Search

Included are the Geometry-Complete Diffusion Model (GCDM)checkpoint filesreferencedin our accompanying GCDM manuscript for 3D molecule generation (https://arxiv.org/abs/2302.04313).

As an aneuploidy, trisomy is associated with mammalian embryonic and postnatal abnormalities. Understanding the underlying mechanisms involved in mutant phenotypes is broadly important and may lead to new strategies to treat clinical manifestations in individuals with trisomies, such as trisomy 21 [Down syndrome (DS)]. Although increased gene dosage effects because of a trisomy may account for the mutant phenotypes, there is also the possibility that phenotypic consequences of a trisomy can arise because of the presence of a freely segregating extra chromosome with its own centromere, i.e. a ‘free trisomy’ independent of gene dosage effects. Presently, there are no reports of attempts to functionally separate these two types of effects in mammals. To fill this gap, here we describe a strategy that employed two new mouse models of DS, Ts65Dn;Df(17)2Yey/+ and Dp(16)1Yey/Df(16)8Yey. Both models carry triplications of the same 103 human chromosome 21 gene orthologs; however, only Ts65Dn;Df(17)2Yey/+ mice carry a free trisomy. Comparison of these models revealed the gene dosage-independent impacts of an extra chromosome at the phenotypic and molecular levels for the first time. They are reflected by impairments of Ts65Dn;Df(17)2Yey/+ males in T-maze tests when compared with Dp(16)1Yey/Df(16)8Yey males. Results from the transcriptomic analysis suggest the extra chromosome plays a major role in trisomy-associated expression alterations of disomic genes beyond gene dosage effects. This model system can now be used to deepen our mechanistic understanding of this common human aneuploidy and obtain new insights into the effects of free trisomies in other human diseases such as cancers.

Cryo-electron microscopy (cryo-EM) is currently the most powerful technique for determining the structures of large protein complexes and assemblies. Picking single-protein particles from cryo-EM micrographs (images) is a key step in reconstructing protein structures. However, the widely used template-based particle picking process is labor-intensive and time-consuming. Though the emerging machine learning-based particle picking can potentially automate the process, its development is severely hindered by lack of large, high-quality, manually labelled training data. Here, we present CryoPPP, a large, diverse, expert-curated cryo-EM image dataset for single protein particle picking and analysis to address this bottleneck. It consists of manually labelled cryo-EM micrographs of 32 non-redundant, representative protein datasets selected from the Electron Microscopy Public Image Archive (EMPIAR). It includes 9,089 diverse, high-resolution micrographs (∼300 cryo-EM images per EMPIAR dataset) in which the coordinates of protein particles were labelled by human experts. The protein particle labelling process was rigorously validated by both 2D particle class validation and 3D density map validation with the gold standard. The dataset is expected to greatly facilitate the development of machine learning and artificial intelligence methods for automated cryo-EM protein particle picking. The dataset and data processing scripts are available athttps://github.com/BioinfoMachineLearning/cryoppp

Motivation Deep learning has revolutionized protein tertiary structure prediction recently. The cutting-edge deep learning methods such as AlphaFold can predict high-accuracy tertiary structures for most individual protein chains. However, the accuracy of predicting quaternary structures of protein complexes consisting of multiple chains is still relatively low due to lack of advanced deep learning methods in the field. Because interchain residue–residue contacts can be used as distance restraints to guide quaternary structure modeling, here we develop a deep dilated convolutional residual network method (DRCon) to predict interchain residue–residue contacts in homodimers from residue–residue co-evolutionary signals derived from multiple sequence alignments of monomers, intrachain residue–residue contacts of monomers extracted from true/predicted tertiary structures or predicted by deep learning, and other sequence and structural features. Results Tested on three homodimer test datasets (Homo_std dataset, DeepHomo dataset and CASP-CAPRI dataset), the precision of DRCon for top L/5 interchain contact predictions (L: length of monomer in a homodimer) is 43.46%, 47.10% and 33.50% respectively at 6 Å contact threshold, which is substantially better than DeepHomo and DNCON2_inter and similar to Glinter. Moreover, our experiments demonstrate that using predicted tertiary structure or intrachain contacts of monomers in the unbound state as input, DRCon still performs well, even though its accuracy is lower than using true tertiary structures in the bound state are used as input. Finally, our case study shows that good interchain contact predictions can be used to build high-accuracy quaternary structure models of homodimers. Availability and implementation The source code of DRCon is available at https://github.com/jianlin-cheng/DRCon. The datasets are available at https://zenodo.org/record/5998532#.YgF70vXMKsB. Supplementary information Supplementary data are available at Bioinformatics online.

Predicting the quaternary structure of protein complex is an important problem. Inter-chain residue-residue contact prediction can provide useful information to guide the ab initio reconstruction of quaternary structures. However, few methods have been developed to build quaternary structures from predicted inter-chain contacts. Here, we develop the first method based on gradient descent optimization (GD) to build quaternary structures of protein dimers utilizing inter-chain contacts as distance restraints. We evaluate GD on several datasets of homodimers and heterodimers using true/predicted contacts and monomer structures as input. GD consistently performs better than both simulated annealing and Markov Chain Monte Carlo simulation. Starting from an arbitrarily quaternary structure randomly initialized from the tertiary structures of protein chains and using true inter-chain contacts as input, GD can reconstruct high-quality structural models for homodimers and heterodimers with average TM-score ranging from 0.92 to 0.99 and average interface root mean square distance from 0.72 Å to 1.64 Å. On a dataset of 115 homodimers, using predicted inter-chain contacts as restraints, the average TM-score of the structural models built by GD is 0.76. For 46% of the homodimers, high-quality structural models with TM-score ≥ 0.9 are reconstructed from predicted contacts. There is a strong correlation between the quality of the reconstructed models and the precision and recall of predicted contacts. Only a moderate precision or recall of inter-chain contact prediction is needed to build good structural models for most homodimers. Moreover, GD improves the quality of quaternary structures predicted by AlphaFold2 on a Critical Assessment of Techniques for Protein Structure Prediction-Critical Assessments of Predictions of Interactions dataset.

Different high temperatures adversely affect crop and algal yields with various responses in photosynthetic cells. The list of genes required for thermotolerance remains elusive. Additionally, it is unclear how carbon source availability affects heat responses in plants and algae. We utilized the insertional, indexed, genome-saturating mutant library of the unicellular, eukaryotic green alga Chlamydomonas reinhardtii to perform genome-wide, quantitative, pooled screens under moderate (35

Protein secondary structure prediction is useful for many applications. It can be considered a language translation problem, i.e., translating a sequence of 20 different amino acids into a sequence of secondary structure symbols (e.g., alpha helix, beta strand, and coil). Here, we develop a novel protein secondary structure predictor called TransPross based on the transformer network and attention mechanism widely used in natural language processing to directly extract the evolutionary information from the protein language (i.e., raw multiple sequence alignment (MSA) of a protein) to predict the secondary structure. The method is different from traditional methods that first generate a MSA and then calculate expert-curated statistical profiles from the MSA as input. The attention mechnism used by TransPross can effectively capture long-range residue-residue interactions in protein sequences to predict secondary structures. Benchmarked on several datasets, TransPross outperforms the state-of-art methods. Moreover, our experiment shows that the prediction accuracy of TransPross positively correlates with the depth of MSAs and it is able to achieve the average prediction accuracy (i.e., Q3 score) above 80% for hard targets with few homologous sequences in their MSAs. TransPross is freely available athttps://github.com/BioinfoMachineLearning/TransPro

An explosion of sequenced genomes and predicted proteomes enabled by low cost deep sequencing has revolutionized biology. Unfortunately, protein functional annotation is more complex, and has not kept pace with the sequencing revolution. We identified unannotated proteins in three model organisms representing distinct parts of the green lineage (Viridiplantae); Arabidopsis thaliana (dicot), Setaria viridis (monocot), and Chlamydomonas reinhardtii (Chlorophyte alga). Using similarity searching we found the subset of unannotated proteins that were conserved between these species and defined them as Deep Green proteins. Informatic, genomic, and structural predictions were leveraged to begin inferring functional information about Deep Green genes and proteins. The Deep Green set was enriched for proteins with predicted chloroplast targeting signals that are predictive of photosynthetic or plastid functions. Strikingly, structural predictions using AlphaFold and comparisons to known structures show that a significant proportion of Deep Green proteins may possess novel protein tertiary structures. The Deep Green genes and proteins provide a starting resource of high value targets for further investigation of potentially new protein structures and functions that are conserved in the green lineage.

The B chromosome of maize undergoes nondisjunction at the second pollen mitosis as part of its accumulation mechanism. Previous work identified 9-Bic-1 (9-B inactivated centromere-1), which comprises an epigenetically silenced B chromosome centromere that was translocated to the short arm of chromosome 9(9S). This chromosome is stable in isolation, but when normal B chromosomes are added to the genotype, it will attempt to undergo nondisjunction during the second pollen mitosis and usually fractures the chromosome in 9S. These broken chromosomes allow a test of whether the inactive centromere is reactivated or whether a de novo centromere is formed elsewhere on the chromosome to allow recovery of fragments. Breakpoint determination on the B chromosome and chromosome 9 showed that mini chromosome B1104 has the same breakpoint as 9-Bic-1 in the B centromere region and includes a portion of 9S. CENH3 binding was found on the B centromere region and on 9S, suggesting both centromere reactivation and de novo centromere formation. Another mini chromosome, B496, showed evidence of rearrangement, but it also only showed evidence for a de novo centromere. Other mini chromosome fragments recovered were directly derived from the B chromosome with breakpoints concentrated near the centromeric knob region, which suggests that the B chromosome is broken at a low frequency due to the failure of the sister chromatids to separate at the second pollen mitosis. Our results indicate that both reactivation and de novo centromere formation could occur on fragments derived from the progenitor possessing an inactive centromere. Supplementary Information The online version contains supplementary material available at 10.1007/s10577-021-09670-5.

Different high temperatures adversely affect crop and algal yields with various responses in photosynthetic cells. The list of genes required for thermotolerance remains elusive. Additionally, it is unclear how carbon source availability affects heat responses in plants and algae. We utilized the insertional, indexed, genome-saturating mutant library of the unicellular, eukaryotic green algaChlamydomonas reinhardtiito perform genome-wide, quantitative, pooled screens under moderate (35°C) or acute (40°C) high temperatures with or without organic carbon sources. We identified heat-sensitive mutants based on quantitative growth rates and identified putative heat tolerance genes (HTGs). By triangulating HTGs with heat-induced transcripts or proteins in wildtype cultures and MapMan functional annotations, we present a high/medium-confidence list of 933Chlamydomonasgenes with putative roles in heat tolerance. Triangulated HTGs include those with known thermotolerance roles and novel genes with little or no functional annotation. About 50% of these high-confidence HTGs in Chlamydomonas have orthologs in green lineage organisms, including crop species.Arabidopsis thalianamutants deficient in the ortholog of a high-confidenceChlamydomonasHTG were also heat sensitive. This work expands our knowledge of heat responses in photosynthetic cells and provides engineering targets to improve thermotolerance in algae and crops.

The inter-residue contact prediction and deep learning showed the promise to improve the estimation of protein model accuracy (EMA) in the 13th Critical Assessment of Protein Structure Prediction (CASP13). To further leverage the improved inter-residue distance predictions to enhance EMA, during the 2020 CASP14 experiment, we integrated several new inter-residue distance features with the existing model quality assessment features in several deep learning methods to predict the quality of protein structural models. According to the evaluation of performance in selecting the best model from the models of CASP14 targets, our three multi-model predictors of estimating model accuracy (MULTICOM-CONSTRUCT, MULTICOM-AI, and MULTICOM-CLUSTER) achieve the averaged loss of 0.073, 0.079, and 0.081, respectively, in terms of the global distance test score (GDT-TS). The three methods are ranked first, second, and third out of all 68 CASP14 predictors. MULTICOM-DEEP, the single-model predictor of estimating model accuracy (EMA), is ranked within top 10 among all the single-model EMA methods according to GDT-TS score loss. The results demonstrate that inter-residue distance features are valuable inputs for deep learning to predict the quality of protein structural models. However, larger training datasets and better ways of leveraging inter-residue distance information are needed to fully explore its potentials.

Most children infected with COVID-19 have no or mild symptoms and can recover automatically by themselves, but some pediatric COVID-19 patients need to be hospitalized or even to receive intensive medical care (e.g., invasive mechanical ventilation or cardiovascular support) to recover from the illnesses. Therefore, it is critical to predict the severe health risk that COVID-19 infection poses to children to provide precise and timely medical care for vulnerable pediatric COVID-19 patients. However, predicting the severe health risk for COVID-19 patients including children remains a significant challenge because many underlying medical factors affecting the risk are still largely unknown. In this work, instead of searching for a small number of most useful features to make prediction, we design a novel large-scale bag-of-words like method to represent various medical conditions and measurements of COVID-19 patients. After some simple feature filtering based on logistical regression, the large set of features is used with a deep learning method to predict both the hospitalization risk for COVID-19 infected children and the severe complication risk for the hospitalized pediatric COVID-19 patients. The method was trained and tested the datasets of the Biomedical Advanced Research and Development Authority (BARDA) Pediatric COVID-19 Data Challenge held from Sept. 15 to Dec. 17, 2021. The results show that the approach can rather accurately predict the risk of hospitalization and severe complication for pediatric COVID-19 patients and deep learning is more accurate than other machine learning methods.

MotivationProteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery.ResultsIn this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures.AvailabilityThe source code, data, and pre-trained models are available athttps://github.com/jianlin-cheng/DProQAContactchengji@missouri.eduSupplementary informationSupplementary data are available atBioinformaticsonline.

Genomic imbalance refers to the more severe phenotypic consequences of changing part of a chromosome compared with the whole genome set. Previous genome imbalance studies in maize have identified prevalent inverse modulation of genes on the unvaried chromosomes (trans) with both the addition or subtraction of chromosome arms. Transposable elements (TEs) comprise a substantial fraction of the genome, and their reaction to genomic imbalance is therefore of interest. Here, we analyzed TE expression using RNA-seq data of aneuploidy and ploidy series and found that most aneuploidies showed an inverse modulation of TEs, but reductions in monosomy and increases in disomy and trisomy were also common. By contrast, the ploidy series showed little TE modulation. The modulation of TEs and genes in the same experimental group were compared, and TEs showed greater modulation than genes, especially in disomy. Class I and II TEs were differentially modulated in most aneuploidies, and some superfamilies in each TE class also showed differential modulation. Finally, the significantly upregulated TEs in three disomies (TB-7Lb, TB9Lc, and TB-10L19) did not increase the proportion of adjacent gene expression when compared with non-differentially expressed TEs, indicating that modulations of TEs do not compound the effect on genes. These results suggest that the prevalent inverse TE modulation in aneuploidy results from stoichiometric upset of the regulatory machinery used by TEs, similar to the response of core genes to genomic imbalance.

Three-dimensional (3D) protein structures reveal the fundamental information about protein function. The state-of-art protein structure prediction methods such as Alphafold are being widely used to predict structures of uncharacterized proteins in biomedical research. There is a significant need to further improve the quality and nativeness of the predicted structures to enhance their usability. Current machine learning methods of refining protein structures focus mostly on improving the backbone quality of predicted structures without effectively leveraging and enhancing the conformation of all atoms including side-chain, while molecular simulation methods are computationally intensive and time-consuming.In this work, we develop ATOMRefine, a deep learning-based, end-to-end, all-atom protein structural model refinement method. It uses a SE(3)-equivariant graph transformer network that is equivariant to the rotation and translation of 3D structures in conjunction with a novel graph representation of all atoms to directly refine protein atomic coordinates of all the atoms in a predicted tertiary structure represented as a molecular graph. The method is first trained and tested on the structural models in AlphafoldDB whose experimental structures are known, and then blindly tested on 69 CASP14 regular targets and 7 CASP14 refinement targets. ATOMRefine improves the quality of both backbone atoms and all-atom conformation of the initial structural models generated by AlphaFold. It also performs better than the state-of-the-art refinement methods in multiple evaluation metrics including an all-atom model quality score – the MolProbity score based on the analysis of all-atom contacts, bond length, atom clashes, torsion angles, and side-chain rotamers. As ATOMRefine can refine a protein structure quickly, it provides a viable, fast solution for improving protein geometry and fixing structural errors of predicted structures through direct coordinate refinement.

Predicted interchain residue-residue contacts can be used to build the quaternary structure of protein complexes from scratch. However, only a small number of methods have been developed to reconstruct protein quaternary structures using predicted interchain contacts. Here, we present an agent-based self-learning method based on deep reinforcement learning (DRLComplex) to build protein complex structures using interchain contacts as distance constraints. We rigorously tested the DRLComplex on two standard datasets of homodimeric and heterodimeric dimers (the CASP-CAPRI homodimer dataset and Std_32 heterodimer dataset) using both true and predicted contacts. Utilizing true contacts as input, the DRLComplex achieved a high average TM-score of 0.9895 and 0.9881 and a low average interface RMSD (I_RMSD) of 0.2197 and 0.92 on the two datasets, respectively. When predicted contacts are used, the method achieves the TM-score of 0.73 and 0.76 for homodimers and heterodimers respectively. The accuracy of reconstructed quaternary structures depends on the accuracy of contact predictions. Compared with other optimization methods of reconstructing quaternary structures from interchain contacts, DRLComplex performs similarly to an advanced gradient descent method and better than a Markov Chain Monte Carlo simulation method and a simulated annealing-based method. The source code of DRLComplex is available at: https://github.com/jianlin-cheng/DRLComplex

A simple and sensitive colorimetric sensing method was constructed for detection of Hg2+ in aqueous solutions and based on silver nanoparticles functionalized with l-cysteine (l-Cys-Ag NPs). In this method, adenosine triphosphate (ATP) induced aggregation of l-Cys-Ag NPs. Simultaneously, the solution colour changed from bright yellow to brown. In the presence of Hg2+ , Hg2+ chelated ATP to form a complex and reduce the degree of aggregation of l-Cys-Ag NPs and was accompanied by a colour change from brown to bright yellow. The changing values of absorbance at 390 nm were linearly correlated with concentration of Hg2+ over the 4.00 × 10-8 to 1.04 × 10-6 mol·L-1 range, with a detection limit of 8 nM. This method was used successfully for detection of Hg2+ in real water samples and performed good selectivity and sensitivity. The recovery range was 91.5-109.1%, indicating that the method has vast application potential for determination of Hg2+ in the environment.

Hydrogen diffusion plays a key role in hydrogen embrittlement which leads to the failure of metals. In the present work, hydrogen diffusions in Fe and α-Fe2O3 were studied by first-principles calculations. The results show the energy barrier of hydrogen diffusion in pure Fe is small and hydrogen atom has a high diffusivity at ambient temperature. In contrast, the hydrogen in α-Fe2O3 has a much higher diffusion energy barrier and doesn't diffuse below 600 K. The present study indicates the in-situ oxidation of iron could be an effective hydrogen diffusion barrier to prevent the hydrogen embrittlement issue in metals.

Background Cryo-electron microscopy (Cryo-EM) is widely used in the determination of the three-dimensional (3D) structures of macromolecules. Particle picking from 2D micrographs remains a challenging early step in the Cryo-EM pipeline due to the diversity of particle shapes and the extremely low signal-to-noise ratio of micrographs. Because of these issues, significant human intervention is often required to generate a high-quality set of particles for input to the downstream structure determination steps. Results Here we propose a fully automated approach (DeepCryoPicker) for single particle picking based on deep learning. It first uses automated unsupervised learning to generate particle training datasets. Then it trains a deep neural network to classify particles automatically. Results indicate that the DeepCryoPicker compares favorably with semi-automated methods such as DeepEM, DeepPicker, and RELION, with the significant advantage of not requiring human intervention. Conclusions Our framework combing supervised deep learning classification with automated un-supervised clustering for generating training data provides an effective approach to pick particles in cryo-EM images automatically and accurately.

Design of materials with desired properties is currently laborious and heavily relies on intuition of researchers through a trial-and-error process. To tackle this challenge, we propose a novel regressional and conditional generative adversarial network (RCGAN) for inverse design of representative two-dimensional materials, the graphene and boron-nitride (BN) hybrids. RCGAN incorporates a supervised regressor network, thus overcoming the common technical barrier in the traditional unsupervised GANs, which cannot generate data when fed with continuous and quantitative labels. RCGAN can autonomously generate graphene/BN hybrids given any target bandgap values. These structures are distinguished from the ones used for training and exhibit high diversity for a given bandgap. Moreover, they exhibit high fidelity, yielding bandgaps within ∼10% MAEF of the desired bandgaps as validated by density functional theory (DFT) calculations. Analysis by the principle component analysis (PCA) and modified locally linear embedding (MLLE) reveals that the generator has successfully generated structures following the statistical distribution of the real structures. It implies the possibility of the RCGAN in recognizing physical rules hidden in the high-dimensional data. The novel strategy for designing regressional GAN architecture together with the successful application to inverse design of materials would inspire further exploration in research fields beyond materials.

Computational biology is one of many scientific disciplines ripe for innovation and acceleration with the advent of high-performance computing (HPC). In recent years, the field of machine learning has also seen significant benefits from adopting HPC practices. In this work, we present a novel HPC pipeline that incorporates various machine-learning approaches for structure-based functional annotation of proteins on the scale of whole genomes. Our pipeline makes extensive use of deep learning and provides computational insights into best practices for training advanced deep-learning models for high-throughput data such as proteomics data. We showcase methodologies our pipeline currently supports and detail future tasks for our pipeline to envelop, including large-scale sequence comparison using SAdLSA and prediction of protein tertiary structures using AlphaFold2.

The non-essential supernumerary maize (Zea mays) B chromosome (B) has recently been shown to contain active genes and to be capable of impacting gene expression of the A chromosomes. However, the effect of the B chromosome on gene expression is still unclear. In addition, it is unknown whether the accumulation of the B chromosome has a cumulative effect on gene expression. To examine these questions, the global expression of genes, microRNAs (miRNAs), and transposable elements (TEs) of leaf tissue of maize W22 plants with 0-7 copies of the B chromosome was studied. All experimental genotypes with B chromosomes displayed a trend of upregulated gene expression for a subset of A-located genes compared to the control. Over 3000 A-located genes are significantly differentially expressed in all experimental genotypes with the B chromosome relative to the control. Modulations of these genes are largely determined by the presence rather than the copy number of the B chromosome. By contrast, the expression of most B-located genes is positively correlated with B copy number, showing a proportional gene dosage effect. The B chromosome also causes increased expression of A-located miRNAs. Differentially expressed miRNAs potentially regulate their targets in a cascade of effects. Furthermore, the varied copy number of the B chromosome leads to the differential expression of A-located and B-located TEs. The findings provide novel insights into the function and properties of the B chromosome.