Biology subjects

Mahbub, S.

Publications and source records attributed to Mahbub, S..

13 recordsLinked to original sources

bioRxiv2025

Uncertainty-Aware Discrete Diffusion Improves Protein Design

Protein inverse folding involves generating amino acid sequences that adopt a specified 3D structure--a key challenge in structural biology and molecular engineering. While discrete diffusion models have demonstrated strong performance, existing methods often apply uniform denoising across residues, overlooking position-specific uncertainty. We propose an uncertainty-aware discrete denoising diffusion model that employs a prior-posterior signaling mechanism to dynamically guide the denoising process. Our approach further integrates learned priors from a pretrained protein large language model and a structure encoder within a modular framework, jointly optimized through multi-objective training. Across multiple benchmarks, our method achieves substantial improvements over state-ofthe-art baselines, offering a principled framework for structure-conditioned sequence generation in proteins and beyond.

bioinformatics↗

bioRxiv2024

Accurate and General DNA Representations Emerge from Genome Foundation Models at Scale

Language models applied to protein sequences have become a panacea, enabling therapeutics development, materials engineering, and core biology research. Despite the successes of protein language models, genome language models remain nascent. Recent studies suggest the bottleneck is data volume or modeling context size, since long-range interactions are widely acknowledged but sparsely annotated. However, it may be the case that even short DNA sequences are modeled poorly by existing approaches, and current models are unable to represent the wide array of functions encoded by DNA. To study this, we develop AIDO.DNA, a pretrained module for DNA representation in an AI-driven Digital Organism [1]. AIDO.DNA is a seven billion parameter encoder-only transformer trained on 10.6 billion nucleotides from a dataset of 796 species. By scaling model size while maintaining a short context length of 4k nucleotides, AIDO.DNA shows substantial improvements across a breadth of supervised, generative, and zero-shot tasks relevant to functional genomics, synthetic biology, and drug development. Notably, AIDO.DNA outperforms prior encoder-only architectures without new data, suggesting that new scaling laws are needed to achieve computeoptimal DNA language models. Models and code are available through Model-Generator in https://github.com/genbio-ai/AIDO and on Hugging Face at https://huggingface.co/genbio-ai.

bioinformatics↗

bioRxiv2024

Mixture of Experts Enable Efficient and Effective Protein Understanding and Design

Proteins play a fundamental role in life. Understanding the language of proteins offers significant potential for gaining mechanistic insights into biological systems and introduces new avenues for treating diseases, enhancing agriculture, and safeguarding the environment. While large protein language models (PLMs) like ESM2-15B and xTrimoPGLM-100B have achieved remarkable performance in diverse protein understanding and design tasks, these models, being dense transformer models, pose challenges due to their computational inefficiency during training and deployment. In this work, we introduce AIDO.Protein, a pretrained module for protein representation in an AI-driven Digital Organism [1]. AIDO.Protein is also the first mixture-of-experts (MoE) model in the protein domain, with model size scales to 16 billion parameters. Leveraging a sparse MoE architecture with 8 experts within each transformer block and selectively activating 2 experts for each input token, our model is significantly more efficient in training and inference. Through pre-training on 1.2 trillion amino acids collected from UniRef90 and ColabfoldDB, our model achieves state-of-the-art results across most tasks in the xTrimoPGLM benchmark. Furthermore, on over 280 ProteinGym Deep Mutational Scanning (DMS) assays, our model achieves nearly 99% of the overall performance of the best MSA-based model and significantly outperforms the previously reported state-of-the-art models that do not utilize MSA. We also adapted this model for structure-conditioned protein sequence generation tasks and achieved new SOTA in this domain. These results indicate that AIDO.Protein can serve as a strong foundation model for protein understanding and design. Models and codes are available through ModelGenerator in https://github.com/genbio-ai/AIDO and on Hugging Face.

bioinformatics↗

bioRxiv2024

A Large-Scale Foundation Model for RNA Function and Structure Prediction

Originally marginalized as an intermediate in the information flow from DNA to protein, RNA has become the star of modern biology, holding the key to precision therapeutics, genetic engineering, evolutionary origins, and our understanding of fundamental cellular processes. Yet RNA is as mysterious as it is prolific, serving as an information store, a messenger, and a catalyst, spanning many underchar-acterized functional and structural classes. Deciphering the language of RNA is important not only for a mechanistic understanding of its biological functions but also for accelerating drug design. Toward this goal, we introduce AIDO.RNA, a pre-trained module for RNA in an AI-driven Digital Organism [1]. AIDO.RNA contains a scale of 1.6 billion parameters, trained on 42 million non-coding RNA (ncRNA) sequences at single-nucleotide resolution, and it achieves state-of-the-art performance on a comprehensive set of tasks, including structure prediction, genetic regulation, molecular function across species, and RNA sequence design. AIDO.RNA after domain adaptation learns to model essential parts of protein translation that protein language models, which have received widespread attention in recent years, do not. More broadly, AIDO.RNA hints at the generality of biological sequence modeling and the ability to leverage the central dogma to improve many biomolecular representations. Models and code are available through ModelGenerator in https://github.com/genbio-ai/AIDO and on Hugging Face.

bioinformatics↗

bioRxiv2024

BiRNA-BERT Allows Efficient RNA Language Modeling with Adaptive Tokenization

Recent advancements in Transformer-based models have spurred interest in their use for biological sequence analysis. However, adapting models like BERT is challenging due to sequence length, often requiring truncation for proteomics and genomics tasks. Additionally, advanced tokenization and relative positional encoding techniques for long contexts in NLP are often not directly transferable to DNA/RNA sequences, which require nucleotide or character-level encodings for tasks such as 3D torsion angle prediction. To tackle these challenges, we propose an adaptive dual tokenization scheme for bioinformatics that utilizes both nucleotide-level (NUC) and efficient BPE tokenizations. Building on the dual tokenization, we introduce BiRNA-BERT, a 117M parameter Transformer encoder pretrained with our proposed tokenization on 28 billion nucleotides across 36 million coding and non-coding RNA sequences. The learned representation by BiRNA-BERT generalizes across a range of applications and achieves state-of-the-art results in long-sequence downstream tasks and achieves a performance comparable to 6x larger models in short-sequence tasks with 27xless pre-training compute. BiRNA-BERT can dynamically adjust its tokenization strategy based on sequence lengths, utilizing NUC for shorter sequences and switching to BPE for longer ones, thereby offering, for the first time, the capability to efficiently handle arbitrarily long DNA/RNA sequences. 1

bioinformatics↗

bioRxiv2023

Pair-EGRET: enhancing the prediction of protein-proteininteraction sites through graph attention networks and protein language models

Proteins are responsible for most biological functions, many of which require the interaction of more than one protein molecule. However, accurately predicting protein-protein interaction (PPI) sites (the interfacial residues of a protein that interact with other protein molecules) remains a challenge. The growing demand and cost associated with the reliable identification of PPI sites using conventional experimental methods call for computational tools for automated prediction and understanding of PPIs. Here, we present Pair-EGRET, an edge-aggregated graph attention network that leverages the features extracted from pre-trained transformer-like models to accurately predict PPI sites. Pair-EGRET works on a k-nearest neighbor graph, representing the three-dimensional structure of a protein, and utilizes the cross-attention mechanism for accurate identification of interfacial residues of a pair of proteins. Through an extensive evaluation study using a diverse array of experimental data, evaluation metrics, and case studies on representative protein sequences, we find that our method outperforms other state-of-the-art methods for predicting PPI sites. Moreover, Pair-EGRET can provide interpretable insights from the learned cross-attention matrix. Pair-EGRET is freely available in open source form at (https://github.com/1705004/Pair-EGRET).

bioinformatics↗

bioRxiv2022

SAINT-Angle: self-attention augmented inception-inside-inception network and transfer learning improve protein backbone torsion angle prediction

MotivationProtein structure provides insight into how proteins interact with one another as well as their functions in living organisms. Protein backbone torsion angles ({phi} and{psi} ) prediction is a key sub-problem in predicting protein structures. However, reliable determination of backbone torsion angles using conventional experimental methods is slow and expensive. Therefore, considerable effort is being put into developing computational methods for predicting backbone angles. ResultsWe present SAINT-Angle, a highly accurate method for predicting protein backbone torsion angles using a self-attention based deep learning network called SAINT, which was previously developed for the protein secondary structure prediction. We extended and improved the existing SAINT architecture as well as used transfer learning to predict backbone angles. We compared the performance of SAINT-Angle with the state-of-the-art methods through an extensive evaluation study on a collection of benchmark datasets, namely, TEST2016, TEST2018, CAMEO, and CASP. The experimental results suggest that our proposed self-attention based network, together with transfer learning, has achieved notable improvements over the best alternate methods. Availability and implementationSAINT-Angle is freely available as an open-source project at https://github.com/bayzidlab/SAINT-Angle. Contactshams_bayzid@cse.buet.ac.bd Supplementary informationSupplementary material SM.pdf.

bioinformatics↗

bioRxiv2022

moRphology - dEep Learning Imaging Cells (RELIC) - to Differentiate Between Normal and Pathological Kidney Exfoliated Cells

Chronic kidney disease (CKD) is characterised by progressive loss of kidney function leading to kidney failure. Significant kidney damage can occur before symptoms are detected. Currently, kidney tissue biopsy is the gold standard for evaluation of renal damage and CKD severity. This study explores how to precisely quantify morphology characteristics of kidney cells exfoliated into urine, with a view to establish a future urine-based non-invasive diagnostic for CKD. We report the development of a novel deep learning method, which was able to discover a RELIC (moRphology dEep Learning Imaging Cells) signature that can differentiate between kidney cells exfoliated in human urine of and CKD patients with varying degree of kidney damage and non-CKD controls. Exfoliated proximal tubule cells (PTCs) originating from kidneys were isolated from the urine of patients with different levels of kidney damage using previously published methods. An advanced combination of artificial intelligence techniques, deep learning, swarm intelligence, and discriminative analysis was used to discover a RELIC signature in brightfield microscopy images of exfoliated PTCs. Kidney damage in the study subjects was characterised by assessing kidney tissues obtained through a nephrectomy or kidney biopsy. A special deep learning algorithm was developed and trained to create a predictive tool. The algorithm was then used to analyse data from patients with normal and fibrotic kidneys. Data were then classified according to different groups (healthy or fibrosis) and clustering of the training and validation cells was determined for model validation. We developed a novel deep learning method, to obtain RELIC signatures and identify specific deep morphological features which can be used to differentiate urinary PTC cells shed by people with CKD (confirmed by tissue histology obtained from an invasive kidney biopsy) from those without CKD, with a discriminatory accuracy of 82%. We identified a RELIC signature which can be used on a collection of bright field images of exfoliated urinary PTCs to create a predictive tool and differentiate between normal and pathological kidney cells. This study, for the first time, provides a proof of concept that urinary exfoliated tubule cells in patients with kidney fibrosis and healthy controls differ in appearance (morphology) as observed under a basic brightfield microscope. The results suggest that morphological signatures of exfoliated PTCs have the potential to serve as a non-invasive marker of kidney fibrosis.

bioinformatics↗

bioRxiv2021

QT-GILD: Quartet Based Gene Tree Imputation Using Deep Learning Improves Phylogenomic Analyses Despite Missing Data

Species tree estimation is frequently based on phylogenomic approaches that use multiple genes from throughout the genome. However, for a combination of reasons (ranging from sampling biases to more biological causes, as in gene birth and loss), gene trees are often incomplete, meaning that not all species of interest have a common set of genes. Incomplete gene trees can potentially impact the accuracy of phylogenomic inference. We, for the first time, introduce the problem of imputing the quartet distribution induced by a set of incomplete gene trees, which involves adding the missing quartets back to the quartet distribution. We present QT-GILD, an automated and specially tailored unsupervised deep learning technique, accompanied by cues from natural language processing (NLP), which learns the quartet distribution in a given set of incomplete gene trees and generates a complete set of quartets accordingly. QT-GILD is a general-purpose technique needing no explicit modeling of the subject system or reasons for missing data or gene tree heterogeneity. Experimental studies on a collection of simulated and empirical data sets suggest that QT-GILD can effectively impute the quartet distribution, which results in a dramatic improvement in the species tree accuracy. Remarkably, QT-GILD not only imputes the missing quartets but it can also account for gene tree estimation error. Therefore, QT-GILD advances the state-of-the-art in species tree estimation from gene trees in the face of missing data. QT-GILD is freely available in open source form at https://github.com/pythonLoader/QT-GILD.

bioinformatics↗

bioRxiv2020

EGAT: Edge Aggregated Graph Attention Networks and Transfer Learning Improve Protein-Protein Interaction Site Prediction

MotivationProtein-protein interactions are central to most biological processes. However, reliable identification of protein-protein interaction (PPI) sites using conventional experimental methods is slow and expensive. Therefore, great efforts are being put into computational methods to identify PPI sites. ResultsWe present EGRET, a highly accurate deep learning based method for PPI site prediction, where we have used an edge aggregated graph attention network to effectively leverage the structural information. We, for the first time, have used transfer learning in PPI site prediction. Our proposed edge aggregated network, together with transfer learning, has achieved notable improvement over the best alternate methods. Furthermore, we systematically investigated EGRETs network behavior to provide insights about the causes of its decisions. AvailabilityEGRET is freely available as an open source project at https://github.com/Sazan-Mahbub/EGRET. Contactshams_bayzid@cse.buet.ac.bd Key PointsO_LIWe present a comprehensive assessment of a compendium of computational protocols to solve an important problem in computational proteomics. C_LIO_LIWe present a highly accurate deep learning method, EGRET, for Protein-Protein Interaction (PPI) site prediction for isolated proteins. C_LIO_LIWe have used an edge aggregated graph attention network to effectively capture the structural information for PPI site prediction. C_LIO_LIWe, for the first time, present a successful utilization of transfer-learning from pretrained transformer-like models in PPI site prediction. C_LI

bioinformatics↗

bioRxiv2020

Non-invasive real-time imaging of reactive oxygen species (ROS) using multispectral auto-fluorescence imaging technique: a novel tool for redox biology

Detecting reactive oxygen species (ROS) that play a critical role as redox modulators and signalling molecules in biological systems currently requires invasive methods such as ROS - specific indicators for imaging and quantification. We developed a non-invasive, real-time, label-free imaging technique for assessing the level of ROS in live cells and thawed cryopreserved tissues that is compatible with in-vivo imaging. The technique is based on autofluorescence multispectral imaging (AFMI) carried out in an adapted fluorescence microscope with an expanded number of spectral channels spanning specific excitation (365 nm-495 nm) and emission (420 nm-700 nm) wavelength ranges. We established a strong quantitative correlation between the spectral information obtained from AFMI and the level of ROS obtained from CellROX staining. The results were obtained in several cell types (HeLa, PANC1 and mesenchymal stem cells) and in live kidney tissue. Additioanly, two spectral regimes were considered: with and without UV excitation (wavelengths > 400 nm); the latter being suitable for UV-sensitive systems such as the eye. Data were analyzed by linear regression combined with an optimization method of swarm intelligence. This allowed the calibration of AFMI signals to the level of ROS with excellent correlation (R= 0.84, p=0.00) in the entire spectral range and very good correlation (R= 0.78, p=0.00) in the limited, UV-free spectral range. We also developed a strong classifier which allowed us to distinguish moderate and high levels of ROS in these two regimes (AUC= 0.91 in the entire spectral range and AUC = 0.78 for UV-free imaging). These results indicate that ROS in cells and tissues can be imaged non-invasively, which opens the way to future clinical applications in conditions where reactive oxygen species are known to contribute to progressive disease such as in ophthalmology, diabetes, kidney disease, cancer and neurodegenerative diseases.

cell biology↗

bioRxiv2019

SAINT: Self-Attention AugmentedInception-Inside-Inception Network Improves ProteinSecondary Structure Prediction

MotivationProtein structures provide basic insight into how they can interact with other proteins, their functions and biological roles in an organism. Experimental methods (e.g., X-ray crystallography, nuclear magnetic resonance spectroscopy) for predicting the secondary structure (SS) of proteins are very expensive and time consuming. Therefore, developing efficient computational approaches for predicting the secondary structure of protein is of utmost importance. Advances in developing highly accurate SS prediction methods have mostly been focused on 3-class (Q3) structure prediction. However, 8-class (Q8) resolution of secondary structure contains more useful information and is much more challenging than the Q3 prediction. ResultsWe present SAINT, a highly accurate method for Q8 structure prediction, which incorporates self-attention mechanism (a concept from natural language processing) with the Deep Inception-Inside-Inception (Deep3I) network in order to effectively capture both the short-range and long-range interactions among the amino acid residues. SAINT offers a more interpretable framework than the typical black-box deep neural network methods. Through an extensive evaluation study, we report the performance of SAINT in comparison with the existing best methods on a collection of benchmark datasets, namely, TEST2016, TEST2018, CASP12 and CASP13. Our results suggest that self-attention mechanism improves the prediction accuracy and outperforms the existing best alternate methods. SAINT is the first of its kind and offers the best known Q8 accuracy. Thus, we believe SAINT represents a major step towards the accurate and reliable prediction of secondary structures of proteins. AvailabilitySAINT is freely available as an open source project at https://github.com/SAINTProtein/SAINT.

bioinformatics↗

bioRxiv2019

NAD+ repletion rescues female fertility during reproductive ageing

Female infertility is a common and devastating condition with life-long health, emotional and social consequences. There is currently no pharmacological therapy for preserving oocyte quality during aging, which is the strongest risk factor for infertility. This leads to an age dependent decline in natural conception and IVF success rates (1). Here, we show that this is due in part to declining levels of the metabolic cofactor nicotinamide adenine dinucleotide (NAD+), and that restoring NAD+ levels with its metabolic precursor nicotinamide mononucleotide (NMN) rejuvenates oocyte quality and quantity in aged animals, leading to improved fertility. These benefits extend to the developing embryo, where NMN supplementation in embryo culture media following IVF enhances blastocyst formation in older mice. The NAD+ dependent deacylase SIRT2 is sufficient, but not essential, to recapitulate the benefits of in vivo NMN treatment, and transgenic overexpression of SIRT2 maintains oocyte spindle assembly, accurate chromosome segregation, decreased oxidative stress and overall fertility with ageing. Pharmacological elevation of NAD+ may be an effective, non-invasive strategy for restoring and maintaining female fertility during ageing, and for improving the success of IVF.

developmental biology↗