Wet-lab Experiments Research Articles

Data-driven discovery of chemotactic migration of bacteria via coordinate-invariant machine learning

BackgroundE. coli chemotactic motion in the presence of a chemonutrient field can be studied using wet laboratory experiments or macroscale-level partial differential equations (PDEs) (among others). Bridging experimental measurements and chemotactic Partial Differential Equations requires knowledge of the evolution of all underlying fields, initial and boundary conditions, and often necessitates strong assumptions. In this work, we propose machine learning approaches, along with ideas from the Whitney and Takens embedding theorems, to circumvent these challenges.ResultsMachine learning approaches for identifying underlying PDEs were (a) validated through the use of simulation data from established continuum models and (b) used to infer chemotactic PDEs from experimental data. Such data-driven models were surrogates either for the entire chemotactic PDE right-hand-side (black box models), or, in a more targeted fashion, just for the chemotactic term (gray box models). Furthermore, it was demonstrated that a short history of bacterial density may compensate for the missing measurements of the field of chemonutrient concentration. In fact, given reasonable conditions, such a short history of bacterial density measurements could even be used to infer chemonutrient concentration.ConclusionData-driven PDEs are an important modeling tool when studying Chemotaxis at the macroscale, as they can learn bacterial motility from various data sources, fidelities (here, computational models, experiments) or coordinate systems. The resulting data-driven PDEs can then be simulated to reproduce/predict computational or experimental bacterial density profile data independent of the coordinate system, approximate meaningful parameters or functional terms, and even possibly estimate the underlying (unmeasured) chemonutrient field evolution.

Computational Analysis of Cell Type-Specific Transcriptional Dynamics in Major Depressive Disorder

Depression, also known as major depressive disorder (MDD), is a complex mental health condition that affects millions of people worldwide. Since disease treatments often depend on levels of understanding, this project strives to learn more about the transcriptional components of MDD to delineate the transcriptomic dynamics in MDD. The sample includes the single-cell transcriptomic profiles in the dorsolateral prefrontal cortex (dlPFC) of 34 postmortem patients. This data was acquired from publicly available datasets and run through R-Studio code. Cell clusters were classified into cell types using cell-type-specific signature markers in the original resource datasets. After analyzing immediate early genes (IEGs), MDD-associated genes, and differentially expressed genes, the trend showed broadly lowered expression levels and frequency in MDD patients than in healthy control with some exceptions. After studying 10 different IEGs, the trend showed a lowered gene expression frequency in MDD patients than in control. For MDD-associated genes, a similar trend showed lower frequency and expression levels in the MDD sample, apart from GAD1 and RELN, which had a higher expression level in the MDD sample. Then, by analyzing the top differentially expressed genes in each cell type, most cells showed a lowered frequency in MDD patients besides macrophage/microglial, which had higher expression frequency in IGHG1 and RP11-315A16.1 for the control sample. With each analytical finding, the underlying elements of MDD may be better understood, leading to more precise wet lab experiments and the eventual treatment of MDD.

Computational Evaluation of Bioactive Compounds in Vernonia Amygdalina as a Novel Therapeutics for Acute Myeloid Leukemia: Targeting the Hedgehog Pathway

AbstractThe drug resistance challenges in acute myeloid leukemia have been linked the hedgehog (HH) signaling pathway activation by many studies. Furthermore, studies have shown that the components of the HH pathway, including 12‐pass transmembrane receptor Patched (PTCH), the 7‐pass transmembrane signal transduction protein Smoothened (SMO), and all three GLI transcription factors, are expressed in AML. Thus, pharmacological inhibition of SMO in the HH signaling in these cells has anti‐leukemic effects. However, the first SMO inhibitor specific to AML (Glasdegib) has been approved based on improved overall survival rates, but alternative approaches are still required. Thus we employed druglikeness screening, molecular docking, molecular dynamics simulation, non‐equilibrium free energy and in silico pharmacokinetics profiling on bioactive compounds from Vernonia amygdalina against SMO protein target. From 30 bioactive compounds in V. amygdalina, 13 had drug‐like potential, 5 had binding energy between −9.2 to −9.9 kcal/mol. Cryptolepine, neocryptolepine and isocryptolepine with the least BE showed good stability, dynamics over 300 ns of MD run and higher binding affinities via the Jarzynski's identity. Hence, these bioactive compounds may serve as potential drugs for the treatment of acute myeloid leukemia by targeting the SMO protein after wet lab experiments.

In silico screening and identifying phytoconstituents of Withania somnifera as potent inhibitors of BRCA1 mutants: A therapeutic against breast cancer

Breast CAncer gene 1 (BRCA1) is an anti-oncogene that helps the cell repair damaged DNA and preserve genetic material. BRCA1 also acts as a cell growth suppressor and produces tumor suppressor gene (TSG) proteins, i.e., BRCA1 protein. Remarkably, BRCA1 mutations account for 90 % of hereditary breast cancer and a majority of hereditary ovarian cancer. Hence, we have considered three mutants of BRCA1 (R1699W, R1699Q, T1700A) in this study and adopted an in-silico approach to find the best possible phytochemical to inhibit these mutated proteins, enabling early breast cancer diagnosis. Perceiving the importance, many natural molecules from ancient medicinal plants are considered for molecular docking. Our findings suggest that though many molecules bind actively with the receptor's active site, the top three phytoconstituents (27-Deoxy-14-hydroxywithaferin A, Withacoagulin, Somniferanolide) of Withania somnifera, commonly known as Ashwagandha, have high binding affinities and suitable pharmacokinetic properties, making these natural compounds potential drug candidates. Further, molecular dynamics (MD) simulation and the binding free energy calculation show stability and thermodynamically favourable. We can, therefore, draw the conclusion that these lead compounds act as potential inhibitors against BRCA1. However, wet lab experiments and clinical trials are recommended to ascertain its efficacy, hence the development of novel BRCA1 inhibitors.

Evaluating the representational power of pre-trained DNA language models for regulatory genomics.

The emergence of genomic language models (gLMs) offers an unsupervised approach to learning a wide diversity of cis-regulatory patterns in the non-coding genome without requiring labels of functional activity generated by wet-lab experiments. Previous evaluations have shown that pre-trained gLMs can be leveraged to improve predictive performance across a broad range of regulatory genomics tasks, albeit using relatively simple benchmark datasets and baseline models. Since the gLMs in these studies were tested upon fine-tuning their weights for each downstream task, determining whether gLM representations embody a foundational understanding of cis-regulatory biology remains an open question. Here we evaluate the representational power of pre-trained gLMs to predict and interpret cell-type-specific functional genomics data that span DNA and RNA regulation. Our findings suggest that probing the representations of pre-trained gLMs do not offer substantial advantages over conventional machine learning approaches that use one-hot encoded sequences. This work highlights a major gap with current gLMs, raising potential issues in conventional pre-training strategies for the non-coding genome.

Promising Drug Delivery System for Cervical Cancer – A Future Approach

There is evidence that peptide targeting can be applied in cervical cancer therapy and for diagnosis involving the use of molecular imaging, hence developing peptide probes for this disease. Cervical cancer, which also has a high possibility of being prevented, is among the common tumors affecting women globally. Despite the occurrence being reduced greatly by screening, the illness remains fatal and its claims many lives annually, especially in the developing nations. In exercising such a perspective, specific public health efforts known to encourage physical activity, proper diet, and early detection of cervical cancer must begin to be taken seriously. When combined, doctors, health officers, and lawmakers could speed up the global deployment of such programs. California’s American Cancer Society, the present review enlists a host of pharmaceutical goods available in the market. This perspective of present-day research and manufacturing is devoted to the development of various types of nanocarriers for possible utilization in medication transport. Thus, overall cancer mortality appears to be not substantially different, though cancer incidence rates for both sexes are 50% lower in impoverished countries when compared to affluent nations. At the moment, there are new peptide probes that are developed solely for cervical cancer-perfectly suitable for targeting peptides applicable in therapeutic and diagnostic imaging. M13KE phage dodecapeptide (12-mer) peptide library was screened for recognition of human immunodeficiency virus type 1 (HIV-1) by immunofluorescence and flow cytometry; the S7 clone was identified as most suitable. A disease that affects many women is gynecologic health problems, and cervical cancer is the leading presenting complaint experienced regularly. Among these studies, QSAR, drug-likeness, PCA, dynamic cross-correlation matrix, molecular docking, molecular dynamics and quantum calculation properties can be listed. In the first literature survey, after identifying the potent antibacterial and anticancer activity of the molecule apigenin, some other promising derivatives were identified and more research has been carried out on them, focusing on their synthesized derivatives as inhibitors of DNA polymerase theta and cervical cancer caused by human papillomavirus. The results were streamlined by the use of in-silico molecular docking, which showed that all Apigenin derivatives and the targeted proteins had potential energy-binding relationships. Further validation is essential because this study used in-silico computational methodologies and produced excellent results. Applying in-silico molecular docking made the data more comprehensible, which showed the possible energy bindings of the targeted proteins and all the Apigenin variants. Due to the fact that this work utilized in-silico computational methods and obtained significant results, further validation is required. Hence, the present wet-lab experiments coupled with both in-vitro and in-vivo conditions, additional validation of the results.

DeepPBI-KG: a deep learning method for the prediction of phage-bacteria interactions based on key genes.

Phages, the natural predators of bacteria, were discovered more than 100years ago. However, increasing antimicrobial resistance rates have revitalized phage research. Methods that are more time-consuming and efficient than wet-laboratory experiments are needed to help screen phages quickly for therapeutic use. Traditional computational methods usually ignore the fact that phage-bacteria interactions are achieved by key genes and proteins. Methods for intraspecific prediction are rare since almost all existing methods consider only interactions at the species and genus levels. Moreover, most strains in existing databases contain only partial genome information because whole-genome information for species is difficult to obtain. Here, we propose a new approach for interaction prediction by constructing new features from key genes and proteins via the application of K-means sampling to select high-quality negative samples for prediction. Finally, we develop DeepPBI-KG, a corresponding prediction tool based on feature selection and a deep neural network. The results show that the average area under the curve for prediction reached 0.93 for each strain, and the overall AUC and area under the precision-recall curve reached 0.89 and 0.92, respectively, on the independent test set; these values are greater than those of other existing prediction tools. The forward and reverse validation results indicate that key genes and key proteins regulate and influence the interaction, which supports the reliability of the model. In addition, intraspecific prediction experiments based on Klebsiella pneumoniae data demonstrate the potential applicability of DeepPBI-KG for intraspecific prediction. In summary, the feature engineering and interaction prediction approaches proposed in this study can effectively improve the robustness and stability of interaction prediction, can achieve high generalizability, and may provide new directions and insights for rapid phage screening for therapy.

Hybrid modeling for in silico optimization of a dynamic perfusion cell culture process.

The bio-pharmaceutical industry heavily relies on mammalian cells for the production of bio-therapeutic proteins. The complexity of implementing and high cost-of-goods of these processes are currently limiting more widespread patient access. This is driving efforts to enhance cell culture productivity and cost reduction. Upstream process intensification (PI), using perfusion approaches in the seed train and/or the main bioreactor, has shown substantial promise to enhance productivity. However, developing optimal process conditions for perfusion-based processes remain challenging due to resource and time constraints. Model-based optimization offers a solution by systematically screening process parameters like temperature, pH, and culture media to find the optimum conditions in silico. To our knowledge, this is the first experimentally validated model to explain the perfusion dynamics under different operating conditions and scales for process optimization. The hybrid model accurately describes Chinese hamster ovary (CHO) cell culture growth dynamics and a neural network model explains the production of mAb, allowing for optimization of media exchange rates. Results from six perfusion runs in Ambr® 250 demonstrated high accuracy, confirming the model's utility. Further, the implementation of dynamic media exchange rate schedule determined through model-based optimization resulted in 50% increase in volumetric productivity. Additionally, two 5 L-scale experiments validated the model's reliable extrapolation capabilities to large bioreactors. This approach could reduce the number of wet lab experiments needed for culture process optimization, offering a promising avenue for improving productivity, cost-of-goods in bio-pharmaceutical manufacturing, in turn improving patient access to pivotal medicine.

Glypred: Lysine Glycation Site Prediction via CCU-LightGBM-BiLSTM Framework with Multi-Head Attention Mechanism.

Glycation, a type of posttranslational modification, preferentially occurs on lysine and arginine residues, impairing protein functionality and altering characteristics. This process is linked to diseases such as Alzheimer's, diabetes, and atherosclerosis. Traditional wet lab experiments are time-consuming, whereas machine learning has significantly streamlined the prediction of protein glycation sites. Despite promising results, challenges remain, including data imbalance, feature redundancy, and suboptimal classifier performance. This research introduces Glypred, a lysine glycation site prediction model combining ClusterCentroids Undersampling (CCU), LightGBM, and bidirectional long short-term memory network (BiLSTM) methodologies, with an additional multihead attention mechanism integrated into the BiLSTM. To achieve this, the study undertakes several key steps: selecting diverse feature types to capture comprehensive protein information, employing a cluster-based undersampling strategy to balance the data set, using LightGBM for feature selection to enhance model performance, and implementing a bidirectional LSTM network for accurate classification. Together, these approaches ensure that Glypred effectively identifies glycation sites with high accuracy and robustness. For feature encoding, five distinct feature types─AAC, KMER, DR, PWAA, and EBGW─were selected to capture a broad spectrum of protein sequence and biological information. These encoded features were integrated and validated to ensure comprehensive protein information acquisition. To address the issue of highly imbalanced positive and negative samples, various undersampling algorithms, including random undersampling, NearMiss, edited nearest neighbor rule, and CCU, were evaluated. CCU was ultimately chosen to remove redundant nonglycated training data, establishing a balanced data set that enhances the model's accuracy and robustness. For feature selection, the LightGBM ensemble learning algorithm was employed to reduce feature dimensionality by identifying the most significant features. This approach accelerates model training, enhances generalization capabilities, and ensures good transferability of the model. Finally, a bidirectional long short-term memory network was used as the classifier, with a network structure designed to capture glycation modification site features from both forward and backward directions. To prevent overfitting, appropriate regularization parameters and dropout rates were introduced, achieving efficient classification. Experimental results show that Glypred achieved optimal performance. This model provides new insights for bioinformatics and encourages the application of similar strategies in other fields. A lysine glycation site prediction software tool was also developed using the PyQt5 library, offering researchers an auxiliary screening tool to reduce workload and improve efficiency. The software and data sets are available on GitHub: https://github.com/ZBYnb/Glypred.

StackDPPred: Multiclass prediction of defensin peptides using stacked ensemble learning with optimized features

Host defense or antimicrobial peptides (AMPs) are promising candidates for protecting host against microbial pathogens for example bacteria, virus, fungi, yeast. Defensins are the type of AMPs that act as potential therapeutic drug agent and perform vital role in various biological process. Conventional Experiments to identify defensin peptides (DPs) are time consuming and expensive. Thus, the shortcomings of wet lab experiments are leveraged by computational methods to accurately predict the functional types of DPs. In this paper, we aim to propose a novel multi-class ensemble-based prediction model called StackDPPred for identifying the properties of DPs. The peptide sequences are encoded using split amino acid composition (SAAC), segmented position specific scoring matrix (SegPSSM), histogram of oriented gradients-based PSSM (HOGPSSM) and feature extraction based graphical and statistical (FEGS) descriptors. Next, principal component analysis (PCA) is used to select the best subset of attributes. After that, the optimized features are fed into single machine learning and stacking-based ensemble classifiers. Furthermore, the ablation study demonstrates the robustness and efficacy of the stacking approach using reduced features for predicting DPs and their families. The proposed StackDPPred method improves the overall accuracy by 13.41% and 7.62% compared to existing DPs predictors iDPF-PseRAAC and iDEF-PseRAAC, respectively on validation test. Additionally, we applied the local interpretable model-agnostic explanations (LIME) algorithm to understand the contribution of selected features to the overall prediction. We believe, StackDPPred could serve as a valuable tool accelerating the screening of large-scale DPs and peptide-based drug discovery process.

Inhibition of MSH6 augments the antineoplastic efficacy of cisplatin in non-small cell lung cancer as autophagy modulator

The altered response to chemotherapeutic agents predominantly stems from heightened single-point mutations within coding regions and dysregulated expression levels of genes implicated in drug resistance mechanisms. The identification of biomarkers based on mutation profiles and expression levels is pivotal for elucidating the underlying mechanisms of altered drug responses and for refining combinatorial therapeutic strategies in the field of oncology. Utilizing comprehensive bioinformatic analyses, we investigated the impact of eight mismatch repair (MMR) genes on overall survival across 23 cancer types, encompassing more than 7500 tumors, by integrating their mutation profiles. Among these genes, MSH6 emerged as the most predictive biomarker, characterized by a pronounced mutation frequency and elevated expression levels, which correlated with poorer patient survival outcomes.The wet lab experiments disclosed the impact of MSH6 in mediating altered drug responses. Cytotoxic assays conducted revealed that the depletion of MSH6 in H460 non-small lung cancer cells augmented the efficacy of cisplatin, carboplatin, and gemcitabine. Pathway analyses further delineated the involvement of MSH6 as a modulator, influencing the delicate equilibrium between the pro-survival and pro-death functions of autophagy.Our study elucidates the intricate interplay between MSH6, autophagy, and cisplatin efficacy, highlighting MSH6 as a potential therapeutic target to overcome cisplatin resistance. By revealing the modulation of autophagy pathways by MSH6 inhibition, our findings offer insights into novel approaches for enhancing the efficacy of cisplatin-based cancer therapy through targeted interventions.

Understanding the Role of Layered Minerals in the Emergence and Preservation of Proto-Proteins and Detection of Traces of Early Life.

ConspectusThe origin of life remains one of the most profound mysteries in science. Over millennia, theories have evolved, yet the question persists: How did life emerge from inanimate matter? At its core, the study of life's origin offers insights into our place in the universe and the nature of life itself. By delving into the chemical and geological processes that led to life's emergence, scientists gain a deeper understanding of the fundamental principles that govern living systems. This knowledge not only expands our scientific understanding but also has profound implications for fields ranging from astrobiology to synthetic biology.This research employs a multidisciplinary approach, combining a diverse array of techniques, from space missions to wet laboratory experiments to theoretical modeling. Investigations into the formation of the first proto-biomolecules are tailored to explore both the complex molecular processes that underpin life and the geological contexts in which these processes may have occurred. While laboratory experiments are aimed at mimicking the processes of early planets, not every process and sample is attainable. To this end, we demonstrate the use of molecular modeling techniques to complement experimental efforts and extraterrestrial missions. The simulations enable researchers to test hypotheses and explore scenarios that are difficult or impossible to replicate in the laboratory, bridging gaps in our understanding of prebiotic processes across vast time and space scales.Minerals, particularly layered structures like clays and hydrotalcites, play diverse and pivotal roles in the origin of life. They concentrate organic species, catalyze polymerization reactions (such as peptide formation), and provide protective environments for the molecules. Minerals have also been suggested to have acted as primitive genetic materials. Nevertheless, they may lack the ability for long-term information replication. Instead, we suggest that minerals may act as transcribers of information encoded in environmental cyclic phenomena, such as tidal or seasonal changes. We argue that extensive protection of the produced polymer will immobilize it, making it inactive for any further function. Therefore, in order to generate a functional polymer, it is essential that it remains mobile and chemically active. Furthermore, we suggest a route to the identification of pseudobiosignatures, a polymer that was polymerized on the same mineral surface and consequently retained through overprotection.This Account presents a comprehensive evaluation of the current understanding of the role of layered mineral surfaces on life's origin and biosignature preservation. It highlights the complexity of mineral-organic interactions and proposes pathways for proto-biomolecule emergence and methods for identifying and interpreting potential biosignatures. Ultimately, the quest to uncover the origin of life continues to drive scientific exploration and innovation, offering profound insights into the fundamental nature of existence and our place in the universe.

Positive-Unlabelled learning for identifying new candidate Dietary Restriction-related genes among ageing-related genes

Dietary Restriction (DR) is one of the most popular anti-ageing interventions; recently, Machine Learning (ML) has been explored to identify potential DR-related genes among ageing-related genes, aiming to minimize costly wet lab experiments needed to expand our knowledge on DR. However, to train a model from positive (DR-related) and negative (non-DR-related) examples, the existing ML approach naively labels genes without known DR relation as negative examples, assuming that lack of DR-related annotation for a gene represents evidence of absence of DR-relatedness, rather than absence of evidence. This hinders the reliability of the negative examples (non-DR-related genes) and the method’s ability to identify novel DR-related genes. This work introduces a novel gene prioritization method based on the two-step Positive-Unlabelled (PU) Learning paradigm: using a similarity-based, KNN-inspired approach, our method first selects reliable negative examples among the genes without known DR associations. Then, these reliable negatives and all known positives are used to train a classifier that effectively differentiates DR-related and non-DR-related genes, which is finally employed to generate a more reliable ranking of promising genes for novel DR-relatedness. Our method significantly outperforms (p<0.05) the existing state-of-the-art approach in three predictive accuracy metrics with up to ∼40% lower computational cost in the best case, and we identify 4 new promising DR-related genes (PRKAB1, PRKAB2, IRS2, PRKAG1), all with evidence from the existing literature supporting their potential DR-related role.

Discovery of potential antidiabetic peptides using deep learning

Antidiabetic peptides (ADPs), peptides with potential antidiabetic activity, hold significant importance in the treatment and control of diabetes. Despite their therapeutic potential, the discovery and prediction of ADPs remain challenging due to limited data, the complex nature of peptide functions, and the expensive and time-consuming nature of traditional wet lab experiments. This study aims to address these challenges by exploring methods for the discovery and prediction of ADPs using advanced deep learning techniques. Specifically, we developed two models: a single-channel CNN and a three-channel neural network (CNN + RNN + Bi-LSTM). ADPs were primarily gathered from the BioDADPep database, alongside thousands of non-ADPs sourced from anticancer, antibacterial, and antiviral peptide datasets. Subsequently, data preprocessing was performed with the evolutionary scale model (ESM-2), followed by model training and evaluation through 10-fold cross-validation. Furthermore, this work collected a series of newly published ADPs as an independent test set through literature review, and found that the CNN model achieved the highest accuracy (90.48 %) in predicting the independent test set, surpassing existing ADP prediction tools. Finally, the application of the model was considered. SeqGAN was used to generate new candidate ADPs, followed by screening with the constructed CNN model. Selected peptides were then evaluated using physicochemical property prediction and structural forecasts for pharmaceutical potential. In summary, this study not only established robust ADP prediction models but also employed these models to screen a batch of potential ADPs, addressing a critical need in the field of peptide-based antidiabetic research.

A Systematic Study on Mirror Repeats in CTLA4 and KCNJ11 Genes of Diabetes

All cellular functions are controlled by the regulatory material which is constituted majorly by variety type of repeat elements. Among that types a unique pattern of bases form a Mirror repeat (MR) which thought to plays variety of roles at the genomic level that include regulation of gene expression, genomic integrity, triplex structure formation etc. The present research focused on identification of Mirror repeats in different genes types involved in both diabetes types. Two different genes CTLA4 (T1D) &amp; KCNJ11 (T2D) were targeted to identify these sequence type. A manual method refers as FPCB is utilized to extract out MR sequences. The targeted gene sequences were divided into short regions so that it can be handled out easily while bioinformatics based analysis. Among the both types it was reported that both genes have different pattern of distribution of MR sequences. CTLA4 have 346 MR sequences in total in which MR235 have highest length of 50bps. In case of KCNJ11 a total no of 235 MR sequences were reported in which MR105 having highest length of 58bps. The present study will be helpful to elucidate the roles of MR sequences in diseases development &amp; progression. It will be helpful for sequence based protein finding studies using bioinformatics tools as well as wet lab experiments.

Multiscale Computational Study of Cellulose Acetate-Water Miscibility: Insights from Molecularly Informed Field-Theoretic Modeling.

Cellulose acetate (CA), a prominent water-soluble derivative of cellulose, is a promising biodegradable ingredient that has applications in films, membranes, fibers, drug delivery, and more. In this work, we present a molecularly informed field-theoretic model for CA to explore its phase behavior in aqueous solutions. By integrating atomistic details into large-scale field-theoretic simulations via the relative entropy coarse-graining framework, our approach enables efficient calculations of CA's miscibility window as a function of the degree of substitution (DS) of cellulose hydroxyl groups with acetate side chains. This allows us to capture the intricate phase behavior of CA, particularly its unique miscibility at intermediate substitution, without relying on experimental input. Additionally, the model directly probes CA solution behavior specific to the relative DS at C2, C3, and C6 alcohol sites, providing insights for the rational design of water-soluble CA for diverse applications. This work demonstrates a promising integration of molecularly informed field theories, complementing wet-lab experimentation, for engineering the next-generation polymeric materials with precisely tailored properties.

Discerning computational, in vitro and in vivo investigations of self-assembling empagliflozin polymeric micelles in type-2 diabetes.

Empagliflozin (EMPA) is an SGLT2 inhibitor, a new class of anti-diabetic medication, indicated for treating type-2 diabetes. Its low permeability, poor solubility and bioavailability limits its use in management of diabetes. The study was aimed to formulate EMPA loaded polymeric micelles (PMs) to overcome these obstacles in oral absorption. In silico studies-molecular docking, molecular dynamic simulation (MDS), and quantum chemical calculation were employed to study the interaction of EMPA with different polymers. EMPA loaded TPGS polymeric micelles (EMPA-TPGS-PMs) were formulated by direct dissolution method and characterized in terms of surface morphology, entrapment, particle size, in vitro drug release, and in vitro cytotoxicity (HEK293 cells). In vivo pharmacokinetic and pharmacodynamic studies were also performed. The results suggested a good interaction between TPGS and EMPA with lowest binding energy compared to other polymers. Further MDS results and DFT calculations validated the stable binding of the complex hence TPGS was selected for further wet lab experiments. The EMPA-TPGS complex displayed lower value of Total energy (T.E.) than its individual components, indicating the overall stability of the complex while, the energy band gap (∆E) value lied between the two individual molecules, signifying the better electron transfer between HOMO and LUMO of the complex. Based on the solubility, entrapment and cytotoxicity studies, 5% TPGS was selected for formulating drug loaded micelles. EMPA-TPGS5-PMs presented a size of 9.008 ± 1.25nm, Polydispersity index (PDI) of 0.254 ± 0.100, a controlled release behaviour upto 24h. SEM and AFM images of the nanoformulation suggested spherical particles whereas, DSC, and PXRD studies confirmed the loss of crystallinity of EMPA. A 3.12-folds higher AUC and a greater reduction in blood glucose levels was exhibited by EMPA-TPGS5-PMs in comparison to EMPA-SUSP in mice model. EMPA-TPGS-PMs has exhibited better bio absorption and therapeutic effectiveness in diabetes treatment. This improved performance would open the possibility of dose reduction, reduced dosing frequency & dose-related side effects, improving pharmaco-economics and thereby improved overall compliance to the patient. However, this translation from bench to bedside would necessitate studies in higher animals and human volunteers.

Hybrid Predictive Machine Learning Model for the Prediction of Immunodominant Peptides of Respiratory Syncytial Virus.

Respiratory syncytial virus (RSV) is a common respiratory pathogen that infects the human lungs and respiratory tract, often causing symptoms similar to the common cold. Vaccination is the most effective strategy for managing viral outbreaks. Currently, extensive efforts are focused on developing a vaccine for RSV. Traditional vaccine design typically involves using an attenuated form of the pathogen to elicit an immune response. In contrast, peptide-based vaccines (PBVs) aim to identify and chemically synthesize specific immunodominant peptides (IPs), known as T-cell epitopes (TCEs), to induce a targeted immune response. Despite their potential for enhancing vaccine safety and immunogenicity, PBVs have received comparatively less attention. Identifying IPs for PBV design through conventional wet-lab experiments is challenging, costly, and time-consuming. Machine learning (ML) techniques offer a promising alternative, accurately predicting TCEs and significantly reducing the time and cost of vaccine development. This study proposes the development and evaluation of eight hybrid ML predictive models created through the permutations and combinations of two classification methods, two feature weighting techniques, and two feature selection algorithms, all aimed at predicting the TCEs of RSV. The models were trained using the experimentally determined TCEs and non-TCE sequences acquired from the Bacterial and Viral Bioinformatics Resource Center (BV-BRC) repository. The hybrid model composed of the XGBoost (XGB) classifier, chi-squared (ChST) weighting technique, and backward search (BST) as the optimal feature selection algorithm (ChST-BST-XGB) was identified as the best model, achieving an accuracy, sensitivity, specificity, F1 score, AUC, precision, and MCC of 97.10%, 0.98, 0.97, 0.98, 0.99, 0.99, and 0.96, respectively. Additionally, K-fold cross-validation (KFCV) was performed to ensure the model's reliability and an average accuracy of 97.21% was recorded for the ChST-BST-XGB model. The results indicate that the hybrid XGBoost model consistently outperforms other hybrid approaches. The epitopes predicted by the proposed model may serve as promising vaccine candidates for RSV, subject to in vitro and in vivo scientific assessments. This model can assist the scientific community in expediting the screening of active TCE candidates for RSV, ultimately saving time and resources in vaccine development.

Protein multi-level structure feature-integrated deep learning method for mutational effect prediction.

Through iterative rounds of mutation and selection, proteins can be engineered to enhance their desired biological functions. Nevertheless, identifying optimal mutation sites for directed evolution remains challenging due to the vastness of the protein sequence landscape and the epistatic mutational effects across residues. To address this challenge, we introduce MLSmut, a deep learning-based approach that leverages multi-level structural features of proteins. MLSmut extracts salient information from protein co-evolution, sequence semantics, and geometric features to predict the mutational effect. Extensive benchmark evaluations on 10 single-site and two multi-site deep mutation scanning datasets demonstrate that MLSmut surpasses existing methods in predicting mutational outcomes. To overcome the limited training data availability, we employ a two-stage training strategy: initial coarse-tuning on a large corpus of unlabeled protein data followed by fine-tuning on a curated dataset of 40-100 experimental measurements. This approach enables our model to achieve satisfactory performance on downstream protein prediction tasks. Importantly, our model holds the potential to predict the mutational effects of any protein sequence. Collectively, these findings suggest that our approach can substantially reduce the reliance on laborious wet lab experiments and deepen our understanding of the intricate relationships between mutations and protein function.

Multioviz: an interactive platform for in silico perturbation and interrogation of gene regulatory networks

In this paper, we aim to build a platform that will help bridge the gap between high-dimensional computation and wet-lab experimentation by allowing users to interrogate genomic signatures at multiple molecular levels and identify best next actionable steps for downstream decision making. We introduce Multioviz: a publicly accessible R package and web application platform to easily perform in silico hypothesis testing of generated gene regulatory networks. We demonstrate the utility of Multioviz by conducting an end-to-end analysis in a statistical genetics application focused on measuring the effect of in silico perturbations of complex trait architecture. By using a real dataset from the Wellcome Trust Centre for Human Genetics, we both recapitulate previous findings and propose hypotheses about the genes involved in the percentage of immune CD8+ cells found in heterogeneous stocks of mice. Source code for the MultiovizR package is available at https://github.com/lcrawlab/multio-viz and an interactive version of the platform is available at https://multioviz.ccv.brown.edu/.