Shodh Sari-An International Multidisciplinary Journal

The convergence of Artificial Intelligence (AI), neuroscience, and nano biomedicine is redefining how researchers analyse, visualise and interpret complicated biological data. Traditionally, a good amount of these studies has consistently relied on coding systems based on programming languages and tools like R, MATLAB and Python, which created what may be termed as a “code-to-wet-lab bottleneck”. Researchers spent disproportionately enormous amounts of time on data cleansing, script debugging, model validation and computational workflow design; tasks that drag down the scientific schedule, the transition to experimental exploration, assay development and medical translation. Recent years have witnessed a paradigm shift. AI-assisted systems now allow scientists to generate extensive analyses and figures from tailored-language prompts, dramatically decreasing computational overhead, lowering the barrier for the earlier non-programmers and enabling the scientists and researchers alike to dedicate their valuable time towards hypothesis testing, wet-lab assays and translational innovation. For example, scientific opinions highlight how deep-learning frameworks for MRI-based prognosis of neurological problems have improved automation and speeded up segmentation and classification tasks [1,6]. 

In neuroimaging studies, a wide variety of AI-associated publications surged sharply from 2019 to 2024, underscoring the expanding role of AI in neuroscience workflows [2]. Furthermore, studies now emphasize that collaboration between human specialists and AI assistants (as an example big-language-model-assisted MRI interpretation) can reduce annotation time and help differential prognosis [3,4]. Within the area of nano biomedicine and precision drug development, AI is likewise accelerating innovation [6]. The combination of AI in nano architectonic design for precision drug development has been shown to reduce data-evaluation time, help predictive modelling of nanoparticle behaviour and enable closed-loop design cycles for translational applications [5]. Such traits make AI-driven workflows particularly critical in Alzheimer’s and other neurodegenerative disease studies. In that context, the window for powerful intervention is narrow and green translation from in-silico prediction to in-vitro validation is critical. Together, these advances highlight a metamorphosis from code-focused, computationally intensive pipelines towards idea-driven, set-off enabled, AI-augmented workflows that enable experimental scientists to contribute their time on biological interpretation, experimental design and translational effects. This transition is especially crucial for multidisciplinary domains such as neuroscience and nano biomedicine, where computational skill requirements have historically limited participation by experimentalists, and where the speed of translation can determine clinical relevance.

AI in Neuroimaging 

In current years, artificial intelligence (AI) has dramatically reshaped neuroimaging workflows, particularly in terms of structural and useful mind facts evaluation. Deep learning (DL) algorithms, particularly convolutional neural networks (CNNs), vision transformers, and hybrid architectures are increasingly being used for tasks of brain segmentation, parcellation, lesion detection, and connectome feature extraction. For instance, a complete review of DL for brain-tumor MRI evaluation stated that computerized segmentation and accuracy checks are similar to that conducted by expert clinicians. Structures inclusive of FreeSurfer‑AI extensions and FSL‑MEGNet (based at the properly-mounted FSL suite) now integrate AI modules to boost up segmentation of cortical and subcortical systems, computation of morphometric indices (e.g., cortical thickness, floor place), and generation of connectivity matrices. A review of automated and semi-automated MRI segmentation stated that AI-based gear significantly improved processing pace and segmentation accuracy across healthy and pathological brain imagery [7]. Validation research supports the promise of AI in neuroimaging. For instance, the segmentation accuracy of numerous AI models (which includes vision-transformer-based models) across big MRI datasets, locating the basis models pretrained on tens of thousands of scans (e.g., BrainSegFounder) outperformed earlier supervised models in the brain-tumor segmentation challenge. Throughout, evaluations of clinical image-segmentations, the emergence of explainable AI (XAI) and truthful AI (TAI) frameworks to address interpretability and safety concerns is evident [8]. In spite of these advances, more than one challenges persist. First, facts-heterogeneity and domain-shift continue to be principal bottlenecks. Models skilled on one imaging protocol or website frequently perform poorly on another scanner or populace. A literature review of early-level Alzheimer’s disorder prediction through AI cited that facts standardization and generalizability continue to be an unresolved issue. Secondly, the “black-box” nature of many deep-learning gear hinders transparency and clinician trust. The shift to XAI/TAI attempts to mitigate this but is still in the evolving phase. Thirdly, scientific integration and regulatory validation are the aspects that lag behind the overall algorithmic performance [9]. Many models continue to be trapped in research settings just as a replacement for habitual workflows. Ultimately, computational demands and reproducibility troubles complicate big-scale adoption particularly in aid-restricted settings. From an academic and translational perspective, these offer significant possibility but additionally require hybrid workflows. For an instance, in the context of work on neurodegenerative disorder and nanomedicine, AI-based neuroimaging pipelines can hand down precious time for performing experimental assays and correlate imaging biomarkers with nanoparticle efficacy [6,10,11]. However, the researcher should continue to be vigilant about validation, cross-website & online reproducibility, and interpretation of output features. In summary, AI in neuroimaging has entered a sturdy growth phase. Segmentation and feature extraction are increasingly computerized, permitting faster, extra reproducible pipelines. Big translational impacts demand strong validation, domain adaptation, explainability, and integration with downstream wet-lab or scientific workflows. The following sections of this review will explore how similar AI frameworks are extending into neuropharmacology, omics, literature-synthesis, and lab automation, thereby joining the loop from imaging to healing innovation.

AI in Neuropharmacology and Nanomedicine

From In-Silico Screening to In-Vitro Translation artificial intelligence (AI) is redefining neuropharmacology and nano biomedicine by accelerating drug discovery, optimizing nanoparticle layout, and enhancing translational precision. Traditionally, the development of neuroprotective compounds for disorders like Alzheimer’s disease required rigorous molecular docking, simulation, and in-vitro validation cycles [6,12]. AI now bridges this gap by presenting in-silico predictive models that simulate ligand-receptor interactions, pharmacokinetics, and blood-brain barrier (BBB) permeability with splendid accuracy. AI-enabled nano architectonic frameworks have manufactured the layout of multifunctional nanocarriers that may deliver drugs without delay to specific neural targets. For example, Bae et al. (2025) brought an AI-pushed nano architectonics platform that makes use of deep neural networks to optimize nanocarrier morphology, floor price, and functionalization for focused drug delivery in neurodegenerative illnesses. This approach drastically reduces the time and cost of preclinical screening even as enhancing healing precision [4]. In parallel, AI-based totally predictive modeling gear consisting of DeepChem, ChemBERTa, and Molecule.one are getting used to simulate molecular interactions and identify excessive-affinity for neuroprotective targets thus getting rid of the need for exhaustive chemical synthesis & evaluation. Recent studies integrating AI with nano diagnostics have proven their capacity for early detection and personalized prevention of neurodegenerative diseases. Hassan et al. (2025) reported that AI-enabled nano diagnostic platforms can distinguish among the subtle biomarker variants, enabling early detection of Alzheimer’s and Parkinson’s disease through non-invasive assays [5]. Together, these improvements highlight how AI is catalyzing the in-silico to in-vitro continuum, empowering researchers to move from predictive simulations to practical experimentation with extraordinary performance. The mixing of modeling with wet-lab validation represents a vital step toward sustainable, moral, and precision-enabled neurotherapeutics in the field of translational nanomedicine.

AI for Omics evaluation

The explosion of multi-omics information spanning across genomics, transcriptomics, proteomics, and metabolomics has created possibilities for informing the molecular underpinnings of neurological and neurodegenerative disorders. But, the sheer complexity and quantity of these datasets have historically required massive coding know-how in bioinformatics tools consisting of R, Python, or MATLAB. Artificial intelligence (AI) is now bridging this analytical divide through set off-based and automatic information interpretation workflows that give access to superior computational evaluation. Current AI-powered structures consisting of OmicVerse, Gene Ontology AI help, and ChatGPT BioQuery can at once organise CSV or FASTA datasets. For an instance, a researcher can enter a prompt like “Upregulated inflammatory genes in the hippocampal transcriptome of Alzheimer’s patients (GSEXXXX)”, and the AI robotically executes statistical assessments, clustering, and pathway enrichment, tasks that historically required huge R code. These tools streamline the   neuroinflammatory and oxidative stress-associated pathways, permitting researchers to focus on experimental validation and biomarker correlation as opposed to manual coding. Moreover, large toolboxes pre-trained on biological data are improving accuracy in information interpretation with the aim of integrating multimodal inputs (e.g., gene expression and imaging information). In a recent evaluation, Ali et al. (2025) cited that deep learning knowledge of integration of omics and neuroimaging capabilities advanced the diagnostic accuracy of neurological disorders classification frameworks [1]. Notwithstanding these advances, demanding situations continue to exist. AI models may additionally overfits because of biased datasets or lack of normalization across structures, leading to spurious biological outcomes. Furthermore, prompt-based AI structures regularly lack transparency in how unique statistical selections are made, raising issues of approximation, reproducibility and interpretability. For this reason, integrating AI-enabled analytics with expert curation remains essential. At same time as AI complements performance and accessibility, rigorous validation and interdisciplinary oversight are important to confirm scientific integrity in AI-enabled neuroscience [2,13]. In summary, AI-assisted omics workflows are remodeling neuroscience studies from code-dependent pipelines into intuitive, prompt-based ecosystems. When used responsibly, these structures not only accelerate discovery but additionally foster a greater inclusive and reproducible framework for next-generation neuroinformatics.

Meta-Analysis Tools

Rapid expansion of scientific literature in neuroscience and nano biomedicine provides a dual challenge that whilst the developing frame of labor accelerates innovation, it concurrently overwhelms researchers with redundant, fragmented, or unstructured facts. Artificial intelligence (AI) is addressing this hurdle by way of automating literature analysis, constructing information graphs, and producing meta-analyses in contrast to dedicated weeks of manual evaluation. AI-powered discovery engines which include Connected Papers, Research Rabbit, and Elicit leverage natural language processing (NLP) and citation community analysis to perceive conceptual relationships among lots of studies in seconds. These systems generate visual information maps that connect seminal and recent papers, allowing researchers to trace the evolution of ideas like amyloid-centered nanomedicine or AI-enabled brain imaging segmentation across time. Unlike conventional databases which include PubMed or Scopus, these gears combine contextual similarity metrics, helping users discover relevant literature even when key phrases or terminology differ. For an example, by way of querying “ursolic acid nanoparticles in Alzheimer’s therapy,” Elicit can synthesize guide clusters that summarize latest findings on antioxidant nanocarriers, latest studies guidelines, and extract key biomarkers linked to neuroprotection. Similarly, Research Rabbit enables dynamic collaboration by way of letting users co-curate literature collections and generate thematics that display interdisciplinary intersections among neuropharmacology, imaging, and omics studies. This automatic synthesis substantially reduces the time spent on literature mining what once took several days or perhaps weeks can now be accomplished in under an hour, freeing researchers to recognise and focus more on experimental design and speculation components. The surge in AI-assisted bibliometric gears display a broader trend towards computational curation of scientific information, enhancing not only performance but also the accuracy of global studies insights [2,13]. However, these systems are not without obstacles. The accuracy of AI-derived summaries depends on the comprehensiveness of the records and the transparency of citation algorithms. Moreover, ethical issues concerning ability biases in model learning and the reproducibility of AI-generated literature networks are the major concerns. To mitigate these aspects, human validation remains important ensuring that automatic outputs are seriously interpreted in terms of their organic and medical context. Overall, AI-enabled meta-analysis and literature analyses algorithms are revolutionizing how neuroscientists and Nano-biomedical researchers navigate the ever-expanding scientific panorama. They serve as intellectual compasses, guiding discovery whilst enabling records-pushed, evidence-based decision-making for translational studies.

Wet-Lab Automation and education 

Artificial intelligence (AI) has entered the experimental centre of neuroscience and nano biomedicine, transforming how laboratory underpinnings are implemented, managed, and circulated. The traditional wet-lab system, frequently restricted through manual managing, complicated facts recording, and variable human precision is now being streamlined via AI-augmented automation and intelligent lab management systems. This shift not only complements efficiency and reproducibility but also revolutionizes how college students and researchers revel in medical education. Current AI based platforms together with BenchSci and LabTwin exemplify this transition. BenchSci employs deep learning to interpret experimental protocols and robotically extract applicable reagent facts, antibody specs, and assay situations from the medical literature. This automation significantly reduces the time devoted for experimental layout, making sure that researchers can emphasise on speculation-enabled inquiry in preference to logistical setup. In addition, LabTwin serves as a voice-activated digital assistant that record actual-time lab observations, organizes experimental facts, and suggests next steps primarily based on pre-trained medical workflows. Collectively, these platforms improve laboratory accuracy, lessen manual errors, and allow researchers to multitask correctly within biosafety environments (BenchSci, 2025) (LabTwin, 2025). In instructional contexts, AI-simulated virtual laboratories are playing an important role in bridging principle and practice. Researchers can now conduct in silico experiments together with virtual FTIR, SEM, or DPPH assays using AI based simulators before moving into actual lab environments. This pre-lab visualization complements conceptual know-how, reduces bio-fabric waste, and builds confidence in procedural execution. For an instance, with AI-integrated platforms like BioRender AI and Gemini molecule, renderers can instantly generate realistic 3-D visualizations of nanoparticles, disposing of the need for advanced coding or modeling information in software like MATLAB. AI in wet-lab management is also facilitating translational efficiency. Through integrating experimental results with computational predictions (e.g., from DeepChem or ChemBERTa models), scientists can directly validate in-silico findings in in-vitro assays. This synergy allows for a more precise testing of neuroprotective formulations for instance UA-Pullulan and UA-Gum Acacia nanoparticles, in which AI assists in predicting most appropriate physicochemical and organic profiles before bench validation [6,10,11]. Moreover, the inclusion of AI in laboratory education encourages interdisciplinary research. Researchers not only discover ways to behavioral experiments but also engage in facts evaluation, automation, judgment, and ethical dimensions of AI systems. As mentioned through Kaushik et al. (2025), AI-assisted preclinical simulations represent a humane and efficient opportunity to animal testing, fostering both ethical and sensible innovation in neuropharmacological research [6,12]. Even as these tools are reshaping lab education and research, challenges exist, specifically regarding facts standardization, AI dependency, and equitability. Addressing these issues via open-source AI systems and worldwide instructional collaborations may be important to making sure a sustainable, inclusive future in experimental neuroscience and nano biomedicine.

Integration Framework and Workflows 

The accelerated convergence of artificial intelligence (AI), neuropharmacology, and nano biomedicine needs a workflow that bridges in-silico modeling with in-vitro and in-vivo validation. Despite foremost advances in AI-assisted imaging, drug discovery, and omics evaluation, a gap persists between virtual prediction and organic awareness; a disconnect usually termed as the code-to-wet-lab translation barrier. Building a unified integration framework is therefore important for knowing the full translational capability of AI-enabled neuroscience. A proposed AI-wet-Lab Integration Framework follows a closed-loop structure encompassing six interconnected modules namely; Records Acquisition and Curation, AI based Preprocessing and feature Extraction, Predictive Modeling and Simulation, Experimental Validation and Wet-Lab Automation, feedback-enabled Optimization, and finally expertise Integration and Reporting. In the first stage, multimodal datasets from neuroimaging (MRI, PET), molecular simulations (MD, QM/MM), and multi-omics structures (proteomics, metabolomics, transcriptomics) are collected and standardized using compliant repositories. Algorithms along with Neurodata without boundaries (NWB) and OpenNeuro facilitate established records ingestion, even as high-quality warranty algorithms make sure reliability and reproducibility. AI frameworks like BrainSegFounder (Cox et al., 2024) and U-Net3D versions beautify segmentation precision in brain MRI, allowing the extraction of structural biomarkers relevant to Alzheimer’s disease and other neurodegenerative conditions [14]. the second stage leverages deep learning models to generate feature embeddings, simulate nanoparticle-protein interactions, and expect organic consequences. AI based systems along with DeepChem, MolBERT, and AlphaFold Multimer provide molecular-stage insights that exhibit nanoparticle method parameters, along with zeta capability, hydrodynamic diameter, and ligand affinity. These insights guide wet-lab researchers toward the most promising formulations, notably decreasing the experimental burden. For an instance, work on UA-Pullulan and UA-Gum Acacia nanoparticles, such AI-informed pre-screening can assist anti-amyloid efficacy and acetylcholinesterase inhibition prior to in-vitro validation [6]. The third and fourth stages of the framework contain computerized laboratory execution and feedback incorporation. Using AI systems along with LabTwin or Benchling, experimental parameters are automatically recorded, analyzed, and fed again into the computational models. This iterative refinement improves prediction accuracy over the years, creating a real AI-guided experimental evolution cycle. Integration with robotics and IoT based biosensors similarly enables remote tracking of assays, decreasing human mistakes and improving reproducibility. In the very last stages, graphs and meta-analytical dashboards (built using AI-assisted literature mining gear like Semantic scholar’s API or Elicit AI) synthesize experimental consequences, computational insights, and organic relevance into interpretable visualizations. This integrative ecosystem now not only hastens discovery but also assists in collaborative technological know-how by means of linking code outputs, experimental records, and literature-based evidence in an interactive workspace. Conclusively, this pipeline transforms AI from a passive analytical resource into an energetic experimental collaborator, bridging the distance between virtual prediction and organic validation. By means of allowing continuous feedback between computational modeling and laboratory experimentation, this framework lays the foundation for the next-generation neuropharmacological innovation, in which AI learns from biology, and biology evolves through AI [6,14]. Table 1. Illustrated below displays AI based key tools and platforms that may be utilized for wet-labs, neuroimaging, and neuroscience research. Their core functionality, application and their translational relevance are also stated (Links to all tools/platforms are provided for readers/researchers’ convenience)

Table 1: Key AI tools and platforms for wet-labs, neuroimaging, and neuroscience research 

Challenges and Ethics

Even as the mixing of artificial intelligence (AI) with neuroscience, neuropharmacology, and nanomedicine promises remarkable innovation, it also introduces considerable challenges in terms of ethics, reproducibility, and statistics governance. As AI increasingly influences speculation technology, medical interpretation, and therapeutic design, researchers ought to navigate the complexities of algorithmic bias, statistics integrity, and safety to make sure that the promise of sensible automation does no longer come on the cost of scientific and moral rigor. AI structures are inherently shaped by means of the statistics on which they may be skilled. In neuroimaging and neurodegenerative diseases research, datasets are regularly biased in the direction of unique demographics, imaging protocols, or disease tiers. Consequently, models skilled on such statistics may underperform when applied to diverse populations or multi-institutional datasets. Ali et al. (2025) emphasized that deep learning frameworks for MRI-based diagnosis regularly suffer from training set homogeneity, skewed diagnostic outputs and reduced generalizability across neurological disorders [1]. Furthermore, black-box AI structures make it difficult to choose pathways, which poses challenges for medical explainability and regulatory approval. To mitigate such bias, the adoption of transparent AI architectures, open-get right of entry to statistics consortia (like ADNI or UK Biobank), and federated learning approaches can promote model variety without compromising affected individual privacy. These approaches permit multi-web page collaboration even as preserving decentralized statistics ownership, thereby balancing inclusivity with confidentiality. Some other critical task lies in the reproducibility of AI-driven discoveries. In contrast to conventional experiments with extensively described protocols, AI models involve hyperparameter tuning, random initialization, and hardware-structured behaviors that could lead to inconsistent results. Sadettin Ersoy et al. (2025) highlighted that even as worldwide AI research in neurology has surged, fewer than 25% of studies report complete reproducibility or offer open-access code and datasets for verification [2]. This loss of transparency impedes peer validation and undermines trust in AI-generated results, especially in excessive-stakes fields like Alzheimer’s disease diagnostics or nanoparticle drug formulation. To produce reproducibility, research groups are more and more adopting frameworks such as models and Datasheets for Datasets, which report statistics provenance, and intended use cases. Journals and investment corporations also are mandating open-access right of entry to repositories for model architectures and codebases to foster verifiable research practices. Growing dependence on huge-scale affected patients’ datasets introduce statistics privacy issues. Neuroimaging, genomics, and behavioral datasets regularly comprise identifiable styles that cannot be fully anonymized. Even as GDPR and HIPAA rules offer suggestions for statistics use, the emergence of multimodal AI structures complicates compliance by means of merging medical, omic, and imaging statistics. Anonymization technologies such as differential privateness, homomorphic encryption, and synthetic statistics technology have shown promise in allowing statistics sharing even as minimizing threat of re-identity. Ethically, consent frameworks ought to evolve in the direction of dynamic consent models that supply participants real-time control over how their statistics are used, especially when included across omics, neuroimaging, and nanomedical systems. Organising these frameworks guarantees affected person’s autonomy even as selling accountable statistics contribute towards scientific development. As AI structures start to make or help in medical and experimental selections, delineating accountability among human researchers and algorithms is essential. Human-AI collaborative studies such as the ones described by means of Kim et al. (2025), display the value of preserving human oversight in diagnostic interpretation, reducing false positives and improving clinicians’ confidence. In experimental nanomedicine design, AI has to remain an aiding mechanism, augmenting human creativity in place to replacing it. Moving ahead, moral AI governance ought to prioritize explainability, inclusivity, transparency, and sustainability. Global consortia should set up standardized AI audit trails and moral evaluation protocols to maintain consensus for in neuro-AI innovations. In summary, addressing bias, reproducibility, and privacy issues isn’t simply a technical duty but a moral necessity. The credibility and translational capability of AI in neuroscience depends upon building frameworks that emphasize on fairness, replicability, and appreciation for human dignity, laying the foundation for an accountable, transparent, and equitable generation of sensible neuro-biomedical research [1,2,3]. 

Conclusions and Future directions 

Artificial intelligence (AI) worked with neuroscience, neuropharmacology, and nanomedicine is catalyzing a paradigm shift from code-intensive computational workflows towards intuitive, interpretable, and translationally focused studies ecosystems. The collective improvements, from AI-enabled neuroimaging segmentation to ligand-target interplay prediction, omics integration, and automated literature syntheses are all transforming how hypotheses are generated, established, and carried out across each preclinical and scientific domain. By the way of lowering the code-to-wet-lab bottleneck, AI enables scientists to devote energy on conceptual innovation, biological interpretation, and ethical validation as opposed to on repetitive coding or facts preprocessing. As an instance, framework which includes DeepBrain AI and FSL-MEGNet have dramatically shortened neuroimaging preprocessing pipelines, whilst molecular design frameworks like DeepChem and ChemBERTa expedite drug-target prediction and nanoparticle optimization. Likewise, in multi-omics evaluation, AI-assisted systems which include OmicVerse and ChatGPT BioQuery are bridging computational biology with experimental neuroscience, assisting actual-time exploration of genomic and proteomic signatures underlying neurodegenerative diseases. Future directions point towards incorporated AI pipelines that seamlessly join imaging, omics, pharmacological modeling, and behavioral facts. Such structures should operate as virtual twins of experimental modules, in which digital simulations dynamically replace primarily the manual lab work. These frameworks could allow predictive modeling of therapeutic hypotheses which includes assessing the neuroprotective potential of nanoparticles before in vivo validation, thereby lowering bio-burden and ethical constraints associated with animal models. Open-access model repositories, standardized metadata codecs, and collaborative systems like the Open Neuroimaging Consortium and NeuroAI Hub may be critical for reproducibility and accountability in future AI studies. Model documentation should become a norm, enabling peers to hint the reasoning in the back of AI-enabled insights and reflect analyses across diverse populations and experimental conditions. The subsequent era of neuro-AI structures needs to emphasize explainability, inclusivity, and anonymity. Human-AI collaboration in scientific neuroscience enhances diagnostic self-assurance when interpretability and oversight are maintained. Embedding ethical design standards into algorithmic improvement which includes bias audits, gaining knowledge of frameworks, and anonymization analytics may be key to ensuring that AI serves as a depended-on co-pilot as opposed to a black-field decision-maker. In academia, AI-augmented academic systems which includes LabTwin and BenchSci will rework how university students and early-profession researchers interact with experimental protocols, offering virtualized wet-lab environments for simulation and talent-constructing. Clinically, AI based neuropharmacological prediction models should accelerate precision drug- design, mainly in neurodegenerative and psychiatric disorders, by way of aligning computational predictions with patient-precise biomarker profiles. The final vision is closed-loop AI-neuroscience surroundings, in which predictive computational models, experimental facts, and scientific insights constantly interact with each other in real time. This convergence will redefine translational neuroscience, enabling in advanced disorder detection, greater sustainable-drug discovery especially catered on nanotherapeutic interventions. The synergy of AI with human understanding will foster a brand-new generation of computational neuro-ethics in which precision, transparency, and compassion accelerate scientific development. In conclusion, AI-assisted neuroscience represents greater than just a technological revolution; it indicates a philosophical shift towards interdisciplinary intelligence surroundings that integrates facts-based inference with biological instinct. The future lies in constructing interpretable, collaborative, and ethically sound AI systems capable of advancing neurological studies and build neurotherapeutics for the advantage of humanity. 

Conflict of Interest

The author(s) declare no commercial, financial, or proprietary conflicts of interest related to this research. AI tools, neuroimaging software suites, and wet-lab automation systems referred are used purely for academic and educational purposes. The author(s) have no financial relationships with any companies or organizations that could inappropriately influence the work presented here. Work presented here is solely the property of author(s) mentioned.