical reactions with a method and tool to make nutritional biochemistry more accessible to nutritionists. A script was developed to extract information from a database with more than 16 000 biochemical reactions so that it can be used for “biochemical bookkeeping”. A system of more than 300 meta-reactions (i.e., the outcome reaction of a series of connected individual reactions) was constructed covering a wide range of metabolic pathways for macro- and micronutrients. Meta-reactions were constructed by identifying metabolic nodes, which are inputs or outputs of a metabolic system or that serve as connection points between meta-reactions. Complete metabolic pathways can be constructed by combining and balancing the meta-reactions using a simple Excel tool. To illustrate the use of meta-reactions and the tool in the teaching of nutritional biochemistry, examples are given to illustrate how much ATP can be synthesized from glucose, either directly or indirectly (i.e., via storage and mobilization or via transfer of intermediate metabolites between tissues and generations). To illustrate how meta-reactions and the tool can be used in research, nutrient balance data of the mammary gland of a dairy cow were used to construct a plausible pathway of nutrient metabolism of the whole mammary gland. The balance data included 34 metabolites taken up or exported by the mammary gland and 39 meta-reactions were used to construct a metabolic pathway that accounted for the uptake and output of metabolites. The results highlighted the importance of the synthesis of proline from arginine and the concomitant synthesis of urea by the mammary gland. It also raised the question of whether the availability of metabolic pathways or glucose uptake would be the more limiting factor for the synthesis of NADPH required for fatty acid synthesis. The availability of an open database with biochemical reactions, the concept of meta-reactions, and the provision of a tool allow users to construct metabolic pathways, which helps acquiring a more comprehensive and integrated view of metabolism and may raise issues that may be difficult to identify otherwise.

Extension of evaluated cross section database for charged particle monitor reactions

The evaluation and deduction of recommended cross section values allowing extension of the database to monitor energy and intensity parameters of charged particle beams is presented. Included are 53 charged particle (p, d, 3He, 4He) induced reactions on suited C, Al, Ti, Fe, Ni, Cu, Nb and Au targets. The new data allow more systematic simultaneous use of multiple reactions on the same target and promote the backings of electrodeposited and sedimented targets as monitoring aids. Where possible the energy range is extended to above 100 MeV. Integral yield curves over the studied energy range are derived and compared to experimentally measured yields at specific energy points. A comparison with the theoretical excitation curve prediction of the TALYS-code as available in the TENDL 2021–2023 libraries is shown.

Metal-Catalyzed Multi-Component Approach to Quinoline-Linked Covalent Organic Frameworks

The development of new reaction chemistry is highly desirable to construct new structural and functional covalent organic frameworks (COFs). Benefiting from the extremely large database of metal-catalyzed reaction database, we herein develop a new synthetic strategy that can generate quinoline-linked COFs via a silver-catalyzed three-component one-pot reaction and achieve functionalization by the simple replacement of alcohols. This metal-catalyzed approach to the construction of robust COF structures characterized by extended π-conjugation holds the potential to pave a novel pathway in the synthesis of COF materials endowed with both heightened stability and functionality.

Multiscale modeling of reactive flow in heterogeneous porous microstructures

This paper presents a multiscale reactive flow model to simulate in-situ leaching of copper in heterogeneous porous microstructures. The introduced workflow combines fluid flow simulation with advection-diffusion-reaction simulation, both required to model reactive flow. The proposed workflow can include the fluid flow in resolved and unresolved pore structures and utilizes required parameters from molecular simulation (ionic diffusivity) and reaction databases (reaction rate parameters). The modeling approach is validated by comparing results to other open-source codes for a model calcite dissolution on acid injection. This model is applied to copper mining by leaching to analyze the reactive flow through a fractured digital rock model of a subsurface sample. Results are analyzed by tracking the concentration distribution along the pore space structure and calculating the outlet concentration of copper to conform the leaching path. Several sensitivity studies are performed to show the robustness of the modeling framework as well as to investigate the importance of each of these parameters on copper production. The complexity of the model is systematically increased from a single scale surface reaction model, to consider the influence of competitive bulk solution reactions, and finally to include flow through porous media to model multiscale reactive flow. This study shows that a multi-scale flow model with homogeneous bulk and heterogeneous surface reactions is required to accurately model copper leaching.

ORDerly: Data Sets and Benchmarks for Chemical Reaction Data.

Machine learning has the potential to provide tremendous value to life sciences by providing models that aid in the discovery of new molecules and reduce the time for new products to come to market. Chemical reactions play a significant role in these fields, but there is a lack of high-quality open-source chemical reaction data sets for training machine learning models. Herein, we present ORDerly, an open-source Python package for the customizable and reproducible preparation of reaction data stored in accordance with the increasingly popular Open Reaction Database (ORD) schema. We use ORDerly to clean United States patent data stored in ORD and generate data sets for forward prediction, retrosynthesis, as well as the first benchmark for reaction condition prediction. We train neural networks on data sets generated with ORDerly for condition prediction and show that data sets missing key cleaning steps can lead to silently overinflated performance metrics. Additionally, we train transformers for forward and retrosynthesis prediction and demonstrate how non-patent data can be used to evaluate model generalization. By providing a customizable open-source solution for cleaning and preparing large chemical reaction data, ORDerly is poised to push forward the boundaries of machine learning applications in chemistry.

Completing and Balancing Database Excerpted Chemical Reactions with a Hybrid Mechanistic-Machine Learning Approach.

Computer-aided synthesis planning (CASP) development of reaction routes requires an understanding of complete reaction structures. However, most reactions in the current databases are missing reaction coparticipants. Although reaction prediction and atom mapping tools can predict major reaction participants and trace atom rearrangements in reactions, they fail to identify the missing molecules to complete reactions. This is because these approaches are data-driven models trained on the current reaction databases, which comprise incomplete reactions. In this work, a workflow was developed to tackle the reaction completion challenge. This includes a heuristic-based method to identify balanced reactions from reaction databases and complete some imbalanced reactions by adding candidate molecules. A machine learning masked language model (MLM) was trained to learn from simplified molecular input line entry system (SMILES) sentences of these completed reactions. The model predicted missing molecules for the incomplete reactions, a workflow analogous to predicting missing words in sentences. The model is promising for the prediction of small- and middle-sized missing molecules in incomplete reaction records. The workflow combining both the heuristic and machine learning methods completed more than half of the entire reaction space.

Rxn-INSIGHT: fast chemical reaction analysis using bond-electron matrices

The challenge of devising pathways for organic synthesis remains a central issue in the field of medicinal chemistry. Over the span of six decades, computer-aided synthesis planning has given rise to a plethora of potent tools for formulating synthetic routes. Nevertheless, a significant expert task still looms: determining the appropriate solvent, catalyst, and reagents when provided with a set of reactants to achieve and optimize the desired product for a specific step in the synthesis process. Typically, chemists identify key functional groups and rings that exert crucial influences at the reaction center, classify reactions into categories, and may assign them names. This research introduces Rxn-INSIGHT, an open-source algorithm based on the bond-electron matrix approach, with the purpose of automating this endeavor. Rxn-INSIGHT not only streamlines the process but also facilitates extensive querying of reaction databases, effectively replicating the thought processes of an organic chemist. The core functions of the algorithm encompass the classification and naming of reactions, extraction of functional groups, rings, and scaffolds from the involved chemical entities. The provision of reaction condition recommendations based on the similarity and prevalence of reactions eventually arises as a side application. The performance of our rule-based model has been rigorously assessed against a carefully curated benchmark dataset, exhibiting an accuracy rate exceeding 90% in reaction classification and surpassing 95% in reaction naming. Notably, it has been discerned that a pivotal factor in selecting analogous reactions lies in the analysis of ring structures participating in the reactions. An examination of ring structures within the USPTO chemical reaction database reveals that with just 35 unique rings, a remarkable 75% of all rings found in nearly 1 million products can be encompassed. Furthermore, Rxn-INSIGHT is proficient in suggesting appropriate choices for solvents, catalysts, and reagents in entirely novel reactions, all within the span of a second, utilizing nothing more than an everyday laptop.

Choose Your Own Adventure: A Comprehensive Database of Reactions Catalyzed by Cytochrome P450 BM3 Variants.

Cytochrome P450 BM3 monooxygenase is the topic of extensive research as many researchers have evolved this enzyme to generate a variety of products. However, the abundance of information on increasingly diversified variants of P450 BM3 that catalyze a broad array of chemistry is not in a format that enables easy extraction and interpretation. We present a database that categorizes variants by their catalyzed reactions and includes details about substrates to provide reaction context. This database of >1500 P450 BM3 variants is downloadable and machine-readable and includes instructions to maximize ease of gathering information. The database allows rapid identification of commonly reported substitutions, aiding researchers who are unfamiliar with the enzyme in identifying starting points for enzyme engineering. For those actively engaged in engineering P450 BM3, the database, along with this review, provides a powerful and user-friendly platform to understand, predict, and identify the attributes of P450 BM3 variants, encouraging the further engineering of this enzyme.

Abstract 4945: Computational modeling-based discovery of novel anticancer drug candidates targeting centromere-associated protein E

Abstract Purpose: Centromere-associated protein E (CENP-E), a mitotic motor protein, is crucial for cell division. Inhibition of CENP-E can lead to chromosome misalignment and aneuploidy. Our recent studies revealed that the CENP-E inhibitor (CENP-Ei), Compound A, induces aneuploid-mediated cGAS-STING pathway activation in cancer cell lines, which is expected to trigger innate immune response and induce immunological conversion of the tumor microenvironment from cold to hot. However, known CENP-Eis exhibited limited efficacy, and none have gone beyond phase I trials since 2012. The aim of this study is to develop a workflow integrating structure and artificial intelligence-based modeling approaches to accelerate the discovery of novel CENP-Eis with improved efficacy and overcome related challenges. Method: The inhibitor-bound CENP-E structure was modeled using chimeric homology modeling followed by induced fit docking with known CENP-Eis. Structure-based virtual screening (VS) was performed on large compound libraries in Enamine REAL, Synthetically Accessible Virtual Inventory, and MolPort databases. Consensus scoring methods were applied by averaging ranks of individual molecules obtained from VS against different CENP-E conformations. An active learning-enhanced VS pipeline was developed using ATOM Modeling PipeLine (AMPL) to find the best-ranked ligands more efficiently. CENP-E ligand candidates were further filtered based on their safety properties predicted by machine learning models trained with curated databases of adverse drug reactions using AMPL. The success of this study was measured by its ability to reveal novel chemotypes that could modulate CENP-E in kinesin ATPase assays. Result: Conformations of CENP-E’s ligand binding site were predicted for VS using the homology model. Structure-based VS was performed to select high-ranked compounds based on consensus scoring. The active learning-enhanced VS pipeline achieved 75% accuracy in ranking the top 20% of hit compounds. The graph convolutional network model with a ROCAUC, 0.76, was created using AMPL to filter ligand candidates based on their predicted safety properties. Seventy-three potential CENP-E ligands computationally prioritized from the Molport database were experimentally tested using kinesin ATPase assays from which 4 potential inhibitors and 8 potential activators were identified indicating overlapping binding sites of inhibitors and activators. Conclusion: Our integrated workflow is effective in discovering novel CENP-E modulators. The discovery of CENP-E activators provides an opportunity to identify novel therapeutics in hepatocellular carcinoma malignancies known to experience decreased CENP-E activity leading to aneuploidy. The predictions generated by computational models combined with experimental validations could further accelerate anticancer drug discovery. Citation Format: Pinyi Lu, Ryo Kamata, Michael R. Weil, Naomi Ohashi, Akihiro Ohashi, Eric A. Stahlberg. Computational modeling-based discovery of novel anticancer drug candidates targeting centromere-associated protein E [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 4945.

PMechDB: A Public Database of Elementary Polar Reaction Steps.

Most online chemical reaction databases are not publicly accessible or are fully downloadable. These databases tend to contain reactions in noncanonicalized formats and often lack comprehensive information regarding reaction pathways, intermediates, and byproducts. Within the few publicly available databases, reactions are typically stored in the form of unbalanced, overall transformations with minimal interpretability of the underlying chemistry. These limitations present significant obstacles to data-driven applications including the development of machine learning models. As an effort to overcome these challenges, we introduce PMechDB, a publicly accessible platform designed to curate, aggregate, and share polar chemical reaction data in the form of elementary reaction steps. Our initial version of PMechDB consists of over 100,000 such steps. In the PMechDB, all reactions are stored as canonicalized and balanced elementary steps, featuring accurate atom mapping and arrow-pushing mechanisms. As an online interactive database, PMechDB provides multiple interfaces that enable users to search, download, and upload chemical reactions. We anticipate that the public availability of PMechDB and its standardized data representation will prove beneficial for chemoinformatics research and education and the development of data-driven, interpretable models for predicting reactions and pathways. PMechDB platform is accessible online at https://deeprxn.ics.uci.edu/pmechdb.

Antineoplastic agents associated with neutropenic enterocolitis in patients with malignancy: A quantitative safety signal analysis.

The use of certain chemotherapy agents is associated with the development of a condition called "chemotherapy-associated neutropenic enterocolitis" (CANE). To determine the risk of CANE associated with the use of each antineoplastic agent. The FDA FAERS database of spontaneous adverse reactions was searched for the occurrence of the MedDRA preferred term "neutropenic colitis." The search resulted in 1134 records of patients (535 [47.3%] females, 479 [42.2%] males, sex not specified in 120 [10.6%]) with neutropenic colitis receiving immunosuppressive chemotherapy. The mean age of patients was 47 (SD 22). 22 antineoplastic agents were found to have a strong association (reported odds ratio [ROR] > 100) with the occurrence of CANE; 9 had ROR < 2. Drug databases have several limitations in providing updated information about newly approved pharmaceutical adverse events. Signal detection is a diagnostic method recognized as practical in pharmacovigilance. It may be utilized in the FDA's adverse event reporting database and has demonstrated a reasonable predictive performance in signaling adverse events. Our study emphasized the substantial knowledge gap between what we know about the potential risk of CANE caused by antineoplastic agents and the reports of the FDA on their new approved products.