Biology subjects

Demir, A.

Publications and source records attributed to Demir, A..

3 recordsLinked to original sources

bioRxiv2023

Topology-Aware Focal Loss for 3D Image Segmentation

The efficacy of segmentation algorithms is frequently compromised by topological errors like overlapping regions, disrupted connections, and voids. To tackle this problem, we introduce a novel loss function, namely Topology-Aware Focal Loss (TAFL), that incorporates the conventional Focal Loss with a topological constraint term based on the Wasserstein distance between the ground truth and predicted segmentation masks persistence diagrams. By enforcing identical topology as the ground truth, the topological constraint can effectively resolve topological errors, while Focal Loss tackles class imbalance. We begin by constructing persistence diagrams from filtered cubical complexes of the ground truth and predicted segmentation masks. We subsequently utilize the Sinkhorn-Knopp algorithm to determine the optimal transport plan between the two persistence diagrams. The resultant transport plan minimizes the cost of transporting mass from one distribution to the other and provides a mapping between the points in the two persistence diagrams. We then compute the Wasserstein distance based on this travel plan to measure the topological dissimilarity between the ground truth and predicted masks. We evaluate our approach by training a 3D U-Net with the MICCAI Brain Tumor Segmentation (BraTS) challenge validation dataset, which requires accurate segmentation of 3D MRI scans that integrate various modalities for the precise identification and tracking of malignant brain tumors. Then, we demonstrate that the quality of segmentation performance is enhanced by regularizing the focal loss through the addition of a topological constraint as a penalty term.

bioinformatics↗

bioRxiv2022

ToDD: Topological Compound Fingerprinting in Computer-Aided Drug Discovery

In computer-aided drug discovery (CADD), virtual screening (VS) is used for identifying the drug candidates that are most likely to bind to a molecular target in a large library of compounds. Most VS methods to date have focused on using canonical compound representations (e.g., SMILES strings, Morgan fingerprints) or generating alternative fingerprints of the compounds by training progressively more complex variational autoencoders (VAEs) and graph neural networks (GNNs). Although VAEs and GNNs led to significant improvements in VS performance, these methods suffer from reduced performance when scaling to large virtual compound datasets. The performance of these methods has shown only incremental improvements in the past few years. To address this problem, we developed a novel method using multiparameter persistence (MP) homology that produces topological fingerprints of the compounds as multidimensional vectors. Our primary contribution is framing the VS process as a new topology-based graph ranking problem by partitioning a compound into chemical substructures informed by the periodic properties of its atoms and extracting their persistent homology features at multiple resolution levels. We show that the margin loss fine-tuning of pretrained Triplet networks attains highly competitive results in differentiating between compounds in the embedding space and ranking their likelihood of becoming effective drug candidates. We further establish theoretical guarantees for the stability properties of our proposed MP signatures, and demonstrate that our models, enhanced by the MP signatures, outperform state-of-the-art methods on benchmark datasets by a wide and highly statistically significant margin (e.g., 93% gain for Cleves-Jain and 54% gain for DUD-E Diverse dataset).

molecular biology↗

bioRxiv2021

Allostery in Proteins as Point-to-Point Telecommunication in a Network: Frequency Decomposed Signal-to-Noise Ratio and Channel Capacity Analysis

AO_SCPLOWBSTRACTC_SCPLOWAllostery in proteins is a phenomenon in which the binding of a ligand induces alterations in the activity of remote functional sites. This can be conceptually viewed as point-to-point telecommunication in a networked communication medium, where a signal (ligand) arriving at the input (binding site) propagates through the network (interconnected and interacting atoms) to reach the output (remote functional site). The reliable transmission of the signal to distal points occurs despite all the disturbances (noise) affecting the protein. Based on this point of view, we propose a computational frequency-domain framework to characterize the displacements and the fluctuations in a region within the protein, originating from the ligand excitation at the binding site and noise, respectively. We characterize the displacements in the presence of the ligand, and the fluctuations in its absence. In the former case, the effect of the ligand is modeled as an external dynamic oscillatory force excitation, whereas in the latter, the sole source of fluctuations is the noise arising from the interactions with the surrounding medium that is further shaped by the internal protein network dynamics. We introduce the excitation frequency as a key factor in a Signal-to-Noise ratio (SNR) based analysis, where SNR is defined as the ratio of the displacements stemming from only the ligand to the fluctuations due to noise alone. We then employ an information-theoretic (communication) channel capacity analysis that extends the SNR based characterization by providing a route for discovering new allosteric regions. We demonstrate the potential utility of the proposed methods for the representative PDZ3 protein.

biophysics↗