bioRxiv [Preprint]. 2024 Apr 26:2024.04.25.590553. doi: 10.1101/2024.04.25.590553.

ABSTRACT

It is projected that 10 million deaths could be attributed to drug-resistant bacteria infections in 2050. To address this concern, identifying new-generation antibiotics is an effective way. Antimicrobial peptides (AMPs), a class of innate immune effectors, have received significant attention for their capacity to eliminate drug-resistant pathogens, including viruses, bacteria, and fungi. Recent years have witnessed widespread applications of computational methods especially machine learning (ML) and deep learning (DL) for discovering AMPs. However, existing methods only use features including compositional, physiochemical, and structural properties of peptides, which cannot fully capture sequence information from AMPs. Here, we present SAMP, an ensemble random projection (RP) based computational model that leverages a new type of features called Proportionalized Split Amino Acid Composition (PSAAC) in addition to conventional sequence-based features for AMP prediction. With this new feature set, SAMP captures the residue patterns like sorting signals at around both the N-terminus and the C-terminus, while also retaining the sequence order information from the middle peptide fragments. Benchmarking tests on different balanced and imbalanced datasets demonstrate that SAMP consistently outperforms existing state-of-the-art methods, such as iAMPpred and AMPScanner V2, in terms of accuracy, MCC, G-measure and F1-score. In addition, by leveraging an ensemble RP architecture, SAMP is scalable to processing large-scale AMP identification with further performance improvement, compared to those models without RP. To facilitate the use of SAMP, we have developed a Python package freely available at https://github.com/wan-mlab/SAMP .

PMID:38712184 | PMC:PMC11071531 | DOI:10.1101/2024.04.25.590553

bioRxiv [Preprint]. 2024 Apr 28:2024.04.12.589090. doi: 10.1101/2024.04.12.589090.

ABSTRACT

Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3 - 20× compared to supervised methods. Our in silico results show improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.

PMID:38712113 | PMC:PMC11071277 | DOI:10.1101/2024.04.12.589090

World J Emerg Surg. 2024 May 6;19(1):17. doi: 10.1186/s13017-024-00546-7.

ABSTRACT

BACKGROUND: Abdominal computed tomography (CT) scan is a crucial imaging modality for creating cross-sectional images of the abdominal area, particularly in cases of abdominal trauma, which is commonly encountered in traumatic injuries. However, interpreting CT images is a challenge, especially in emergency. Therefore, we developed a novel deep learning algorithm-based detection method for the initial screening of abdominal internal organ injuries.

METHODS: We utilized a dataset provided by the Kaggle competition, comprising 3,147 patients, of which 855 were diagnosed with abdominal trauma, accounting for 27.16% of the total patient population. Following image data pre-processing, we employed a 2D semantic segmentation model to segment the images and constructed a 2.5D classification model to assess the probability of injury for each organ. Subsequently, we evaluated the algorithm's performance using 5k-fold cross-validation.

RESULTS: With particularly noteworthy performance in detecting renal injury on abdominal CT scans, we achieved an acceptable accuracy of 0.932 (with a positive predictive value (PPV) of 0.888, negative predictive value (NPV) of 0.943, sensitivity of 0.887, and specificity of 0.944). Furthermore, the accuracy for liver injury detection was 0.873 (with PPV of 0.789, NPV of 0.895, sensitivity of 0.789, and specificity of 0.895), while for spleen injury, it was 0.771 (with PPV of 0.630, NPV of 0.814, sensitivity of 0.626, and specificity of 0.816).

CONCLUSIONS: The deep learning model demonstrated the capability to identify multiple organ injuries simultaneously on CT scans and holds potential for application in preliminary screening and adjunctive diagnosis of trauma cases beyond abdominal injuries.

PMID:38711150 | DOI:10.1186/s13017-024-00546-7

Plant Methods. 2024 May 6;20(1):63. doi: 10.1186/s13007-024-01195-2.

ABSTRACT

BACKGROUND: The detection of internal defects in seeds via non-destructive imaging techniques is a topic of high interest to optimize the quality of seed lots. In this context, X-ray imaging is especially suited. Recent studies have shown the feasibility of defect detection via deep learning models in 3D tomography images. We demonstrate the possibility of performing such deep learning-based analysis on 2D X-ray radiography for a faster yet robust method via the X-Robustifier pipeline proposed in this article.

RESULTS: 2D X-ray images of both defective and defect-free seeds were acquired. A deep learning model based on state-of-the-art object detection neural networks is proposed. Specific data augmentation techniques are introduced to compensate for the low ratio of defects and increase the robustness to variation of the physical parameters of the X-ray imaging systems. The seed defects were accurately detected (F1-score >90%), surpassing human performance in computation time and error rates. The robustness of these models against the principal distortions commonly found in actual agro-industrial conditions is demonstrated, in particular, the robustness to physical noise, dimensionality reduction and the presence of seed coating.

CONCLUSION: This work provides a full pipeline to automatically detect common defects in seeds via 2D X-ray imaging. The method is illustrated on sugar beet and faba bean and could be efficiently extended to other species via the proposed generic X-ray data processing approach (X-Robustifier). Beyond a simple proof of feasibility, this constitutes important results toward the effective use in the routine of deep learning-based automatic detection of seed defects.

PMID:38711143 | DOI:10.1186/s13007-024-01195-2

Eye Vis (Lond). 2024 May 6;11(1):17. doi: 10.1186/s40662-024-00384-3.

ABSTRACT

BACKGROUND: Artificial intelligence (AI) that utilizes deep learning (DL) has potential for systemic disease prediction using retinal imaging. The retina's unique features enable non-invasive visualization of the central nervous system and microvascular circulation, aiding early detection and personalized treatment plans for personalized care. This review explores the value of retinal assessment, AI-based retinal biomarkers, and the importance of longitudinal prediction models in personalized care.

MAIN TEXT: This narrative review extensively surveys the literature for relevant studies in PubMed and Google Scholar, investigating the application of AI-based retina biomarkers in predicting systemic diseases using retinal fundus photography. The study settings, sample sizes, utilized AI models and corresponding results were extracted and analysed. This review highlights the substantial potential of AI-based retinal biomarkers in predicting neurodegenerative, cardiovascular, and chronic kidney diseases. Notably, DL algorithms have demonstrated effectiveness in identifying retinal image features associated with cognitive decline, dementia, Parkinson's disease, and cardiovascular risk factors. Furthermore, longitudinal prediction models leveraging retinal images have shown potential in continuous disease risk assessment and early detection. AI-based retinal biomarkers are non-invasive, accurate, and efficient for disease forecasting and personalized care.

CONCLUSION: AI-based retinal imaging hold promise in transforming primary care and systemic disease management. Together, the retina's unique features and the power of AI enable early detection, risk stratification, and help revolutionizing disease management plans. However, to fully realize the potential of AI in this domain, further research and validation in real-world settings are essential.

PMID:38711111 | DOI:10.1186/s40662-024-00384-3

J Imaging Inform Med. 2024 May 6. doi: 10.1007/s10278-024-01136-4. Online ahead of print.

ABSTRACT

Saliency maps are popularly used to "explain" decisions made by modern machine learning models, including deep convolutional neural networks (DCNNs). While the resulting heatmaps purportedly indicate important image features, their "trustworthiness," i.e., utility and robustness, has not been evaluated for musculoskeletal imaging. The purpose of this study was to systematically evaluate the trustworthiness of saliency maps used in disease diagnosis on upper extremity X-ray images. The underlying DCNNs were trained using the Stanford MURA dataset. We studied four trustworthiness criteria-(1) localization accuracy of abnormalities, (2) repeatability, (3) reproducibility, and (4) sensitivity to underlying DCNN weights-across six different gradient-based saliency methods (Grad-CAM (GCAM), gradient explanation (GRAD), integrated gradients (IG), Smoothgrad (SG), smooth IG (SIG), and XRAI). Ground-truth was defined by the consensus of three fellowship-trained musculoskeletal radiologists who each placed bounding boxes around abnormalities on a holdout saliency test set. Compared to radiologists, all saliency methods showed inferior localization (AUPRCs: 0.438 (SG)-0.590 (XRAI); average radiologist AUPRC: 0.816), repeatability (IoUs: 0.427 (SG)-0.551 (IG); average radiologist IOU: 0.613), and reproducibility (IoUs: 0.250 (SG)-0.502 (XRAI); average radiologist IOU: 0.613) on abnormalities such as fractures, orthopedic hardware insertions, and arthritis. Five methods (GCAM, GRAD, IG, SG, XRAI) passed the sensitivity test. Ultimately, no saliency method met all four trustworthiness criteria; therefore, we recommend caution and rigorous evaluation of saliency maps prior to their clinical use.

PMID:38710971 | DOI:10.1007/s10278-024-01136-4

Sci Rep. 2024 May 6;14(1):10371. doi: 10.1038/s41598-024-60977-9.

ABSTRACT

Emotion is a human sense that can influence an individual's life quality in both positive and negative ways. The ability to distinguish different types of emotion can lead researchers to estimate the current situation of patients or the probability of future disease. Recognizing emotions from images have problems concealing their feeling by modifying their facial expressions. This led researchers to consider Electroencephalography (EEG) signals for more accurate emotion detection. However, the complexity of EEG recordings and data analysis using conventional machine learning algorithms caused inconsistent emotion recognition. Therefore, utilizing hybrid deep learning models and other techniques has become common due to their ability to analyze complicated data and achieve higher performance by integrating diverse features of the models. However, researchers prioritize models with fewer parameters to achieve the highest average accuracy. This study improves the Convolutional Fuzzy Neural Network (CFNN) for emotion recognition using EEG signals to achieve a reliable detection system. Initially, the pre-processing and feature extraction phases are implemented to obtain noiseless and informative data. Then, the CFNN with modified architecture is trained to classify emotions. Several parametric and comparative experiments are performed. The proposed model achieved reliable performance for emotion recognition with an average accuracy of 98.21% and 98.08% for valence (pleasantness) and arousal (intensity), respectively, and outperformed state-of-the-art methods.

PMID:38710806 | DOI:10.1038/s41598-024-60977-9

Sci Rep. 2024 May 6;14(1):10341. doi: 10.1038/s41598-024-60743-x.

ABSTRACT

Interpretability in machine learning has become increasingly important as machine learning is being used in more and more applications, including those with high-stakes consequences such as healthcare where Interpretability has been regarded as a key to the successful adoption of machine learning models. However, using confounding/irrelevant information in making predictions by deep learning models, even the interpretable ones, poses critical challenges to their clinical acceptance. That has recently drawn researchers' attention to issues beyond the mere interpretation of deep learning models. In this paper, we first investigate application of an inherently interpretable prototype-based architecture, known as ProtoPNet, for breast cancer classification in digital pathology and highlight its shortcomings in this application. Then, we propose a new method that uses more medically relevant information and makes more accurate and interpretable predictions. Our method leverages the clustering concept and implicitly increases the number of classes in the training dataset. The proposed method learns more relevant prototypes without any pixel-level annotated data. To have a more holistic assessment, in addition to classification accuracy, we define a new metric for assessing the degree of interpretability based on the comments of a group of skilled pathologists. Experimental results on the BreakHis dataset show that the proposed method effectively improves the classification accuracy and interpretability by respectively 8 % and 18 % . Therefore, the proposed method can be seen as a step toward implementing interpretable deep learning models for the detection of breast cancer using histopathology images.

PMID:38710757 | DOI:10.1038/s41598-024-60743-x

Sci Rep. 2024 May 6;14(1):10357. doi: 10.1038/s41598-024-60596-4.

ABSTRACT

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses adaptive background modeling. It also addresses shadow and illumination issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this framework with respect to other methods.

PMID:38710753 | DOI:10.1038/s41598-024-60596-4

Sci Rep. 2024 May 6;14(1):10375. doi: 10.1038/s41598-024-59291-1.

ABSTRACT

Tuberculosis (TB) a disease caused by Mycobacterium tuberculosis (Mtb) poses a significant threat to human life, and current BCG vaccinations only provide sporadic protection, therefore there is a need for developing efficient vaccines. Numerous immunoinformatic methods have been utilized previously, here for the first time a deep learning framework based on Deconvolutional Neural Networks (DCNN) and Bidirectional Long Short-Term Memory (DCNN-BiLSTM) was used to predict Mtb Multiepitope vaccine (MtbMEV) subunits against six Mtb H37Rv proteins. The trained model was used to design MEV within a few minutes against TB better than other machine learning models with 99.5% accuracy. The MEV has good antigenicity, and physiochemical properties, and is thermostable, soluble, and hydrophilic. The vaccine's BLAST search ruled out the possibility of autoimmune reactions. The secondary structure analysis revealed 87% coil, 10% beta, and 2% alpha helix, while the tertiary structure was highly upgraded after refinement. Molecular docking with TLR3 and TLR4 receptors showed good binding, indicating high immune reactions. Immune response simulation confirmed the generation of innate and adaptive responses. In-silico cloning revealed the vaccine is highly expressed in E. coli. The results can be further experimentally verified using various analyses to establish a candidate vaccine for future clinical trials.

PMID:38710737 | DOI:10.1038/s41598-024-59291-1

Sci Rep. 2024 May 6;14(1):10395. doi: 10.1038/s41598-024-60807-y.

ABSTRACT

To assess the feasibility of code-free deep learning (CFDL) platforms in the prediction of binary outcomes from fundus images in ophthalmology, evaluating two distinct online-based platforms (Google Vertex and Amazon Rekognition), and two distinct datasets. Two publicly available datasets, Messidor-2 and BRSET, were utilized for model development. The Messidor-2 consists of fundus photographs from diabetic patients and the BRSET is a multi-label dataset. The CFDL platforms were used to create deep learning models, with no preprocessing of the images, by a single ophthalmologist without coding expertise. The performance metrics employed to evaluate the models were F1 score, area under curve (AUC), precision and recall. The performance metrics for referable diabetic retinopathy and macular edema were above 0.9 for both tasks and CDFL. The Google Vertex models demonstrated superior performance compared to the Amazon models, with the BRSET dataset achieving the highest accuracy (AUC of 0.994). Multi-classification tasks using only BRSET achieved similar overall performance between platforms, achieving AUC of 0.994 for laterality, 0.942 for age grouping, 0.779 for genetic sex identification, 0.857 for optic, and 0.837 for normality with Google Vertex. The study demonstrates the feasibility of using automated machine learning platforms for predicting binary outcomes from fundus images in ophthalmology. It highlights the high accuracy achieved by the models in some tasks and the potential of CFDL as an entry-friendly platform for ophthalmologists to familiarize themselves with machine learning concepts.

PMID:38710726 | DOI:10.1038/s41598-024-60807-y

Sci Data. 2024 May 6;11(1):458. doi: 10.1038/s41597-024-03299-9.

ABSTRACT

The advent of single-particle cryo-electron microscopy (cryo-EM) has brought forth a new era of structural biology, enabling the routine determination of large biological molecules and their complexes at atomic resolution. The high-resolution structures of biological macromolecules and their complexes significantly expedite biomedical research and drug discovery. However, automatically and accurately building atomic models from high-resolution cryo-EM density maps is still time-consuming and challenging when template-based models are unavailable. Artificial intelligence (AI) methods such as deep learning trained on limited amount of labeled cryo-EM density maps generate inaccurate atomic models. To address this issue, we created a dataset called Cryo2StructData consisting of 7,600 preprocessed cryo-EM density maps whose voxels are labelled according to their corresponding known atomic structures for training and testing AI methods to build atomic models from cryo-EM density maps. Cryo2StructData is larger than existing, publicly available datasets for training AI methods to build atomic protein structures from cryo-EM density maps. We trained and tested deep learning models on Cryo2StructData to validate its quality showing that it is ready for being used to train and test AI methods for building atomic models.

PMID:38710720 | DOI:10.1038/s41597-024-03299-9

Psychol Methods. 2024 May 6. doi: 10.1037/met0000645. Online ahead of print.

ABSTRACT

Bayesian model comparison (BMC) offers a principled approach to assessing the relative merits of competing computational models and propagating uncertainty into model selection decisions. However, BMC is often intractable for the popular class of hierarchical models due to their high-dimensional nested parameter structure. To address this intractability, we propose a deep learning method for performing BMC on any set of hierarchical models which can be instantiated as probabilistic programs. Since our method enables amortized inference, it allows efficient re-estimation of posterior model probabilities and fast performance validation prior to any real-data application. In a series of extensive validation studies, we benchmark the performance of our method against the state-of-the-art bridge sampling method and demonstrate excellent amortized inference across all BMC settings. We then showcase our method by comparing four hierarchical evidence accumulation models that have previously been deemed intractable for BMC due to partly implicit likelihoods. Additionally, we demonstrate how transfer learning can be leveraged to enhance training efficiency. We provide reproducible code for all analyses and an open-source implementation of our method. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

PMID:38709626 | DOI:10.1037/met0000645

Microsc Microanal. 2024 May 6:ozae038. doi: 10.1093/mam/ozae038. Online ahead of print.

ABSTRACT

We have developed a methodology for the systematic generation of a large image dataset of macerated wood references, which we used to generate image data for nine hardwood genera. This is the basis for a substantial approach to automate, for the first time, the identification of hardwood species in microscopic images of fibrous materials by deep learning. Our methodology includes a flexible pipeline for easy annotation of vessel elements. We compare the performance of different neural network architectures and hyperparameters. Our proposed method performs similarly well to human experts. In the future, this will improve controls on global wood fiber product flows to protect forests.

PMID:38709570 | DOI:10.1093/mam/ozae038

Methods Mol Biol. 2024;2800:217-229. doi: 10.1007/978-1-0716-3834-7_15.

ABSTRACT

High-throughput microscopy has enabled screening of cell phenotypes at unprecedented scale. Systematic identification of cell phenotype changes (such as cell morphology and protein localization changes) is a major analysis goal. Because cell phenotypes are high-dimensional, unbiased approaches to detect and visualize the changes in phenotypes are still needed. Here, we suggest that changes in cellular phenotype can be visualized in reduced dimensionality representations of the image feature space. We describe a freely available analysis pipeline to visualize changes in protein localization in feature spaces obtained from deep learning. As an example, we use the pipeline to identify changes in subcellular localization after the yeast GFP collection was treated with hydroxyurea.

PMID:38709487 | DOI:10.1007/978-1-0716-3834-7_15

Methods Mol Biol. 2024;2800:203-215. doi: 10.1007/978-1-0716-3834-7_14.

ABSTRACT

Cell tracking is an essential step in extracting cellular signals from moving cells, which is vital for understanding the mechanisms underlying various biological functions and processes, particularly in organs such as the brain and heart. However, cells in living organisms often exhibit extensive and complex movements caused by organ deformation and whole-body motion. These movements pose a challenge in obtaining high-quality time-lapse cell images and tracking the intricate cell movements in the captured images. Recent advances in deep learning techniques provide powerful tools for detecting cells in low-quality images with densely packed cell populations, as well as estimating cell positions for cells undergoing large nonrigid movements. This chapter introduces the challenges of cell tracking in deforming organs and moving animals, outlines the solutions to these challenges, and presents a detailed protocol for data preparation, as well as for performing cell segmentation and tracking using the latest version of 3DeeCellTracker. This protocol is expected to enable researchers to gain deeper insights into organ dynamics and biological processes.

PMID:38709486 | DOI:10.1007/978-1-0716-3834-7_14

Methods Mol Biol. 2024;2800:189-202. doi: 10.1007/978-1-0716-3834-7_13.

ABSTRACT

Understanding how signaling networks are regulated offers valuable insights into how cells and organisms react to internal and external stimuli and is crucial for developing novel strategies to treat diseases. To achieve this, it is necessary to delineate the intricate interactions between the nodes in the network, which can be accomplished by measuring the activities of individual nodes under perturbation conditions. To facilitate this, we have recently developed a biosensor barcoding technique that enables massively multiplexed tracking of numerous signaling activities in live cells using genetically encoded fluorescent biosensors. In this chapter, we detail how we employed this method to reconstruct the EGFR signaling network by systematically monitoring the activities of individual nodes under perturbations.

PMID:38709485 | DOI:10.1007/978-1-0716-3834-7_13

J Appl Clin Med Phys. 2024 May 6:e14372. doi: 10.1002/acm2.14372. Online ahead of print.

ABSTRACT

BACKGROUND: Quality assurance (QA) of patient-specific treatment plans for intensity-modulated radiation therapy (IMRT) and volumetric modulated arc therapy (VMAT) necessitates prior validation. However, the standard methodology exhibits deficiencies and lacks sensitivity in the analysis of positional dose distribution data, leading to difficulties in accurately identifying reasons for plan verification failure. This issue complicates and impedes the efficiency of QA tasks.

PURPOSE: The primary aim of this research is to utilize deep learning algorithms for the extraction of 3D dose distribution maps and the creation of a predictive model for error classification across multiple machine models, treatment methodologies, and tumor locations.

METHOD: We devised five categories of validation plans (normal, gantry error, collimator error, couch error, and dose error), conforming to tolerance limits of different accuracy levels and employing 3D dose distribution data from a sample of 94 tumor patients. A CNN model was then constructed to predict the diverse error types, with predictions compared against the gamma pass rate (GPR) standard employing distinct thresholds (3%, 3 mm; 3%, 2 mm; 2%, 2 mm) to evaluate the model's performance. Furthermore, we appraised the model's robustness by assessing its functionality across diverse accelerators.

RESULTS: The accuracy, precision, recall, and F1 scores of CNN model performance were 0.907, 0.925, 0.907, and 0.908, respectively. Meanwhile, the performance on another device is 0.900, 0.918, 0.900, and 0.898. In addition, compared to the GPR method, the CNN model achieved better results in predicting different types of errors.

CONCLUSION: When juxtaposed with the GPR methodology, the CNN model exhibits superior predictive capability for classification in the validation of the radiation therapy plan on different devices. By using this model, the plan validation failures can be detected more rapidly and efficiently, minimizing the time required for QA tasks and serving as a valuable adjunct to overcome the constraints of the GPR method.

PMID:38709158 | DOI:10.1002/acm2.14372

J Chem Inf Model. 2024 May 6. doi: 10.1021/acs.jcim.4c00171. Online ahead of print.

ABSTRACT

Developing new pharmaceuticals is a costly and time-consuming endeavor fraught with significant safety risks. A critical aspect of drug research and disease therapy is discerning the existence of interactions between drugs and proteins. The evolution of deep learning (DL) in computer science has been remarkably aided in this regard in recent years. Yet, two challenges remain: (i) balancing the extraction of profound, local cohesive characteristics while warding off gradient disappearance and (ii) globally representing and understanding the interactions between the drug and target local attributes, which is vital for delivering molecular level insights indispensable to drug development. In response to these challenges, we propose a DL network structure, MolLoG, primarily comprising two modules: local feature encoders (LFE) and global interactive learning (GIL). Within the LFE module, graph convolution networks and leap blocks capture the local features of drug and protein molecules, respectively. The GIL module enables the efficient amalgamation of feature information, facilitating the global learning of feature structural semantics and procuring multihead attention weights for abstract features stemming from two modalities, providing biologically pertinent explanations for black-box results. Finally, predictive outcomes are achieved by decoding the unified representation via a multilayer perceptron. Our experimental analysis reveals that MolLoG outperforms several cutting-edge baselines across four data sets, delivering superior overall performance and providing satisfactory results when elucidating various facets of drug-target interaction predictions.

PMID:38709146 | DOI:10.1021/acs.jcim.4c00171

Cancer Res Commun. 2024 May 6. doi: 10.1158/2767-9764.CRC-24-0031. Online ahead of print.

ABSTRACT

Deep learning may detect biologically important signals embedded in tumor morphologic features that confer distinct prognoses. Tumor morphological features were quantified to enhance patient risk stratification within DNA mismatch repair (MMR) groups using deep learning. Using a quantitative segmentation algorithm (QuantCRC) that identifies 15 distinct morphological features, we analyzed 402 resected stage III colon carcinomas (191 d-MMR; 189 p-MMR) from participants in a phase III trial of FOLFOX-based adjuvant chemotherapy. Results were validated in an independent cohort (176 d-MMR; 1094 p-MMR). Association of morphological features with clinicopathologic variables, MMR, KRAS, BRAFV600E, and time-to-recurrence (TTR) was determined. Multivariable Cox proportional hazard models were developed to predict TTR. Tumor morphological features differed significantly by MMR status. Cancers with p-MMR had more immature desmoplastic stroma. Tumors with d-MMR had increased inflammatory stroma, epithelial tumor-infiltrating lymphocytes (TILs), high grade histology, mucin, and signet ring cells. Stromal subtype did not differ by BRAFV600E or KRAS status. In p-MMR tumors, multivariable analysis identified tumor-stroma ratio (TSR) as the strongest feature associated with TTR [HRadj 2.02; 95% CI,1.14-3.57; P=0.018; 3-year recurrence: 40.2% vs 20.4%; Q1 vs Q2-4]. Among d-MMR tumors, extent of inflammatory stroma [continuous HRadj 0.98; 95% CI,0.96-0.99; P=0.028; 3-year recurrence: 13.3% vs 33.4%, Q4 vs Q1] and N stage were the most robust prognostically. Association of TSR with TTR was independently validated. In conclusion, QuantCRC can quantify morphological differences within MMR groups in routine tumor sections to determine their relative contributions to patient prognosis, and may elucidate relevant pathophysiologic mechanisms driving prognosis.

PMID:38709069 | DOI:10.1158/2767-9764.CRC-24-0031