Set Of Data Files Research Articles

Visualization-based comprehensive feature representation with improved EfficientNet for malicious file and variant recognition

Malicious file attacks seriously affect network and data security, and recognizing malicious files and variants is crucial for preventing network attacks. Faced with the challenge of traditional methods in quickly, effectively, and efficiently recognizing malicious files or variants, visualization-based feature representation methods have shown promising results. However, practical applications encounter issues such as loss of crucial information, high spatiotemporal overhead, and the need for model performance improvement. Therefore, this paper introduces a novel recognition framework focusing on feature representation and model performance. The framework uses the proposed visualization-based comprehensive feature representation method (VCFR) to extract file information into the Gray-Level Co-occurrence Matrix (GLCM), 2-gram frequency matrix, and interval 2-gram frequency matrix, followed by feature fusion to generate the three-channel RGB images. Subsequently, the proposed lightweight model is applied for recognizing those files, which utilizes ideas such as group convolution, channel shuffle, and attention mechanisms to improve model performance while significantly reducing model parameters, size, and FLOPs. In summary, through a series of experiments conducted on manually collected malicious file dataset (MFD) and public dataset MMCC, the proposed framework significantly outperformed other state-of-the-art technologies and has F1-Score as high as 94.10% and 98.58%, respectively, further verifying its outstanding effectiveness and efficiency.

Burst-classifier: Automated classification of solar radio burst type II, III and IV for CALLISTO spectra using physical properties during maximum of solar cycle 24

Continuous observation of solar radio bursts (SRBs) throughout the year using the CALLISTO spectrometer generates a huge volume of spectral data. This study introduces a burst-classifier algorithm, which is an automated algorithm, to classify the SRB spectrum into three solar radio bursts, namely Type II (SRBT II), Type III (SRBT III) and Type IV (SRBT IV). The proposed algorithm was designed using four characteristic parameters derived from a collection of training dataset files. The characteristic parameters were derived from the intensity bursts observed on frequency channels and timesteps of the spectrum. This dataset consisted of 50 spectra of SRBT II and SRBT III, along with 40 spectra for SRBT IV, collected during the solar maximum of 2014 (Solar Cycle 24). After observations and analysis of the training dataset, each burst type was set up with a threshold. A training dataset of 80 data spectra from 2013 to 2016 was used to test the algorithm. Accuracy of the proposed algorithm was calculated using the percentage of true positives (TP) and false positives (FP). Findings demonstrate an accuracy of ∼74 % with 57 out of 80 spectra classified as TP and 23 spectra as FP.

Incidence of Postsurgical Intraocular Inflammation 6 Months After Implantation with a Multifocal Intraocular Lens.

This study assessed the incidence of postsurgical intraocular inflammation after cataract extraction by phacoemulsification and implantation with AcrySof IQ ReSTOR intraocular lenses (IOLs) produced using an updated manufacturing process. Incidence rates were compared with historical rates of postsurgical intraocular inflammation. This was a prospective, multicenter, post-approval study at 34 sites. Patients aged ≥22 years received a study lens in at least 1 eye. Postsurgical intraocular inflammation (aqueous cell grade ≥3+ within 14 days after surgery, aqueous cell ≥2+ at 14 to ≤60 days after surgery, or aqueous cell ≥1+ at >60 days) was assessed within a 180-day period after implantation. Rates of toxic anterior segment syndrome (TASS), acute postoperative endophthalmitis, chronic postoperative endophthalmitis, and uncategorized cases of postsurgical intraocular inflammation were assessed. Ocular adverse events (AEs) and ocular adverse device effects (ADEs) were evaluated. Historical rates of postsurgical intraocular inflammation were determined from the 2011-2013 Medicare Limited Data Set files (a 5% sample of the Medicare data set representative of patients aged ≥65 years). Final safety analysis set included 3357 eyes (1792 patients; mean age, 68.6 ± 7.9 years). Postsurgical intraocular inflammation (any type) rate was 5.1 per 1000 attempted IOL implants (95% CI, 2.95, 8.10). TASS, acute postoperative endophthalmitis, and uncategorized inflammation rates were 0.6 (95% CI, 0.07, 2.15), 0.3 (95% CI, 0.01, 1.66), and 4.2 (95% CI, 2.28, 6.99) per 1000 attempted IOL implants, respectively. There were no events of chronic postoperative endophthalmitis. Ocular AEs and ADEs were reported in 17% and 1.5% of eyes, respectively. Most common ADEs were halo (0.63%) and glare (0.51%). The historical postsurgical inflammation rate from 221,519 cataract procedures was 10.3/1000 cataract surgeries, and the endophthalmitis rate was 1.2/1000 surgeries. The updated IOL manufacturing process resulted in postoperative intraocular inflammation rates that were substantially lower than the historic rate.

National Analysis of Clinical Outcomes Associated With Cirrhotic Blunt Trauma Patients Undergoing Emergency Laparotomy Versus Non-operative Management: A Propensity Case-Matched Analysis.

This study aims to evaluate clinical outcomes among severely injured trauma patients presenting with isolated blunt abdominal solid organ injuries with a pre-diagnosis of liver cirrhosis (LC) undergoing emergency laparotomy vs nonoperative management (NOM). This retrospective cohort study utilized the American College of Surgeons Trauma Quality Program Participant Use File (ACS-TQIP-PUF) dataset from 2017 to 2021. Adults (≥18years) with a pre-existing diagnosis of LC who presented with severe blunt (ISS ≥ 16) isolated solid organ abdominal injuries and underwent laparotomy or NOM were included. Outcomes of interest included in-hospital mortality, intensive care unit length of stay (ICU-LOS), and in-hospital complications such as acute renal failure and deep vein thrombosis. 929 patients were included in this analysis, with 355 undergoing laparotomy and 574 managed nonoperatively. Laparotomy patients suffered greater in-hospital mortality (n = 186, 52.3% vs n = 115, 20.0%; P < .01), required significantly more blood within 4hours (8.9 units vs 4.3 units, P < .01), and had a significantly longer ICU-LOS (10.2days vs 6.7days, P < .01). In the 1:1 propensity score matched analysis of 556 matched patients, in-hospital mortality was greater for laparotomy patients (52.3% vs 20.0%, P < .01). Laparotomy was associated with significantly higher in-hospital mortality in propensity-matched trauma patients, longer ICU-LOS, and more blood products given at 4hours compared to NOM. These findings illustrate that NOM may be a safe approach in managing severely injured trauma patients with isolated blunt abdominal solid organ injuries and a pre-diagnosis of LC.

Melody Generation using Deep Learning: Unleashing the Power of RNN and LSTM

This project aims to develop a novel approach for piano melody generation using Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models in deep learning.The suggested models will be trained on a dataset of MIDI files with piano melodies to use sequential learning capabilities and capture the complex patterns and relationships present in musical compositions. [1] The project aims to gen- erate a variety of melodies that are both musically coherent and diverse by experimenting with various network designs, hyperparameters, and training procedures. The developed tunes will be evaluated primarily on their originality, conformity to stylistic elements, and general quality. The results of this study could lead to new developments in AI-driven music composition as well as opportunities for computational creativity in the music industry.

MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Classification Tasks

This paper presents a benchmark study of MIDI-domain music classification using the mask language modeling approach of the Bidirectional Encoder Representations from Transformers (BERT). Specifically, with five public-domain datasets of single-track polyphonic piano MIDI files, we pre-train a 12-layer Transformer model using the BERT approach and fine-tune it for four downstream classification tasks. These include two note-level classification tasks---melody extraction and velocity prediction, and two sequence-level classification tasks---artist classification and emotion classification. Compared to strong recurrent neural network (RNN)-based baselines, the BERT approach does lead to higher classification accuracy, with less than 10 epochs of fine-tuning. Ablation studies further show that the pre-training remains effective even if the MIDI data of the downstream tasks are not seen during the pre-training stage, and that freezing the self-attention layers at the fine-tuning stage only slightly degrades the performance. For reproducibility, we share the weights of our pre-trained and fine-tuned models.

Fruits Leaf Disease Detection Using Convolutional Neural Network

Due to the traditional agricultural system, losses of millions of money have been loses every year. Farmers were always ready in agricultural work without risking their lives. If smart methods can be adopted in the agricultural system, the farmers will not have to suffer much damage. Using machine learning and testing with Convolutional Neural Network algorithm (mobileNet method), in this research to find out the actual accuracy, 3642 photos of apple leaves of Kaggle dataset and CSV files are used. In this paper, using Python language with the help of Jupyter notebook, Eposes has been tested 15 times to create confusion metrics. In this paper, precision, recall, f1_ score and average accuracy have been found and studied. An average accuracy of 95 percent has been obtained from the study. 95% accuracy is considered as a good result of the test using machine learning. By adopting this method, we can also give more motivation to the agricultural sector.

Assessment of the gender gap in urology industry payments: An Open Payments Program data analysis.

The Open Payments Program (OPP), established in 2013 under the Sunshine Act, mandated medical device and pharmaceutical manufacturers to submit records of financial incentives given to physicians for public availability. The study aims to characterize the gap in real general and real research payments between man and woman urologists. The study sample included all urologists in the United States who received at least one general or research payment in the OPP database from 2015 to 2021. Recipients were identified using the National Provider Identifier and National Downloadable File datasets. Payments were analyzed by geography, year, payment type, and years since graduation. Multivariable analysis on odds of being in above the median in terms of money received was done with gender as a covariate. This analysis was also completed for all academic urologists. There was a total of 15,980 urologists; 13.6% were woman, and 86.4% were man. Compared to man urologists, woman urologists were less likely to be in the top half of total payments received (odds ratio [OR] 0.62) when adjusted for other variables. When looking at academic urologists, 18.1% were woman and 81.9% were man. However, woman academic urologists were even less likely to be in the top 50% of payments received (OR 0.55). This study is the first to characterize the difference in industry payments between man and woman urologists. The results should be utilized to educate physicians and industry, in order to achieve equitable engagement and funding for woman urologists.

Automated Indonesian Text Augmentation with Web-Based Application Using Flask Framework

Text classification is one of the fundamental tasks in natural language processing (NLP). In the real world, data and resources available for text classification are limited. One of the issues with labeled data is imbalanced data. The problem of imbalanced data affects the performance and accuracy of the model because the model only focuses on data with majority labels. This impacts the model performance, which tends to classify correctly for the majority label only. Meanwhile, in some cases, it is more important for the minority label to be predicted correctly. Therefore, the measure of model accuracy cannot describe the true performance of the model. To overcome this, an oversampling approach is carried out. Text-based oversampling is known as text augmentation. However, NLP resources for the Indonesian language are still limited, especially in performing text augmentation. Therefore, this research conducts the development of a web application to augment Indonesian text automatically. The application was built using the prototype method. Users can perform augmentation automatically for the entire text in the dataset. Users can select preferred augmentation techniques and are required to upload datasets as input. The output of the application is the same dataset file as the input, with an additional column containing synthetic text augmented by the application.

High Medicaid Nursing Homes: Contextual Factors Associated with the Availability of Specialized Resources Required to Care for Obese Residents

ABSTRACT Obesity is an increasingly important concern in the delivery of high-quality nursing home care. Obese nursing home residents require specialized equipment and resources. As high Medicaid nursing homes have limited financial ability, they may lack the necessary resources to address the needs of obese residents. Moreover, there are variations in the availability of obesity-related specialized resources across these facilities. This study aims to investigate the organizational and market factors associated with the availability of obesity-related specialized resources in high-Medicaid nursing homes. Survey and secondary data sources for the study period 2017–2018 were utilized. The survey data were merged with Brown University’s Long Term Care Focus (LTCFocus), Nursing Home Compare, and Area Health Resource File datasets. The dependent variable was the composite score of obesity-related specialized resources, ranging from 0–19. An ordinary least square regression with propensity score weights (to adjust for potential survey non-response bias), along with appropriate organizational/market level control variables were used for our analysis. Our results suggest that payer-mix (>Medicare residents) and a higher proportion of obese residents were positively associated with the availability of obesity-related specialized resources. Policymakers should consider implementing incentives, such as increased Medicaid payments, to assist high Medicaid nursing homes in addressing the specific needs of obese residents.

Towards Smarter Positioning through Analyzing Raw GNSS and Multi-Sensor Data from Android Devices: A Dataset and an Open-Source Application

The state-of-the-art Android environment, available on a major market share of smartphones, provides an open playground for sensor data gathering. Moreover, the rise in new types of devices (e.g., wearables/smartwatches) is further extending the market opportunities with a variety of new sensor types. The existing implementations of biometric/medical sensors can allow the general public to directly access their health measurements, such as Electrocardiogram (ECG) or Oxygen Saturation (SpO2). This access greatly increases the possible applications of these devices with the combination of all the onboard sensors that are broadly in use nowadays. In this study, we look beyond the current state of the art into the positioning capacities of Android smart devices and wearables, with a focus on raw Global Navigation Satellite Systems (GNSS) measurements that are still mostly lacking in the research world. We develop a novel open-source Android application working in both smartphone and smartwatch environments for multi-sensor measurement data logging that also includes GNSS, an Inertial Navigation System (INS) magnetometer, and a barometer. Four smartphones and one smartwatch are used to perform surveys in different scenarios. The extraction of GNSS raw data from a wearable device has not been reported yet in the literature and no open-source app has existed so far for extracting GNSS data from wearables. Not only the developed app but also the results of these measurement surveys are provided as an open-access dataset. We start by defining our methodology and the acquisition protocol, and we dive into the structure of the dataset files. We also propose a first analysis of the data logged and evaluate the data according to several performance metrics. A discussion reviewing the capacities of smart devices for advanced positioning is proposed, as well as the current open challenges.

Exploring the Factors Influencing Traffic Accidents: An Analysis of Black Spots and Decision Tree for Injury Severity

This research aimed to examine the spatial distribution of road traffic accidents in Budapest, Hungary. The primary objective was to identify the factors associated with traffic accidents on the city's transportation network and to determine the locations of the most frequent accidents during peak and off-peak hours. A quantitative methodology was employed in this study, utilizing a dataset of recent accidents that occurred between 2019 and 2021, classified into peak and off-peak incidents. The data was analyzed using Python software and Quantum Geographic Information System (QGIS) tools for big data analytics. These programs enabled the creation of spatial maps of the study area and the identification of accident spots based on latitude and longitude information. A decision tree classification approach was used in the machine-learning method implemented with Python software. Additionally, the dataset file was uploaded to QGIS, which applied the heatmap (Kernel Density Estimation) algorithm to identify accident hotspots. The study findings revealed that the city center was the most common location for accidents overall, with peak and off-peak times, lanes, and days of the week investigated as potential contributing factors. The target variable was the number of accidents involving serious and minor injuries, which were found to be significantly associated with the identified accidents in this study.

Automated prediction of acute promyelocytic leukemia from flow cytometry data using a graph neural network pipeline.

Our study aimed to develop a machine learning (ML) model to accurately classify acute promyelocytic leukemia (APL) from other types of acute myeloid leukemia (other AML) using multicolor flow cytometry (MFC) data. Multicolor flow cytometry is used to determine immunophenotypes that serve as disease signatures for diagnosis. We used a data set of MFC files from 27 patients with APL and 41 patients with other AML, including those with uncommon immunophenotypes. Our ML pipeline involved training a graph neural network (GNN) to output graph-level labels and identifying the most crucial MFC parameters and cells for predictions using an input perturbation method. The top-performing GNN achieved 100% accuracy on the training/validation and test sets on classifying APL from other AML and used MFC parameters similarly to expert pathologists. Pipeline performance is amenable to use in a clinical decision support system, and our deep learning architecture readily enables prediction explanations. Our ML pipeline shows robust performance on predicting APL and could be used to screen for APL using MFC data. It also allowed for intuitive interrogation of the model's predictions by clinicians.

The prevalence of infertility and factors associated with infertility in Ethiopia: Analysis of Ethiopian Demographic and Health Survey (EDHS).

Despite having a high fertility rate, low-resource countries are also home to couples with infertility problems. Although many couples are suffering from the psychological impacts of infertility, its level and determinants are not adequately known. The main objective of this study is to assess the prevalence and factors associated with infertility among couples in Ethiopia using the 2016 Ethiopian Demographic and Health Survey (EDHS) data. The study employed a cross-sectional study design extracting variables from the 2016 EDHS. The study included all married or cohabitating women aged 15 to 49 years in the Couples Recode (CR) file data set. Weighted samples of 6141 respondents were analyzed. We used Stata 14 software for analyzing the data. The association of selected independent variables with primary, secondary, and total infertility was analyzed using a logistic regression model. We presented the results using an adjusted odds ratio (AOR) with a 95% confidence interval (CI) and a p-value <0.05 as a cut-off point for declaring statistical significance. The prevalence of infertility in the past 12 months was 24.2% (95% CI: 23.1-25.3%), of which the majority (90.7%) was secondary infertility. Greater than 35 years of age (AOR = 2.45, 95% CI (1.58-3.79)), rural residence (AOR = 1.06, 95% CI (1.01-1.39)), smoking (AOR = 2.29, 95% CI (1.39-3.77)), and <18.5 Body Mass Index (BMI) (AOR = 1.71, 95% CI (1.43-2.04)) were significantly associated with infertility. Conversely, infertility was less likely among women with formal education and better wealth index. Primary infertility was significantly higher among women whose partners drink alcohol (AOR = 1.55; 95% CI 1.06-2.28)) and chew khat (AOR = 1.62; 95% CI (1.12-2.36)). Secondary infertility was significantly higher among women with <18.5 BMI (AOR = 1.59, 95% CI (1.37-1.84)), >30 BMI (AOR = 1.54; 95% CI 1.01-2.35)), and <15 years of age at first birth (AOR = 1.40; 95% CI 1.15-1.69)). More than one in five couples in Ethiopia has an infertility problem. Both male and female-related factors are associated with infertility. Primary infertility was significantly higher among women whose partner chews khat and drinks alcohol. Secondary infertility was significantly associated with being underweight, obese, smoking, and young age at first birth. Hence, taking action on preventable factors is the most critical treatment approach and will improve the health status of the couples in other ways.

Closing the gap: Technology access and telehealth use among older adults in the U.S. Medicare beneficiaries

The use of digital technology offers numerous benefits for older individuals. However, failure to access technology could result in missed resources and opportunities, with some in this age group being hesitant to adopt new technology due to unfamiliarity or fear. Telehealth, as a form of digital technology, holds the potential to overcome geographic and temporal limitations, enabling socially isolated and physically homebound older adults to access a broader spectrum of healthcare options. Despite the potential advantages, the availability, acceptability, and accessibility of telehealth interventions for aging care remain unclear. This study aims to examine the impact of digital technologies on access to health and social care for older adults while identifying socioeconomic factors that may hinder access to services. We utilized the 2021 Medicare Current Beneficiary Survey COVID-19 Winter Supplement Public Use File dataset and the total sample size was 10,592 Medicare beneficiaries aged 65 years and above. Several statistical analyses, including multivariable logistic regression, were conducted. Our findings revealed that individuals from Black non-Hispanic and Hispanic racial and ethnic groups, as well as those with lower income and residing in non-metro areas, had lower odds of using technology devices and accessing the internet, This highlights the need for targeted interventions and policies to promote equitable access to digital resources and healthcare services for all seniors. Moreover, seniors who possess technology devices and have internet access are more inclined to engage with primary care providers (PCPs) who provide telehealth consultations. The study discussed future directions and limitations, providing valuable insights into the intersection of digital technology, healthcare access, and socioeconomic factors for older adults.

A WAV file dataset of bottlenose dolphin whistles, clicks, and pulse sounds during trawling interactions

Globally, interactions between fishing activities and dolphins are cause for concern due to their negative effects on both mammals and fishermen. The recording of acoustic emissions could aid in detecting the presence of dolphins in close proximity to fishing gear, elucidating their behavior, and guiding potential management measures designed to limit this harmful phenomenon. This data descriptor presents a dataset of acoustic recordings (WAV files) collected during interactions between common bottlenose dolphins (Tursiops truncatus) and fishing activities in the Adriatic Sea. This dataset is distinguished by the high complexity of its repertoire, which includes various different typologies of dolphin emission. Specifically, a group of free-ranging dolphins was found to emit frequency-modulated whistles, echolocation clicks, and burst pulse signals, including feeding buzzes. An analysis of signal quality based on the signal-to-noise ratio was conducted to validate the dataset. The signal digital files and corresponding features make this dataset suitable for studying dolphin behavior in order to gain a deeper understanding of their communication and interaction with fishing gear (trawl).

Diffraction anisotropy and paired refinement: crystal structure of H33, a protein binder to interleukin 10.

Binder H33 is a small protein binder engineered by ribosome display to bind human interleukin 10. Crystals of binder H33 display severe diffraction anisotropy. A set of data files with correction for diffraction anisotropy based on different local signal-to-noise ratios was prepared. Paired refinement was used to find the optimal anisotropic high-resolution diffraction limit of the data: 3.13-2.47 Å. The structure of binder H33 belongs to the 2% of crystal structures with the highest solvent content in the Protein Data Bank.

Evaluation of live forensic techniques, towards Salsa20-Based cryptographic ransomware mitigation

Ransomware has been established as one of the largest current threats to organisations, small businesses, governments, and individuals alike. The appearance of cryptocurrencies and the enhancement of encryption key management schemes increased the capacity of this malicious software to compromise the victim's data and demand ransom payments. The variety of ransomware families and their continued evolution make the task of detecting and mitigating these attacks extremely difficult. Current ransomware typically uses complex multi-layer hybrid encryption methods, which cannot be mitigated using conventional methods such as attacking the encryption keys directly. Recent studies have shown that when using live forensic techniques, it is possible to find the ransomware data encryption keys in the volatile memory of an infected machine while the ransomware is being executed, in a form of a side-channel attack. However, the related work in the field does not address the most recent cryptography typically now used by ransomware, including stream ciphers such as Salsa20. Related work has also not fully explored the typical use of unique keys per victim's file which is now common with current ransomware. The work described in this paper reproduces these latest cryptographic management techniques being used and explores methods for both, Salsa20 key extraction from memory, and one key per file ransomware encryption key recovery. The methods have been evaluated against recent real-world ransomware samples with various victim file data sets. The method has been shown in some cases to successfully recover over 90% of Salsa20 key and nonce pairs from volatile memory, which in turn have been used to decrypt victim files to validate the extracted pairs. This method could facilitate the recovery of victims' files without the need for paying a ransom and bypasses the complex hybrid encryption methods typically used by current ransomware. The findings from the experiments show that it is possible to use live memory forensics to extract multiple ransomware symmetric encryption keys during execution, and then use these to successfully decrypt a large percentage of the victim's encrypted files without requiring the master key. The developed method could be used to help recover from the most advanced current ransomware attack and can prove useful when developing new cryptographic ransomware mitigation techniques.

Delineating the heterogeneity of embryo preimplantation development using automated and accurate morphokinetic annotation

PurposeOur objective was to design an automated deep learning model that extracts the morphokinetic events of embryos that were recorded by time-lapse incubators. Using automated annotation, we set out to characterize the temporal heterogeneity of preimplantation development across a large number of embryos.MethodsTo perform a retrospective study, we used a dataset of video files of 67,707 embryos from four IVF clinics. A convolutional neural network (CNN) model was trained to assess the developmental states that appear in single frames from 20,253 manually-annotated embryos. Probability-weighted superposition of multiple predicted states was permitted, thus accounting for visual uncertainties. Superimposed embryo states were collapsed onto discrete series of morphokinetic events via monotonic regression of whole-embryo profiles. Unsupervised K-means clustering was applied to define subpopulations of embryos of distinctive morphokinetic profiles.ResultsWe perform automated assessment of single-frame embryo states with 97% accuracy and demonstrate whole-embryo morphokinetic annotation with R-square 0.994. High quality embryos that had been valid candidates for transfer were clustered into nine subpopulations, as characterized by distinctive developmental dynamics. Retrospective comparative analysis of transfer versus implantation rates reveals differences between embryo clusters as marked by poor synchronization of the third mitotic cell-cleavage cycle.ConclusionsBy demonstrating fully automated, accurate, and standardized morphokinetic annotation of time-lapse embryo recordings from IVF clinics, we provide practical means to overcome current limitations that hinder the implementation of morphokinetic decision-support tools within clinical IVF settings due to inter-observer and intra-observer manual annotation variations and workload constrains. Furthermore, our work provides a platform to address embryo heterogeneity using dimensionality-reduced morphokinetic descriptions of preimplantation development.

Chemical features of melanoma tumor resident TRG CDR3s associated with better survival probabilities.

We assessed the T-cell receptor gamma (TRG) recombination reads from the cancer genome atlas melanoma tumor exome files and the TRG recombination reads from an independent, melanoma exome file dataset, from the Moffitt Cancer Center. TRG complementarity determining region-3 (CDR3) amino acid (AA) sequences were assessed for chemical complementarity to cancer testis antigens, with such complementarity for FAM133A and CRISP2 associated with better survival probabilities for both datasets. These results, along with related TRG CDR3 AA chemical feature assessments provided in this report, have indicated opportunities for melanoma patient stratifications based on the recovery of TRG recombination reads from both tumor and blood samples, and the results may point towards novel, effective melanoma antigens.