Molecular Fingerprints Research Articles

Data and Molecular Fingerprint-Driven Machine Learning Approaches to Halogen Bonding.

The ability to predict the strength of halogen bonds and properties of halogen bond (XB) donors has significant utility for medicinal chemistry and materials science. XBs are typically calculated through expensive ab initio methods. Thus, the development of tools and techniques for fast, accurate, and efficient property predictions has become increasingly more important. Herein, we employ three machine learning models to classify the XB donors and complexes by their principal halogen atom as well as predict the values of the maximum point on the electrostatic potential surface (VS,max) and interaction strength of the XB complexes through a molecular fingerprint and data-based analysis. The fingerprint analysis produces a root-mean-square error of ca. 7.5 and ca. 5.5 kcal mol-1 while predicting the VS,max for the halobenzene and haloethynylbenzene systems, respectively. However, the prediction of the binding energy between the XB donors and ammonia acceptor is shown to be within 1 kcal mol-1 of the density functional theory (DFT)-calculated energy. More accurate predictions can be made from the precalculated DFT data when compared to the fingerprint analysis.

High-sensitivity multi-gas detection using dual-ridge metasurface emitters with polarization-distinguishable emission spectra

The metasurface thermal emitter offers an energy-efficient, compact, and sensitive solution as a radiation source for non-contact gas detection, enabling the “molecular fingerprint” technique to be widely applied, from medical diagnostics to environmental monitoring. However, most narrowband emitters are designed for a single target gas, hindering the miniaturization of multi-gas detection systems. In this work, a one-dimensional dual-ridge grating emitter is employed, achieving dual-band and tri-band polarization-distinguishable emission spectra through the excitation of Fabry-Perot (FP) resonances and quasi-bound states in the continuum (qBICs). These emission spectra can be readily matched to multiple non-overlapping absorption peaks of gases such as CH4, CO2, CO, NO, and NH3 within the 3–6 µm range, thereby reducing the impact of mixed gases on measurements. Compared to conventional metal-dielectric-metal structures, the use of a single metal layer results in lower material losses, enabling higher Q-factors and more pronounced directional radiation intensity variations. Furthermore, adjusting the asymmetry to modulate the qBIC-excited absorption peaks does not affect the Q-factor of the FP resonance absorption, thus achieving high-sensitivity multi-band gas detection. This work provides a promising approach for the miniaturization and integration of multi-gas channel detection, facilitating more accurate and sensitive sensing strategies.

MetaboScope: A statistical toolbox for analyzing 1H nuclear magnetic resonance spectra from human clinical studies

Abstract Motivation Metabolic phenotyping, using high-resolution spectroscopic molecular fingerprints of biological samples, has demonstrated diagnostic, prognostic, and mechanistic value in clinical studies. However, clinical translation is hindered by the lack of viable workflows and challenges in converting spectral data into usable information. Results MetaboScope is an analytical and statistical workflow for learning, designing and analyzing clinically relevant 1H nuclear magnetic resonance data. It features modular pre-processing pipelines, multivariate modeling tools including principal components analysis (PCA), orthogonal-projection to latent structure discriminant analysis, and biomarker discovery tools (multiblock PCA and statistical spectroscopy). A simulation tool is also provided, allowing users to create synthetic spectra for hypothesis testing and power calculations. Availability and implementation MetaboScope is built as a pipeline where each module accepts the output generated by the previous one. This provides flexibility and simplicity of use, while being straightforward to maintain. The system and its libraries were developed in JavaScript and run as a web app; therefore, all the operations are performed on the local computer, circumventing the need to upload data. The MetaboScope tool is available at https://www.cheminfo.org/flavor/metabolomics/index.html. The code is open-source and can be deployed locally if necessary. Module notes, video tutorials, and clinical spectral datasets are provided for modeling. Supplementary information Supplementary data are available at Bioinformatics Advances online.

Hybrid Raman and Partial Wave Spectroscopy Microscope for the Characterization of Molecular and Structural Alterations in Tissue.

We present a hybrid Raman spectroscopy (RS) and partial wave spectroscopy (PWS) microscope for the characterization of molecular and structural tissue alterations. The PWS performance was assessed with surface roughness standards, while the Raman performance with a silicon crystal standard. We also validated the system on stomach and intestinal mouse tissues, two closely-related tissue types, and demonstrate that the addition of PWS information improves RS data classification for these tissue types from R2 = 0.892 to R2 = 0.964 (norm of residuals 0.863 and 0.497, respectively). Then, in a proof-of-concept experiment, we show that the hybrid system can detect changes in intestinal tissues harvested from a tumorigenic Villin-Cre, Apcfl/wt mouse. We discuss how the hybrid modality offers new abilities to identify the relative roles of PWS morphological features and Raman molecular fingerprints, possibly allowing for their combination to enhance the study of carcinogenesis and early cancer diagnostics in the future.

SERS Performance Factor: A Convenient Parameter for the Enhancement Evaluation of SERS Substrates.

Surface-enhanced Raman spectroscopy (SERS), with molecular fingerprint information and single-molecule sensitivity, has been widely used for qualitative and quantitative analysis in various fields. Plenty of nanostructured plasmonic materials have been fabricated to achieve high SERS activity. Currently, great difficulty lies in evaluating the SERS performance among substrates, making it difficult to standardize. Addressing this problem, this work proposed the SERS performance factor () as a practically operational parameter to evaluate the sensitivity of SERS substrates. Experimentally, SPF can be obtained by taking the ratio of the slopes (i.e., the sensitivity) for concentration-dependent SERS and normal Raman measurements in the linear range of the intensity response under identical experimental conditions. Theoretically, SPF quantitatively describes the overall contribution to the SERS performance, (i.e., the electromagnetic (EM) enhancement of the SERS substrate and the interfacial interaction between the probe and substrate). The use of SPF as the criterion for evaluating the SERS performance was validated on Au nanoparticles in colloidal and solid states, where the tendency of SPF is consistent with that of the sensitivity of the probe molecules. Derived from the typically used surface enhancement factor EF in which accurate parameters are hardly achievable and different from concentration-dependent analytical enhancement factor AEF, SPF distinguishes itself with a simpler calculation and thereby offers a convenient and reliable protocol for the evaluation of the performance of different SERS substrates, which is very important to the practical application of SERS.

ML-Based Models as a Strategy to Discover Novel Antiepileptic Drugs Targeting Sodium Receptor Channel.

Epilepsy remains the most common and chronic disorder demanding longterm management. The impact of epilepsy disease is a cause of great concern and has resulted in efforts to develop treatment for epilepsy. It occurs due to an increase in neuronal excitability produced by changes affecting the voltage-dependent properties of Voltage-gated Sodium Channels (VGSCs). Weka, a popular suite for machine learning techniques, was used on a dataset comprising 1781 chemical compounds, showing inhibition activity for sodium channel protein IX alpha subunit. After the analysis of the dataset obtained from ChEMBL, molecular fingerprints were computed for the molecules by the ChemDes server. Different classifiers available in the Weka software were explored to find out the algorithm that could be more suitable for the dataset or produce the highest accuracy for the classification of molecules as active or inactive. In this work, a comprehensive comparison of different classifiers in the Weka suite for the prediction of active, inactive, and intermediate classes of molecules showing inhibition against human NaV1.7 protein was made. The prediction accuracy of these classifiers was assessed based on performance measures, including accuracy, Root Mean Squared Error (RMSE), Receiver Operating Characteristic (ROC), precision, Mathews Correlation Coefficient (MCC), recall, and Fmeasure. The comparison of results for model performance demonstrated that the OneR classifier performed best over others when validated using percentage split, cross-validation, and supplied test methods. J48 and Bagging also performed equally well in the prediction of different classes with an MCC value of 1, ROC area equal to 1, and RMSE close to 0. Machine Learning (ML) tools provide a fast, reliable, and cost-effective approach required to identify or predict inhibitory molecules for the treatment of a disease. This study shows that the ML methods, particularly OneR, J48, and Bagging have the ability to identify active and inactive classes of compounds for the human NaV1.7 protein target. Such predictive models may provide a reliable and time-saving approach that can aid in the design of potential inhibitors for the treatment of epilepsy disease.

AI-DPAPT: a machine learning framework for predicting PROTAC activity.

Proteolysis Targeting Chimeras are part of targeted protein degradation (TPD) techniques, which are significant for pharmacological and therapy development. Small-molecule interaction with the targeted protein is a complicated endeavor and a challenge to predict the proteins accurately. This study used machine learning algorithms and molecular fingerprinting techniques to build an AI-powered PROTAC Activity Prediction Tool that could predict PROTAC activity by examining chemical structures. The chemical structures of a diverse set of PROTAC drugs and their corresponding activities are selected as a dataset for training the tool. The processes used in this study included data preparation, feature extraction, and model training. Further, evaluation was done for the performance of the various classifiers, such as AdaBoost, Support Vector Machine, Random Forest, Gradient Boosting, and Multi-Layer Perceptron. The findings show that the methods selected here depict accurate PROTAC activities. All the models in this study showed an ROC curve better than 0.9, while the random forest on the test set of the AI-DPAPT had an area under the curve score of 0.97, thus showing accurate results. Furthermore, the study revealed significant insights into the molecular features that can influence the functions of the PROTAC. These findings can potentially increase the understanding of the structure-activity correlations involved in the TPD. Overall, the investigation contributes to computational drug development by introducing this platform powered by artificial intelligence that predicts the function of PROTAC. In addition, it sped up the processes of identifying and improving previously unknown medications. The AI-DPAPT platform can be accessed online using a web server at https://ai-protac.streamlit.app/ .

On-chip phonon-enhanced IR near-field detection of molecular vibrations

Phonon polaritons – quasiparticles formed by strong coupling of infrared (IR) light with lattice vibrations in polar materials – can be utilized for surface-enhanced infrared absorption (SEIRA) spectroscopy and even for vibrational strong coupling with nanoscale amounts of molecules. Here, we introduce and demonstrate a compact on-chip phononic SEIRA spectroscopy platform, which is based on an h-BN/graphene/h-BN heterostructure on top of a metal split-gate creating a p-n junction in graphene. The metal split-gate concentrates the incident light and launches hyperbolic phonon polaritons (HPhPs) in the heterostructure, which serves simultaneously as SEIRA substrate and room-temperature infrared detector. When thin organic layers are deposited directly on top of the heterostructure, we observe a photocurrent encoding the layer’s molecular vibrational fingerprint, which is strongly enhanced compared to that observed in standard far-field absorption spectroscopy. A detailed theoretical analysis supports our results, further predicting an additional sensitivity enhancement as the molecular layers approach deep subwavelength scales. Future on-chip integration of infrared light sources such as quantum cascade lasers or even electrical generation of the HPhPs could lead to fully on-chip phononic SEIRA sensors for molecular and gas sensing.

CODI: Enhancing machine learning-based molecular profiling through contextual out-of-distribution integration

Abstract Molecular analytics increasingly utilize machine learning (ML) for predictive modeling based on data acquired through molecular profiling technologies. However, developing robust models that accurately capture physiological phenotypes is challenged by the dynamics inherent to biological systems, variability stemming from analytical procedures, and the resource-intensive nature of obtaining sufficiently representative datasets. Here, we propose and evaluate a new method: Contextual Out-of-Distribution Integration (CODI). Based on experimental observations, CODI generates synthetic data that integrate unrepresented sources of variation encountered in real-world applications into a given molecular fingerprint dataset. By augmenting a dataset with out-of-distribution variance, CODI enables an ML model to better generalize to samples beyond the seed training data, reducing the need for extensive experimental data collection. Using three independent longitudinal clinical studies and a case-control study, we demonstrate CODI's application to several classification tasks involving vibrational spectroscopy of human blood. We showcase our approach's ability to enable personalized fingerprinting for multi-year longitudinal molecular monitoring and enhance the robustness of trained ML models for improved disease detection. Our comparative analyses reveal that incorporating CODI into the classification workflow consistently leads to increased robustness against data variability and improved predictive accuracy.

Machine learning assisted prediction of absorption maxima in cyclohexene: A comparison using molecular descriptors and fingerprints

Light absorption plays important role in different photovoltaics devices. Easy and fast prediction of absorption properties is essential for fast screening of efficient materials. In our pursuit of identifying the optimal model for predicting absorption maxima, we systematically evaluated over 40 machine learning models, employing both molecular descriptors and fingerprints as input features. Notably, models trained on molecular descriptors demonstrated superior predictive capabilities as compared to those relying on molecular fingerprints. This not only showcased the efficacy of molecular descriptors but also highlighted the potential of these models as rapid and efficient alternatives to the density functional theory (DFT) based approaches. The use of machine learning models based on molecular descriptors introduced a level of simplicity and speed in predictions, surpassing the computational demands associated with traditional DFT-based methods. Our introduced framework that is based on machine learning, offers a valuable tool for the easy and fast prediction of properties.

Fabrication of Surface-Enhanced Raman Scattering (SERS) Substrates in Analytical Science by Natural-inspired Materials: A Review

Surface-Enhanced Raman Scattering (SERS) spectroscopy, as a novel rapid detection technology, offers molecular fingerprinting capabilities that achieve trace-level detection. The key to optimizing SERS sensitivity and reliability lies in the precise control of the nanostructures of SERS substrates. Nature, through billions of years of evolution, has served as a masterful creator, developing organisms with remarkable abilities based on micro/nanostructures, such as the superhydrophobicity of lotus leaves and the strong adhesive forces of gecko feet. This review categorizes the recent developments in SERS substrates inspired by natural materials into three main types: plant-based, animal-based, and virus-based. Each category is explored in detail, describing how their unique nanoarchitectures inspire the development of highly sensitive SERS substrates, along with their fabrication methods and applications in analytical science. Additionally, the review identifies current challenges, such as the uniformity and scalability of naturally inspired SERS substrates and suggests future directions, including the integration of hybrid biomimetic structures and advanced manufacturing techniques. By fostering a deeper understanding of these nature-inspired materials, we aim to enhance the practical application of SERS in analytical science in the future.

Steering research on mRNA splicing in cancer towards clinical translation.

Splicing factors are affected by recurrent somatic mutations and copy number variations in several types of haematologic and solid malignancies, which is often seen as prima facie evidence that splicing aberrations can drive cancer initiation and progression. However, numerous spliceosome components also 'moonlight' in DNA repair and other cellular processes, making their precise role in cancer difficult to pinpoint. Still, few would deny that dysregulated mRNA splicing is a pervasive feature of most cancers. Correctly interpreting these molecular fingerprints can reveal novel tumour vulnerabilities and untapped therapeutic opportunities. Yet multiple technological challenges, lingering misconceptions, and outstanding questions hinder clinical translation. To start with, the general landscape of splicing aberrations in cancer is not well defined, due to limitations of short-read RNA sequencing not adept at resolving complete mRNA isoforms, as well as the shallow read depth inherent in long-read RNA-sequencing, especially at single-cell level. Although individual cancer-associated isoforms are known to contribute to cancer progression, widespread splicing alterations could be an equally important and, perhaps, more readily actionable feature of human cancers. This is to say that in addition to 'repairing' mis-spliced transcripts, possible therapeutic avenues include exacerbating splicing aberration with small-molecule spliceosome inhibitors, targeting recurrent splicing aberrations withsynthetic lethal approaches, and training the immune system to recognize splicing-derived neoantigens.

Artifacts and Anomalies in Raman Spectroscopy: A Review on Origins and Correction Procedures

Raman spectroscopy, renowned for its unique ability to provide a molecular fingerprint, is an invaluable tool in industry and academic research. However, various constraints often hinder the measurement process, leading to artifacts and anomalies that can significantly affect spectral measurements. This review begins by thoroughly discussing the origins and impacts of these artifacts and anomalies stemming from instrumental, sampling, and sample-related factors. Following this, we present a comprehensive list and categorization of the existing correction procedures, including computational, experimental, and deep learning (DL) approaches. The review concludes by identifying the limitations of current procedures and discussing recent advancements and breakthroughs. This discussion highlights the potential of these advancements and provides a clear direction for future research to enhance correction procedures in Raman spectral analysis.

Morphological traits and molecular fingerprinting for assessing biodiversity in native Iranian Rosa persica Michx. ex Juss

Morphological traits and molecular fingerprinting for assessing biodiversity in native Iranian Rosa persica Michx. ex Juss

Repairing Noise-Contaminated Low-Frequency Vibrational Spectra with an Attention U-Net.

Low-frequency vibrational modes in infrared (IR) and Raman spectra, often termed molecular fingerprints, are sensitive probes of subtle structural changes and chemical interactions. However, their inherent weakness and susceptibility to environmental interference make them challenging to detect and analyze. To tackle this issue, we developed a deep learning denoising protocol based on an attention-enhanced U-net architecture. This model leverages the inherent correlations between high- and low-frequency vibrational modes within a molecule, effectively reconstructing low-frequency spectral features from their high-frequency counterparts. We demonstrate the effectiveness of this method by recovering low-frequency signals of trans-1,2-bis(4-pyridyl)ethylene (BPE) adsorbed on an Ag surface, a representative system for surface enhancement Raman spectroscopy (SERS). Notably, the trained model exhibits promising transferability to SERS spectra acquired under different surface and external field conditions. Furthermore, we applied this method to experimental IR and Raman spectra of BPE, achieving high-quality, low-frequency spectral recovery.

Inhalable Advanced Co-Spray Dried Microparticles/Nanoparticles of a Novel RhoA/Rho Kinase Inhibitor with Lung Surfactant Biomimetic Phospholipids for Targeted Lung Delivery.

Co-spray dried inhalable powder formulations of fasudil monohydrochloride salt (FMCS) and inhalable lung surfactant-based nanocarriers composed of synthetic phospholipids, zwitterionic DPPC (1,2-palmitoyl-sn-glycero-3-phosphocholine) and anionic DPPG (1,2-dipalmitoyl-sn-glycero-3-[phosphor-rac-1-glycerol]) sodium salt, were designed and optimized using organic solution advanced spray drying. FMCS can potentially be used for the treatment of various complex pulmonary diseases with this current work focusing on pulmonary arterial hypertension. Comprehensive physicochemical characterization, electron and optical microscopy imaging, thermal analysis, molecular fingerprinting spectroscopy, in vitro aerosol dispersion performance with human dry powder inhaler (DPI) devices, in vitro membrane permeation and drug release, and in vitro human cellular studies were conducted. Well-defined, small, and smooth nanoparticles/microparticles in the solid state were engineered at different molar ratios of FMCS/DPPC/DPPG (25:75, 50:50, and 75:25) and successfully produced as inhalable powders having the properties necessary for targeted pulmonary delivery as dry powder inhalers. In vitro aerosol performance demonstrated excellent aerosol dispersion with different DPI devices. The phospholipid bilayer biophysical properties were confirmed and retained following cospray drying. Sustained release of fasudil drug and in vitro biocompatibility were demonstrated on human lung cells from different airway regions.

A multi-view feature representation for predicting drugs combination synergy based on ensemble and multi-task attention models

This paper proposes a novel multi-view ensemble predictor model that is designed to address the challenge of determining synergistic drug combinations by predicting both the synergy score value values and synergy class label of drug combinations with cancer cell lines. The proposed methodology involves representing drug features through four distinct views: Simplified Molecular-Input Line-Entry System (SMILES) features, molecular graph features, fingerprint features, and drug-target features. On the other hand, cell line features are captured through four views: gene expression features, copy number features, mutation features, and proteomics features. To prevent overfitting of the model, two techniques are employed. First, each view feature of a drug is paired with each corresponding cell line view and input into a multi-task attention deep learning model. This multi-task model is trained to simultaneously predict both the synergy score value and synergy class label. This process results in sixteen input view features being fed into the multi-task model, producing sixteen prediction values. Subsequently, these prediction values are utilized as inputs for an ensemble model, which outputs the final prediction value. The ‘MVME’ model is assessed using the O’Neil dataset, which includes 38 distinct drugs combined across 39 distinct cancer cell lines to output 22,737 drug combination pairs. For the synergy score value, the proposed model scores a mean square error (MSE) of 206.57, a root mean square error (RMSE) of 14.30, and a Pearson score of 0.76. For the synergy class label, the model scores 0.90 for accuracy, 0.96 for precision, 0.57 for kappa, 0.96 for the area under the ROC curve (ROC-AUC), and 0.88 for the area under the precision-recall curve (PR-AUC).

In Vivo Raman Spectroscopy of Muscle Is Highly Sensitive for Detection of Healthy Muscle and Highly Specific for Detection of Disease.

Raman spectroscopy of muscle provides a molecular fingerprint to identify the disease. Previous work has demonstrated effectiveness in differentiating between two groups of equal sizes (e.g., healthy vs disease) but imbalanced multiclass scenarios are more common in medicine. We performed in vivo Raman spectroscopy in a total of 151 mice across four different histopathologies (healthy, acute myopathy, chronic myopathy, neurogenic), with variable numbers in each (class "imbalance"). Using hierarchical modeling and synthetic data generation, we demonstrate high sensitivity (94%) for detection of healthy muscle and high specificity (≥97%) for disease. Further, we demonstrate the potential for unique biomarker development by demonstrating variations in the protein structure across different pathologies. The findings demonstrate the potential of Raman spectroscopy to provide accurate disease identification and unique molecular insights.

2D Material-Based Surface-Enhanced Raman Spectroscopy Platforms (Either Alone or in Nanocomposite Form)-From a Chemical Enhancement Perspective.

Surface-enhanced Raman spectroscopy (SERS) is a vibrational spectroscopic technique with molecular fingerprinting capability and high sensitivity, even down to the single-molecule level. As it is 50 years since the observation of the phenomenon, it has now become an important task to discuss the challenges in this field and determine the areas of development. Electromagnetic enhancement has a mature theoretical explanation, while a chemical mechanism which involves more complex interactions has been difficult to elucidate until recently. This article focuses on the 2D material-based platforms where chemical enhancement (CE) is a significant contributor to SERS. In the context of a diverse range (transition metal dichalcogenides, MXenes, etc.) and categories (insulating, semiconducting, semimetallic, and metallic) of 2D materials, the review aims to realize the influence of various factors on SERS response such as substrates (layer thickness, structural phase, etc.), analytes (energy levels, molecular orientation, etc.), excitation wavelengths, molecular resonances, charge-transfer transitions, dipole interactions, etc. Some examples of special treatments or approaches have been outlined for overcoming well-known limitations of SERS and include how CE benefits from the defect-induced physicochemical changes to 2D materials mostly via the charge-transport ability or surface interaction efficiency. The review may help readers understand different phenomena involved in CE and broaden the substrate-designing approaches based on a diverse set of 2D materials.

Right Ventricular Hypertrophy in Spontaneously Hypertensive Rats (SHR/NHsd) Is Associated with Inter-Individual Variations of the Pulmonary Endothelin System.

Spontaneously hypertensive rats (SHRs) develop severe hypertension and subsequently left ventricular hypertrophy. Whether they also develop right ventricular hypertrophy is not clear. We analyzed 76 female SHRs (strain SHR/NHsd) and observed severe right ventricular hypertrophy in 7% of these rats (SHR-RVH). Right ventricular hypertrophy did not correlate with the age of the rats and was already seen in one rat at the pre-hypertensive state. The current study investigated the molecular fingerprint of the lung and right ventricle from SHR-RVH and compared this first to SHRs that did develop left but not right ventricular hypertrophy, and second to normotensive rats without hypertrophy. Rats with right ventricular hypertrophy had a decreased expression of the endothelin-B receptor (EDNRB) in the lung, together with an increased protein content of endothelin-1 and an increased expression of ACTA2A. Furthermore, in the right ventricle, a down-regulation of the endothelin-A receptor (EDNRA) was found, consistent with a mild phenotype. The data suggest that in a sub-group of SHR/NHsd rats, low expression of the endothelin clearance receptor (endothelin-B receptor) in the lung triggers an increase in vascular resistance to the right ventricle that then triggers hypertrophy. Our study is the first description of a genetic variant in a defined SHR strain.