RESUMO
BACKGROUND: Determining protein-protein interactions and their binding affinity are important in understanding cellular biological processes, discovery and design of novel therapeutics, protein engineering, and mutagenesis studies. Due to the time and effort required in wet lab experiments, computational prediction of binding affinity from sequence or structure is an important area of research. Structure-based methods, though more accurate than sequence-based techniques, are limited in their applicability due to limited availability of protein structure data. RESULTS: In this study, we propose a novel machine learning method for predicting binding affinity that uses protein 3D structure as privileged information at training time while expecting only protein sequence information during testing. Using the method, which is based on the framework of learning using privileged information (LUPI), we have achieved improved performance over corresponding sequence-based binding affinity prediction methods that do not have access to privileged information during training. Our experiments show that with the proposed framework which uses structure only during training, it is possible to achieve classification performance comparable to that which is obtained using structure-based features. Evaluation on an independent test set shows improved performance over the PPA-Pred2 method as well. CONCLUSIONS: The proposed method outperforms several baseline learners and a state-of-the-art binding affinity predictor not only in cross-validation, but also on an additional validation dataset, demonstrating the utility of the LUPI framework for problems that would benefit from classification using structure-based features. The implementation of LUPI developed for this work is expected to be useful in other areas of bioinformatics as well.
Assuntos
Algoritmos , Biologia Computacional/métodos , Aprendizado de Máquina , Proteínas/metabolismo , Sequência de Aminoácidos , Ligantes , Ligação Proteica , Proteínas/química , Curva ROC , Reprodutibilidade dos Testes , Máquina de Vetores de SuporteRESUMO
Due to Ca2+ -dependent binding and the sequence diversity of Calmodulin (CaM) binding proteins, identifying CaM interactions and binding sites in the wet-lab is tedious and costly. Therefore, computational methods for this purpose are crucial to the design of such wet-lab experiments. We present an algorithm suite called CaMELS (CalModulin intEraction Learning System) for predicting proteins that interact with CaM as well as their binding sites using sequence information alone. CaMELS offers state of the art accuracy for both CaM interaction and binding site prediction and can aid biologists in studying CaM binding proteins. For CaM interaction prediction, CaMELS uses protein sequence features coupled with a large-margin classifier. CaMELS models the binding site prediction problem using multiple instance machine learning with a custom optimization algorithm which allows more effective learning over imprecisely annotated CaM-binding sites during training. CaMELS has been extensively benchmarked using a variety of data sets, mutagenic studies, proteome-wide Gene Ontology enrichment analyses and protein structures. Our experiments indicate that CaMELS outperforms simple motif-based search and other existing methods for interaction and binding site prediction. We have also found that the whole sequence of a protein, rather than just its binding site, is important for predicting its interaction with CaM. Using the machine learning model in CaMELS, we have identified important features of protein sequences for CaM interaction prediction as well as characteristic amino acid sub-sequences and their relative position for identifying CaM binding sites. Python code for training and evaluating CaMELS together with a webserver implementation is available at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#camels.
Assuntos
Proteínas de Ligação a Calmodulina/química , Calmodulina/química , Proteoma/genética , Software , Algoritmos , Sequência de Aminoácidos , Sítios de Ligação , Proteínas de Ligação a Calmodulina/genética , Simulação por Computador , Ligação Proteica , Proteoma/químicaRESUMO
Earthworm diversity and ecology in Pakistan is poorly known, especially in the region of Azad Jammu & Kashmir. An earthworm community survey assisted by genetic barcoding detected an unidentified species which could constitute a new record for Pakistan. Morphological study revealed its identity as Perelia kaznakovi. Additionally, Bayesian phylogenetic inference based on five mitochondrial and nuclear molecular markers was performed. Results provided a phylogenetic placement of the genus Perelia within Lumbricidae for the first time, indicating a close relationship with Eophila. This approach should be implemented to Perelia arnoldiana and further representatives of the genus in order to understand their biogeography, diversity and evolutionary history.
Assuntos
Oligoquetos , Animais , Filogenia , Oligoquetos/genética , Paquistão , Teorema de BayesRESUMO
Glycoproteins play an important and ubiquitous role in many biological processes such as protein folding, cell-to-cell signaling, invading microorganism infection, tumor metastasis, and leukocyte trafficking. The key mechanism of glycoproteins must be revealed to model and refine glycosylated protein recognition, which will eventually assist in the design and discovery of carbohydrate-derived therapeutics. Experimental procedures involving wet-lab experiments to reveal glycoproteins are very time-consuming, laborious, and highly costly. However, costly and tedious experimental procedures can be assisted by ranking the most probable glycoproteins through computational methods with improved accuracy. In this study, we have proposed a novel machine learning-based predictive model for glycoproteins identification. Our proposed model is based on sequence-derived structural descriptors (SDSD) that fill the gap of unavailability of protein 3D structures and lack of accuracy in sequence information alone. Through a series of simulation studies, we have shown that our proposed model gives state-of-the-art generalization performance verified through various machine learning-centric and biologically relevant techniques and metrics. Through data mining in this study, we have also identified the role of descriptors in determining glycoproteins. Python-based standalone code together with a webserver implementation of our proposed model (COYOTE: identifiCation Of glYcoprOteins Through sEquences) is available at the URL: https://sites.google.com/view/wajidarshad/software.
Assuntos
Coiotes , Animais , Glicoproteínas/química , Aprendizado de Máquina , Simulação por Computador , Biologia Computacional/métodosRESUMO
Heavy metals contamination in the soil is a major threat to wildlife, the environment, and human health. Microbial remediation is an emerging and promising technology to reduce heavy metals toxicity. Therefore, the present research aimed to isolate and to identify the heavy metals tolerated bacteria from the Eisenia fetida for the first time, and to screen the bacto-remediation capabilities and plant growth promoting traits of vermi-bacterial isolates. Vermi-bacteria was isolated from the gut of E. fetida, identified through staining, culturing, biochemical tests, and ribotyping. Plant growth-promoting traits were also evaluated. Phylogenetic results revealed that isolated Vermi-bacterial strains showed resemblance with Bacillus thuringiensis, Bacillus aryabhattai, Staphylococcus hominis, Bacillus toyonensis, Bacillus cabrialesii, Bacillus tequilensis, Bacillus mojavensis, Bacillus amyloliquefaciens, Bacillus toyonensis, Bacillus anthracis, and Bacillus paranthracis. All identified Vermi-bacterial species are Gram-positive (rod and cocci) in nature, not only indicated the efficient biosorption of lead, cadmium, and chromium but also produce all plant growth stimulating traits such as indole acetic acid (IAA), amylase, protease, lipase, hydrogen cyanide, ammonia, and siderophore production, and also act as a phosphate solubilizers. Bacillus anthracis showed significant production of siderophore (33.0±0.0 mm), phosphate solubilizing (33.0±0.0 mm), proteolytic (15.0±0.0 mm), and lipolytic activities (20.0±0.0 mm) compared to other vermi-bacterial isolates. Bioaccumulation factor results revealed that Bacillus anthracis showed more accumulation of Cd (12.00±0.01 ppm), Cr (5.38±0.01 ppm), and Pb (4.38±0.01 ppm). Therefore, the current findings showed that all identified vermi-bacteria could be used as potential bactoremediation agents in heavy metals polluted environments and could be used as microbial biofertilizers to enhance crop production in a polluted area.
Assuntos
Metais Pesados , Oligoquetos , Poluentes do Solo , Animais , Bacillus , Bactérias , Biodegradação Ambiental , Humanos , Metais Pesados/análise , Metais Pesados/toxicidade , Fosfatos , Filogenia , Sideróforos , Solo , Microbiologia do Solo , Poluentes do Solo/análise , Poluentes do Solo/toxicidadeRESUMO
S-Adenosyl methionine (SAM), a universal methyl group donor, plays a vital role in biosynthesis and acts as an inhibitor to many enzymes. Due to protein interaction-dependent biological role, SAM has become a favorite target in various therapeutical and clinical studies such as treating cancer, Alzheimer's, epilepsy, and neurological disorders. Therefore, the identification of the SAM interacting proteins and their interaction sites is a biologically significant problem. However, wet-lab techniques, though accurate, to identify SAM interactions and interaction sites are tedious and costly. Therefore, efficient and accurate computational methods for this purpose are vital to the design and assist such wet-lab experiments. In this study, we present machine learning-based models to predict SAM interacting proteins and their interaction sites by using only primary structures of proteins. Here we modeled SAM interaction prediction through whole protein sequence features along with different classifiers. Whereas, we modeled SAM interaction site prediction through overlapping sequence windows and ranking with multiple instance learning that allows handling imprecisely annotated SAM interaction sites. Through a series of simulation studies along with biological significant evaluation, we showed that our proposed models give a state-of-the-art performance for both SAM interaction and interaction site prediction. Through data mining in this study, we have also identified various characteristics of amino acid sub-sequences and their relative position to effectively locate interaction sites in a SAM interacting protein. Python code for training and evaluating our proposed models together with a webserver implementation as SIP (Sam Interaction Predictor) is available at the URL: https://sites.google.com/view/wajidarshad/software.
Assuntos
Proteínas , S-Adenosilmetionina , Sequência de Aminoácidos , Simulação por Computador , Aprendizado de Máquina , Proteínas/metabolismo , S-Adenosilmetionina/química , S-Adenosilmetionina/metabolismoRESUMO
Earthworms are highly productive invertebrates and play a vital role in organic farming and improving soil structure and function. The gastrointestinal tract of earthworms possessed agricultural important bacteria. So, the current research aimed was to examine, screen, and identify the plant growth promoting bacteria existing in the digestive tract of Eisenia fetida called plant growth promoting vermi-bacteria. The plant growth promoting traits such as siderophore, phytohormone, and hydrolytic enzymes production, and phosphate solubiliation were assessed. Eleven vermi-bacteria i.e. Bacillus mycoides, B. aryabhattai, B. megaterium, Staphylococcus hominis, B. subtilis, B. spizizenii, B. licheniformis, B. mojavensis, B. toyonensis, B. anthracis, B. cereus, B. thuringiensis, and B. paranthracis were isolated and identified based on microscopic studies, biochemical tests, ribotyping, and agricultural traits. All vermi-bacteria are Gram-positive rods except Staphylococcus hominis and produce different compounds such as siderophore, indole acetic acid, catalase, oxidase, proteases, amylases, and lipases. All vermi-bacteria also act as phosphate solubilizers. Therefore, all isolated vermi-bacteria could be used as potential microbial biofertilizers to enhance crops production in Pakistan.
Assuntos
Oligoquetos , Animais , Bactérias/genética , Trato Gastrointestinal , Fosfatos , Sideróforos , Microbiologia do SoloRESUMO
Accurately determining a change in protein binding affinity upon mutations is important to find novel therapeutics and to assist mutagenesis studies. Determination of change in binding affinity upon mutations requires sophisticated, expensive, and time-consuming wet-lab experiments that can be supported with computational methods. Most of the available computational prediction techniques depend upon protein structures that bound their applicability to only protein complexes with recognized 3D structures. In this work, we explore the sequence-based prediction of change in protein binding affinity upon mutation and question the effectiveness of [Formula: see text]-fold cross-validation (CV) across mutations adopted in previous studies to assess the generalization ability of such predictors with no known mutation during training. We have used protein sequence information instead of protein structures along with machine learning techniques to accurately predict the change in protein binding affinity upon mutation. Our proposed sequence-based novel change in protein binding affinity predictor called PANDA performs comparably to the existing methods gauged through an appropriate CV scheme and an external independent test dataset. On an external test dataset, our proposed method gives a maximum Pearson correlation coefficient of 0.52 in comparison to the state-of-the-art existing protein structure-based method called MutaBind which gives a maximum Pearson correlation coefficient of 0.59. Our proposed protein sequence-based method, to predict a change in binding affinity upon mutations, has wide applicability and comparable performance in comparison to existing protein structure-based methods. We made PANDA easily accessible through a cloud-based webserver and python code available at https://sites.google.com/view/wajidarshad/software and https://github.com/wajidarshad/panda, respectively.
Assuntos
Aprendizado de Máquina , Proteínas , Sequência de Aminoácidos , Mutação , Ligação Proteica , Proteínas/genética , Proteínas/metabolismoRESUMO
Earthworms (Crassiclitellata) being ecosystem engineers significantly affect the physical, chemical, and biological properties of the soil by recycling organic material, increasing nutrient availability, and improving soil structure. The efficiency of earthworms in ecology varies along with species. Therefore, the role of taxonomy in earthworm study is significant. The taxonomy of earthworms cannot reliably be established through morphological characteristics because the small and simple body plan of the earthworm does not have anatomical complex and highly specialized structures. Recently, molecular techniques have been adopted to accurately classify the earthworm species but these techniques are time-consuming and costly. To combat this issue, in this study, we propose a machine learning-based earthworm species identification model that uses digital images of earthworms. We performed a stringent performance evaluation not only through 10-fold cross-validation and on an external validation dataset but also in real settings by involving an experienced taxonomist. In all the evaluation settings, our proposed model has given state-of-the-art performance and justified its use to aid earthworm taxonomy studies. We made this model openly accessible through a cloud-based webserver and python code available at https://sites.google.com/view/wajidarshad/software and https://github.com/wajidarshad/ESIDE.
Assuntos
Processamento de Imagem Assistida por Computador/métodos , Aprendizado de Máquina , Oligoquetos/classificação , Fotografação/instrumentação , Animais , Simulação por Computador , Ecossistema , Oligoquetos/fisiologiaRESUMO
Vermi-composting is an environmental friendly and economic process to decompose organic waste. The objective of this study was to produce vermi-compost using E isenia fetida and to investigate the impact of vermi-compost (VC) and organic manure (cow dung) on seed germination, seedlings, and growth parameters of Tagetes erecta. Physio-chemical parameters of vermi-compost and organic manure were recorded. A potting experiment was designed, germination medium containing soil, sand, and various concentrations of vermi-composts. The composition of germinating media was: TO (Sand + Soil), TCC (Sand + Soil + Cow dung), 10% VC (Sand + Soil + 0.1 kg VC), 15% VC (Sand + Soil + 0.15 kg VC), 20% VC (Sand + Soil + 0.2 kg VC), 25% VC (Sand + Soil + 0.25 kg VC), 30% VC (Sand + Soil + 0.3 kg VC), and 35% VC (Sand + Soil + 0.35 kg VC). Seed germination, seedling, vegetative plant growth, and flowering parameters were evaluated in different germinating media. Pre and post-physio-chemical parameters of germination media were also recorded to check their stability and quality. Results showed that 20% VC was effective for the early initiation of seed germination (2.0 ± 0.0 days) and all growth parameters of marigold seedlings. The germination percentage at 20% VC was recorded as 87.5 ± 1.40 %. The best vegetative plant growth and flowering parameters of marigold plants were observed with 35% VC after transplantation. Findings showed that vermi-compost is the best-suited germination and growing media, which not only improved the soil health but also promoted seed germination and plant growth. Our study undoubtedly indicates that vermi-compost is a more encouraging and advantageous bio-fertilizer and can be used as a powerful and effective for immediate marigold production.
RESUMO
Early diagnosis of Coronavirus disease 2019 (COVID-19) is significantly important, especially in the absence or inadequate provision of a specific vaccine, to stop the surge of this lethal infection by advising quarantine. This diagnosis is challenging as most of the patients having COVID-19 infection stay asymptomatic while others showing symptoms are hard to distinguish from patients having different respiratory infections such as severe flu and Pneumonia. Due to cost and time-consuming wet-lab diagnostic tests for COVID-19, there is an utmost requirement for some alternate, non-invasive, rapid, and discounted automatic screening system. A chest CT scan can effectively be used as an alternative modality to detect and diagnose the COVID-19 infection. In this study, we present an automatic COVID-19 diagnostic and severity prediction system called COVIDC (COVID-19 detection using CT scans) that uses deep feature maps from the chest CT scans for this purpose. Our newly proposed system not only detects COVID-19 but also predicts its severity by using a two-phase classification approach (COVID vs non-COVID, and COVID-19 severity) with deep feature maps and different shallow supervised classification algorithms such as SVMs and random forest to handle data scarcity. We performed a stringent COVIDC performance evaluation not only through 10-fold cross-validation and an external validation dataset but also in a real setting under the supervision of an experienced radiologist. In all the evaluation settings, COVIDC outperformed all the existing state-of-the-art methods designed to detect COVID-19 with an F1 score of 0.94 on the validation dataset and justified its use to diagnose COVID-19 effectively in the real setting by classifying correctly 9 out of 10 COVID-19 CT scans. We made COVIDC openly accessible through a cloud-based webserver and python code available at https://sites.google.com/view/wajidarshad/software and https://github.com/wajidarshad/covidc.
RESUMO
BACKGROUND: Determining binding affinity in protein-protein interactions is important in the discovery and design of novel therapeutics and mutagenesis studies. Determination of binding affinity of proteins in the formation of protein complexes requires sophisticated, expensive and time-consuming experimentation which can be replaced with computational methods. Most computational prediction techniques require protein structures that limit their applicability to protein complexes with known structures. In this work, we explore sequence-based protein binding affinity prediction using machine learning. METHOD: We have used protein sequence information instead of protein structures along with machine learning techniques to accurately predict the protein binding affinity. RESULTS: We present our findings that the true generalization performance of even the state-of-the-art sequence-only predictor is far from satisfactory and that the development of machine learning methods for binding affinity prediction with improved generalization performance is still an open problem. We have also proposed a sequence-based novel protein binding affinity predictor called ISLAND which gives better accuracy than existing methods over the same validation set as well as on external independent test dataset. A cloud-based webserver implementation of ISLAND and its python code are available at https://sites.google.com/view/wajidarshad/software . CONCLUSION: This paper highlights the fact that the true generalization performance of even the state-of-the-art sequence-only predictor of binding affinity is far from satisfactory and that the development of effective and practical methods in this domain is still an open problem.
RESUMO
Begomoviruses interfere with host plant machinery to evade host defense mechanism by interacting with plant proteins. In the old world, this group of viruses are usually associated with betasatellite that induces severe disease symptoms by encoding a protein, ßC1, which is a pathogenicity determinant. Here, we show that ßC1 encoded by Cotton leaf curl Multan betasatellite (CLCuMB) requires Gossypium hirsutum calmodulin-like protein 11 (Gh-CML11) to infect cotton. First, we used the in silico approach to predict the interaction of CLCuMB-ßC1 with Gh-CML11. A number of sequence- and structure-based in-silico interaction prediction techniques suggested a strong putative binding of CLCuMB-ßC1 with Gh-CML11 in a Ca+2-dependent manner. In-silico interaction prediction was then confirmed by three different experimental approaches: The Gh-CML11 interaction was confirmed using CLCuMB-ßC1 in a yeast two hybrid system and pull down assay. These results were further validated using bimolecular fluorescence complementation system showing the interaction in cytoplasmic veins of Nicotiana benthamiana. Bioinformatics and molecular studies suggested that CLCuMB-ßC1 induces the overexpression of Gh-CML11 protein and ultimately provides calcium as a nutrient source for virus movement and transmission. This is the first comprehensive study on the interaction between CLCuMB-ßC1 and Gh-CML11 proteins which provided insights into our understating of the role of ßC1 in cotton leaf curl disease.
Assuntos
Begomovirus/metabolismo , Calmodulina , Gossypium , Doenças das Plantas , Proteínas de Plantas , Calmodulina/genética , Calmodulina/metabolismo , Gossypium/genética , Gossypium/metabolismo , Gossypium/virologia , Doenças das Plantas/genética , Doenças das Plantas/virologia , Proteínas de Plantas/genética , Proteínas de Plantas/metabolismo , Nicotiana/genética , Nicotiana/metabolismo , Nicotiana/virologiaRESUMO
Detection of protein-protein interactions (PPIs) plays a vital role in molecular biology. Particularly, pathogenic infections are caused by interactions of host and pathogen proteins. It is important to identify host-pathogen interactions (HPIs) to discover new drugs to counter infectious diseases. Conventional wet lab PPI detection techniques have limitations in terms of cost and large-scale application. Hence, computational approaches are developed to predict PPIs. This study aims to develop machine learning models to predict inter-species PPIs with a special interest in HPIs. Specifically, we focus on seeking answers to three questions that arise while developing an HPI predictor: (1) How should negative training examples be selected? (2) Does assigning sample weights to individual negative examples based on their similarity to positive examples improve generalization performance? and, (3) What should be the size of negative samples as compared to the positive samples during training and evaluation? We compare two available methods for negative sampling: random versus DeNovo sampling and our experiments show that DeNovo sampling offers better accuracy. However, our experiments also show that generalization performance can be improved further by using a soft DeNovo approach that assigns sample weights to negative examples inversely proportional to their similarity to known positive examples during training. Based on our findings, we have also developed an HPI predictor called HOPITOR (Host-Pathogen Interaction Predictor) that can predict interactions between human and viral proteins. The HOPITOR web server can be accessed at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#HoPItor .
Assuntos
Biologia Computacional/métodos , Interações Hospedeiro-Patógeno/fisiologia , Mapeamento de Interação de Proteínas/métodos , Software , Proteínas Virais/metabolismo , Área Sob a Curva , Simulação por Computador , Bases de Dados de Proteínas , Internet , Aprendizado de Máquina , Distribuição Aleatória , Fator de Transcrição STAT1/metabolismo , Fator de Transcrição STAT2/metabolismoRESUMO
The study of interactions between host and pathogen proteins is important for understanding the underlying mechanisms of infectious diseases and for developing novel therapeutic solutions. Wet-lab techniques for detecting protein-protein interactions (PPIs) can benefit from computational predictions. Machine learning is one of the computational approaches that can assist biologists by predicting promising PPIs. A number of machine learning based methods for predicting host-pathogen interactions (HPI) have been proposed in the literature. The techniques used for assessing the accuracy of such predictors are of critical importance in this domain. In this paper, we question the effectiveness of K-fold cross-validation for estimating the generalization ability of HPI prediction for proteins with no known interactions. K-fold cross-validation does not model this scenario, and we demonstrate a sizable difference between its performance and the performance of an alternative evaluation scheme called leave one pathogen protein out (LOPO) cross-validation. LOPO is more effective in modeling the real world use of HPI predictors, specifically for cases in which no information about the interacting partners of a pathogen protein is available during training. We also point out that currently used metrics such as areas under the precision-recall or receiver operating characteristic curves are not intuitive to biologists and propose simpler and more directly interpretable metrics for this purpose.