Abstract

Determining spin state energy gaps (SSE) of 3d transition metal complexes (TMCs) is a major challenge in theoretical chemistry, as high-level quantum methods, though reliable, are computationally impractical for large-scale studies. This work explores a machine learning (ML)-based approach to predict DFT adiabatic SSE gaps using descriptors derived from a single high-spin DFT calculation. This approach is adopted to eliminate the differential treatment of electronic correlation between high-spin and low-spin structures. Our descriptors aim to incorporate the knowledge of crystal field theory into the ML model. They include atomic energy levels of bare metal ions, natural charges of ligating atoms, d-orbital molecular orbital eigenvalues derived from an high spin calculation, HOMO–LUMO gaps of free ligands, and simple identity-based features. We train ML models on 1434 SSE values spanning 934 complexes and demonstrate their transferability to more challenging complexes having bidentate π-bonding ligands despite being trained on simpler Werner-type monodentate complexes. We achieved a minimum MAE of 4.0 kcal mol−1 on the monodentate test set, and maintained a comparable MAE of 6.6 kcal mol−1 in the transferability assessment. This approach bypasses the need for multi-reference low-spin optimizations while retaining predictive accuracy, offering a cost-effective strategy for SSE estimation in transition metal chemistry. We hope the insights covered in this study will contribute to the development of additional electronic structure-based descriptors for SSE predictions.

Abstract

Inverse of an invertible convolution is an important operation that comes up in Normalizing Flows, Image Deblurring, etc. The naive algorithm for backpropagation of this operation using Gaussian elimination has running time where is the number of pixels in the image. We give a fast parallel backpropagation algorithm with running time for a square image and provide a GPU implementation of the same. Inverse Convolutions are usually used in Normalizing Flows in the sampling pass, making them slow. We propose to use Inverse Convolutions in the forward (image to latent vector) pass of the Normalizing flow. Since the sampling pass is the inverse of the forward pass, it will use convolutions only, resulting in efficient sampling times. We use our parallel backpropagation algorithm for optimizing the inverse convolution layer resulting in fast training times also. We implement this approach in various Normalizing Flow backbones, resulting in our Inverse-Flow models. We benchmark Inverse-Flow on standard datasets and show significantly improved sampling times with similar bits per dimension compared to previous models.

Abstract

Purpose : Foveal Hypoplasia (FH) is a macular abnormality characterised by incomplete development of the foveal region. This abnormality is most commonly observed alongside rare inherited disorders such as albinism, but the precise mechanisms behind abnormal foveal development remain unclear. Thus, we aimed to identify genetic loci associated with FH, to provide insight into the genetic architecture of normal and abnormal foveal development. Methods : We developed a deep learning model to analyse retinal OCT scans from a subset of UK Biobank participants, classifying individuals of European descent into FH (n=4403) and control groups (n=30069). FH classification was then used to conduct a genome-wide association study (GWAS) using these 34,472 individuals, and associations were mapped to causative genes using single nuclei multi-omics data obtained from embryonic and foetal retinal tissue. Further prioritisation of candidate genes was sought by performing CRISPR-Cas9 mediated knockout of target genes in Zebrafish. Genes were prioritised based on the impact of gene knockouts on visual function in Zebrafish, assessed using the optokinetic response. Results : Our GWAS identified 44 genetic variants independently associated with FH (P<5×10-8), including 31 novel variants not previously linked to FH or related traits. These novel associations include variants in genes such as TYR and OCA2, known for their roles in FH in a Mendelian context, and 28 novel genes not previously associated with FH. The identified genes operate in various biological processes such as the melanin biosynthesis pathway, melanosome function, cell fate and temporal patterning. This aligns with the functional characteristics of causative FH genes. Conclusions : In the first GWAS study of FH, we uncovered novel genetic associations critical to understanding foveal development. The identified associations offer new avenues for research, providing mechanistic insight into the genetic factors underpinning the foveal region's development and the pathogenesis of FH.

Abstract

Purpose : This study aims to develop an artificial intelligence (AI)-based system for accurately grading arrested retinal development using optical coherence tomography (OCT) across various manufacturers. We employ deep learning techniques, specifically Unsupervised Domain Adaptation (UDA), to create a device-agnostic classification model distinguishing normal and abnormal retinal development. Methods : Foveal scans from three OCT manufacturers (TM-OCT1, HH-OCT1, TM-OCT2, TM-OCT3) were collected and annotated from datasets exceeding 20,000 OCT scans. The dataset was divided into training (80%) and testing (20%) sets. We utilised Convolutional Neural Networks (CNN) with ResNet50 backbone, assessing each pair as the source (for supervised training) and target (for unsupervised training). The diagnostic accuracy of the AI models was compared to seven clinician graders with varying experience (1 to 10 years), evaluating sensitivity, specificity, and overall accuracy. Results : The cross-domain binary classification demonstrated exceptional diagnostic accuracy ranging from 87.75% to 96.06%. Sensitivity and specificity metrics further validated the robustness of our AI system (sensitivity: 88.68% to 98.38%, specificity: 78.00% to 98.02%). Notably, the model trained on TM-OCT1 and HH-OCT1 achieved 96.06% accuracy, 98.38% sensitivity, and 89.11% specificity on the HH-OCT1 test set, with an Area Under the Curve (AUC) of 99.4 (95% CI). These outcomes highlight the system's ability to distinguish normal and abnormal retinal development across diverse OCT devices. Conclusions : Our study demonstrates, for the first time, the feasibility of employing a device-agnostic AI system in paediatric OCT interpretation without additional labelled data. The AI system's diagnostic performance is comparable to a clinician with over 10 years of experience, showcasing its potential to reduce inter-examiner variability and enhance clinical care pathways. With integration of paediatric OCT into routine clinical assessment, our AI system serves as a robust foundation for the development of a real-time, frontline diagnostic tool for retinal developmental disorders.

Abstract

Large-scale deployment of fully autonomous vehicles requires a very high degree of robustness to unstructured traffic, weather conditions, and should prevent unsafe mispredictions. While there are several datasets and benchmarks focusing on segmentation for drive scenes, they are not specifically focused on safety and robustness issues. We introduce the IDD-AW dataset, which provides 5000 pairs of high-quality images with pixel-level annotations, captured under rain, fog, low light, and snow in unstructured driving conditions. As compared to other adverse weather datasets, we provide i.) more annotated images, ii.) paired Near-Infrared (NIR) image for each frame, iii.) larger label set with a 4-level label hierarchy to capture unstructured traffic conditions. We benchmark state-of-the-art models for semantic segmentation in IDD-AW. We also propose a new metric called “Safe mean Intersection over Union (Safe mIoU)” for hierarchical datasets which penalizes dangerous mispredictions that are not captured in the traditional definition of mean Intersection over Union (mIoU). The results show that IDD-AW is one of the most challenging datasets to date for these tasks. The dataset and code will be available here: http://iddaw.github.io.

Abstract

Molecular spectroscopy studies the interaction of molecules with electromagnetic radiation, and interpreting the resultant spectra is invaluable for deducing the molecular structures. However, predicting the molecular structure from spectroscopic data is a strenuous task that requires highly specific domain knowledge. DeepSPInN is a deep reinforcement learning method that predicts the molecular structure when given Infrared and 13C Nuclear magnetic resonance spectra by formulating the molecular structure prediction problem as a Markov decision process (MDP) and employs Monte-Carlo tree search to explore and choose the actions in the formulated MDP. On the QM9 dataset, DeepSPInN is able to predict the correct molecular structure for 91.5% of the input spectra in an average time of 77 seconds for molecules with less than 10 heavy atoms. This study is the first of its kind that uses only infrared and 13C nuclear magnetic resonance spectra for molecular structure prediction without referring to any pre-existing spectral databases or molecular fragment knowledge bases, and is a leap forward in automated molecular spectral analysis.

Abstract

The discovery of potential therapeutic agents for life‑threatening diseases has become a significant problem. There is a requirement for fast and accurate methods to identify drug‑like molecules that can be used as potential candidates for novel targets. Existing techniques like high‑throughput screening and virtual screening are time‑consuming and inefficient. Traditional molecule generation pipelines are more efficient than virtual screening but use time‑consuming docking software. Such docking functions can be emulated using Machine Learning models with comparable accuracy and faster execution times. However, we find that when pre‑trained machine learning models are employed in generative pipelines as oracles, they suffer from model degradation in areas where data is scarce. In this study, we propose an active learning‑based model that can be added as a supplement to enhanced molecule generation architectures. The proposed method uses uncertainty sampling on the molecules created by the generator model and dynamically learns as the generator samples molecules from different regions of the chemical space. The proposed framework can generate molecules with high binding affinity with ∼a 70% improvement in runtime compared to the baseline model by labeling only ∼30% of molecules compared to the baseline oracle.

Abstract

Air pollution is a growing concern across the world. Road traffic is one of the major contributors to air pollution in urban areas. One of the approaches to solve this problem is to design a transportation policy that i) avoids extreme pollution in any area, ii) enables short transit times, and iii) makes effective use of the road capacities. Previous work to address this problem named MaxFlow-MCMC algorithm, proposed a novel sampling-based approach for this problem. In this work, we propose a significantly faster extension to the algorithm without compromising on the performance involving the following contributions: (a) We provide the first construction of a Markov Chain to sample a set of k-optimal max flow solutions directly from a planar graph. (b) We simulate traffic on large-scale real-world roadmaps using the SUMO traffic simulator. We observe a significant speed improvement in the range of 22 to 242 times in our experiments while obtaining lesser average pollution.

Abstract

Semantic segmentation provides a pixel-level understanding of an image essential for various scene-understanding vision tasks. However, semantic segmentation models demand significant computational resources during training and inference. These requirements pose a challenge in resource-constraint scenarios. To address this issue, we present a compression algorithm based on differentiable meta-pruning through hypernetwork: MPHyp. Our proposed method MPHyp utilizes hypernetworks that take latent vectors as input and output weight matrices for the segmentation model. L1 sparsification follows the proximal gradient optimizer, updates the latent vectors and introduces sparsity leading to automatic model pruning. The proposed method offers the benefit of achieving controllable compression during the training and significantly reducing the training time. We compare our methodology with a popular pruning approach and demonstrate its efficacy by reducing the number of parameters and floating point operations while maintaining the mean Intersection over Union (mIoU) metric. We conduct experiments on two widely accepted semantic segmentation architectures: UNet and ERFNet. Our experiments and ablation study demonstrate the effectiveness of our proposed methodology by achieving efficient and reasonable segmentation results.

Abstract

Large-scale deployment of fully autonomous vehicles re- quires a very high degree of robustness to unstructured traf- fic, weather conditions, and should prevent unsafe mispre- dictions. While there are several datasets and benchmarks focusing on segmentation for drive scenes, they are not specifically focused on safety and robustness issues. We introduce the IDD-AW dataset, which provides 5000 pairs of high-quality images with pixel-level annotations, cap- tured under rain, fog, low light, and snow in unstructured driving conditions. As compared to other adverse weather datasets, we provide i.) more annotated images, ii.) paired Near-Infrared (NIR) image for each frame, iii.) larger label set with a 4-level label hierarchy to capture unstructured traffic conditions. We benchmark state-of-the-art models for semantic segmentation in IDD-AW. We also propose a new metric called “Safe mean Intersection over Union (Safe mIoU)” for hierarchical datasets which penalizes danger- ous mispredictions that are not captured in the traditional definition of mean Intersection over Union (mIoU). The re- sults show that IDD-AW is one of the most challenging datasets to date for these tasks. The dataset and code will be available here: http://iddaw.github.io