A5029563560- Computational Drug Discovery Methods
- Cutaneous Melanoma Detection and Management
- Optical Coherence Tomography Applications
- Protein Structure and Dynamics
- Analytical Chemistry and Chromatography
- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Machine Learning in Materials Science
- Statistical Methods in Clinical Trials
- Biosensors and Analytical Detection
- Machine Learning and Algorithms
- Pharmacogenetics and Drug Metabolism
- Plasma Applications and Diagnostics
- Metabolomics and Mass Spectrometry Studies
- Gold and Silver Nanoparticles Synthesis and Applications
- Skin Protection and Aging
- Cancer Genomics and Diagnostics
- Radiomics and Machine Learning in Medical Imaging
- vaccines and immunoinformatics approaches
- Medical Coding and Health Information
- Nonmelanoma Skin Cancer Studies
- Advanced biosensing and bioanalysis techniques
- Bluetooth and Wireless Communication Technologies
- Plasma Diagnostics and Applications
- Photoacoustic and Ultrasonic Imaging
Argonne National Laboratory
2023-2025
College Station Medical Center
2024
Texas A&M University
2020-2022
Indian Institute of Technology Madras
2016
It is well-known that cancers of the same histology type can respond differently to a treatment. Thus, computational drug response prediction paramount importance for both preclinical screening studies and clinical treatment design. To build models, data need be generated through experiments used as input train models. In this study, we investigate various active learning strategies selecting generate purposes (1) improving performance models built on (2) identifying effective treatments....
Abstract The rapid evolution of machine learning has led to a proliferation sophisticated models for predicting therapeutic responses in cancer. While many these show promise research, standards clinical evaluation and adoption are lacking. Here, we propose seven hallmarks by which predictive oncology can be assessed compared. These Data Relevance Actionability, Expressive Architecture, Standardized Benchmarking, Generalizability, Interpretability, Accessibility Reproducibility, Fairness....
Abstract Drug response prediction (DRP) methods tackle the complex task of associating effectiveness small molecules with specific genetic makeup patient. Anti-cancer DRP is a particularly challenging requiring costly experiments as underlying pathogenic mechanisms are broad and associated multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving path various machine learning models that attempt reason over data...
Abstract Anti-cancer drug response prediction is of paramount importance to development and patient treatment design. However, publicly available screening datasets on cell lines patient-derived organoids or xenografts contain highly unbalanced information with most experiments corresponding non-responsive tumor combinations. While previous research explored augmenting gene expression for cancer type classification, we target a more challenging problem - guided generation the responder...
Every year more than 5.4 million new cases of skin cancer are reported in the US. Melanoma is most lethal type with only 5% occurrence rate, but accounts for over 75% all deaths. Non-melanoma cancer, especially basal cell carcinoma (BCC) commonly occurring and often curable that affects 3 people causes about 2000 deaths US annually. The current diagnosis involves visual inspection, followed by biopsy lesions. major drawbacks this practice include difficulty border detection causing...
There is no clinical tool available to primary care physicians or dermatologists that could provide objective identification of suspicious skin cancer lesions. Multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy enables label-free biochemical and metabolic This study investigated the use pixel-level maFLIM features for discrimination malignant from visually similar benign pigmented Clinical images were acquired 60 lesions before undergoing a biopsy examination. Random forest...
Cancer is a heterogeneous disease in that tumors of the same histology type can respond differently to treatment. Anti-cancer drug response prediction paramount importance for both development and patient treatment design. Although various computational methods data have been used develop models, it remains challenging problem due complexities cancer mechanisms cancer-drug interactions. To better characterize interaction between drugs, we investigate feasibility integrating computationally...
Accurate early diagnosis of malignant skin lesions is critical in providing adequate and timely treatment; unfortunately, initial clinical evaluation similar-looking benign can result missed unnecessary biopsy ones.To develop validate a label-free objective image-guided strategy for the suspicious pigmented based on multispectral autofluorescence lifetime imaging (maFLIM) dermoscopy.We tested hypothesis that maFLIM-derived global features be used machine-learning (ML) models to discriminate...
This work studies a particular setting for regression problems – tasks with complex combinatorial data space where samples can be divided into distinct groups. Anti-cancer drug response prediction is perfect example of this setting, in which each sample includes cancer biological features and chemical information. Many existing works pan-drug pan-cancer modeling treat different combinations drugs cancers as individual samples. A potential problem these that model may heavily influenced...
Drug response prediction (DRP) methods tackle the complex task of associating effectiveness small molecules with specific genetic makeup patient. Anti-cancer DRP is a particularly challenging requiring costly exper-iments as underlying pathogenic mechanisms are broad and associated multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving path various machine learning (ML) models that attempt reason over data space...
Human cancers present a significant public health challenge and require the discovery of novel drugs through translational research. Transcriptomics profiling data that describes molecular activities in tumors cancer cell lines are widely utilized for predicting anti-cancer drug responses. However, existing AI models face challenges due to noise transcriptomics lack biological interpretability. To overcome these limitations, we introduce VETE (Variational Explanatory Encoder), neural network...
Cancer drug response prediction (DRP) models present a promising approach towards precision oncology, tailoring treatments to individual patient profiles. While deep learning (DL) methods have shown great potential in this area, that can be successfully translated into clinical practice and shed light on the molecular mechanisms underlying treatment will likely emerge from collaborative research efforts. This highlights need for reusable adaptable improved tested by wider scientific...
In this study, gold nanoparticles and thin film coated U-bent fiber optic probes were compared for SERS based immunobiosensing using direct sandwich assays with the help of Raman labeled conjugated antibodies.
Melanoma is the most aggressive type of skin cancer with an estimated 106,110 new cases in US 2021. The 5-year survival rate patients early-stage melanoma ~99%; however, ~13% are diagnosed lesions already at intermediate or advance stages, associated a ~66% and ~27% respectively. current diagnosis technique involving visual inspection biopsy often fail to visually distinguish clinically similar lesions; particular, can be mistaken for benign lesion pigmented seborrheic keratosis (pSK). In...
Abstract Predictive modeling holds great promise for improving personalized cancer treatment and efficiency of drug development. In recent years, deep learning (DL) has been extensively explored response prediction (DRP), outperforming classical machine in generalization to new data. Despite the considerable interest DRP, no agreed-upon methodology evaluating comparing diverse DL models yet exists. Existing papers generally demonstrate performance proposed using cross-validation within a...
Informed selection of drug candidates for laboratory experimentation provides an efficient means identifying suitable anti-cancer treatments. The advancement artificial intelligence has led to the development computational models predict cancer cell line response treatment. It is important analyze false positive rate (FPR) models, increase number effective treatments identified and minimize unnecessary experimentation. Such analysis will also aid in drugs or types that require more data...