Biology subjects

Saeed, F.

Publications and source records attributed to Saeed, F..

18 recordsLinked to original sources

bioRxiv2026

CViT-ESP: Lightweight Pre-trained Vision Transformers for EEG-based Epileptic Seizure Prediction

Background and Objective Epileptic seizure prediction is a critical challenge requiring the discrimination of subtle preictal physiological changes from interictal brain activity. While deep learning has shown promise in this domain, existing models often face limitations due to small EEG datasets, high computational costs for training from scratch, and a lack of patient-independent generalizability. In this paper, we present a novel framework for EEG-based seizure prediction that leverages pre-trained Vision Transformers (ViTs) through custom architectural modifications and optimized re-training strategies. Methods Our primary contributions include: [bullet]CVIT-ESP: A family of vision transformer architectures that replaces standard patch embedding layers with custom N-dimensional CNN stages to refine EEG representations. [bullet] ESPFormer: A lightweight, custom-designed transformer specifically engineered to mitigate overfitting on limited-scale EEG datasets. We identified optimal fine-tuning combinations for transformer blocks by devising a heuristic search-space reduction strategy, significantly reducing the training complexity. We validated our methods using the patient-independent MLSPred-Bench, involving 12 diverse benchmarks with varying seizure prediction horizons. Results Results demonstrate a clear progression in performance: while prior ResNet and vanilla Transformer models achieved an AUC-ROC of 69.0%, our CVIT-ESP architectures achieved the highest performance with a maximum average AUC of 76.4%. Conclusions These findings suggest that adapting pre-trained ViTs with domain-specific CNN front-ends and strategic fine-tuning offers a robust, generalizable, and resource-efficient path forward for clinical seizure prediction systems. Our code is available at: https://github.com/pcdslab/CVitEsp and https://github.com/pcdslab/ESPFormer

neuroscience↗

bioRxiv2026

ProtEnrich: Residual Multimodal Enrichment of Protein Sequence Embeddings

Protein language models effectively capture evolutionary and functional signals from sequence data but lack explicit representation of the biophysical properties that govern protein structure and dynamics. Existing multimodal approaches attempt to integrate such physical information through direct fusion, often requiring multimodal inputs at inference time and distorting the geometry of the sequence embedding space, which can disrupt the semantic organization learned from evolutionary information. Consequently, a fundamental challenge of how to incorporate structural and dynamical knowledge into sequence representations without disrupting their semantic organization, enabling sequence-based models to better capture the biophysical properties governing protein structure and function. We introduce ProtEnrich, a representation learning framework based on a residual multimodal enrichment paradigm. ProtEnrich decomposes sequence embeddings into two complementary latent subspaces, an anchor subspace that preserves sequence semantics, and an alignment subspace that encodes biophysical relationships. By converting multimodal information derived from ProstT5 and RocketSHP to a low-energy residual component, our approach injects physical representation while maintaining the original sequence embedding while preserving their original semantic geometry, avoiding the need for multimodal inputs at inference time. Across eight diverse protein foundational models trained on 550,120 SwissProt proteins with AlphaFold structures, enriched embeddings improved zero-shot remote homology retrieval, increasing Precision@10 and MRR by up to 0.13 and 0.11, respectively. Downstream performance also improved on structure-dependent tasks, reducing fluorescence prediction error by up to 16% and increasing metal ion binding AUCROC by up to 2.4 points, while requiring only sequence input at inference. Source code is available at https://github.com/pcdslab/ProtEnrich, pretrained models and datasets are available at https://huggingface.co/collections/SaeedLab/protenrich.

bioinformatics↗

bioRxiv2026

BindScreen: Protein-Centric Contrastive Learning for Sequence-Based Virtual Screening

Virtual screening ranks candidate molecules against a protein target. Sequence-based deep learning avoids dockings structural requirements, but pair-based models need one forward pass per protein-molecule pair and scale poorly to large libraries. Dual-encoder contrastive models remove that bottleneck, yet standard CLIP training assumes a symmetric, one-to-one correspondence, whereas protein-molecule binding is asymmetric and many-to-many. We present Bind-Screen, a sequence-only dual-encoder screening model, and show that the decisive design choice is not the contrastive loss but how the batch is built. BindScreen combines a protein-centric batch construction and an asymmetric multi-positive InfoNCE loss. A factorial ablation separates the two contributions: the loss alone degrades performance under standard CLIP batching, the protein-centric batch alone recovers most of the gain, and the combination performs best. The effect is encoder-agnostic across eight protein language models spanning four architectural families. By decoupling protein count from molecule count per batch, BindScreen reaches higher validation BEDROC in 86 hours than standard CLIP reaches in 460 hours, and needs about seven times fewer forward passes to screen LIT-PCBA than pair-based models. The source code, pretrained checkpoints, and datasets are publicly available at https://github.com/pcdslab/BindScreen and https://huggingface.co/collections/SaeedLab/bindscreen

bioinformatics↗

bioRxiv2026

A Machine Learning and Benchmarking Approach for Molecular Formula Assignment of Ultra High-Resolution Mass Spectrometry Data from Complex Mixtures

A machine learning approach to molecular formula assignment is crucial for unlocking the full potential of ultra-high resolution mass spectrometry (UHRMS) when analyzing complex mixtures. By combining data-driven models with rigorous benchmarking, the accuracy, consistency, and speed in identifying plausible molecular formulas from vast spectral datasets can be improved. Compared with traditional de novo methods that rely heavily on rule-based heuristics, and manual parameter tuning, machine learning approaches can capture complex patterns in data and adapt more readily to diverse sample types. In this paper, we describe the application of a machine learning methods using the k-nearest neighbors (KNN) algorithm trained on curated chemical formula datasets of UHRMS analysis of dissolved organic matter (DOM) covering the saline river continuum and tropical wet/dry season variability. The influence of the mass accuracy (training set with 0.15-1ppm) was evaluated on a blind test set of DOMs of different geographical origins. A Decision Tree Regressor (DTR) and Random Forest Regressor (RFR) based on mass accuracy (<1ppm) was used. Results from our ML models exhibit 43% more formulas annotated than traditional methods (5796 vs 4047), Model-Synthetic achieved 99.9% assignment rate and annotated/assigned 2x more formulas (8,268 vs 4047). DTR and RFR achieved formula-level accuracies (FA) of 86.5% and 60.4%, respectively. Overall, results show an increase in formula assignment when compared with traditional methods. This ultimately enables more reliable characterization of complex natural and engineered systems, supporting advances in fields such as environmental science, metabolomics, and petroleomics. Furthermore, the novel data set produced for this study is made publicly available, establishing an initial benchmark for molecular formula assignment in UHRMS using machine learning. The dataset and code are publicly available at: https://github.com/pcdslab/dom-formula-assignment-using-ml CCS CONCEPTSComputing methodologies [->] Machine Learning [->] Learning paradigms [->] Supervised Learning

bioinformatics↗

bioRxiv2026

TITAN-BBB: Predicting BBB Permeability using Multi-Modal Deep-Learning Models

Computational prediction of blood-brain barrier (BBB) permeability has emerged as a vital alternative to traditional experimental assays, which are often resource-intensive and low-throughput to meet the demands of early-stage drug discovery. While early machine learning approaches have shown promise, integration of traditional chemical descriptors with deep learning embeddings remains an underexplored frontier. In this paper, we introduce TITAN-BBB, a multi-modal deep-learning architecture that utilizes tabular, image, and text-based features and combines them using attention mechanisms. To evaluate, we aggregated multiple literature sources to create the largest BBB permeability dataset to date, enabling robust training for both classification and regression tasks. Our results demonstrate that TITAN-BBB achieves 86.5% of balanced accuracy on classification tasks and 0.436 of mean absolute error for regression, outperforming the state-of-the-art by 3.1 percentage points in balanced accuracy and reducing the regression error by 20%. Our approach also outperforms state-of-the-art models in both classification and regression performance, demonstrating the benefits of combining deep and domain-specific representations. The source code is publicly available at https://github.com/pcdslab/TITAN-BBB. The inference-ready model is hosted on Hugging Face at https://huggingface.co/SaeedLab/TITAN-BBB, and the aggregated BBB permeability datasets are available at https://huggingface.co/datasets/SaeedLab/BBBP.

bioinformatics↗

bioRxiv2026

MolDeBERTa: Foundational Model for Physicochemical and Structural-Informed Molecular Representation Learning

Foundational models that learn the "language" of molecules are essential for accelerating material and drug discovery. These self-learning models can be trained on large collections of unlabelled molecules, enabling applications such as property prediction, molecule design, and screening for specific functions. However, existing molecular language models rely on masked language modeling, a generic token-level objective that is agnostic to physico-chemical and substructure molecular properties. Here we introduce MolDeBERTa, a chemistry-informed self-supervised molecular encoder built upon the DeBERTaV2 architecture with byte-level Byte-Pair Encoding (BPE) tokenization. MolDeBERTa is pre-trained on up to 123 million SMILES from PubChem using three novel pretraining objectives designed to inject strong inductive biases for molecular properties and substructure similarity directly into the latent space. The model is systematically investigated across three architectural scales, two dataset sizes, and five distinct pretraining objectives, of which three are novel and two are adapted from prior work. When evaluated on 9 MoleculeNet benchmarks, MolDeBERTa achieves the best overall performance on 4 out of 9 tasks and outperforms SMILES-based encoders on 7 out of 9 tasks, with up to a 16% reduction in regression error, and improvements of up to 2.2 ROC-AUC points on classification tasks. The source code, pretrained checkpoints, and datasets are publicly available at https://github.com/pcdslab/MolDeBERTa and https://huggingface.co/collections/SaeedLab/moldeberta. CCS ConceptsO_LIComputing methodologies [->] Neural networks; Natural language processing; Learning paradigms. C_LI

bioinformatics↗

bioRxiv2026

FiCOPS: Hardware/Software Co-Design of FPGA Computational Framework for Mass Spectrometry-Based Peptide Database Search

Improving the speed and efficiency of database search algorithms that deduce peptides from mass spectrometry (MS) data has been an active area of research for more than three decades. The significance of the need for faster database search methods has rapidly increased due to the growing interest in studying non-model organisms, meta-proteomics, and proteogenomic data, which are notorious for their enormous search space. Poor scalability of serial algorithms with the growing size of the database and increasing parameters of post-translational modifications is a widely recognized problem. While high-performance computing techniques can be used on supercomputing machines, the need for real-time, on-the-instrument solutions necessitates the development of an efficient sytem-on-chip that optimizes design constraints such as cost, performance, and power of the system. To show case that such a system can work, we present an FPGA-based computational framework called FiCOPS to accelerate database search using a hardware/software co-design methodology. First, we theoretically analyze the database-search algorithm (closed-search) to reveal opportunities for parallelism and uncover computational bottlenecks. We then design an FPGA-based architectural template to exploit parallelism inherent in the search workload. We also formulate an analytical performance model for the architecture template to perform rapid design space exploration and find a near-optimal accelerator configuration. Finally, we implement our design on the Intel Stratix 10 FPGA platform and evaluate it using real-world datasets. Our experiments demonstrate that FiCOPS achieves 3.5 x speed-up over existing CPU solutions and 3x and 5x reduction in power consumption compared to existing CPU and GPU solutions.

bioinformatics↗

bioRxiv2025

Habenula alterations in resting state functional connectivity among autistic individuals

BackgroundThe reward-based theoretical framework of autism suggests that altered reward circuitry contributes to core symptoms. Recent prior research has revealed autism-related structural alterations in the habenula, a small epithalamic structure associated with motivation and emotion; however, potential alterations in functional connectivity (FC) remain unexplored. MethodsAnatomical and resting state functional magnetic resonance imaging (rs-fMRI) data were accessed for 1,479 participants (N=661 autism; agem: 16.68{+/-}8.23 years) in the Autism Brain Imaging Data Exchange (ABIDE). To investigate habenula alterations, we conducted a whole-brain resting state FC analysis using manually delineated subject-specific seeds, followed by regression analyses to explore age and brain-behavior interactions. ResultsAcross the entire sample, extensive habenula connectivity was observed within the midbrain dopaminergic reward system. Compared to neurotypical (NT) controls, autistic participants exhibited significantly increased habenular connectivity with the bilateral middle and superior temporal gyri. From childhood to early adulthood, autistic adolescents displayed an accelerated developmental habenula FC trajectory than NTs with the cingulate gyrus. Between groups, habenula hyperconnectivity was inversely associated with behavioral scores for social motivation and communication. ConclusionsThis study provides novel evidence of habenula connectivity alterations in autism, highlighting atypical FC with sensory processing regions. Further findings suggest that habenula circuitry develops differently among autistic adolescents, with links between habenula hyperconnectivity and social behaviors. Taken together, these results contribute to emerging evidence that the dopaminergic reward system may play a critical role in the pathophysiology of autism.

neuroscience↗

bioRxiv2024

Identifying Alzheimer's disease-associated genes using PhenoGeneRanker

Alzheimers disease (AD) is a neurogenerative disease that affects millions worldwide with no effective treatment. Several studies have been conducted to decipher to genomic underpinnings of AD. Due to its complex nature, many genes have been found to be associated with AD. Despite these findings, the pathophysiology of the disease is still elusive. To discover new putative AD-associated genes, in this study, we integrated multimodal gene and phenotype datasets of AD using network biology methods to prioritize potential AD-related genes. We constructed a multiplex heterogeneous network composed of patient and gene similarity networks utilizing phenotypic and omics datasets of AD patients from the Alzheimers Disease Neuroimaging Initiative (ADNI) database. We applied PhenoGeneRanker to traverse this network to discover potential AD-associated genes. To assess the impact of each network layer and seed gene, we also run PhenoGeneRanker on different variants of the network and seed genes. Our results showed that top-ranked genes captured several known AD-related genes and were enriched in Gene Ontology (GO) terms related to AD. We also observed that several top-ranked genes that are not in AD-associated gene list had literature supporting their potential relevance to AD.

bioinformatics↗

bioRxiv2024

Utilizing Pretrained Vision Transformers and LargeLanguage Models for Epileptic Seizure Prediction

Repeated unprovoked seizures is a major source of concern for patients suffering from epilepsy. Predicting seizures before they occur is of interest to both machine-learning scientists as well as clinicians, and is an active area of research. The variability of EEG sensors, type of seizures, and specialized knowledge required for annotating the data complicates the large-scale annotation process essential for supervised predictive models. To address these challenges, we propose the use of Vision Transformers (ViTs) and Large Language Models (LLMs) that were originally trained on publicly available image or text data. Our work leverages these pre-trained models by refining the input, embedding, and classification layers in a minimalistic fashion to predict seizures. Our results demonstrate that LLMs outperforms the ViTs in patient-independent seizure prediction achieving a sensitivity of 79.02% which is 8% higher compared to ViTs and about 12% higher compared to a custom-designed ResNet-based model. Our work demonstrates the successful feasibility of pre-trained models for seizure prediction with its potential for improving the quality of life of people with epilepsy. Our code and related materials are available open-source at: https://github.com/pcdslab/UtilLLM_EPS/

bioinformatics↗

bioRxiv2024

Predicting peptide properties from mass spectrometry data using deep attention-based multitask network and uncertainty quantification

Database search algorithms reduce the number of potential candidate peptides against which scoring needs to be performed using a single (i.e. mass) property for filtering. While useful, filtering based on one property may lead to exclusion of non-abundant spectra and uncharacterized peptides - potentially exacerbating the streetlight effect. Here we present ProteoRift, a novel attention and multitask deep-network, which can predict multiple peptide properties (length, missed cleavages, and modification status) directly from spectra. We demonstrate that ProteoRift can predict these properties with up to 97% accuracy resulting in search-space reduction by more than 90%. As a result, our end-to-end pipeline is shown to exhibit 8x to 12x speedups with peptide deduction accuracy comparable to algorithmic techniques. We also formulate two uncertainty estimation metrics, which can distinguish between in-distribution and out-of-distribution data (ROC-AUC 0.99) and predict high-scoring mass spectra against correct peptide (ROC-AUC 0.94). These models and metrics are integrated in an end-to-end ML pipeline available at https://github.com/pcdslab/ProteoRift.

bioinformatics↗

bioRxiv2024

MLSPred-Bench: ML-Ready Benchmark LeveragingSeizure Detection EEG data for Predictive Models

Predicting epileptic seizures is a significantly challenging task as compared to detection. While electroen-cephalography (EEG) data annotated for detection is available from multiple repositories, they cannot readily be used for predictive modeling. In this paper, we designed and developed a strategy that can be used for converting any EEG big data annotated for detection into ML-ready data suitable for prediction. The generalizability of our strategy is demonstrated by executing it on Temple University Seizure (TUSZ) corpus which is annotated for seizure detection. This execution results in 12 ML-ready datasets, collectively called MLSPred-Bench benchmark, which constitutes data for training, validating and testing seizure prediction models. Our strategy uses different variations of seizure prediction horizon (SPH) and the seizure occurrence period (SOP) to make more than 150GB of ML-ready data. To illustrate that the generated data can be used for predictive modeling, we executed an ML model on all the benchmarks which resulted in variable performances when compared with the original model and its performance. We expect that our strategy can be used as a general method to transform seizure detection EEG big data into ML-ready datasets useful for seizure prediction. Our code and related materials will be made available at https://github.com/pcdslab/MLSPred-Bench.

bioinformatics↗

bioRxiv2023

PVTAD: ALZHEIMERS DISEASE DIAGNOSIS USING PYRAMID VISION TRANSFORMER APPLIED TO WHITE MATTER OF T1-WEIGHTED STRUCTURAL MRI DATA

Alzheimers disease (AD) is a neurodegenerative disorder, and timely diagnosis is crucial for early interventions. AD is known to have disruptive local and global brain neural connections that may be instrumental in understanding and extracting specific biomarkers. Previous machine-learning approaches are mostly based on convolutional neural network (CNN) and standard vision transformer (ViT) models which may not sufficiently capture the multidimensional local and global patterns that may be indicative of AD. Therefore, in this paper, we propose a novel approach called PVTAD to classify AD and cognitively normal (CN) cases using pretrained pyramid vision transformer (PVT) and white matter (WM) of T1-weighted structural MRI (sMRI) data. Our approach combines the advantages of CNN and standard ViT to extract both local and global features indicative of AD from the WM coronal middle slices. We performed experiments on subjects with T1-weighed MPRAGE sMRI scans from the ADNI dataset. Our results demonstrate that the PVTAD achieves an average accuracy of 97.7% and F1-score of 97.6%, outperforming the single and parallel CNN and standard ViT architectures based on sMRI data for AD vs. CN classification.

bioinformatics↗

bioRxiv2023

DEVELOPMENT AND EVALUATION OF COATED RICOTTA CHEESE WITH WHEY PROTEIN AND CLOVE OIL

Cheese, oldest dairy product which is used to preserve the nutrients of milk for long time. It is available in different shapes, sizes, flavors and textures. Ricotta is fresh soft cheese, is prepared through coagulating the whey proteins. It is a value-added product manufactured from cheese whey. Microbial spoiling occurs as a result of unmanaged conditions, resulting in the unfavorable changes in odor, flavor, and texture. That leads to food poisoning when infected food is consumed. Natural preservatives are preferred by consumers over synthetic preservatives since they are safer and extend the shelf life of food goods. Synthetic preservatives are poisonous and have negative health consequences. Edible coatings are biodegradable, natural films that can improve the products safety, quality, and nutritional content until it is consumed. This research was carried out to analyse the effect of whey protein and clove essential oil on the shelf life of ricotta cheese due to their excellent gas barrier properties, antioxidant and antimicrobial properties. Different concentrations of clove oil (0.1, 0.2, 0.3 %) are incorporated in whey protein coating solution (2.5,5,7.5%). The overall findings for all groups showed that there was gradual decrease in acidity and moisture content. Therefore, sample TRC3 treated with 0.75 % whey protein and 0.3% clove oil showed significant results (P<0.05). They showed less microbial count, increased fat and protein value. But it also had great impact on sensory analysis such as on color, texture, aroma while it showed significant overall acceptability due to high clove oil and whey protein concentrations. Hence, this study showed significant effect on shelf life of ricotta cheese and its shelf life increased from 7 to 21 days.

microbiology↗

bioRxiv2023

PPAD: A deep learning architecture to predict progression of Alzheimer's disease

Alzheimers disease (AD) is a neurodegenerative disease that affects millions of people worldwide. Mild cognitive impairment (MCI) is an intermediary stage between cognitively normal (CN) state and AD. Not all people who have MCI convert to AD. The diagnosis of AD is made after significant symptoms of dementia such as short-term memory loss are already present. Since AD is currently an irreversible disease, diagnosis at the onset of disease brings a huge burden on patients, their caregivers, and the healthcare sector. Thus, there is a crucial need to develop methods for the early prediction AD for patients who have MCI. Recurrent Neural Networks (RNN) have been successfully used to handle Electronic Health Records (EHR) for predicting conversion from MCI to AD. However, RNN ignores irregular time intervals between successive events which occurs common in EHR data. In this study, we propose two deep learning architectures based on RNN, namely Predicting Progression of Alzheimers Disease (PPAD) and PPAD-Autoencoder (PPAD-AE). PPAD and PPAD-AE are designed for early predicting conversion from MCI to AD at the next visit and multiple visits ahead for patients, respectively. To minimize the effect of the irregular time intervals between visits, we propose using age in each visit as an indicator of time change between successive visits. Our experimental results conducted on Alzheimers Disease Neuroimaging Initiative (ADNI) and National Alzheimers Coordinating Center (NACC) datasets showed that our proposed models outperformed all baseline models for most prediction scenarios in terms of F2 and sensitivity. We also observed that the age feature was one of top features and was able to address irregular time interval problem.

bioinformatics↗

bioRxiv2019

SLM-Transform: A Method for Memory-Efficient Indexing of Spectra for Database Search in LC-MS/MS Proteomics

The most commonly used strategy for peptide identification in shotgun LC-MS/MS proteomics involves searching of MS/MS data against an in-silico digested protein sequence database. Typically, the digested peptide sequences are indexed into the memory to allow faster search times. However, subjecting a database to post-translational modifications (PTMs) during digestion results in an exponential increase in the number of peptides and therefore memory consumption. This limits the usage of existing fragment-ion based open-search algorithms for databases with several PTMs. In this paper, we propose a novel fragment-ion indexing technique which is analogous to suffix array transformation and allows constant time querying of indexed ions. We extend our transformation method, called SLM-Transform, by constructing ion buckets that allow querying of all indexed ions by mass by only storing information on distribution of ion-frequencies within buckets. The stored information is used with a regression technique to locate the position of ions in constant time. Moreover, the number of theoretical b- and y-ions generated and indexed for each theoretical spectrum are limited. Our results show that SLM-Transform allows indexing of up to 4x peptides than other leading fragment-ion based database search tools within the same memory constraints. We show that SLM-Transform based index allows indexing of over 83 million peptides within 26GB RAM as compared to 80GB required by MSFragger. Finally, we show the constant ion retrieval time for SLM-Transform based index allowing ultrafast peptide search speeds. Source code will be made available at: https://github.com/pcdslab/slmindex

bioinformatics↗

bioRxiv2018

MaSS-Simulator: A highly configurable MS/MS simulator for generating test datasets for big data algorithms.

Mass Spectrometry (MS) based proteomics has become an essential tool in the study of proteins. The big data from MS machines has led to the development of novel serial and parallel algorithmic tools. However, the absence of data benchmarks and ground truth makes the algorithmic integrity testing and reproducibility a challenging problem. To this end, we present MaSS-Simulator, which is an easy to use simulator and can be configured to generate MS/MS datasets for a wide variety of conditions with known ground truths. MaSS-Simulator offers a large number of configuration options to simulate control datasets with desired properties thus enabling rigorous and large scale algorithmic testing. We assessed 8,031 spectra generated by MaSS-Simulator by comparing them against the experimentally generated spectra of same peptides. Our results showed that MaSS-Simulator generated spectra were very close to the real-experimental spectra and had a relative-error distribution centered around 25%. In contrast the theoretical spectra for same peptides had relative-error distribution centered around 150%. Source code, executables and a user manual can be downloaded from https://github.com/pcdslab/MaSS-Simulator

systems biology↗

bioRxiv2017

Estrogen and Soy Isoflavonoids Decrease Sensitivity of Medulloblastoma and Central Nervous System Primitive Neuroectodermal Tumor Cells to Chemotherapeutic Cytotoxicity

BackgroundOur previous studies demonstrated that growth and migration of medulloblastoma (MB), the most common malignant brain tumor in children, are stimulated by 17{beta}-estradiol. The growth stimulating effects of estrogens are mediated through ER{beta} and insulin-like growth factor 1 signaling to inhibit caspase 3 activity and reduce tumor cell apoptosis. The objective of this study was to determine whether estrogens decreased sensitivity of MB cells to cytotoxic actions of chemotherapeutic drugs.\n\nMethodsUsing in vitro cell viability and clonogenic survival assays, concentration response analysis was used to determine whether the cytoprotective effects of estradiol protected human D283 Med MB cells from the cytotoxic actions of the MB chemotherapeutic drugs cisplatin, vincristine, or lomustine. Additional experiments were done to determine whether the ER antagonist fulvestrant or the selective ER modulator tamoxifen blocked the cytoprotective actions of estradiol. ER-selective agonists and antagonists were used to define receptor specificity, and the impacts of the soy-derived phytoestrogens genistein, daidzein, and s-equol on chemosensitivity were evaluated.\n\nResultsIn D283 Med cells the presence of 10 nM estradiol increased the IC50 for cisplatin-induced inhibition of viability 2-fold from ~5 M to >10 M. In clonogenic survival assays estradiol decreased the chemosensitivity of D283 Med exposed to cisplatin, lomustine and vincristine. The ER{beta} selective agonist DPN and low physiological concentrations of the soy-derived phytoestrogens genistein, daidzein, and s-equol also decreased sensitivity of D283 Med cells to cisplatin. The protective effects of estradiol were blocked by the antiestrogens 4-hydroxytamoxifen, fulvestrant (ICI 182,780) and the ER{beta} selective antagonist PPHTP. Whereas estradiol also decreased chemosensitivity of PFSK1 cells, estradiol increased sensitivity of Daoy cell to cisplatin, suggesting that ER{beta} mediated effects may vary in different subtypes of MB.\n\nConclusionsThese findings demonstrate that E2 and environmental estrogens decrease sensitivity of MB to cytotoxic chemotherapeutics, and that ER{beta} selective and non-selective inhibition of estrogen receptor activity blocks these cytoprotective actions. These findings support the therapeutic potential of antiestrogen adjuvant therapies for MB, and findings that soy phytoestrogens also decrease sensitivity of MB cells to cytotoxic chemotherapeutics suggest that decreased exposure to environmental estrogens may benefit MB patient responses to chemotherapy.

pharmacology and toxicology↗