Biology subjects

Mall, R.

Publications and source records attributed to Mall, R..

12 recordsLinked to original sources

bioRxiv2026

Methylation-Guided Stratification of Colorectal Cancer Reveals Immune Subtypes with Distinct Clinical Outcomes

BackgroundAberrant DNA methylation is a hallmark of colorectal cancer (CRC). Yet, how DNA methylation is linked to transcriptional states, immune programs, and tissue resident microbiome within the same tumors has not been systematically analyzed. MethodsWe profiled genome-wide DNA methylation (Illumina MethylationEPIC) in 182 colon tumors and 76 adjacent normals from AC-ICAM, and integrated with matched transcriptomes, whole exome, microbiome, and clinical data. Tumor-specific methylation, promoter methylation-expression links, microbiome associations, and survival were analyzed and validated in TCGA-COAD. ResultsTumor and normal tissues exhibited distinct DNA methylation patterns, reflecting widespread epigenetic alterations in cancer. Pathway analysis identified two major tumor pathways regulated by DNA methylation. The first involved extracellular signaling and adhesion genes, with higher methylation linked to increased proliferation and lower immune infiltration. Similarly, higher tumor methylation in nitric oxide signaling was associated with reduced adaptive immune activity and interestingly, influenced immune-related survival. These findings were also validated in the TCGA-COAD cohort. An inverse methylation-expression pattern implicated modifications of TCR signaling in naive CD8, and interferon-/{beta} signaling which were hypermethylated and hypomethylated in tumors compared to normal, respectively. Combining methylation and microbiome revealed connections between Akkermansia muciniphila and TGF-{beta} and Prevotella nigrescens with MAPK signaling pathways. Finally, a methylation-based model using 43 promoters CpGs successfully identified patients with different survival outcomes, underscoring the clinical relevance of these epigenetic alterations in colon cancer. ConclusionDNA methylation shapes the molecular and immune landscape of colon cancer, altering signaling pathways and immune programs, interacting with the microbiome, and impacting patients survival.

cancer biology↗

bioRxiv2025

PRESTIGE-ST: Patch Resolution and Encoder STrategies for Inference of Gene Expression from Spatial Transcriptomics

Spatial Transcriptomics (ST) integrates histology with spatially resolved gene expression, offering rich insights into tissue architecture and function. However, its clinical and large-scale deployment is hindered by high costs, technical complexity, and limited accessibility. To address this, computational pathology methods have emerged to predict gene expression directly from histology images, typically framing the task as a multi-output regression problem mapping image patches to gene expression profiles. While several Convolutional Neural Network (CNN) models have been proposed, little is known about how performance is influenced by (a) the number of trainable parameters and (b) the patch size used for prediction. Moreover, existing studies rely primarily on quantitative metrics and overlook biological relevance of predictions. In this study, we systematically evaluated multiple convolution based models (including a Vision Transformer (ViT) model) with different patch sizes on the Xenium based Autoimmune Machine Learning Challenge (AMLC) dataset. We assessed model performance on both globally expressed genes and subsets enriched for immune or disease associated pathways. Our findings reveal that compact CNNs trained on larger patches outperform deeper models, offering superior accuracy in predicting gene expression, especially for biologically important genes. These insights provide practical guidance for designing efficient and biologically meaningful models in the emerging field of image-based gene expression prediction. CCS CONCEPTSComputing methodologies [->] Computer vision; Neural networks; * Applied computing [->] Computational genomics; Imaging.

pathology↗

bioRxiv2024

Benchmarking Protein Language Models for Protein Crystallization

The problem of protein structure determination is usually solved by X-ray crystallography. Several in silico deep learning methods have been developed to overcome the high attrition rate, cost of experiments and extensive trial-and-error settings, for the predicting the crystallization propensities of proteins based on their sequences. In this work, we benchmark the power of open protein language models (PLMs) through the TRILL platform, a bespoke framework democratizing the usage of PLMs for the task of predicting crystallization propensities of proteins. By comparing LightGBM / XGBoost classifiers built on the embedding representations learned by different PLMs, such as ESM2, Ankh, ProtT5-XL, ProstT5, with the performance of state-of-the-art sequence-based methods like DeepCrystal, ATTCrys and CLPred, we identify the most effective methods for predicting crystallization outcomes. The LightGBM classifiers utilizing embeddings from ESM2 model with 30 and 36 transformer layers and 150 and 3, 000 million parameters respectively have performance gains by 3 - 5% then all compared models for various evaluation metrics, including AUPR (Area Under Precision-Recall Curve), AUC (Area Under the Receiver Operating Characteristic Curve), and F1 score on independent test sets. Furthermore, we fine-tune the ProtGPT2 model available via TRILL to generate crystallizable proteins. Starting with 3, 000 generated proteins and through a step of filtration processes including consensus of all open PLM-based classifiers, sequence identity through CD-HIT, secondary structure compatibility, aggregation screening, homology search and foldability evaluation, we identified a set of 5 novel proteins as potentially crystallizable.

bioinformatics↗

bioRxiv2024

MATE-Pred: Multimodal Attention-based TCR-Epitope interaction Predictor

An accurate binding affinity prediction between T-cell receptors and epitopes contributes decisively to develop successful immunotherapy strategies. Some state-of-the-art computational methods implement deep learning techniques by integrating evolutionary features to convert the amino acid residues of cell receptors and epitope sequences into numerical values, while some other methods employ pre-trained language models to summarize the embedding vectors at the amino acid residue level to obtain sequence-wise representations. Here, we propose a highly reliable novel method, MATE-Pred, that performs multi-modal attention-based prediction of T-cell receptors and epitopes binding affinity. The MATE-Pred is compared and benchmarked with other deep learning models that leverage multi-modal representations of T-cell receptors and epitopes. In the proposed method, the textual representation of proteins is embedded with a pre-trained bi-directional encoder model and combined with two additional modalities: a) a comprehensive set of selected physicochemical properties; b) predicted contact maps that estimate the 3D distances between amino acid residues in the sequences. The MATE-Pred demonstrates the potential of multi-modal model in achieving state-of-the-art performance (+8.4% MCC, +5.5% AUC compared to baselines) and efficiently capturing contextual, physicochemical, and structural information from amino acid residues. The performance of MATE-Pred projects its potential application in various drug discovery regimes.

bioinformatics↗

bioRxiv2022

A Community Challenge to Predict Clinical Outcomes After Immune Checkpoint Blockade in Non-Small Cell Lung Cancer

PurposePredictive biomarkers of immune checkpoint inhibitors (ICIs) efficacy are currently lacking for non-small cell lung cancer (NSCLC). Here, we describe the results from the Anti-PD-1 Response Prediction DREAM Challenge, a crowdsourced initiative that enabled the assessment of predictive models by using data from two randomized controlled clinical trials (RCTs) of ICIs in first-line metastatic NSCLC. MethodsParticipants developed and trained models using public resources. These were evaluated with data from the CheckMate 026 trial (NCT02041533), according to the model-to-data paradigm to maintain patient confidentiality. The generalizability of the models with the best predictive performance was assessed using data from the CheckMate 227 trial (NCT02477826). Both trials were phase III RCTs with a chemotherapy control arm, which supported the differentiation between predictive and prognostic models. Isolated model containers were evaluated using a bespoke strategy that considered the challenges of handling transcriptome data from clinical trials. ResultsA total of 59 teams participated, with 417 models submitted. Multiple predictive models, as opposed to a prognostic model, were generated for predicting overall survival, progression-free survival, and progressive disease status with ICIs. Variables within the models submitted by participants included tumor mutational burden (TMB), programmed death ligand 1 (PD-L1) expression, and gene-expression-based signatures. The bestperforming models showed improved predictive power over reference variables, including TMB or PD-L1. ConclusionThis DREAM Challenge is the first successful attempt to use protected phase III clinical data for a crowdsourced effort towards generating predictive models for ICIs clinical outcomes and could serve as a blueprint for similar efforts in other tumor types and disease states, setting a benchmark for future studies aiming to identify biomarkers predictive of ICIs efficacy. Context summaryO_ST_ABSKey objectiveC_ST_ABSNot all patients with non-small cell lung cancer (NSCLC) eligible for immune checkpoint inhibitor (ICIs) respond to treatment, but accurate predictive biomarkers of ICIs clinical outcomes are currently lacking. This crowdsourced initiative enabled the robust assessment of predictive models using data from two randomized clinical trials of first-line ICI in metastatic NSCLC. Knowledge generatedModels submitted indicate that a combination of programmed death ligand 1 (PD-L1), tumor mutational burden (TMB), and immune gene signatures might be able to identify patients more likely to respond to ICIs. TMB and PD-L1 seemed important to predict progression-free survival and overall survival. Mechanisms including apoptosis, T-cell crosstalk, and adaptive immune resistance appeared essential to predict response. Relevance

cancer biology↗

bioRxiv2019

SolXplain: An Explainable Sequence-Based Protein Solubility Predictor

MotivationProtein solubility is a property associated with protein expression and is a critical determinant of the manufacturability of therapeutic proteins. It is thus imperative to design accurate in-silico sequence-based solubility predictors.\n\nMethodsIn this study, we propose SolXplain, an extreme gradient boosting machine based protein solubility predictor which achieves state-of-the-art performance using physio-chemical, sequence and novel structure derived features from protein sequences. Moreover, SolXplain has a unique attribute that it can provide explanation for the predicted class label for each test protein based on its corresponding feature values using SHapley Additive exPlanations (SHAP) method.\n\nResultsBased on an independent test set, SolXplain outperformed other sequence-based methods by at least 2% in accuracy and 2% in Matthews correlation coefficient, with an overall accuracy of 78% and Matthews correlation coefficient of 0.56. Additionally, for fractions of exposed residues (FER) at various residual solvent accessibility (RSA) cutoffs, we observed higher fractions to associate positively with protein solubility, and tripeptide stretches that contain one isoleucine and one or more histidines, to associate negatively with solubility. The improved prediction accuracy of SolXplain enables it to predict protein solubility with greater consistency and screen for sequences with enhanced manufacturability.

bioinformatics↗

bioRxiv2019

Conditional activation of immune-related signatures and prognostic significance: a pan-cancer analysis

BackgroundIt is becoming clear that tumor immune T cell infiltration and its functional orientation have substantial effect on cancer progression, influencing both response to therapy and prognosis. In this pan-cancer study, the previously described Immunologic Constant of Rejection (ICR) signature is used to define opposing immune phenotypes (i.e., immuneactive and immune-silent) across 31 different histologies. We systematically analyze the interconnections between the genetic programming of neoplasms and their immune orientation across different histologies, and the prognostic impact of such interplay. Moreover, we investigated the predictive value of ICR classification across various public datasets of immune checkpoint inhibition therapy. MethodsRNA-seq data of samples from a total of 9,282 patient tumor samples representing 31 cancer types were obtained from The Cancer Genome Atlas (TCGA). We classified each cancer type based on the expression of the ICR gene signature. Oncogenic pathway gene set enrichment and mutational status were analyzed in relation to ICR phenotypes. To explore whether tumorintrinsic attributes associate with the prognostic value of ICR across cancers, we compared mutational load, oncogenic alterations and expression of oncogenic pathways between cancer types using an integrative bioinformatic pipeline. ResultsOur analyses identified a distinct prognostic connotation of ICR depending on cancer histology. We identified several oncogenic pathways whose enrichment inversely correlated with ICR in multiple tumor types. We found several cancer specific pathways that were differentially enriched between tumors in which ICR had a prognostic impact versus the ones in which ICR did not bear any prognostic connotation such as proliferation and TGF-beta signaling. Importantly, this conditional impact of ICR was also validated in the context of immune checkpoint inhibition treatment. ConclusionsWe identified tumor-intrinsic attributes that correlate with immune phenotypes and potentially influence their development. In addition, a relationship was observed between the enrichment of oncogenic pathways and the prognostic significance of the ICR and its predictive value for patients treated with anti-CTLA4 immune checkpoint inhibition. Such information can be used to prioritize potential candidates for therapies aimed at converting immune-silent into immuneactive tumors and to refine stratification algorithms.

cancer biology↗

bioRxiv2018

Accurate Prediction of Antibody Resistance in Clinical HIV-1 Isolates

Broadly neutralizing antibodies (bNAbs) targeting the HIV-1 envelope glycoprotein (Env) have promising utility in prevention and treatment of HIV-1 infection with several undergoing clinical trials. Due to high sequence diversity and mutation rate of HIV-1, viral isolates are often resistant to particular bNAbs. Resistant strains are commonly identified by time-consuming and expensive in vitro neutralization experiments. Here, we developed machine learning-based classifiers that accurately predict resistance of HIV-1 strains to 33 neutralizing antibodies. Notably, our classifiers achieved an overall prediction accuracy of 96% for 212 clinical isolates from patients enrolled in four different clinical trials. Moreover, use of the tree-based machine learning method gradient boosting machine enabled us to identify critical epitope features that distinguish between antibody resistance and sensitivity. The availability of an in silico antibody resistance predictor will facilitate informed decisions of antibody usage in clinical settings.

bioinformatics↗

bioRxiv2017

Integrative Statistical Inferences for Drug Sensitivity Biomarkers in Cancer

Personal medicine has been associated with different patient responses to different anti-cancer therapies. Recently, scientists are looking not only for new biomarkers associated with a disease such as cancer but also identifying biomarkers that predict patients who are most likely to respond to a particular cancer treatment. Orderly endeavors to relate cancer mutational information with biological conditions may encourage the interpretation of somatic mutation indexes into significant biomarkers for patient stratification.\n\nWe have screened and incorporated a board of cancer cell lines from Genomics of Drug Sensitivity in Cancer (GDSC) database to recognize genomic highlights related with drug sensitivity. We used mutation, DNA copy number variation, and gene expression information from Catalogue of Somatic Mutations in Cancer (COSMIC) and The Cancer Genome ATLAS (TCGA) for cell lines with their reactions to associate focused and cytotoxic treatments with approved drugs and drugs under clinical and preclinical examination.\n\nWe discovered mutated cancer genes were related with cell reaction to, mostly accessible, cancer medications and some mutated genes were related with sensitivity to an expansive scope of therapeutic agents. By connecting drug activity to the useful many-sided quality of cancer genomes, efficient pharmacogenomic profiling in tumor cell lines gives an intense biomarker revelation stage to guide balanced malignancy remedial systems.\n\nOur study highlights that gene ANK2 amplification, and gene CELSER1 amplification and deletion are highly associated with anti-leukemic drug candidate LFM-A13. It also highlights that gene NUP214 and ROS1 copy number and gene NSD1 amplification are as a group highly associated with the parkinson drug Nilotinib. Finally, our study confirms that gene BRAF mutation is interacting with the BRAF-selective inhibitors drugs PLX4720 and SB590885. On the other hand, our study provides two open source analysis packages: bastah for the multitask-association analysis, and UNGeneAnno for automatic annotation of the variants.

genomics↗

bioRxiv2017

Application of High-Dimensional Statistics and Network based Visualization techniques on Arab Diabetes and Obesity data

BackgroundObesity and its co-morbidities are characterized by a chronic low-grade inflammatory state, uncontrolled expression of metabolic measurements and dis-regulation of various forms of stress response. However, the contribution and correlation of inflammation, metabolism and stress responses to the disease are not fully elucidated. In this paper a cross-sectional case study was conducted on clinical data comprising 117 human male and female subjects with and without type 2 diabetes (T2D). Characteristics such as anthropometric, clinical and bio-chemical measurements were collected.\n\nMethodsAssociation of these variables with T2D and BMI were assessed using penalized hierarchical linear and logistic regression. In particular, elastic net, hdi and glinternet were used as regularization models to distinguish between cases and controls. Differential network analysis using closed-form approach was performed to identify pairwise-interaction of variables that influence prediction of the phenotype.\n\nResultsFor the 117 participants, physical variables such as PBF, HDL and TBW had absolute coefficients 0.75, 0.65 and 0.34 using the glinternet approach, biochemical variables such as MIP, ROS and RANTES were identified as determinants of obesity with some interaction between inflammatory markers such as IL4, IL-6, MIP, CSF, Eotaxin and ROS. Diabetes was associated with a significant increase in thiobarbituric acid reactive substances (TBARS) which are considered as an index of endogenous lipid peroxidation and an increase in two inflammatory markers, MIP-1 and RANTES. Furthermore, we obtained 13 pairwise effects. The pairwise effects include pairs from and within physical, clinical and biochemical features, in particular metabolic, inflammatory, and oxidative stress markers.\n\nConclusionsWe showcase that markers of oxidative stress (derived from lipid peroxidation) such as MIP-1 and RANTES participate in the pathogenesis of diseases such as diabetes and obesity in the Arab population.

bioinformatics↗

bioRxiv2017

Differential Community Detection in Paired Biological Networks

MotivationBiological networks unravel the inherent structure of molecular interactions which can lead to discovery of driver genes and meaningful pathways especially in cancer context. Often due to gene mutations, the gene expression undergoes changes and the corresponding gene regulatory network sustains some amount of localized re-wiring. The ability to identify significant changes in the interaction patterns caused by the progression of the disease can lead to the revelation of novel relevant signatures.\n\nMethodsThe task of identifying differential sub-networks in paired biological networks (A:control,B:case) can be re-phrased as one of finding dense communities in a single noisy differential topological (DT) graph constructed by taking absolute difference between the topological graphs of A and B. In this paper, we propose a fast two-stage approach, namely Differential Community Detection (DCD), to identify differential sub-networks as differential communities in a de-noised version of the DT graph. In the first stage, we iteratively re-order the nodes of the DT graph to determine approximate block diagonals present in the DT adjacency matrix using neighbourhood information of the nodes and Jaccard similarity. In the second stage, the ordered DT adjacency matrix is traversed along the diagonal to remove all the edges associated with a node, if that node has no immediate edges within a window. We then apply community detection methods on this de-noised DT graph to discover differential sub-networks as communities.\n\nResultsOur proposed DCD approach can effectively locate differential sub-networks in several simulated paired random-geometric networks and various paired scale-free graphs with different power-law exponents. The DCD approach easily outperforms community detection methods applied on the original noisy DT graph and recent statistical techniques in simulation studies. We applied DCD method on two real datasets: a) Ovarian cancer dataset to discover differential DNA co-methylation sub-networks in patients and controls; b) Glioma cancer dataset to discover the difference between the regulatory networks of IDH-mutant and IDH-wild-type. We demonstrate the potential benefits of DCD for finding network-inferred bio-markers/pathways associated with a trait of interest.\n\nConclusionThe proposed DCD approach overcomes the limitations of previous statistical techniques and the issues associated with identifying differential sub-networks by use of community detection methods on the noisy DT graph. This is reflected in the superior performance of the DCD method with respect to various metrics like Precision, Accuracy, Kappa and Specificity. The code implementing proposed DCD method is available at https://sites.google.com/site/ raghvendramallmlresearcher/codes.

systems biology↗

bioRxiv2017

RGBM: Regularized Gradient Boosting Machines For The Identification of Transcriptional Regulators Of Discrete Glioma Subtypes

The transcription factors (TF) which regulate gene expressions are key determinants of cellular phenotypes. Reconstructing large-scale genome-wide networks which capture the influence of TFs on target genes are essential for understanding and accurate modelling of living cells. We propose RGBM: a gene regulatory network (GRN) inference algorithm, which can handle data from heterogeneous information sources including dynamic time-series, gene knockout, gene knockdown, DNA microarrays and RNA-Seq expression profiles. RGBM allows to use an a priori mechanistic of active biding network consisting of TFs and corresponding target genes. RGBM is evaluated on the DREAM challenge datasets where it surpasses the winners of the competitions and other established methods for two evaluation metrics by about 10-15%.\n\nWe use RGBM to identify the main regulators of the molecular subtypes of brain tumors. Our analysis reveals the identity and corresponding biological activities of the master regulators driving transformation of the G-CIMP-high into the G-CIMP-low subtype of glioma and PA-like into LGm6-GBM, thus, providing a clue to the yet undetermined nature of the transcriptional events driving the evolution among these novel glioma subtypes.\n\nRGBM is available for download on CRAN at https://cran.rproject.org/web/packages/RGBM/index.html

bioinformatics↗