Screening Pipeline Research Articles

Characterization of novel small molecule inhibitors of estrogen receptor-activation function 2 (ER-AF2).

Up to 40% of patients with estrogen receptor (ER)-positive breast cancer will develop resistance against the majority of current ER-directed therapies. Resistance can arise through various mechanisms such as increased expression levels of coregulators, and key mutations acquired in the receptor's ligand binding domain rendering it constitutively active. To overcome these resistance mechanisms, we explored targeting the ER Activation Function 2 (AF2) site, which is essential for coactivator binding and activation. Using artificial intelligence and the deep docking methodology, we virtually screened > 1billion small molecules and identified 290 potential AF2 binders that were then characterized and validated through an iterative screening pipeline of cell-based and cell-free assays. We ranked the compounds based on their ability to reduce the transcriptional activity of the estrogen receptor and the viability of ER-positive breast cancer cells. We identified a lead compound, VPC-260724, which inhibits ER activity at low micromolar range. We confirmed its direct binding to the ER-AF2 site through a PGC1α peptide displacement experiment. Using proximity ligation assays, we showed that VPC-260724 disrupts the interaction between ER-AF2 and the coactivator SRC-3 and reduces the expression of ER target genes in various breast cancer models including the tamoxifen resistant cell line TamR3. In conclusion, we developed a novel ER-AF2 binder, VPC-260724, which shows antiproliferative activity in ER-positive breast cancer models. The use of an ER-AF2 inhibitor in combination with current treatments may provide a novel complementary therapeutic approach to target treatment resistance in ER-positive breast cancer.

Discovery of dual-specificity tyrosine-phosphorylation-regulated kinase 1A (DYRK1A) inhibitors using an artificial intelligence model and their effects on tau and tubulin dynamics

The dual-specificity tyrosine-phosphorylation-regulated kinase 1 A (DYRK1A) presents a promising therapeutic target for neurological diseases. However, current inhibitors lack selectivity, which can lead to unexpected side effects and increase the difficulty of studying DYRK1A. Therefore, identifying selective inhibitors targeting DYRK1A is essential for reducing side effects and facilitating neurological disease research. This study aimed to discover DYRK1A inhibitors through a screening pipeline incorporating a deep neural network (DNN) model. Herein, we report an optimized model with an accuracy of 0.93 on a testing set. The pipeline was then performed to identify potential DYRK1A inhibitors from the National Cancer Institute (NCI) library. Four novel DYRK1A inhibitors were identified, and compounds NSC657702 and NSC31059 were noteworthy for their potent inhibition, with IC50 values of 50.9 and 39.5 nM, respectively. NSC31059 exhibited exceptional selectivity across 70 kinases. The compounds also significantly reduced DYRK1A-induced tau phosphorylation at key sites associated with the pathology of neurodegenerative diseases. Moreover, they promoted tubulin polymerization, suggesting a role in microtubule stabilization. Cytotoxicity assessments further confirmed the neuronal safety of the compounds. Together, the results demonstrated a promising screening pipeline and novel DYRK1A inhibitors as candidates for further optimization and development.

Niche-Aware Metagenomic Screening for Enzyme Methioninase Illuminates Its Contribution to Metabolic Syntrophy

The single-step methioninase-mediated degradation of methionine (as a sulfur containing amino acid) is a reaction at the interface of carbon, nitrogen, sulfur, and methane metabolism in microbes. This enzyme also has therapeutic application due to its role in starving auxotrophic cancer cells. Applying our refined in silico screening pipeline on 33,469 publicly available genome assemblies and 1878 metagenome assembled genomes/single-cell amplified genomes from brackish waters of the Caspian Sea and the Fennoscandian Shield deep groundwater resulted in recovering 1845 methioninases. The majority of recovered methioninases belong to representatives of phyla Proteobacteria (50%), Firmicutes (29%), and Firmicutes_A (13%). Prevalence of methioninase among anaerobic microbes and in the anoxic deep groundwater together with the relevance of its products for energy conservation in anaerobic metabolism highlights such environments as desirable targets for screening novel methioninases and resolving its contribution to microbial metabolism and interactions. Among archaea, majority of detected methioninases are from representatives of Methanosarcina that are able to use methanethiol, the sulfur containing product from methionine degradation, as a precursor for methanogenesis. Branching just outside these archaeal methioninases in the phylogenetic tree, we recovered three methioninases belonging to representatives of Patescibacteria reconstructed from deep groundwater metagenomes. We hypothesize that methioninase in Patescibacteria could contribute to their syntrophic interactions where their methanogenic partners/hosts benefit from the produced 2-oxobutyrate and methanethiol. Our results underscore the significance of accounting for specific ecological niche in screening for enzyme variates with desired characteristics. Finally, complementing of our findings with experimental validation of methioninase activity confirms the potential of our in silico screening in clarifying the peculiar ecological role of methioninase in anoxic environments.

AI Promoted Virtual Screening, Structure-Based Hit Optimization, and Synthesis of Novel COVID-19 S-RBD Domain Inhibitors.

Coronavirus disease 2019 (COVID-19) is caused by a new, highly pathogenic severe-acute-respiratory syndrome coronavirus 2 (SARS-CoV-2) that infects human cells through its transmembrane spike (S) glycoprotein. The receptor-binding domain (RBD) of the S protein interacts with the angiotensin-converting enzyme II (ACE2) receptor of the host cells. Therefore, pharmacological targeting of this interaction might prevent infection or spread of the virus. Here, we performed a virtual screening to identify small molecules that block S-ACE2 interaction. Large compound libraries were filtered for drug-like properties, promiscuity and protein-protein interaction-targeting ability based on their ADME-Tox descriptors and also to exclude pan-assay interfering compounds. A properly designed AI-based virtual screening pipeline was applied to the remaining compounds, comprising approximately 10% of the starting data sets, searching for molecules that could bind to the RBD of the S protein. All molecules were sorted according to their screening score, grouped based on their structure and postfiltered for possible interaction patterns with the ACE2 receptor, yielding 31 hits. These hit molecules were further tested for their inhibitory effect on Spike RBD/ACE2 (19-615) interaction. Six compounds inhibited the S-ACE2 interaction in a dose-dependent manner while two of them also prevented infection of human cells from a pseudotyped virus whose entry is mediated by the S protein of SARS-CoV-2. Of the two compounds, the benzimidazole derivative CKP-22 protected Vero E6 cells from infection with SARS-CoV-2, as well. Subsequent, hit-to-lead optimization of CKP-22 was effected through the synthesis of 29 new derivatives of which compound CKP-25 suppressed the Spike RBD/ACE2 (19-615) interaction, reduced the cytopathic effect of SARS-CoV-2 in Vero E6 cells (IC50 = 3.5 μM) and reduced the viral load in cell culture supernatants. Early in vitro ADME-Tox studies showed that CKP-25 does not possess biodegradation or liver metabolism issues, while isozyme-specific CYP450 experiments revealed that CKP-25 was a weak inhibitor of the CYP450 system. Moreover, CKP-25 does not elicit mutagenic effect on Escherichia coli WP2 uvrA strain. Thus, CKP-25 is considered a lead compound against COVID-19 infection.

Using Microfluidic and Conventional Platforms to Evaluate the Effects of Lanthanides on Spheroid Formation

Metastasis contributes to the increased mortality rate of cancer, but the intricate mechanisms remain unclear. Cancer cells from a primary tumor invade nearby tissues and access the lymphatic or circulatory system. If these cells manage to survive and extravasate from the vasculature into distant tissues and ultimately adapt to survive, they will proliferate and facilitate malignant tumor formation. Traditional two-dimensional (2D) cell cultures offer a rapid and convenient method for validating the efficacy of anticancer drugs within a reasonable cost range, but their utility is limited because of tumors’ high heterogeneity in vivo and spatial complexities. Three-dimensional (3D) cell cultures that mimic the physiological conditions of cancer cells in vivo have gained considerable interest. In these cultures, cells assemble into spheroids through gravity, magnetic forces, or their low-adhesion to the plates. Although these approaches address some of the limitations of 2D cultures, they often require a considerable amount of time and cost. Therefore, this study aims to enhance the effectiveness of 3D culture techniques by using microfluidic systems to provide a high-throughput and sensitive pipeline for drug screening. Using these systems, we studied the effects of lanthanide elements, which have garnered interest in cancer treatment, on spheroid formation and cell spreading. Our findings suggest that these elements alter the compactness of cell spheroids and decrease cell mobility.

AlphaFold opens the doors to deorphanizing secreted proteins

Danneskiold-Samsøe and coworkers1 have developed an in silico screening pipeline based on AlphaFold2 for identifying single-pass transmembrane receptors for secreted peptides that play important roles in cell-cell signaling. Their approach can be used to deorphanize a diverse range of ligands. The overall strategy can be valuable in screening for weak and transient interactions.

High-throughput screening of more than 30,000 compounds for anthelmintics against gastrointestinal nematode parasites.

Gastrointestinal nematodes (GINs) are amongst the most common parasites of humans, livestock, and companion animals. GIN parasites infect 1-2 billion people worldwide, significantly impacting hundreds of millions of children, pregnant women, and adult workers, thereby perpetuating poverty. Two benzimidazoles with suboptimal efficacy are currently used to treat GINs in humans as part of mass drug administrations, with many instances of lower-than-expected or poor efficacy and possible resistance. Thus, new anthelmintics are urgently needed. However, screening methods for new anthelmintics using human GINs typically have low throughput. Here, using our novel screening pipeline that starts with human hookworms, we screened 30,238 unique small molecules from a wide range of compound libraries, including ones with generic diversity, repurposed drugs, natural derivatives, known mechanisms of action, as well as multiple target-focused libraries (e.g., targeting kinases, GPCRs, and neuronal proteins). We identified 55 compounds with broad-spectrum activity against adult stages of two evolutionary divergent GINs, hookworms ( Ancylostoma ceylanicum ) and whipworms ( Trichuris muris ). Based on known databases, the targets of these 55 compounds were predicted in nematode parasites. One novel scaffold from the diversity set library, F0317-0202, showed good activity (high motility inhibition) against both GINs. To better understand this novel scaffold's structure-activity relationships (SAR), we screened 28 analogs and created SAR models highlighting chemical and functional groups required for broad-spectrum activity. These studies validate our new and efficient screening pipeline at the level of tens of thousands of compounds and provide an important set of new GIN-active compounds for developing novel and broadly-active anthelmintics.

Discovery of Highly Bioactive Peptides through Hierarchical Structural Information and Molecular Dynamics Simulations.

Peptide drugs play an essential role in modern therapeutics, but the computational design of these molecules is hindered by several challenges. Traditional methods like molecular docking and molecular dynamics (MD) simulation, as well as recent deep learning approaches, often face limitations related to computational resource demands, complex binding affinity assessments, extensive data requirements, and poor model interpretability. Here, we introduce PepHiRe, an innovative methodology that utilizes the hierarchical structural information in peptide sequences and employs a novel strategy called Ladderpath, rooted in algorithmic information theory, to rapidly generate and enhance the efficiency and clarity of novel peptide design. We applied PepHiRe to develop BH3-like peptide inhibitors targeting myeloid cell leukemia-1, a protein associated with various cancers. By analyzing just eight known bioactive BH3 peptide sequences, PepHiRe effectively derived a hierarchy of subsequences used to create new BH3-like peptides. These peptides underwent screening through MD simulations, leading to the selection of five candidates for synthesis and subsequent in vitro testing. Experimental results demonstrated that these five peptides possess high inhibitory activity, with IC50 values ranging from 28.13 ± 7.93 to 167.42 ± 22.15 nM. Our study explores a white-box model driven technique and a structured screening pipeline for identifying and generating novel peptides with potential bioactivity.

Computational screening of umami tastants using deep learning.

Umami, a fundamental human taste modality, refers to the savory flavors in meats and broths, often associated with monosodium glutamate and protein richness. With limited knowledge of umami molecules, the food industry seeks efficient approaches for identifying novel tastants. In this study, we have devised a virtual screening pipeline for identifying highly potent umami tastants from large molecular databases. We curated the most extensive classification dataset containing 439 umami and 428 non-umami molecules and trained a transformer-based architecture to differentiate between the two classes, achieving 93% accuracy. Additionally, we built a neural network model for predicting the potency of umami compounds, the first effort of its kind. The classification and potency prediction models were combined with similarity analysis and toxicity screening to build an end-to-end virtual framework for the rational discovery of novel tastants. We applied this framework to the FooDB database containing around 70,000 molecules as an illustrative use case for screening potent umami compounds. The screened molecules were validated using molecular docking with the umami taste receptor. This study demonstrates the potential of data-driven methods in discovering new tastants from structural and chemical features of molecules and proposes an efficient implementation for industrial applications.

From Small Data Modeling to Large Language Model Screening: A Dual-Strategy Framework for Materials Intelligent Design.

Small data in materials present significant challenges to constructing highly accurate machine learning models, severely hindering the widespread implementation of data-driven materials intelligent design. In this study, the Dual-Strategy Materials Intelligent Design Framework (DSMID) is introduced, which integrates two innovative methods. The Adversarial domain Adaptive Embedding Generative network (AAEG) transfers data between related property datasets, even with only 90 data points, enhancing material composition characterization and improving property prediction. Additionally, to address the challenge of screening and evaluating numerous alloy designs, the Automated Material Screening and Evaluation Pipeline (AMSEP) is implemented. This pipeline utilizes large language models with extensive domain knowledge to efficiently identify promising experimental candidates through self-retrieval and self-summarization. Experimental findings demonstrate that this approach effectively identifies and prepares new eutectic High Entropy Alloy (EHEA), notably Al14(CoCrFe)19Ni28, achieving an ultimate tensile strength of 1085 MPa and 24% elongation without heat treatment or extra processing. This demonstrates significantly greater plasticity and equivalent strength compared to the typical as-cast eutectic HEA AlCoCrFeNi2.1. The DSMID framework, combining AAEG and AMSEP, addresses the challenges of small data modeling and extensive candidate screening, contributing to cost reduction and enhanced efficiency of material design. This framework offers a promising avenue for intelligent material design, particularly in scenarios constrained by limited data availability.

The landscape of drug sensitivity and resistance in sarcoma

Sarcomas are rare malignancies with over 100 distinct histological subtypes. Their rarity and heterogeneity pose significant challenges to identifying effective therapies, and approved regimens show varied responses. Novel, personalized approaches to therapy are needed to improve patient outcomes. Patient-derived tumor organoids (PDTOs) model tumor behavior across an array of malignancies. We leverage PDTOs to characterize the landscape of drug resistance and sensitivity in sarcoma, collecting 194 specimens from 126 patients spanning 24 distinct sarcoma subtypes. Our high-throughput organoid screening pipeline tested single agents and combinations, with results available within a week from surgery. Drug sensitivity correlated with clinical features such as tumor subtype, treatment history, and disease trajectory. PDTO screening can facilitate optimal drug selection and mirror patient outcomes in sarcoma. We could identify at least one FDA-approved or NCCN-recommended effective regimen for 59% of the specimens, demonstrating the potential of our pipeline to provide actionable treatment information.

Peer Review of “A Hybrid Pipeline for Covid-19 Screening Incorporating Lungs Segmentation and Wavelet Based Preprocessing of Chest X-Rays (Preprint)”

Peer Review of “A Hybrid Pipeline for Covid-19 Screening Incorporating Lungs Segmentation and Wavelet Based Preprocessing of Chest X-Rays (Preprint)”

Abstract C066: Identifying Transcriptional Drivers of Plasticity in Pancreatic Cancer

Abstract Pancreatic ductal adenocarcinoma (PDAC) remains a deadly disease with few effective treatments. Even with the advent of mutationally-directed therapies targeting the KRAS oncogene, PDAC transcriptional plasticity remains a major mechanism of therapeutic resistance. As a result, there is a desperate need to develop additional strategies to treat this deadly disease. In addition to the canonical genomic alterations in KRAS, TP53, CDKN2A, and SMAD4, PDAC tumors exhibit diverse transcriptional programs, or "cell states," with prognostic implications: PDAC tumors in the “classical state” are more responsive to upfront chemotherapy and have better outcomes, while those in the “basal state” are more aggressive with poorer prognoses. Currently, PDAC cell states are not used to direct therapy. Cell state is an integrative property shaped by both cell-intrinsic (e.g., mutations, epigenetics) and cell-extrinsic (e.g., tumor microenvironment) factors. In our prior work, single-cell analyses of clinical PDAC samples demonstrated notable cell state heterogeneity and plasticity. In addition, longitudinal monitoring of patient-derived organoids showed that cells can shift from classical to basal or coexpressor states as the environment changes, and that these cell states can drastically influence drug response. However, it remains unknown which signaling and transcriptional pathways induce basal or classical states, and whether these gene regulatory networks can be targeted therapeutically. Thus, there is a pressing need to devise scalable methods to determine essential drivers for prognostically relevant cancer cell states.Here, we aim to systematically and unbiasedly identify transcription factors (TFs) that drive basal and classical cell states in PDAC. We have successfully established a high-throughput screening pipeline to 1) over-express all human TF isoforms in a pooled format within a cohort of PDAC models; 2) sort cells using antibodies against state-specific cell surface markers; and 3) perform single-cell RNA sequencing on sorted cells to nominate individual TFs or combinations that induce specific cell state transitions. Preliminary results identify both previously reported (e.g., GATA4) and new TFs that can induce the classical state. By overexpressing TFs individually or in combination, we are able to engineer PDAC cell line models that more faithfully reflect the transcriptional phenotypes observed in patient tumors. Ultimately, we aim to use this approach to construct high-fidelity isogenic but state-variant PDAC models for use both in therapeutic screening and as a substrate for investigating mechanisms governing cancer cell state plasticity. Citation Format: Yuzhou Evelyn Tong, Aswanth Mahalingam, Walaa E Katan, Julia Joung, Alex K Shalek, Peter S Winter, Srivatsan Raghavan. Identifying Transcriptional Drivers of Plasticity in Pancreatic Cancer [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Advances in Pancreatic Cancer Research; 2024 Sep 15-18; Boston, MA. Philadelphia (PA): AACR; Cancer Res 2024;84(17 Suppl_2):Abstract nr C066.

Discovery of novel BfmR inhibitors restoring carbapenem susceptibility against carbapenem-resistant Acinetobacter baumannii by structure-based virtual screening and biological evaluation

ABSTRACT The emergence and spread of Acinetobacter baumannii pose a severe threat to public health, highlighting the urgent need for the next generation of therapeutics due to its increasing resistance to existing antibiotics. BfmR, a response regulator modulating virulence and antimicrobial resistance, shows a promising potential as a novel antimicrobial target. Developing BfmR inhibitors may propel a new therapeutic direction for intractable infection of resistant strains. In this study, we conducted a structure-based hierarchical virtual screening pipeline combining molecular docking, molecular dynamic simulation, and MM/GBSA calculation to sift the Specs chemical library and finally discover three novel potential BfmR inhibitors. The three hits can reduce the MIC of meropenem for the carbapenem-resistant Acinetobacter baumannii (CRAB) strain ZJ06. Similar to the BfmR knockout strain, Cmp-98 was demonstrated to downregulate the expression of K locus genes, indicating it as a BfmR inhibitor. Bacteria underwent harmful morphological changes after treatment with these inhibitors. Molecular dynamic simulations found that all the hits tend to dynamically bind to different positions of the phosphorylation site of BfmR. Wherein we identified a potential inhibitory-binding cleft, beside a possible activated binding cleft at the edge of the phosphorylation site. Restraining the ligand binding poses may help exert inhibitory effects. This study reports a group of new scaffold BfmR inhibitors, offering new insights for novel antibiotic therapeutics against CRAB.

A Drug Discovery Pipeline for MAPK/ERK Pathway Inhibitors in Caenorhabditis elegans.

Many tumors depend on MAPK/ERK signaling to sustain growth, avoid cell death, and metastasize. We show that specific and clinically relevant MAPK/ERK signaling inhibitors can be discovered in vivo with a high-throughput screening pipeline in small animals.

Multitask Learning on Graph Convolutional Residual Neural Networks for Screening of Multitarget Anticancer Compounds.

Recently, various modern experimental screening pipelines and assays have been developed to find promising anticancer drug candidates. However, it is time-consuming and almost infeasible to screen an immense number of compounds for anticancer activity via experimental approaches. To partially address this issue, several computational advances have been proposed. In this study, we present iACP-GCR, a model based on multitask learning on graph convolutional residual neural networks with two types of shortcut connections, to identify multitarget anticancer compounds. In our architecture, the graph convolutional residual neural networks are shared by all the prediction tasks before being separately customized. The NCI-60 data set, one of the most reliable and well-known sources of experimentally verified compounds, was used to develop our model. From that data set, we collected and refined data about compounds screened across nine cancer types (panels), including breast, central nervous system, colon, leukemia, nonsmall cell lung, melanoma, ovarian, prostate, and renal, for model training and evaluation. The model performance evaluated on an independent test set shows that iACP-GCR surpasses the three advanced computational methods for multitask learning. The integration of two shortcut connection types in the shared networks also improves the prediction efficiency. We also deployed the model as a public web server to assist the research community in screening potential anticancer compounds.

In vitro small molecule screening to inform novel candidates for use in fluconazole combination therapy in vivo against Coccidioides.

Developing new drugs, especially for regional orphan diseases, such as Valley Fever, is a slow and costly endeavor. However, there is a wealth of FDA-approved drugs available for repurposing, offering a more economical and expedited approach to improve treatment. Those existing compounds with antifungal properties can become novel therapies with relative ease: a considerable advantage for patients in need of alternative treatment. Despite the scope of remaining tasks, our comprehensive screening of potential candidates has revealed promising combinations for further exploration. This effort outlines a practical pipeline for Valley fever drug screening and identifies viable drug combinations that could impact patients more rapidly than single drug development pathways.

The potential of Chlorella spp. as antiviral source against African swine fever virus through a virtual screening pipeline

African swine fever (ASF) causes high mortality in pigs and threatens global swine production. There is still a lack of therapeutics available, with two vaccines under scrutiny and no approved small-molecule drugs. Eleven (11) viral proteins were used to identify potential antivirals in in silico screening of secondary metabolites (127) from Chlorella spp. The metabolites were screened for affinity and binding selectivity. High-scoring compounds were assessed through in silico ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) predictions, compared to structurally similar drugs, and checked for off-target docking with prepared swine receptors. Molecular dynamics (MD) simulations determined binding stability while binding energy was measured in Molecular Mechanics - Generalized Born Surface Area (MMGBSA) or Poisson-Boltzmann Surface Area (MMPBSA). Only six (6) compounds passed until MD analyses, of which five (5) were stable after 100 ns of MD runs. Of these five compounds, only three had binding affinities that were comparable to or stronger than controls. Specifically, phytosterols 24,25-dihydrolanosterol and CID 4206521 that interact with the RNA capping enzyme (pNP868R), and ergosterol which bound to the Erv-like thioreductase (pB119L). The compounds identified in this study can be used as a theoretical basis for in vitro screening to develop potent antiviral drugs against ASFV.

Identification and Validation of New DNA-PKcs Inhibitors through High-Throughput Virtual Screening and Experimental Verification.

DNA-PKcs is a crucial protein target involved in DNA repair and response pathways, with its abnormal activity closely associated with the occurrence and progression of various cancers. In this study, we employed a deep learning-based screening and molecular dynamics (MD) simulation-based pipeline, identifying eight candidates for DNA-PKcs targets. Subsequent experiments revealed the effective inhibition of DNA-PKcs-mediated cell proliferation by three small molecules (5025-0002, M769-1095, and V008-1080). These molecules exhibited anticancer activity with IC50 (inhibitory concentration at 50%) values of 152.6 μM, 30.71 μM, and 74.84 μM, respectively. Notably, V008-1080 enhanced homology-directed repair (HDR) mediated by CRISPR/Cas9 while inhibiting non-homologous end joining (NHEJ) efficiency. Further investigations into the structure-activity relationships unveiled the binding sites and critical interactions between these small molecules and DNA-PKcs. This is the first application of DeepBindGCN_RG in a real drug screening task, and the successful discovery of a novel DNA-PKcs inhibitor demonstrates its efficiency as a core component in the screening pipeline. Moreover, this study provides important insights for exploring novel anticancer therapeutics and advancing the development of gene editing techniques by targeting DNA-PKcs.

HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery.

We propose HydraScreen, a deep-learning framework for safe and robust accelerated drug discovery. HydraScreen utilizes a state-of-the-art 3D convolutional neural network designed for the effective representation of molecular structures and interactions in protein-ligand binding. We designed an end-to-end pipeline for high-throughput screening and lead optimization, targeting applications in structure-based drug design. We assessed our approach using established public benchmarks based on the CASF-2016 core set, achieving top-tier results in affinity and pose prediction (Pearson's r = 0.86, RMSE = 1.15, Top-1 = 0.95). We introduced a novel approach for interaction profiling, aimed at detecting potential biases within both the model and data sets. This approach not only enhanced interpretability but also reinforced the impartiality of our methodology. Finally, we demonstrated HydraScreen's ability to generalize effectively across novel proteins and ligands through a temporal split. We also provide insights into potential avenues for future development aimed at enhancing the robustness of machine learning scoring functions. HydraScreen (accessible at http://hydrascreen.ro5.ai/paper) provides a user-friendly GUI and a public API, facilitating the easy-access assessment of protein-ligand complexes.