Comput Methods Programs Biomed. 2024 Mar 10;248:108121. doi: 10.1016/j.cmpb.2024.108121. Online ahead of print.

ABSTRACT

BACKGROUND AND OBJECTIVE: Deep Learning models have emerged as a significant tool in generating efficient solutions for complex problems including cancer detection, as they can analyze large amounts of data with high efficiency and performance. Recent medical studies highlight the significance of molecular subtype detection in breast cancer, aiding the development of personalized treatment plans as different subtypes of cancer respond better to different therapies.

METHODS: In this work, we propose a novel lightweight dual-channel attention-based deep learning model MOB-CBAM that utilizes the backbone of MobileNet-V3 architecture with a Convolutional Block Attention Module to make highly accurate and precise predictions about breast cancer. We used the CMMD mammogram dataset to evaluate the proposed model in our study. Nine distinct data subsets were created from the original dataset to perform coarse and fine-grained predictions, enabling it to identify masses, calcifications, benign, malignant tumors and molecular subtypes of cancer, including Luminal A, Luminal B, HER-2 Positive, and Triple Negative. The pipeline incorporates several image pre-processing techniques, including filtering, enhancement, and normalization, for enhancing the model's generalization ability.

RESULTS: While identifying benign versus malignant tumors, i.e., coarse-grained classification, the MOB-CBAM model produced exceptional results with 99 % accuracy, precision, recall, and F1-score values of 0.99 and MCC of 0.98. In terms of fine-grained classification, the MOB-CBAM model has proven to be highly efficient in accurately identifying mass with (benign/malignant) and calcification with (benign/malignant) classification tasks with an impressive accuracy rate of 98 %. We have also cross-validated the efficiency of the proposed MOB-CBAM deep learning architecture on two datasets: MIAS and CBIS-DDSM. On the MIAS dataset, an accuracy of 97 % was reported for the task of classifying benign, malignant, and normal images, while on the CBIS-DDSM dataset, an accuracy of 98 % was achieved for the classification of mass with either benign or malignant, and calcification with benign and malignant tumors.

CONCLUSION: This study presents lightweight MOB-CBAM, a novel deep learning framework, to address breast cancer diagnosis and subtype prediction. The model's innovative incorporation of the CBAM enhances precise predictions. The extensive evaluation of the CMMD dataset and cross-validation on other datasets affirm the model's efficacy.

PMID:38531147 | DOI:10.1016/j.cmpb.2024.108121

J Comput Biol. 2024 Mar;31(3):213-228. doi: 10.1089/cmb.2023.0187.

ABSTRACT

Molecular prediction tasks normally demand a series of professional experiments to label the target molecule, which suffers from the limited labeled data problem. One of the semisupervised learning paradigms, known as self-training, utilizes both labeled and unlabeled data. Specifically, a teacher model is trained using labeled data and produces pseudo labels for unlabeled data. These labeled and pseudo-labeled data are then jointly used to train a student model. However, the pseudo labels generated from the teacher model are generally not sufficiently accurate. Thus, we propose a robust self-training strategy by exploring robust loss function to handle such noisy labels in two paradigms, that is, generic and adaptive. We have conducted experiments on three molecular biology prediction tasks with four backbone models to gradually evaluate the performance of the proposed robust self-training strategy. The results demonstrate that the proposed method enhances prediction performance across all tasks, notably within molecular regression tasks, where there has been an average enhancement of 41.5%. Furthermore, the visualization analysis confirms the superiority of our method. Our proposed robust self-training is a simple yet effective strategy that efficiently improves molecular biology prediction performance. It tackles the labeled data insufficient issue in molecular biology by taking advantage of both labeled and unlabeled data. Moreover, it can be easily embedded with any prediction task, which serves as a universal approach for the bioinformatics community.

PMID:38531049 | DOI:10.1089/cmb.2023.0187

Dtsch Arztebl Int. 2024 May 3;(Forthcoming):arztebl.m2024.0040. doi: 10.3238/arztebl.m2024.0040. Online ahead of print.

ABSTRACT

BACKGROUND: Population-wide research on potential new imaging biomarkers of the kidney depends on accurate automated segmentation of the kidney and its compartments (cortex, medulla, and sinus).

METHODS: We developed a robust deep-learning framework for kidney (sub-)segmentation based on a hierarchical, three-dimensional convolutional neural network (CNN) that was optimized for multi-scale problems of combined localization and segmentation. We applied the CNN to abdominal magnetic resonance images from the population-based German National Cohort (NAKO) study.

RESULTS: There was good to excellent agreement between the model predictions and manual segmentations. The median values for the body-surface normalized total kidney, cortex, medulla, and sinus volumes of 9934 persons were 158, 115, 43, and 24 mL/m2. Distributions of these markers are provided both for the overall study population and for a subgroup of persons without kidney disease or any associated conditions. Multivariable adjusted regression analyses revealed that diabetes, male sex, and a higher estimated glomerular filtration rate (eGFR) are important predictors of higher total and cortical volumes. Each increase of eGFR by one unit (i.e., 1 mL/min per 1.73 m2 body surface area) was associated with a 0.98 mL/m2 increase in total kidney volume, and this association was significant. Volumes were lower in persons with eGFR-defined chronic kidney disease.

CONCLUSION: The extraction of image-based biomarkers through CNN-based renal sub-segmentation using data from a population-based study yields reliable results, forming a solid foundation for future investigations.

PMID:38530931 | DOI:10.3238/arztebl.m2024.0040

PLoS One. 2024 Mar 26;19(3):e0297996. doi: 10.1371/journal.pone.0297996. eCollection 2024.

ABSTRACT

Alzheimer's disease is the most prevalent form of dementia, which is a gradual condition that begins with mild memory loss and progresses to difficulties communicating and responding to the environment. Recent advancements in neuroimaging techniques have resulted in large-scale multimodal neuroimaging data, leading to an increased interest in using deep learning for the early diagnosis and automated classification of Alzheimer's disease. This study uses machine learning (ML) methods to determine the severity level of Alzheimer's disease using MRI images, where the dataset consists of four levels of severity. A hybrid of 12 feature extraction methods is used to diagnose Alzheimer's disease severity, and six traditional machine learning methods are applied, including decision tree, K-nearest neighbor, linear discrimination analysis, Naïve Bayes, support vector machine, and ensemble learning methods. During training, optimization is performed to obtain the best solution for each classifier. Additionally, a CNN model is trained using a machine learning system algorithm to identify specific patterns. The accuracy of the Naïve Bayes, Support Vector Machines, K-nearest neighbor, Linear discrimination classifier, Decision tree, Ensembled learning, and presented CNN architecture are 67.5%, 72.3%, 74.5%, 65.6%, 62.4%, 73.8% and, 95.3%, respectively. Based on the results, the presented CNN approach outperforms other traditional machine learning methods to find Alzheimer severity.

PMID:38530836 | DOI:10.1371/journal.pone.0297996

ACS Appl Mater Interfaces. 2024 Mar 26. doi: 10.1021/acsami.4c00972. Online ahead of print.

ABSTRACT

Inkjet printing is a powerful direct material writing process. It can be used to deposit microfluidic droplets in designated patterns at submicrometer resolution, which reduces materials usage. Nonetheless, predicting jetting characterizations is not easy because of the intrinsic complexity of the ink-nozzle-air interactions. Thus, inkjet processes are monitored by skilled engineers to ensure process reliability. This is a bottleneck in industry, resulting in high labor costs for multiple nozzles. To address this, we present a deep learning-based method for jetting characterizations. Inkjet printing is recorded by an in situ CCD camera and each droplet is detected by YOLOv5, a 1-stage detector using a convolutional neural network (CNN). The precision, recall, and mean average precision (mAP) at a 0.5 intersection over the union (IoU) threshold of the trained model were 0.86, 0.89, and 0.90, respectively. Each regression result for a detected droplet is accumulated in chronological order for each class of droplet and nozzle. The quantified information includes velocity, diameter, length, and translation, which can be used to synchronize multinozzle jetting and, eventually, the printed patterns. This demonstrates the feasibility of autonomous real-time process testing for large-scale electronics manufacturing, such as the high-resolution patterning of biosensor electrodes and QD display pixels while exploiting big data obtained from jetting characterizations.

PMID:38530805 | DOI:10.1021/acsami.4c00972

IEEE Trans Image Process. 2024 Mar 26;PP. doi: 10.1109/TIP.2024.3379902. Online ahead of print.

ABSTRACT

Accurate segmentation of lesions is crucial for diagnosis and treatment of early esophageal cancer (EEC). However, neither traditional nor deep learning-based methods up to today can meet the clinical requirements, with the mean Dice score - the most important metric in medical image analysis - hardly exceeding 0.75. In this paper, we present a novel deep learning approach for segmenting EEC lesions. Our method stands out for its uniqueness, as it relies solely on a single input image from a patient, forming the so-called "You-Only-Have-One" (YOHO) framework. On one hand, this "one-image-one-network" learning ensures complete patient privacy as it does not use any images from other patients as the training data. On the other hand, it avoids nearly all generalization-related problems since each trained network is applied only to the same input image itself. In particular, we can push the training to "over-fitting" as much as possible to increase the segmentation accuracy. Our technical details include an interaction with clinical doctors to utilize their expertise, a geometry-based data augmentation over a single lesion image to generate the training dataset (the biggest novelty), and an edge-enhanced UNet. We have evaluated YOHO over an EEC dataset collected by ourselves and achieved a mean Dice score of 0.888, which is much higher as compared to the existing deep-learning methods, thus representing a significant advance toward clinical applications. The code and dataset are available at: https://github.com/lhaippp/YOHO.

PMID:38530733 | DOI:10.1109/TIP.2024.3379902

IEEE Trans Neural Netw Learn Syst. 2024 Mar 26;PP. doi: 10.1109/TNNLS.2024.3377446. Online ahead of print.

ABSTRACT

The majority of the results on modeling recurrent neural networks (RNNs) are obtained using delayed differential equations, which imply continuous time representation. On the other hand, these models must be discrete in time, given their practical implementation in computer systems, requiring their versatile utilization across arbitrary time scales. Hence, the goal of this research is to model and investigate the architecture design of a delayed RNN using delayed differential equations on a time scale. Internal memory can be utilized to describe the calculation of the future states using discrete and distributed delays, which is a representation of the deep learning architecture for artificial RNNs. We focus on qualitative behavior and stability study of the system. Special attention is paid to taking into account the effect of the time-scale parameters on neural network dynamics. Here, we delve into the exploration of exponential stability in RNN models on a time scale that incorporates multiple discrete and distributed delays. Two approaches for constructing exponential estimates, including the Hilger and the usual exponential functions, are considered and compared. The Lyapunov-Krasovskii (L-K) functional method is employed to study stability on a time scale in both cases. The established stability criteria, resulting in an exponential-like estimate, utilizes a tuple of positive definite matrices, decay rate, and graininess of the time scale. The models of RNNs for the two-neuron network with four discrete and distributed delays, as well as the ring lattice delayed network of seven identical neurons, are numerically investigated. The results indicate how the time scale (graininess) and model characteristics (weights) influence the qualitative behavior, leading to a transition from stable focus to quasiperiodic limit cycles.

PMID:38530720 | DOI:10.1109/TNNLS.2024.3377446

IEEE Trans Med Imaging. 2024 Mar 26;PP. doi: 10.1109/TMI.2024.3381994. Online ahead of print.

ABSTRACT

Cancer is widely recognized as the primary cause of mortality worldwide, and pathology analysis plays a pivotal role in achieving accurate cancer diagnosis. The intricate representation of features in histopathological images encompasses abundant information crucial for disease diagnosis, regarding cell appearance, tumor microenvironment, and geometric characteristics. However, recent deep learning methods have not adequately exploited geometric features for pathological image classification due to the absence of effective descriptors that can capture both cell distribution and gathering patterns, which often serve as potent indicators. In this paper, inspired by clinical practice, a Hierarchical Graph Pyramid Transformer (HGPT) is proposed to guide pathological image classification by effectively exploiting a geometric representation of tissue distribution which was ignored by existing state-of-the-art methods. First, a graph representation is constructed according to morphological feature of input pathological image and learn geometric representation through the proposed multi-head graph aggregator. Then, the image and its graph representation are feed into the transformer encoder layer to model long-range dependency. Finally, a locality feature enhancement block is designed to enhance the 2D local representation of feature embedding, which is not well explored in the existing vision transformers. An extensive experimental study is conducted on Kather-5K, MHIST, NCT-CRC-HE, and GasHisSDB for binary or multi-category classification of multiple cancer types. Results demonstrated that our method is capable of consistently reaching superior classification outcomes for histopathological images, which provide an effective diagnostic tool for malignant tumors in clinical practice.

PMID:38530716 | DOI:10.1109/TMI.2024.3381994

IEEE Trans Med Imaging. 2024 Mar 26;PP. doi: 10.1109/TMI.2024.3382042. Online ahead of print.

ABSTRACT

Pulmonary nodules may be an early manifestation of lung cancer, the leading cause of cancer-related deaths among both men and women. Numerous studies have established that deep learning methods can yield high-performance levels in the detection of lung nodules in chest X-rays. However, the lack of gold-standard public datasets slows down the progression of the research and prevents benchmarking of methods for this task. To address this, we organized a public research challenge, NODE21, aimed at the detection and generation of lung nodules in chest X-rays. While the detection track assesses state-of-the-art nodule detection systems, the generation track determines the utility of nodule generation algorithms to augment training data and hence improve the performance of the detection systems. This paper summarizes the results of the NODE21 challenge and performs extensive additional experiments to examine the impact of the synthetically generated nodule training images on the detection algorithm performance.

PMID:38530714 | DOI:10.1109/TMI.2024.3382042

Phys Chem Chem Phys. 2024 Mar 26. doi: 10.1039/d3cp05659g. Online ahead of print.

ABSTRACT

In the last ten years, combinations of state-of-the-art gas-phase spectroscopies and quantum chemistry calculations have suggested several intuitive trends in the structure of small polypeptides that may not hold true. For example, the preference for the cis form of the peptide bond and multiple protonated sites was proposed by comparing experimental spectra with low-energy minima obtained from limited structural sampling using various density functional theory methods. For understanding the structures of polypeptides, extensive sampling of their configurational space with high-accuracy computational methods is required. In this work, we demonstrated the use of deep-learning neural network potential (DL-NNP) to assist in exploring the structure and energy landscape of di-, tri-, and tetra-glycine with the accuracy of high-level quantum chemistry methods, and low-energy conformers of small polypeptides can be efficiently located. We hope that the structures of these polypeptides we found and our preliminary analysis will stimulate further experimental investigations.

PMID:38530660 | DOI:10.1039/d3cp05659g

Insights Imaging. 2024 Mar 26;15(1):93. doi: 10.1186/s13244-024-01659-y.

ABSTRACT

OBJECTIVE: To develop a deep learning (DL) model for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI and further develop a DL model for classifying axial spondyloarthritis (axSpA) and non-axSpA.

MATERIALS AND METHODS: This study retrospectively collected 706 patients with FM who underwent SIJ MRI from center 1 (462 axSpA and 186 non-axSpA) and center 2 (37 axSpA and 21 non-axSpA). Patients from center 1 were divided into the training, validation, and internal test sets (n = 455, 64, and 129). Patients from center 2 were used as the external test set. We developed a UNet-based model to segment FM. Based on segmentation results, a classification model was built to distinguish axSpA and non-axSpA. Dice Similarity Coefficients (DSC) and area under the curve (AUC) were used for model evaluation. Radiologists' performance without and with model assistance was compared to assess the clinical utility of the models.

RESULTS: Our segmentation model achieved satisfactory DSC of 81.86% ± 1.55% and 85.44% ± 6.09% on the internal cross-validation and external test sets. The classification model yielded AUCs of 0.876 (95% CI: 0.811-0.942) and 0.799 (95% CI: 0.696-0.902) on the internal and external test sets, respectively. With model assistance, segmentation performance was improved for the radiological resident (DSC, 75.70% vs. 82.87%, p < 0.05) and expert radiologist (DSC, 85.03% vs. 85.74%, p > 0.05).

CONCLUSIONS: DL is a novel method for automatic and accurate segmentation of FM on SIJ MRI and can effectively increase radiologist's performance, which might assist in improving diagnosis and progression of axSpA.

CRITICAL RELEVANCE STATEMENT: DL models allowed automatic and accurate segmentation of FM on sacroiliac joint MRI, which might facilitate quantitative analysis of FM and have the potential to improve diagnosis and prognosis of axSpA.

KEY POINTS: • Deep learning was used for automatic segmentation of fat metaplasia on MRI. • UNet-based models achieved automatic and accurate segmentation of fat metaplasia. • Automatic segmentation facilitates quantitative analysis of fat metaplasia to improve diagnosis and prognosis of axial spondyloarthritis.

PMID:38530554 | DOI:10.1186/s13244-024-01659-y

Physiol Meas. 2024 Mar 26. doi: 10.1088/1361-6579/ad37ee. Online ahead of print.

ABSTRACT

Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with significant health ramifications, including an elevated susceptibility to ischemic stroke, heart disease, and heightened mortality. Photoplethysmography (PPG) has emerged as a promising technology for continuous AF monitoring for its cost-effectiveness and widespread integration into wearable devices. Our team previously conducted an exhaustive review on PPG-based AF detection before June 2019. However, since then, more advanced technologies have emerged in this field. This paper offers a comprehensive review of the latest advancements in PPG-based AF detection, utilizing digital health and artificial intelligence (AI) solutions, within the timeframe spanning from July 2019 to December 2022. Through extensive exploration of scientific databases, we have identified 57 pertinent studies. Our comprehensive review encompasses an in-depth assessment of the statistical methodologies, traditional machine learning techniques, and deep learning approaches employed in these studies. In addition, we address the challenges encountered in the domain of PPG-based AF detection. Furthermore, we maintain a dedicated website to curate the latest research in this area, with regular updates on a regular basis.&#xD.

PMID:38530307 | DOI:10.1088/1361-6579/ad37ee

J Chem Inf Model. 2024 Mar 26. doi: 10.1021/acs.jcim.3c02013. Online ahead of print.

ABSTRACT

DeepKa is a deep-learning-based protein pKa predictor proposed in our previous work. In this study, a web server was developed that enables online protein pKa prediction driven by DeepKa. The web server provides a user-friendly interface where a single step of entering a valid PDB code or uploading a PDB format file is required to submit a job. Two case studies have been attached in order to explain how pKa's calculated by the web server could be utilized by users. Finally, combining the web server with post processing as described in case studies, this work suggests a quick workflow of investigating the relationship between protein structure and function that are pH dependent. The web server of DeepKa is freely available at http://www.computbiophys.com/DeepKa/main.

PMID:38530291 | DOI:10.1021/acs.jcim.3c02013

Radiology. 2024 Mar;310(3):e249009. doi: 10.1148/radiol.249009.

NO ABSTRACT

PMID:38530188 | DOI:10.1148/radiol.249009

Radiology. 2024 Mar;310(3):e231429. doi: 10.1148/radiol.231429.

ABSTRACT

Background Differentiating between benign and malignant vertebral fractures poses diagnostic challenges. Purpose To investigate the reliability of CT-based deep learning models to differentiate between benign and malignant vertebral fractures. Materials and Methods CT scans acquired in patients with benign or malignant vertebral fractures from June 2005 to December 2022 at two university hospitals were retrospectively identified based on a composite reference standard that included histopathologic and radiologic information. An internal test set was randomly selected, and an external test set was obtained from an additional hospital. Models used a three-dimensional U-Net encoder-classifier architecture and applied data augmentation during training. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) and compared with that of two residents and one fellowship-trained radiologist using the DeLong test. Results The training set included 381 patients (mean age, 69.9 years ± 11.4 [SD]; 193 male) with 1307 vertebrae (378 benign fractures, 447 malignant fractures, 482 malignant lesions). Internal and external test sets included 86 (mean age, 66.9 years ± 12; 45 male) and 65 (mean age, 68.8 years ± 12.5; 39 female) patients, respectively. The better-performing model of two training approaches achieved AUCs of 0.85 (95% CI: 0.77, 0.92) in the internal and 0.75 (95% CI: 0.64, 0.85) in the external test sets. Including an uncertainty category further improved performance to AUCs of 0.91 (95% CI: 0.83, 0.97) in the internal test set and 0.76 (95% CI: 0.64, 0.88) in the external test set. The AUC values of residents were lower than that of the best-performing model in the internal test set (AUC, 0.69 [95% CI: 0.59, 0.78] and 0.71 [95% CI: 0.61, 0.80]) and external test set (AUC, 0.70 [95% CI: 0.58, 0.80] and 0.71 [95% CI: 0.60, 0.82]), with significant differences only for the internal test set (P < .001). The AUCs of the fellowship-trained radiologist were similar to those of the best-performing model (internal test set, 0.86 [95% CI: 0.78, 0.93; P = .39]; external test set, 0.71 [95% CI: 0.60, 0.82; P = .46]). Conclusion Developed models showed a high discriminatory power to differentiate between benign and malignant vertebral fractures, surpassing or matching the performance of radiology residents and matching that of a fellowship-trained radiologist. © RSNA, 2024 See also the editorial by Booz and D'Angelo in this issue.

PMID:38530172 | DOI:10.1148/radiol.231429

Radiology. 2024 Mar;310(3):e240409. doi: 10.1148/radiol.240409.

NO ABSTRACT

PMID:38530170 | DOI:10.1148/radiol.240409

Med Phys. 2024 Mar 26. doi: 10.1002/mp.17028. Online ahead of print.

ABSTRACT

BACKGROUND: The kernel used in CT image reconstruction is an important factor that determines the texture of the CT image. Consistency of reconstruction kernel choice is important for quantitative CT-based assessment as kernel differences can lead to substantial shifts in measurements unrelated to underlying anatomical structures.

PURPOSE: In this study, we investigate kernel harmonization in a multi-vendor low-dose CT lung cancer screening cohort and evaluate our approach's validity in quantitative CT-based assessments.

METHODS: Using the National Lung Screening Trial, we identified CT scan pairs of the same sessions with one reconstructed from a soft tissue kernel and one from a hard kernel. In total, 1000 pairs of five different paired kernel types (200 each) were identified. We adopt the pix2pix architecture to train models for kernel conversion. Each model was trained on 100 pairs and evaluated on 100 withheld pairs. A total of 10 models were implemented. We evaluated the efficacy of kernel conversion based on image similarity metrics including root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM) as well as the capability of the models to reduce measurement shifts in quantitative emphysema and body composition measurements. Additionally, we study the reproducibility of standard radiomic features for all kernel pairs before and after harmonization.

RESULTS: Our approach effectively converts CT images from one kernel to another in all paired kernel types, as indicated by the reduction in RMSE (p < 0.05) and an increase in the PSNR (p < 0.05) and SSIM (p < 0.05) for both directions of conversion for all pair types. In addition, there is an increase in the agreement for percent emphysema, skeletal muscle area, and subcutaneous adipose tissue (SAT) area for both directions of conversion. Furthermore, radiomic features were reproducible when compared with the ground truth features.

CONCLUSIONS: Kernel conversion using deep learning reduces measurement variation in percent emphysema, muscle area, and SAT area.

PMID:38530135 | DOI:10.1002/mp.17028

J Acoust Soc Am. 2024 Mar 1;155(3):2221-2232. doi: 10.1121/10.0025178.

ABSTRACT

The accuracy of modern automatic speaker verification (ASV) systems, when trained exclusively on adult data, drops substantially when applied to children's speech. The scarcity of children's speech corpora hinders fine-tuning ASV systems for children's speech. Hence, there is a timely need to explore more effective ways of reusing adults' speech data. One promising approach is to align vocal-tract parameters between adults and children through children-specific data augmentation, referred here to as ChildAugment. Specifically, we modify the formant frequencies and formant bandwidths of adult speech to emulate children's speech. The modified spectra are used to train emphasized channel attention, propagation, and aggregation in time-delay neural network recognizer for children. We compare ChildAugment against various state-of-the-art data augmentation techniques for children's ASV. We also extensively compare different scoring methods, including cosine scoring, probabilistic linear discriminant analysis (PLDA), and neural PLDA. We also propose a low-complexity weighted cosine score for extremely low-resource children ASV. Our findings on the CSLU kids corpus indicate that ChildAugment holds promise as a simple, acoustics-motivated approach, for improving state-of-the-art deep learning based ASV for children. We achieve up to 12.45% (boys) and 11.96% (girls) relative improvement over the baseline. For reproducibility, we provide the evaluation protocols and codes here.

PMID:38530014 | DOI:10.1121/10.0025178

J Chem Inf Model. 2024 Mar 26. doi: 10.1021/acs.jcim.4c00065. Online ahead of print.

ABSTRACT

Along with the development of machine learning, deep learning, and large language models (LLMs) such as GPT-4 (GPT: Generative Pre-Trained Transformer), artificial intelligence (AI) tools have been playing an increasingly important role in chemical and material research to facilitate the material screening and design. Despite the exciting progress of GPT-4 based AI research assistance, open-source LLMs have not gained much attention from the scientific community. This work primarily focused on metal-organic frameworks (MOFs) as a subdomain of chemistry and evaluated six top-rated open-source LLMs with a comprehensive set of tasks including MOFs knowledge, basic chemistry knowledge, in-depth chemistry knowledge, knowledge extraction, database reading, predicting material property, experiment design, computational scripts generation, guiding experiment, data analysis, and paper polishing, which covers the basic units of MOFs research. In general, these LLMs were capable of most of the tasks. Especially, Llama2-7B and ChatGLM2-6B were found to perform particularly well with moderate computational resources. Additionally, the performance of different parameter versions of the same model was compared, which revealed the superior performance of higher parameter versions.

PMID:38529913 | DOI:10.1021/acs.jcim.4c00065

J Biomol Struct Dyn. 2024 Mar 26:1-11. doi: 10.1080/07391102.2024.2323699. Online ahead of print.

ABSTRACT

The serine/threonine kinase (STK) plays a central role as the primary kinase in poxviruses, directing phosphoryl transfer reactions. Such reactions are pivotal for the activation of certain proteins during viral replication, assembly, and maturation. Therefore, targeting this key protein is anticipated to impede virus replication. In this work, a structural bioinformatics approach was employed to evaluate the potential of drug-like kinase inhibitors in binding to the ATP-binding pocket on the STK of the Mpox virus. Virtual screening of known kinase inhibitors revealed that the top 10 inhibitors exhibited binding affinities ranging from -8.59 to -12.05 kcal/mol. The rescoring of compounds using the deep-learning default model in GNINA was performed to predict accurate binding poses. Subsequently, the top three inhibitors underwent unbiased molecular dynamics (MD) simulations for 100 ns. Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) analysis and Principal Component Analysis (PCA) suggested tepotinib as a competitive inhibitor for Mpox virus STK as evidenced by its binding free energy and the induction of similar conformational behavior of the enzyme. Nevertheless, it is sensible to experimentally test all top 10 compounds, as scoring functions and energy calculations may not consistently align with experimental findings. These insights are poised to provide an attempt to identify an effective inhibitor for the Mpox virus.Communicated by Ramaswamy H. Sarma.

PMID:38529847 | DOI:10.1080/07391102.2024.2323699