Biology subjects

Berenberg, D.

Publications and source records attributed to Berenberg, D..

10 recordsLinked to original sources

bioRxiv2026

On the state of protein function prediction: a report on the fourth CAFA challenge

BackgroundThe Critical Assessment of Functional Annotation (CAFA) is a community effort held to understand the field of computational protein function prediction. Every three years, since 2010, the organizers initiate an experiment to collect function predictions on a large set of proteins and then evaluate the performance of predicting methods on a subset of proteins that have accumulated experimental annotations between the submission deadline and the evaluation time. CAFA provides an independent and rigorous assessment of the current state of the art, thus leveling the playing field, highlighting successes, revealing bottlenecks, and offering a forum for the exchange of ideas in protein science. Here, we report the results of the fourth CAFA experiment (CAFA4). ResultsCAFA4 featured the participation of 148 methods from 70 research groups on a total of 46,205 unique proteins over a 5-year annotation accumulation phase, the longest in any CAFA. In a comparison across CAFA2-CAFA4 methods, the prediction of Gene Ontology (GO) terms has clearly improved across all three GO aspects and traditional evaluation settings. While not achieving the first rank, several CAFA2 and CAFA3 methods featured in the top ten methods in many evaluations, suggesting that earlier methods still hold relevance. The performance is weaker in the newly introduced "partial knowledge" evaluation category (proteins with experimental annotations before submission deadline that gained additional annotations in the same GO aspect during the annotation accumulation phase), highlighting the need for a new class of methods. The rankings of the methods were stable over the years in traditional evaluation settings, but less so in the new partial knowledge evaluation. Overall, the field continues to progress with some influx of new participants. Sustained efforts will be necessary to substantially advance it.

bioinformatics↗

bioRxiv2025

PlasmoFP: leveraging deep learning to predict protein function of uncharacterized proteins across the malaria parasite genus

The first malaria parasite Plasmodium falciparum genome published in 2002 jump-started functional studies, but a large fraction of all predicted proteins remains partially annotated and of unknown function. Here, we introduce Plasmodium Function Predictor (PlasmoFP), deep learning models designed specifically for species of genus Plasmodium. Innovatively, PlasmoFP models are trained on structure-function relationships of the phylogenetically relevant SAR (Stramenopiles, Alveolate, and Rhizarians) supergroup proteins, addressing challenges to annotating Plasmodium proteins due to their low sequence similarity to well-characterized model organism proteins. PlasmoFP models estimate epistemic uncertainty, control false discovery rates in model predictions, and are validated using proteins with manually curated GO terms and experimentally characterized proteins. Integrating PlasmoFP predictions with current protein annotations, we reduced the proportion of unannotated proteins without Gene Ontology terms from 15-59% to 3-28% across 19 Plasmodium species, and improved the proportion of fully annotated proteins from 7-42% to 36-68%. PlasmoFP predictions advance Plasmodium basic research, an important component of global malaria R&D.

bioinformatics↗

bioRxiv2025

Lab-in-the-loop therapeutic antibody design with deep learning

Therapeutic antibody design is a complex multi-property optimization problem with substantial promise for improvement with the application of machine-learning methods. Towards realizing that promise, we introduce "Lab-in-the-loop," a new approach that orchestrates state-of-the-art repertoire mining methods, generative machine learning models, multi-task property predictors, active learning ranking and selection, and in vitro experimentation in a semi-autonomous, iterative optimization loop. By automating the design of antibody variants, property prediction, ranking and selection of designs to assay in the lab, and ingestion of in vitro data, we enable an end-to-end approach to developing computationally-informed therapeutic antibody design pipelines. We apply lab-in-the-loop to eleven seed antibodies obtained via animal immunization with four clinically relevant antigen targets: EGFR, IL-6, HER2, and OSM. Over 1,800 unique antibody variants are tested throughout four rounds of iterative optimization identifying 3-100x better binding variants for all targets and 10/11 seeds, with the best binders exceeding 100 pM affinity, demonstrating a process by which end-to-end machine learning can be developed for therapeutic antibody development.

bioengineering↗

bioRxiv2024

Comparative genomics of the sexually transmitted parasite Trichomonas vaginalis reveals relaxed and convergent evolution and genes involved in spillover from birds to humans

Trichomonas vaginalis is the causative agent of the venereal disease trichomoniasis which infects men and women globally and is associated with serious outcomes during pregnancy and cancers of the human reproductive tract. Trichomonads parasitize a range of hosts in addition to humans including birds, livestock, and domesticated animals. Recent genetic analysis of trichomonads recovered from columbid birds has provided evidence that these parasite species undergo frequent host-switching, and that a current epoch spillover event from columbids likely gave rise to T. vaginalis in humans. We undertook a comparative evolutionary genomics study of seven trichomonad species, generating chromosome-scale reference genomes for T. vaginalis and its avian sister species Trichomonas stableri, and assemblies of five other species that infect birds and mammals. Human-infecting trichomonad lineages have undergone recent and convergent genome size expansions compared to their avian sister species, and the major contributor to their increased genome size is increased repeat expansions, especially multicopy gene families and transposable elements, with genetic drift likely a driver due to relaxed selection. Trichomonads have independently host-switched twice from birds to humans, and genes implicated in the transition to the human host include those associated with host tissue adherence and phagocytosis, extracellular vesicles, and CAZyme virulence factors.

microbiology↗

bioRxiv2022

OpenFold: Retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization

AlphaFold2 revolutionized structural biology with the ability to predict protein structures with exceptionally high accuracy. Its implementation, however, lacks the code and data required to train new models. These are necessary to (i) tackle new tasks, like protein-ligand complex structure prediction, (ii) investigate the process by which the model learns, which remains poorly understood, and (iii) assess the models generalization capacity to unseen regions of fold space. Here we report OpenFold, a fast, memory-efficient, and trainable implementation of AlphaFold2. We train OpenFold from scratch, fully matching the accuracy of AlphaFold2. Having established parity, we assess OpenFolds capacity to generalize across fold space by retraining it using carefully designed datasets. We find that OpenFold is remarkably robust at generalizing despite extreme reductions in training set size and diversity, including near-complete elisions of classes of secondary structure elements. By analyzing intermediate structures produced by OpenFold during training, we also gain surprising insights into the manner in which the model learns to fold proteins, discovering that spatial dimensions are learned sequentially. Taken together, our studies demonstrate the power and utility of OpenFold, which we believe will prove to be a crucial new resource for the protein modeling community.

bioinformatics↗

bioRxiv2022

TM-Vec: template modeling vectors for fast homology detection and alignment

Exploiting sequence-structure-function relationships in molecular biology and computational modeling relies on detecting proteins with high sequence similarities. However, the most commonly used sequence alignment-based methods, such as BLAST, frequently fail on proteins with low sequence similarity to previously annotated proteins. We developed a deep learning method, TM-Vec, that uses sequence alignments to learn structural features that can then be used to search for structure-structure similarities in large sequence databases. We train TM-Vec to accurately predict TM-scores as a metric of structural similarity for pairs of structures directly from sequence pairs without the need for intermediate computation or solution of structures. For remote homologs (sequence similarity [≤] 10%) that are highly structurally similar (TM-score ? 0.6), we predict TM-scores within 0.026 of their value computed by TM-align. TM-Vec outperforms traditional sequence alignment methods and performs similar to structure-based alignment methods. TM-Vec was trained on the CATH and SwissModel structural databases and it has been tested on carefully curated structure-structure alignment databases that were designed specifically to test very remote homology detection methods. It scales sub-linearly for search against large protein databases and is well suited for discovering remotely homologous proteins.

bioinformatics↗

bioRxiv2022

Sequence-structure-function relationships in the microbial protein universe

Abstract / SummaryFor the past half-century, structural biologists relied on the notion that similar protein sequences give rise to similar structures and functions. While this assumption has driven research to explore certain parts of the protein universe, it disregards spaces that dont rely on this assumption. Here we explore areas of the protein universe where similar protein functions can be achieved by different sequences and different structures. We predict [~]200,000 structures for diverse protein sequences from 1,003 representative genomes1 across the microbial tree of life, and annotate them functionally on a per-residue basis. Structure prediction is accomplished using the World Community Grid, a large-scale citizen science initiative. The resulting database of structural models is complementary to the AlphaFold database, with regards to domains of life as well as sequence diversity and sequence length. We identify 148 novel folds and describe examples where we map specific functions to structural motifs. We also show that the structural space is continuous and largely saturated, highlighting the need for shifting the focus from obtaining structures to putting them into context, to transform all branches of biology, including a shift from sequence-based to sequence-structure-function based meta-omics analyses.

bioinformatics↗

bioRxiv2021

Function-guided protein design by deep manifold sampling

Protein design is challenging because it requires searching through a vast combinatorial space that is only sparsely functional. Self-supervised learning approaches offer the potential to navigate through this space more effectively and thereby accelerate protein engineering. We introduce a sequence denoising autoencoder (DAE) that learns the manifold of protein sequences from a large amount of potentially unlabelled proteins. This DAE is combined with a function predictor that guides sampling towards sequences with higher levels of desired functions. We train the sequence DAE on more than 20M unlabeled protein sequences spanning many evolutionarily diverse protein families and train the function predictor on approximately 0.5M sequences with known function labels. At test time, we sample from the model by iteratively denoising a sequence while exploiting the gradients from the function predictor. We present a few preliminary case studies of protein design that demonstrate the effectiveness of this proposed approach, which we refer to as "deep manifold sampling", including metal binding site addition, function-preserving diversification, and global fold change.

bioinformatics↗

bioRxiv2020

Protein Structural Alignments From Sequence

Computing sequence similarity is a fundamental task in biology, with alignment forming the basis for the annotation of genes and genomes and providing the core data structures for evolutionary analysis. Standard approaches are a mainstay of modern molecular biology and rely on variations of edit distance to obtain explicit alignments between pairs of biological sequences. However, sequence alignment algorithms struggle with remote homology tasks and cannot identify similarities between many pairs of proteins with similar structures and likely homology. Recent work suggests that using machine learning language models can improve remote homology detection. To this end, we introduce DeepBLAST, that obtains explicit alignments from residue embeddings learned from a protein language model integrated into an end-to-end differentiable alignment framework. This approach can be accelerated on the GPU architectures and outperforms conventional sequence alignment techniques in terms of both speed and accuracy when identifying structurally similar proteins.

bioinformatics↗

bioRxiv2019

Structure-Based Function Prediction using Graph Convolutional Networks

The large number of available sequences and the diversity of protein functions challenge current experimental and computational approaches to determining and predicting protein function. We present a deep learning Graph Convolutional Network (GCN) for predicting protein functions and concurrently identifying functionally important residues. This model is initially trained using experimentally determined structures from the Protein Data Bank (PDB) but has significant de-noising capability, with only a minor drop in performance observed when structure predictions are used. We take advantage of this denoising property to train the model on > 200,000 protein structures, including many homology-predicted structures, greatly expanding the reach and applications of the method. Our model learns general structure-function relationships by robustly predicting functions of proteins with [≤] 40% sequence identity to the training set. We show that our GCN architecture predicts functions more accurately than Convolutional Neural Networks trained on sequence data alone and previous competing methods. Using class activation mapping, we automatically identify structural regions at the residue-level that lead to each function prediction for every confidently predicted protein, advancing site-specific function prediction. We use our method to annotate PDB and SWISS-MODEL proteins, making several new confident function predictions spanning both fold and function classifications.

bioinformatics↗