arXiv subjects

Souparno Ghosh

Publications and source records attributed to Souparno Ghosh.

11 recordsLinked to original sources

arXiv2025

Benchmarking community drug response prediction models: datasets, models, tools, and metrics for cross-dataset generalization analysis

Deep learning (DL) and machine learning (ML) models have shown promise in drug response prediction (DRP), yet their ability to generalize across datasets remains an open question, raising concerns about their real-world applicability. Due to the lack of standardized benchmarking approaches, model evaluations and comparisons often rely on inconsistent datasets and evaluation criteria, making it difficult to assess true predictive capabilities. In this work, we introduce a benchmarking framework for evaluating cross-dataset prediction generalization in DRP models. Our framework incorporates five publicly available drug screening datasets, six standardized DRP models, and a scalable workflow for systematic evaluation. To assess model generalization, we introduce a set of evaluation metrics that quantify both absolute performance (e.g., predictive accuracy across datasets) and relative performance (e.g., performance drop compared to within-dataset results), enabling a more comprehensive assessment of model transferability. Our results reveal substantial performance drops when models are tested on unseen datasets, underscoring the importance of rigorous generalization assessments. While several models demonstrate relatively strong cross-dataset generalization, no single model consistently outperforms across all datasets. Furthermore, we identify CTRPv2 as the most effective source dataset for training, yielding higher generalization scores across target datasets. By sharing this standardized evaluation framework with the community, our study aims to establish a rigorous foundation for model comparison, and accelerate the development of robust DRP models for real-world applications.

cs.LG↗

arXiv2024

Assessing Reusability of Deep Learning-Based Monotherapy Drug Response Prediction Models Trained with Omics Data

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, models that can be successfully translated into clinical practice and shed light on the molecular mechanisms underlying treatment response will likely emerge from collaborative research efforts. This highlights the need for reusable and adaptable models that can be improved and tested by the wider scientific community. In this study, we present a scoring system for assessing the reusability of prediction DRP models, and apply it to 17 peer-reviewed DL-based DRP models. As part of the IMPROVE (Innovative Methodologies and New Data for Predictive Oncology Model Evaluation) project, which aims to develop methods for systematic evaluation and comparison DL models across scientific domains, we analyzed these 17 DRP models focusing on three key categories: software environment, code modularity, and data availability and preprocessing. While not the primary focus, we also attempted to reproduce key performance metrics to verify model behavior and adaptability. Our assessment of 17 DRP models reveals both strengths and shortcomings in model reusability. To promote rigorous practices and open-source sharing, we offer recommendations for developing and sharing prediction models. Following these recommendations can address many of the issues identified in this study, improving model reusability without adding significant burdens on researchers. This work offers the first comprehensive assessment of reusability and reproducibility across diverse DRP models, providing insights into current model sharing practices and promoting standards within the DRP and broader AI-enabled scientific research community.

q-bio.BM↗

arXiv2024

Efficient Normalized Conformal Prediction and Uncertainty Quantification for Anti-Cancer Drug Sensitivity Prediction with Deep Regression Forests

Deep learning models are being adopted and applied on various critical decision-making tasks, yet they are trained to provide point predictions without providing degrees of confidence. The trustworthiness of deep learning models can be increased if paired with uncertainty estimations. Conformal Prediction has emerged as a promising method to pair machine learning models with prediction intervals, allowing for a view of the model's uncertainty. However, popular uncertainty estimation methods for conformal prediction fail to provide heteroskedastic intervals that are equally accurate for all samples. In this paper, we propose a method to estimate the uncertainty of each sample by calculating the variance obtained from a Deep Regression Forest. We show that the deep regression forest variance improves the efficiency and coverage of normalized inductive conformal prediction on a drug response prediction task.

cs.LG↗

arXiv2023

A Matrix Ensemble Kalman Filter-based Multi-arm Neural Network to Adequately Approximate Deep Neural Networks

Deep Learners (DLs) are the state-of-art predictive mechanism with applications in many fields requiring complex high dimensional data processing. Although conventional DLs get trained via gradient descent with back-propagation, Kalman Filter (KF)-based techniques that do not need gradient computation have been developed to approximate DLs. We propose a multi-arm extension of a KF-based DL approximator that can mimic DL when the sample size is too small to train a multi-arm DL. The proposed Matrix Ensemble Kalman Filter-based multi-arm ANN (MEnKF-ANN) also performs explicit model stacking that becomes relevant when the training sample has an unequal-size feature set. Our proposed technique can approximate Long Short-term Memory (LSTM) Networks and attach uncertainty to the predictions obtained from these LSTMs with desirable coverage. We demonstrate how MEnKF-ANN can "adequately" approximate an LSTM network trained to classify what carbohydrate substrates are digested and utilized by a microbiome sample whose genomic sequences consist of polysaccharide utilization loci (PULs) and their encoded genes.

stat.ML↗

arXiv2022

Spatio-temporal models of infectious disease with high rates of asymptomatic transmission

The surprisingly mercurial Covid-19 pandemic has highlighted the need to not only accelerate research on infectious disease, but to also study them using novel techniques and perspectives. A major contributor to the difficulty of containing the current pandemic is due to the highly asymptomatic nature of the disease. In this investigation, we develop a modeling framework to study the spatio-temporal evolution of diseases with high rates of asymptomatic transmission, and we apply this framework to a hypothetical country with mathematically tractable geography; namely, square counties uniformly organized into a rectangle. We first derive a model for the temporal dynamics of susceptible, infected, and recovered populations, which is applied at the county level. Next we use likelihood-based parameter estimation to derive temporally varying disease transmission parameters on the state-wide level. While these two methods give us some spatial structure and show the effects of behavioral and policy changes, they miss the evolution of hot zones that have caused significant difficulties in resource allocation during the current pandemic. It is evident that the distribution of cases will not be stagnantly based on the population density, as with many other diseases, but will continuously evolve. We model this as a diffusive process where the diffusivity is spatially varying based on the population distribution, and temporally varying based on the current number of simulated asymptomatic cases. With this final addition coupled to the SIR model with temporally varying transmission parameters, we capture the evolution of "hot zones" in our hypothetical setup.

q-bio.PE↗

arXiv2021

Investigation of REFINED CNN ensemble learning for anti-cancer drug sensitivity prediction

Anti-cancer drug sensitivity prediction using deep learning models for individual cell line is a significant challenge in personalized medicine. REFINED (REpresentation of Features as Images with NEighborhood Dependencies) CNN (Convolutional Neural Network) based models have shown promising results in drug sensitivity prediction. The primary idea behind REFINED CNN is representing high dimensional vectors as compact images with spatial correlations that can benefit from convolutional neural network architectures. However, the mapping from a vector to a compact 2D image is not unique due to variations in considered distance measures and neighborhoods. In this article, we consider predictions based on ensembles built from such mappings that can improve upon the best single REFINED CNN model prediction. Results illustrated using NCI60 and NCIALMANAC databases shows that the ensemble approaches can provide significant performance improvement as compared to individual models. We further illustrate that a single mapping created from the amalgamation of the different mappings can provide performance similar to stacking ensemble but with significantly lower computational complexity.

cs.LG↗

arXiv2020

REFINED (REpresentation of Features as Images with NEighborhood Dependencies): A novel feature representation for Convolutional Neural Networks

Deep learning with Convolutional Neural Networks has shown great promise in various areas of image-based classification and enhancement but is often unsuitable for predictive modeling involving non-image based features or features without spatial correlations. We present a novel approach for representation of high dimensional feature vector in a compact image form, termed REFINED (REpresentation of Features as Images with NEighborhood Dependencies), that is conducible for convolutional neural network based deep learning. We consider the correlations between features to generate a compact representation of the features in the form of a two-dimensional image using minimization of pairwise distances similar to multi-dimensional scaling. We hypothesize that this approach enables embedded feature selection and integrated with Convolutional Neural Network based Deep Learning can produce more accurate predictions as compared to Artificial Neural Networks, Random Forests and Support Vector Regression. We illustrate the superior predictive performance of the proposed representation, as compared to existing approaches, using synthetic datasets, cell line efficacy prediction based on drug chemical descriptors for NCI60 dataset and drug sensitivity prediction based on transcriptomic data and chemical descriptors using GDSC dataset. Results illustrated on both synthetic and biological datasets shows the higher prediction accuracy of the proposed framework as compared to existing methodologies while maintaining desirable properties in terms of bias and feature extraction.

cs.LG↗

arXiv2019

Tumor ablation due to inhomogeneous -- anisotropic diffusion in generic 3-dimensional topologies

We derive a full 3-dimensional (3-D) model of inhomogeneous -- anisotropic diffusion in a tumor region coupled to a binary population model. The diffusion tensors are acquired using Diffusion Tensor Magnetic Resonance Imaging (DTI) from a patient diagnosed with glioblastoma multiform (GBM). Then we numerically simulate the full model with Finite Element Method (FEM) and produce drug concentration heat maps, apoptosis regions, and dose-response curves. Finally, predictions are made about optimal injection locations and volumes, which are presented in a form that can be employed by doctors and oncologists.

physics.med-ph↗

arXiv2018

Modeling of drug diffusion in a solid tumor leading to tumor cell death

It has been shown recently that changing the fluidic properties of a drug can improve its efficacy in ablating solid tumors. We develop a modeling framework for tumor ablation, and present the simplest possible model for drug diffusion in a spherical tumor with leaky boundaries and assuming cell death eventually leads to ablation of that cell effectively making the two quantities numerically equivalent. The death of a cell after a given exposure time depends on both the concentration of the drug and the amount of oxygen available to the cell. Higher oxygen availability leads to cell death at lower drug concentrations. It can be assumed that a minimum concentration is required for a cell to die, effectively connecting diffusion with efficacy. The concentration threshold decreases as exposure time increases, which allows us to compute dose-response curves. Furthermore, these curves can be plotted at much finer time intervals compared to that of experiments, which is used to produce a dose-threshold-response surface giving an observer a complete picture of the drug's efficacy for an individual. In addition, since the diffusion, leak coefficients, and the availability of oxygen is different for different individuals and tumors, we produce artificial replication data through bootstrapping to simulate error. While the usual data-driven model with Sigmoidal curves use 12 free parameters, our mechanistic model only has two free parameters, allowing it to be open to scrutiny rather than forcing agreement with data. Even so, the simplest model in our framework, derived here, shows close agreement with the bootstrapped curves, and reproduces well established relations, such as Haber's rule.

q-bio.CB↗

arXiv2013

Scaling Integral Projection Models for Analyzing Size Demography

Historically, matrix projection models (MPMs) have been employed to study population dynamics with regard to size, age or structure. To work with continuous traits, in the past decade, integral projection models (IPMs) have been proposed. Following the path for MPMs, currently, IPMs are handled first with a fitting stage, then with a projection stage. Model fitting has, so far, been done only with individual-level transition data. These data are used in the fitting stage to estimate the demographic functions (survival, growth, fecundity) that comprise the kernel of the IPM specification. The estimated kernel is then iterated from an initial trait distribution to obtain what is interpreted as steady state population behavior. Such projection results in inference that does not align with observed temporal distributions. This might be expected; a model for population level projection should be fitted with population level transitions.

stat.ME↗

arXiv2011

A generalized linear mixed model for longitudinal binary data with a marginal logit link function

Longitudinal studies of a binary outcome are common in the health, social, and behavioral sciences. In general, a feature of random effects logistic regression models for longitudinal binary data is that the marginal functional form, when integrated over the distribution of the random effects, is no longer of logistic form. Recently, Wang and Louis [Biometrika 90 (2003) 765--775] proposed a random intercept model in the clustered binary data setting where the marginal model has a logistic form. An acknowledged limitation of their model is that it allows only a single random effect that varies from cluster to cluster. In this paper we propose a modification of their model to handle longitudinal data, allowing separate, but correlated, random intercepts at each measurement occasion. The proposed model allows for a flexible correlation structure among the random intercepts, where the correlations can be interpreted in terms of Kendall's $τ$. For example, the marginal correlations among the repeated binary outcomes can decline with increasing time separation, while the model retains the property of having matching conditional and marginal logit link functions. Finally, the proposed method is used to analyze data from a longitudinal study designed to monitor cardiac abnormalities in children born to HIV-infected women.

stat.AP↗