A mini-review on perturbation modelling across single-cell omic modalities.

Recent advances in single-cell omics technology have transformed the landscape of cellular and molecular research, enriching the scope and intricacy of cellular characterisation. Perturbation modelling seeks to comprehensively grasp the effects of external influences like disease onset or molecular knock-outs or external stimulants on cellular physiology, specifically on transcription factors, signal transducers, biological pathways, and dynamic cell states. Machine and deep learning tools transform complex perturbational phenomena in algorithmically tractable tasks to formulate predictions based on various types of single-cell datasets. However, the recent surge in tools and datasets makes it challenging for experimental biologists and computational scientists to keep track of the recent advances in this rapidly expanding filed of single-cell modelling. Here, we recapitulate the main objectives of perturbation modelling and summarise novel single-cell perturbation technologies based on genetic manipulation like CRISPR or compounds, spanning across omic modalities. We then concisely review a burgeoning group of computational methods extending from classical statistical inference methodologies to various machine and deep learning architectures like shallow models or autoencoders, to biologically informed approaches based on gene regulatory networks, and to combinatorial efforts reminiscent of ensemble learning. We also discuss the rising trend of large foundational models in single-cell perturbation modelling inspired by large language models. Lastly, we critically assess the challenges that underline single-cell perturbation modelling while pointing towards relevant future perspectives like perturbation atlases, multi-omics and spatial datasets, causal machine learning for interpretability, multi-task learning for performance and explainability as well as prospects for solving interoperability and benchmarking pitfalls.

Targeting mitochondrial bioenergetics by combination treatment with imatinib and dichloroacetate in human erythroleukemic K­562 and colorectal HCT­116 cancer cells.

Tumor malignant cells are characterized by dysregulation of mitochondrial bioenergetics due to the 'Warburg effect'. In the present study, this metabolic imbalance was explored as a potential target for novel cancer chemotherapy. Imatinib (IM) downregulates the expression levels of SCΟ2 and FRATAXIN (FXN) genes involved in the heme­dependent cytochrome c oxidase biosynthesis and assembly pathway in human erythroleukemic IM­sensitive K­562 chronic myeloid leukemia cells (K­562). In the present study, it was investigated whether the treatment of cancer cells with IM (an inhibitor of oxidative phosphorylation) separately, or together with dichloroacetate (DCA) (an inhibitor of glycolysis), can inhibit cell proliferation or cause death. Human K­562 and IM­chemoresistant K­562 chronic myeloid leukemia cells (K­562R), as well as human colorectal carcinoma cells HCT­116 (+/+p53) and (­/­p53, with double TP53 knock-in disruptions), were employed. Treatments of these cells with either IM (1 or 2 µM) and/or DCA (4 mΜ) were also assessed for the levels of several process biomarkers including SCO2, FXN, lactate dehydrogenase A, glyceraldehyde­3­phosphate dehydrogenase, pyruvate kinase M2, hypoxia inducing factor­1a, heme oxygenase­1, NF­κB, stem cell factor and vascular endothelial growth factor via western blot analysis. Computational network biology models were also applied to reveal the connections between the ten proteins examined. Combination treatment of IM with DCA caused extensive cell death (>75%) in K­562 and considerable (>45%) in HCT­116 (+/+p53) cultures, but less in K­562R and HCT­116 (­/­p53), with the latter deficient in full length p53 protein. Such treatment, markedly reduced reactive oxygen species levels, as measured by flow­cytometry, in K­562 cells and affected the oxidative phosphorylation and glycolytic biomarkers in all lines examined. These findings indicated, that targeting of cancer mitochondrial bioenergetics with such a combination treatment was very effective, although chemoresistance to IM in leukemia and the absence of a full length p53 in colorectal cells affected its impact.

Benchmarking of Machine Learning classifiers on plasma proteomic for COVID-19 severity prediction through interpretable artificial intelligence.

The SARS-CoV-2 pandemic highlighted the need for software tools that could facilitate patient triage regarding potential disease severity or even death. In this article, an ensemble of Machine Learning (ML) algorithms is evaluated in terms of predicting the severity of their condition using plasma proteomics and clinical data as input. An overview of AI-based technical developments to support COVID-19 patient management is presented outlining the landscape of relevant technical developments. Based on this review, the use of an ensemble of ML algorithms that analyze clinical and biological data (i.e., plasma proteomics) of COVID-19 patients is designed and deployed to evaluate the potential use of AI for early COVID-19 patient triage. The proposed pipeline is evaluated using three publicly available datasets for training and testing. Three ML "tasks" are defined, and several algorithms are tested through a hyperparameter tuning method to identify the highest-performance models. As overfitting is one of the typical pitfalls for such approaches (mainly due to the size of the training/validation datasets), a variety of evaluation metrics are used to mitigate this risk. In the evaluation procedure, recall scores ranged from 0.6 to 0.74 and F1-score from 0.62 to 0.75. The best performance is observed via Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM) algorithms. Additionally, input data (proteomics and clinical data) were ranked based on corresponding Shapley additive explanation (SHAP) values and evaluated for their prognosticated capacity and immuno-biological credence. This "interpretable" approach revealed that our ML models could discern critical COVID-19 cases predominantly based on patient's age and plasma proteins on B cell dysfunction, hyper-activation of inflammatory pathways like Toll-like receptors, and hypo-activation of developmental and immune pathways like SCF/c-Kit signaling. Finally, the herein computational workflow is corroborated in an independent dataset and MLP superiority along with the implication of the abovementioned predictive biological pathways are corroborated. Regarding limitations of the presented ML pipeline, the datasets used in this study contain less than 1000 observations and a significant number of input features hence constituting a high-dimensional low-sample (HDLS) dataset which could be sensitive to overfitting. An advantage of the proposed pipeline is that it combines biological data (plasma proteomics) with clinical-phenotypic data. Thus, in principle, the presented approach could enable patient triage in a timely fashion if used on already trained models. However, larger datasets and further systematic validation are needed to confirm the potential clinical value of this approach. The code is available on Github: https://github.com/inab-certh/Predicting-COVID-19-severity-through-interpretable-AI-analysis-of-plasma-proteomics.

Identifying Actionability as a Key Factor for the Adoption of 'Intelligent' Systems for Drug Safety: Lessons Learned from a User-Centred Design Approach.

INTRODUCTION: Information technology (IT) plays an important role in the healthcare landscape via the increasing digitization of medical data and the use of modern computational paradigms such as machine learning (ML) and knowledge graphs (KGs). These 'intelligent' technical paradigms provide a new digital 'toolkit' supporting drug safety and healthcare processes, including 'active pharmacovigilance'. While these technical paradigms are promising, intelligent systems (ISs) are not yet widely adopted by pharmacovigilance (PV) stakeholders, namely the pharma industry, academia/research community, drug safety monitoring organizations, regulatory authorities, and healthcare institutions. The limitations obscuring the integration of ISs into PV activities are multifaceted, involving technical, legal and medical hurdles, and thus require further elucidation. OBJECTIVE: We dissect the abovementioned limitations by describing the lessons learned during the design and implementation of the PVClinical platform, a web platform aiming to support the investigation of potential adverse drug reactions (ADRs), emphasizing the use of knowledge engineering (KE) as its main technical paradigm. RESULTS: To this end, we elaborate on the related 'business processes' (i.e. operational processes) and 'user goals' identified as part of the PVClinical platform design process based on Design Thinking principles. We also elaborate on key challenges restricting the adoption of such ISs and their integration in the clinical setting and beyond. CONCLUSIONS: We highlight the fact that beyond providing analytics and useful statistics to the end user, 'actionability' has emerged as the operational priority identified through the whole process. Furthermore, we focus on the needs for valid, reproducible, explainable and human-interpretable results, stressing the need to emphasize on usability.

Pharmacovigilance and Clinical Environment: Utilizing OMOP-CDM and OHDSI Software Stack to Integrate EHR Data.

Information Technology (IT) and specialized systems could have a prominent role towards the support of drug safety processes, both in the clinical context but also beyond that. PVClinical project aims to build an IT platform, enabling the investigation of potential Adverse Drug Reactions (ADRs). In this paper, we outline the utilization of Observational Medical Outcomes Partnership - Common Data Model (OMOP-CDM) and the openly available Observational Health Data Sciences and Informatics (OHDSI) software stack as part of PVClinical platform. OMOP-CDM offers the capacity to integrate data from Electronic Health Records (EHRs) (e.g., encounters, patients, providers, diagnoses, drugs, measurements and procedures) via an accepted data model. Furthermore, the OHDSI software stack provides valuable analytics tools which could be used to address important questions regarding drug safety quickly and efficiently, enabling the investigation of potential ADRs in the clinical environment.

Using Business Process Management Notation to Model Therapeutic Prescription Protocols: The PrescIT Approach.

Clinical Decision Support Systems (CDSS) could play a prominent role in preventing Adverse Drug Reactions (ADRs) especially when integrated in larger healthcare systems (e.g. Electronic Health Record - EHR systems, Hospital Management Systems - HMS, e-Prescription systems etc.). This poster presents an approach to model Therapeutic Prescription Protocols (TPPs) via the Business Process Management Notation (BPMN), as part of the e-Prescription CDSS developed in the context of the PrescIT project.

Stem cell factor is implicated in microenvironmental interactions and cellular dynamics of chronic lymphocytic leukemia.

The inflammatory cytokine stem cell factor (SCF, ligand of c-kit receptor) has been implicated as a pro-oncogenic driver and an adverse prognosticator in several human cancers. Increased SCF levels have recently been reported in a small series of patients with chronic lymphocytic leukemia (CLL), however its precise role in CLL pathophysiology remains elusive. In this study, CLL cells were found to express predominantly the membrane isoform of SCF, which is known to elicit a more robust activation of the c-kit receptor. SCF was significantly overexpressed in CLL cells compared to healthy tonsillar B cells and it correlated with adverse prognostic biomarkers, shorter time-to-first treatment and shorter overall survival. Activation of immune receptors and long-term cell-cell interactions with the mesenchymal stroma led to an elevation of SCF primarily in CLL cases with an adverse prognosis. Contrariwise, suppression of oxidative stress and the BTK inhibitor ibrutinib lowered SCF levels. Interestingly, SCF significantly correlated with mitochondrial dynamics and hypoxia-inducible factor-1a which have previously been linked with clinical aggressiveness in CLL. SCF was able to elicit direct biological effects in CLL cells, affecting redox homeostasis and cell proliferation. Overall, the aberrantly expressed SCF in CLL cells emerges as a key response regulator to microenvironmental stimuli while correlating with poor prognosis. On these grounds, specific targeting of this inflammatory molecule could serve as a novel therapeutic approach in CLL.

Supporting Active Pharmacovigilance via IT Tools in the Clinical Setting and Beyond: Regulatory and Management Aspects.

Information Technology (IT) could have a prominent role towards the "Active Pharmacovigilance" (AP) paradigm by facilitating the analysis of potential Adverse Drug Reactions (ADRs). PVClinical project aims to build an IT platform enabling the investigation of potential ADRs in the clinical environment and beyond. In this paper, we outline the respective EU regulatory framework and the related Business Processes (BPs), elaborated based on input from clinicians and PV experts as part of the project's "user requirements analysis" phase, highlighting their potential pivotal role in the design of IT tools aiming to support AP.

Production and Transduction of a Human Recombinant ß-Globin Chain into Proerythroid K-562 Cells To Replace Missing Endogenous ß-Globin.

Protein replacement therapy (PRT) has been applied to treat severe monogenetic/metabolic disorders characterized by a protein deficiency. In disorders where an intracellular protein is missing, PRT is not easily feasible due to the inability of proteins to cross the cell membrane. Instead, gene therapy has been applied, although still with limited success. ß-Thalassemias are severe congenital hemoglobinopathies, characterized by deficiency or reduced production of the adult ß-globin chain. The resulting imbalance of α-/ß-globin chains of adult hemoglobin (α2ß2) leads to precipitation of unpaired α-globin chains and, eventually, to defective erythropoiesis. Since protein transduction domain (PTD) technology has emerged as a promising therapeutic approach, we produced a human recombinant ß-globin chain in fusion with the TAT peptide and successfully transduced it into human proerythroid K-562 cells, deficient in mature ß-globin chain. Notably, the produced human recombinant ß-globin chain without the TAT peptide, used as internal negative control, failed to be transduced into K-562 cells under similar conditions. In silico studies complemented by SDS-PAGE, Western blotting, co-immunoprecipitation and LC-MS/MS analysis indicated that the transduced recombinant fusion TAT-ß-globin protein interacts with the endogenous native α-like globins to form hemoglobin α2ß2-like tetramers to a limited extent. Our findings provide evidence that recombinant TAT-ß-globin is transmissible into proerythroid K-562 cells and can be potentially considered as an alternative protein therapeutic approach for ß-thalassemias.