Biology subjects

Bayzid, M. S.

Publications and source records attributed to Bayzid, M. S..

35 records · Page 2Linked to original sources

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↗

bioRxiv2023

wQFM-DISCO: DISCO-enabled wQFM improves phylogenomic analyses despite the presence of paralogs

Gene trees often differ from the species trees that contain them due to various factors, including incomplete lineage sorting (ILS), gene duplication and loss (GDL), and horizontal gene transfer (HGT). Several highly accurate species tree estimation methods have been introduced to explicitly address ILS, including AS-TRAL, a widely used statistically consistent method, and wQFM, a quartet amalgamation approach that is experimentally shown to be more accurate than ASTRAL. Two recent advancements, ASTRAL-Pro and DISCO, have emerged in the field of phylogenomics to consider gene duplication and loss (GDL) events. ASTRAL-Pro introduces a refined measure of quartet similarity, accounting for both orthology and paralogy. DISCO, on the other hand, offers a general strategy to decompose multicopy gene family trees into a collection of single-copy trees, allowing the utilization of methods previously designed for species tree inference in the context of single-copy gene trees. In this study, we first introduce some variants of DISCO to examine its underlying hypotheses and present analytical results on the statistical guarantees of DISCO. In particular, we introduce DISCO-R, a variant of DISCO with a refined and improved pruning strategy that provides more accurate and robust results. We then propose wQFM-DISCO (wQFM paired with DISCO) as an adaptation of wQFM to handle multicopy gene trees resulting from GDL events. Extensive evaluation studies on a collection of simulated and real data sets demonstrate that wQFM-DISCO is significantly more accurate than ASTRAL-Pro and other competing methods.

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

Terraces in Species Tree Inference from Gene Trees

A terrace in a phylogenetic tree space is a region where all trees contain the same set of subtrees, due to certain patterns of missing data among the taxa sampled, resulting in an identical optimality score for a given data set. This was first investigated in the context of phylogenetic tree estimation from sequence alignments using maximum likelihood (ML) and maximum parsimony (MP). The concept of terraces was later extended to the species tree inference problem from a collection of gene trees, where a set of equally optimal species trees was referred to as a "pseudo" species tree terrace. Pseudo terraces do not consider the topological proximity of the trees in terms of the induced subtrees resulting from certain patterns of missing data. In this study, we mathematically characterize species tree terraces and investigate the mathematical properties and conditions that lead multiple species trees to induce/display an identical set of locus-specific subtrees owing to missing data. We report that species tree terraces are agnostic to gene tree topologies and the discordance therein. Therefore, we introduce and characterize a special type of gene tree topology-aware terrace which we call "peak terrace", and investigate conditions on the patterns of missing data that give rise to peak terraces. In addition to the theoretical and analytical results, we empirically investigated different challenges as well as various opportunities pertaining to the multiplicity of equally good species trees in terraced landscapes. Based on an extensive experimental study involving both simulated and real biological datasets, we present the prevalence of species tree terraces and the resulting ambiguity created for tree search algorithms. Remarkably, our findings indicate that the identification of terraces and the trees within them can substantially enhance the accuracy of summary methods. Furthermore, we demonstrate that reasonably accurate branch support can be computed by leveraging trees sourced from these terraces.

bioinformatics↗

bioRxiv2021

Genome-wide alignment-free phylogenetic distance estimation under a no strand-bias model

While aligning sequences has been the dominant approach for determining homology prior to phylogenetic inference, alignment-free methods have much appeal in terms of simplifying the process of inference, especially when analyzing genome-wide data. Furthermore, alignment-free methods present the only option for some emerging forms of data, such as genome skims, which cannot be assembled. Despite the appeal, alignment-free methods have not been competitive with alignment-based methods in terms of accuracy. One limitation of alignment-free methods is that they typically rely on simplified models of sequence evolution such as Jukes-Cantor. It is possible to compute pairwise distances under more complex models by computing frequencies of base substitutions provided that these quantities can be estimated in the alignment-free setting. A particular limitation is that for many forms of genomewide data, which arguably present the best use case for alignment-free methods, the strand of DNA sequences is unknown. Under such conditions, the so-called no-strand bias models are the most complex models that can be used. Here, we show how to calculate distances under a no-strain bias restriction of the General Time Reversible (GTR) model called TK4 without relying on alignments. The method relies on replacing letters in the input sequences, and subsequent computation of Jaccard indices between k-mer sets. For the method to work on large genomes, we also need to compute the number of k-mer mismatches after replacement due to random chance as opposed to homology. We show in simulation that these alignment-free distances can be highly accurate when genomes evolve under the assumed models, and we examine the effectiveness of the method on real genomic data.

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

wQFM: Statistically Consistent Genome-scale Species Tree Estimation from Weighted Quartets

MotivationSpecies tree estimation from genes sampled from throughout the whole genome is complicated due to the gene tree-species tree discordance. Incomplete lineage sorting (ILS) is one of the most frequent causes for this discordance, where alleles can coexist in populations for periods that may span several speciation events. Quartet-based summary methods for estimating species trees from a collection of gene trees are becoming popular due to their high accuracy and statistical guarantee under ILS. Generating quartets with appropriate weights, where weights correspond to the relative importance of quartets, and subsequently amalgamating the weighted quartets to infer a single coherent species tree allows for a statistically consistent way of estimating species trees. However, handling weighted quartets is challenging. ResultsWe propose wQFM, a highly accurate method for species tree estimation from multi-locus data, by extending the quartet FM (QFM) algorithm to a weighted setting. wQFM was assessed on a collection of simulated and real biological datasets, including the avian phylogenomic dataset which is one of the largest phylogenomic datasets to date. We compared wQFM with wQMC, which is the best alternate method for weighted quartet amalgamation, and with ASTRAL, which is one of the most accurate and widely used coalescent-based species tree estimation methods. Our results suggest that wQFM matches or improves upon the accuracy of wQMC and ASTRAL. AvailabilitywQFM is available in open source form at https://github.com/Mahim1997/wQFM-2020.

bioinformatics↗

bioRxiv2020

Genome Wide Association Studies on 7 Yield-relatedTraits of 183 Rice Varieties in Bangladesh

MotivationRice genetic diversity is regulated by multiple genes and is largely dependent on various environmental factors. Uncovering the genetic variations associated with the diversity in rice populations is the key to breed stable and high yielding rice varieties. ResultsWe performed Genome Wide Association Studies (GWAS) on 7 rice yielding traits (grain length, grain width, grain weight, panicle length, leaf length, leaf width and leaf angle) based on a population of 183 rice landraces of Bangladesh. Our GWA studies reveal various chromosomal regions and candidate genes that are associated with different traits in Bangladeshi rice varieties. Noteworthy was the recurrent implication of chromosome 10 in all three grain shape related traits (grain length, grain width, and grain weight), indicating its pivotal role in shaping rice grain morphology. Our study also underscores the involvement of transposon gene families across these three traits. For leaf related traits, chromosome 10 was found to harbor regions that are significantly associated with leaf length and leaf width. The results of these association studies support previous findings as well as provide additional insights into the genetic diversity of rice. ConclusionsThis is the first known GWAS study on various yield-related traits in the varieties of Oryza sativa available in Bangladesh - the fourth largest rice-producing country. We believe this study will accelerate rice genetics research and breeding stable high-yielding rice in Bangladesh.

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

Phylogenomic terraces: presence and implication in species tree estimation from gene trees

Species tree estimation from multi-locus dataset is extremely challenging, especially in the presence of gene tree heterogeneity across the genome due to incomplete lineage sorting (ILS). Summary methods have been developed which estimate gene trees and then combine the gene trees to estimate a species tree by optimizing various optimization scores. In this study, we have formalized the concept of "phylogenomic terraces" in the species tree space, where multiple species trees with distinct topologies may have exactly the same optimization score (quartet score, extra lineage score, etc.) with respect to a collection of gene trees. We investigated the presence and implication of terraces in species tree estimation from multi-locus data by taking ILS into account. We analyzed two of the most popular ILS-aware optimization criteria: maximize quartet consistency (MQC) and minimize deep coalescence (MDC). Methods based on MQC are provably statistically consistent, whereas MDC is not a consistent criterion for species tree estimation. Our experiments, on a collection of dataset simulated under ILS, indicate that MDC-based methods may achieve competitive or identical quartet consistency score as MQC but could be significantly worse than MQC in terms of tree accuracy - demonstrating the presence and affect of phylogenomic terraces. This is the first known study that formalizes the concept of phylogenomic terraces in the context of species tree estimation from multi-locus data, and reports the presence and implications of terraces in species tree estimation under ILS.

bioinformatics↗

bioRxiv2019

An Alignment-free Method for Phylogeny Estimation using Maximum Likelihood

While alignment has traditionally been the primary approach for establishing homology prior to phylogenetic inference, alignment-free methods offer a simplified alternative, particularly beneficial when handling genome-wide data involving long sequences and complex events such as rearrangements. Moreover, alignment-free methods become crucial for data types like genome skims, where assembly is impractical. However, despite these benefits, alignment-free techniques have not gained widespread acceptance since they lack the accuracy of alignment-based techniques, primarily due to their reliance on simplified models of pairwise distance calculation. Here, we present a likelihood based alignment-free technique for phylogenetic tree construction. We encode the presence or absence of k-mers in genome sequences in a binary matrix, and estimate phylogenetic trees using a maximum likelihood approach. We analyze the performance of our method on seven real datasets and compare the results with the state of the art alignment-free methods. Results suggest that our method is competitive with existing alignment-free tools. This indicates that maximum likelihood based alignment-free methods may in the future be refined to outperform alignment-free methods relying on distance calculation as has been the case in the alignment-based setting. A likelihood based alignment-free method for phylogeny estimation is implemented for the first time in a software named PO_SCPLOWEAFOWLC_SCPLOW, which is available at: https://github.com/hasin-abrar/Peafowlrepo.

bioinformatics↗

bioRxiv2019

eMED-DNA: An in silico operating system for clinical medical data storage within the human genome

The propitious developments in molecular biology and next generation sequencing have enabled the possibility for DNA storage technologies. However, the full application and power of our genomic revolution have not been fully utilized in clinical medicine given a lack of transition from research to real world clinical practice. This has identified an increasing need for an operating system which allows for the transition from research to clinical use. We present eMED-DNA, an in silico operating system for archiving and managing all forms of electronic health records (EHRs) within ones own copy of the sequenced genome to aid in the application and integration of genomic medicine within real world clinical practice. We incorporated an efficient and sophisticated in-DNA file management system for the lossless management of EHRs within a genome. This represents the first in silico integrative system which would bring closer the utopian ideal for integrating genotypic data with phenotypic clinical data for future medical practice.

bioinformatics↗

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

Machine learning based imputation techniques forestimating phylogenetic trees from incompletedistance matrices

BackgroundDue to the recent advances in sequencing technologies and species tree estimation methods capable of taking gene tree discordance into account, notable progress has been achieved in constructing large scale phylogenetic trees from genome wide data. However, substantial challenges remain in leveraging this huge amount of molecular data. One of the foremost among these challenges is the need for efficient tools that can handle missing data. Popular distance-based methods such as neighbor joining and UPGMA require that the input distance matrix does not contain any missing values. ResultsWe introduce two highly accurate machine learning based distance imputation techniques. One of our approaches is based on matrix factorization, and the other one is an autoencoder based deep learning technique. We evaluate these two techniques on a collection of simulated and biological datasets, and show that our techniques match or improve upon the best alternate techniques for distance imputation. Moreover, our proposed techniques can handle substantial amount of missing data, to the extent where the best alternate methods fail. ConclusionsThis study shows for the first time the power and feasibility of applying deep learning techniques for imputing distance matrices. The autoencoder based deep learning technique is highly accurate and scalable to large dataset. We have made these techniques freely available as a cross-platform software (available at https://github.com/Ananya-Bhattacharjee/ImputeDistances).

genomics↗

bioRxiv2019

STELAR: A statistically consistent coalescent-based species tree estimation method by maximizing triplet consistency

BackgroundSpecies tree estimation is frequently based on phylogenomic approaches that use multiple genes from throughout the genome. However, estimating a species tree from a collection of gene trees can be complicated due to the presence of gene tree incongruence resulting from incomplete lineage sorting (ILS), which is modelled by the multi-species coalescent process. Maximum likelihood and Bayesian MCMC methods can potentially result in accurate trees, but they do not scale well to large datasets.\n\nResultsWe present STELAR (Species Tree Estimation by maximizing tripLet AgReement), a new fast and highly accurate statistically consistent coalescent-based method for estimating species trees from a collection of gene trees. We formalized the constrained triplet consensus (CTC) problem and showed that the solution to the CTC problem is a statistically consistent estimate of the species tree under the multi-species coalescent (MSC) model. STELAR is an efficient dynamic programming based solution to the CTC problem which is highly accurate and scalable. We evaluated the accuracy of STELAR in comparison with SuperTriplets, which is an alternate fast and highly accurate triplet-based supertree method, and with MP-EST and ASTRAL - two of the most popular and accurate coalescent-based methods. Experimental results suggest that STELAR matches the accuracy of ASTRAL and improves on MP-EST and SuperTriplets.\n\nConclusionsTheoretical and empirical results (on both simulated and real biological datasets) suggest that STELAR is a valuable technique for species tree estimation from gene tree distributions.

bioinformatics↗

bioRxiv2019

NORTH: a highly accurate and scalable Naive Bayes based ORTHologous gene clustering algorithm

BackgroundThe principal objective of comparative genomics is inferring attributes of an unknown gene by comparing it with well-studied genes. In this regard, identifying orthologous genes plays a pivotal role as the orthologous genes remain less diverged in the course of evolution. However, identifying orthologous genes is often difficult, slow, and idiosyncratic, especially in the presence of multiplicity of domains in proteins, evolutionary dynamics (gene duplication, transfer, loss, introgression etc.), multiple paralogous genes, incomplete genome data, and for distantly related species where similarity is hard to recognize. MotivationAdvances in identifying orthologs have mostly been constrained to developing databases of genes or methods which involve computationally expensive BLAST search or constructing phylogenetic trees to infer orthologous relationships. These methods do not generally scale well and cannot analyze large amount of data from diverse organisms with high accuracy. Moreover, most of these methods involve manual parameter tuning, and hence are neither fully automated nor free from human bias. ResultsWe present NORTH, a novel, automated, highly accurate and scalable machine learning based orhtologous gene clustering method. We have utilized the biological basis and intuition of orthologous genes and made an effort to incorporate appropriate ideas from machine learning (ML) and natural language processing (NLP). We have discovered that the BLAST search based protocols deeply resemble a "text classification" problem. Thus, we employ the robust bag-of-words model accompanied by a Naive Bayes classifier to cluster the orthologous genes. We studied 1,255,877 genes in the largest 250 ortholog clusters from the KEGG database, across 3,880 organisms comprising the six major groups of life, namely, Archaea, Bacteria, Animals, Fungi, Plants and Protists. Despite having more than a million of genes on distantly related species with acute data imbalance, NORTH is able to cluster them with 98.48% Precision, 98.43% Recall and 98.44% F1 score, showing that automatic orthologous gene clustering can be both highly accurate and scalable. NORTH is available as a web interface with a server side application, along with cross-platform native applications (available at https://nibtehaz.github.io/NORTH/) - allowing queries based on individual genes.

bioinformatics↗

bioRxiv2018

Multi-objective formulation of MSA for phylogeny estimation (Do phylogeny-aware measures guide towards better phylogenetic tree?)

Multiple sequence alignment (MSA) is a basic step in many analyses in computational biology, including predicting the structure and function of proteins, orthology prediction and estimating phylogenies. The objective of MSA is to infer the homology among the sequences of chosen species. Commonly, the MSAs are inferred by optimizing a single function or objective. The alignments estimated under one criterion may be different to the alignments generated by other criteria, inferring discordant homologies and thus leading to different evolutionary histories relating the sequences. In recent past, researchers have advocated for the multi-objective formulation of MSA, to address this issue, where multiple conflicting objective functions are being optimized simultaneously to generate a set of alignments. However, no theoretical or empirical justification with respect to a real-life application has been shown for a particular multi-objective formulation. In this study, we investigate the impact of multi-objective formulation in the context of phylogenetic tree estimation. Employing multi-objective metaheuristics, we demonstrate that trees estimated on the alignments generated by multi-objective formulation are substantially better than the trees estimated by the state-of-the-art MSA tools, including PASTA, MUSCLE, CLUSTAL, MAFFT etc. We also demonstrate that highly accurate alignments with respect to popular measures like sum-of-pair (SP) score and total-column (TC) score do not necessarily lead to highly accurate phylogenetic trees. Thus in essence we ask the question whether a phylogeny-aware metric can guide us in choosing appropriate multi-objective formulations that can result in better phylogeny estimation. And we answer the question affirmatively through carefully designed extensive empirical study. As a by-product we also suggest a methodology for primary selection of a set of objective functions for a multi-objective formulation based on the association with the resulting phylogenetic tree.

bioinformatics↗