Biology subjects

Akpinaroglu, D.

Publications and source records attributed to Akpinaroglu, D..

6 recordsLinked to original sources

bioRxiv2025

A combinatorial mutational map of active non-native protein kinases by deep learning guided sequence design

Mapping protein sequence-function landscapes has either been limited to small steps (only few mutations) or to sequences similar to those already explored by evolution to maintain activity. Here, we overcome both limitations by applying deep-learning guided redesign to a natural protein tyrosine kinase to generate novel, functional sequences with highly combinatorial mutations. Using cell-free assays, we measure the activities and concentrations of 537 redesigned sequences, which differ from the wild-type by an average of 37 mutations while retaining activity in 85% of variants. These sequences sample 436 unique mutations at 76 different positions throughout the kinase domain. A simple regression model identifies key sequence determinants of function and predicts the function of unseen sequences. Our approach demonstrates how integrating deep-learning guided redesign, functional measurement at scale, and interpretable computational modelling enables functional exploration of highly combinatorial and sparse sequence-function landscapes at mutational scales not possible before.

biochemistry↗

bioRxiv2025

An improved model for prediction of de novo designed proteins with diverse geometries

Nature uses structural variations on protein folds to fine-tune the geometries of proteins for diverse functions, yet deep learning-based de novo protein design methods generate highly regular, idealized protein fold geometries that fail to capture natural diversity. Here, using physics-based design methods, we generated and experimentally validated a dataset of 5,996 stable, de novo designed proteins with diverse non-ideal geometries. We show that deep learning-based structure prediction methods applied to this set have a systematic bias towards idealized geometries. To address this problem, we present a fine-tuned version of Alphafold2 that is capable of recapitulating geometric diversity and generalizes to a new dataset of thousands of geometrically diverse de novo proteins from 5 fold families unseen in fine-tuning. Our results suggest that current deep learning-based structure prediction methods do not capture some of the physics that underlie the specific conformational preferences of proteins designed de novo and observed in nature. Ultimately, approaches such as ours and further informative datasets should lead to improved models that reflect more of the physical principles of atomic packing and hydrogen bonding interactions and enable improved generalization to more challenging design problems.

bioinformatics↗

bioRxiv2024

Deep learning guided design of dynamic proteins

Deep learning has greatly advanced design of highly stable static protein structures, but the controlled conformational dynamics that are hallmarks of natural switch-like signaling proteins have remained inaccessible to de novo design. Here, we describe a general deep-learning-guided approach for de novo design of dynamic changes between intra-domain geometries of proteins, similar to switch mechanisms prevalent in nature, with atom-level precision. We solve 4 structures validating the designed conformations, show microsecond transitions between them, and demonstrate that the conformational landscape can be modulated by orthosteric ligands and allosteric mutations. Physics-based simulations are in remarkable agreement with deep-learning predictions and experimental data, reveal distinct state-dependent residue interaction networks, and predict mutations that tune the designed conformational landscape. Our approach demonstrates that new modes of motion can now be realized through de novo design and provides a framework for constructing biology-inspired, tunable and controllable protein signaling behavior de novo.

bioengineering↗

bioRxiv2023

Structure-conditioned masked language models for protein sequence design generalize beyond the native sequence space

Machine learning has revolutionized computational protein design, enabling significant progress in protein backbone generation and sequence design. Here, we introduce Frame2seq, a structure-conditioned masked language model for protein sequence design. Frame2seq generates sequences in a single pass, achieves 49.1% sequence recovery on the CATH 4.2 test dataset, and accurately estimates the error in its own predictions, outperforming the autoregressive ProteinMPNN model with over six times faster inference. To probe the ability of Frame2seq to generate novel designs beyond the native-like sequence space it was trained on, we experimentally test 26 Frame2seq designs for de novo backbones with low identity to the starting sequences. We show that Frame2seq successfully designs soluble (22/26), monomeric, folded, and stable proteins (17/26), including a design with 0% sequence identity to native. The speed and accuracy of Frame2seq will accelerate exploration of novel sequence space across diverse design tasks, including challenging applications such as multi-objective optimization.

bioengineering↗

bioRxiv2021

Separable mechanisms drive local and global polarity establishment in the C. elegans intestinal epithelium

Apico-basolateral polarization is essential for epithelial cells to function as selective barriers and transporters, and to provide mechanical resiliency to organs. Epithelial polarity is established locally, within individual cells to establish distinct apical, junctional, and basolateral domains, and globally, within a tissue where cells coordinately orient their apico-basolateral axes. Using live imaging of endogenously tagged proteins and tissue specific protein depletion in the C. elegans embryonic intestine, we found that local and global polarity establishment are temporally and genetically separable. Local polarity is initiated prior to global polarity and is robust to perturbation. PAR-3 is required for global polarization across the intestine but is not required for local polarity establishment as small groups of cells are able to correctly establish polarized domains in PAR-3 depleted intestines in an HMR-1/E-cadherin dependent manner. Despite belonging to the same apical protein complex, we additionally find that PAR-3 and PKC-3/aPKC have distinct roles in the establishment and maintenance of local and global polarity. Together, our results indicate that different mechanisms are required for local and global polarity establishment in vivo. SUMMARY STATEMENTLive-imaging and intestine specific protein depletion reveal that apico-basolateral polarity establishment can be temporally and genetically separated at the local level of individual cells and globally, across a tissue.

cell biology↗

bioRxiv2021

Improved antibody structure prediction by deep learning of side chain conformations

Antibody engineering is becoming increasingly popular in medicine for the development of diagnostics and immunotherapies. Antibody function relies largely on the recognition and binding of antigenic epitopes via the loops in the complementarity determining regions. Hence, accurate high-resolution modeling of these loops is essential for effective antibody engineering and design. Deep learning methods have previously been shown to effectively predict antibody backbone structures described as a set of inter-residue distances and orientations. However, antigen binding is also dependent on the specific conformations of surface side chains. To address this shortcoming, we created DeepSCAb: a deep learning method that predicts inter-residue geometries as well as side chain dihedrals of the antibody variable fragment. The network requires only sequence as input, rendering it particularly useful for antibodies without any known backbone conformations. Rotamer predictions use an interpretable self-attention layer, which learns to identify structurally conserved anchor positions across several species. We evaluate the performance of our model for discriminating near-native structures from sets of decoys and find that DeepSCAb outperforms similar methods lacking side chain context. When compared to alternative rotamer repacking methods, which require an input backbone structure, DeepSCAb predicts side chain conformations competitively. Our findings suggest that DeepSCAb improves antibody structure prediction with accurate side chain modeling and is adaptable to applications in docking of antibody-antigen complexes and design of new therapeutic antibody sequences.

biophysics↗