Biology subjects

Gorantla, R.

Publications and source records attributed to Gorantla, R..

11 recordsLinked to original sources

bioRxiv2026

Do LLM Proposers Improve Budgeted Search for Ionizable Lipids?

Efficient lipid design under limited experimental budgets is a central challenge in computational chemistry and drug discovery. We introduce LEAF (Lipid Evolutionary Adaptive Framework), a matched-budget protocol for testing whether language-model proposers improve combinatorial molecular search relative to classical baselines. The study uses a 30,044-candidate ionizable-lipid space, a frozen Gaussian-process oracle fitted to experimental potency labels, and a separate active-learning surrogate. Four language models evaluated over eight seeds and three splits show no significant improvement over genetic-algorithm or random-search baselines. For Llama 8B, 79.1% of acquisition-selected queries repeat previously evaluated archive members. Removing duplicates reduces the performance gap on some splits but increases proposal cost and can prevent budget exhaustion. Larger models reduce duplication without establishing superiority or equivalence. Exploratory scored prompts and stricter novelty controls yield positive median differences against the genetic algorithm, yet wide intervals and shared-seed dependence preclude stronger conclusions. A validated single-assay reanalysis preserves the chemotype-cold deficit at a smaller numerical scale, and exploratory expected hypervolume improvement does not reverse the result. Follow-up checks address whether proposers genuinely use injected evidence. These checks include a zero-shot leakage probe, rank-only and chain-of-thought-rationale prompts, a score-shuffle perturbation, an evidence-conflict probe, and a genuine reasoning-mode proposer. They show measurable engagement with supplied information without a corresponding performance gain. LEAF isolates proposal quality as the experimental variable and documents a concrete failure mode of zero-shot LLM proposers under controlled budgets.

bioinformatics↗

bioRxiv2026

GRASP: Graph Representation Learning with Assay Supervision for Molecular Properties

Molecular structures are abundant, while experimental bioactivity is sparse and distributed across assays. We introduce GRASP, a 93.5M-parameter graph Transformer that learns from these sources in sequence. GRASP first learns molecular structure through replaced-token detection on 1.54 billion ZINC20 molecule presentations, then adapts to sparse bioactivity across 642 ChEMBL assays. Across 23 cluster-held-out OpenADMET endpoints, GRASP achieves a mean MAE of 0.374, compared with 0.383 for CheMeleon, 0.408 for ECFP4-LightGBM, and 0.440 for Chemprop. ChEMBL adaptation reduces mean MAE from 0.407 to 0.374 and improves 21 of 23 endpoints, showing the value of intermediate bioactivity supervision. On 22 TDC ADMET tasks, GRASP gives a better point estimate than CheMeleon on 13 tasks. These results support staged molecular representation learning, where abundant molecular structure and sparse experimental measurements provide complementary supervision at different stages of training.

bioinformatics↗

bioRxiv2026

Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states

Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.

bioinformatics↗

bioRxiv2026

Antibody-Antigen Affinity Prediction with Chain-Aware Protein Language Modeling

MotivationAntibody-antigen affinity determines which antibodies advance in therapeutic discovery, repertoire analysis and affinity maturation, but experimental measurements are sparse relative to the scale of sequence libraries. Structure-based predictors can exploit interface geometry when reliable complexes are available, yet early discovery often requires ranking many heavy-light chain pairs against antigens for which no complex structure exists. Existing sequence-based models are scalable, but frequently compress heavy and light chains into a single antibody representation or concatenate antibody and antigen features obscuring the chain-specific and epitope-specific signals that drive binding. ResultsWe present AbAffinity, a sequence-only chain-aware three-stream architecture that maintains heavy chain, light chain and antigen as distinct streams. It integrates frozen ESM-2 embeddings with heavy-chain CDR-focused pooling, heavy-light self-attention, adaptive fusion gating and gated cross-attention, training only a compact interaction module. On the SAAINT-DB benchmark, AbAffinity achieves strong predictive performance under ten-fold cross-validation and maintains robust accuracy on novel antigens. It consistently outperforms recent sequence-based models across external benchmarks including SAbDab, AB-Bind and SKEMPI 2.0. Ablation studies highlight the contributions of chain-specific representations, CDR-focused pooling and the gated interaction pathway. Integrated Gradients attributions recover known paratope and epitope residues at structurally validated interfaces. AbAffinity provides a lightweight, explainable sequence-first framework for antibody triage and prioritisation when structural information is limited or unavailable.

bioinformatics↗

bioRxiv2026

Explainable protein-protein binding affinity prediction via fine-tuning protein language models

Protein-protein interactions underpin virtually every aspect of cellular life, and the precise quantification of their binding affinity is fundamental to understanding immune recognition, disease mechanisms, and the rational design of therapeutic antibodies. Yet predicting binding affinity at scale remains an unsolved challenge: reliable experimental assays are low-throughput and expensive, while computational methods that depend on three-dimensional complex struc-tures cannot be applied to the vast majority of clinically relevant targets where structural data are absent. Here we present BALM-PPI, a framework that predicts protein-protein binding affinity from amino acid sequence alone. Both proteins are encoded by a protein language model trained on evolutionary sequence data and projected into a shared representational space, where their distance directly reflects binding strength. Fine-tuning this protein language model requires updating fewer than 1% of its parameters, and we show that this targeted adaptation steers the model toward interface-relevant sequence signals rather than spurious background correlations. On a curated benchmark of over 12,000 protein complexes, BALM-PPI matches or exceeds the accuracy of structure-based methods and retains predictive power for proteins with less than 30% sequence identity to the training set. Using only a subset of project-specific assay data, BALM-PPI outperforms a recent method trained on three times the data, suggesting that the model has already encoded the underlying interaction signals and requires only minimal supervision to specialise to a new target. BALM-PPI further provides residue-level attribution maps that pinpoint the amino acid positions driving each affinity prediction, consistently re-covering experimentally validated interaction hotspots across enzyme-inhibitor, signalling, and antibody-antigen systems without any structural input during training. This allows predictions to be cross-validated against structural and mutagenesis evidence, providing a mechanistic basis for candidate shortlisting ahead of experimental follow-up. BALM-PPI is freely accessible via an interactive web server.

bioinformatics↗

bioRxiv2025

Explainable Active Learning Framework for Ligand BindingAffinity Prediction

Active learning (AL) prioritises which compounds to measure next for protein-ligand affinity when assay or simulation budgets are limited. We present an explainable AL framework built on Gaussian process regression and assess how molecular representations, covariance kernels, and acquisition policies affect enrichment across four drug-relevant targets. Using recall of top active compounds, we find that dataset identity--the targets chemical landscape--sets the performance ceiling, while method choices modulate outcomes rather than overturn them. Fingerprints with simple Gaussian process kernels provide robust, low-variance enrichment, whereas learned embeddings with non-linear kernels can reach higher peaks but with greater variability. Uncertainty-guided acquisition consistently outperforms random selection, yet no single policy is universally optimal; the best choice follows structure-activity relationship (SAR) complexity. To enhance interpretability beyond black-box selection, we integrate SHapley Additive exPlanations (SHAP) to link high-impact fingerprint bits to chemically meaningful fragments across AL cycles, illustrating how the models attention progressively concentrates on SAR-relevant motifs.

biophysics↗

bioRxiv2024

Learning Binding Affinities via Fine-tuning of Protein and Ligand Language Models

Accurate in-silico prediction of protein-ligand binding affinity is essential for efficient hit identification in large molecular libraries. Commonly used structure-based methods such as docking often fail to rank compounds effectively, and free energy-based approaches, while accurate, are too computationally intensive for large-scale screening. Existing deep learning models struggle to generalize to new targets or drugs, and current evaluation methods often do not accurately reflect real-world performance. We introduce BALM, a deep learning framework that predicts binding affinity using pre-trained protein and ligand language models. We also propose improved evaluation strategies with diverse data sets and metrics to assess model performance to new targets better. Using the BindingDB dataset, BALM generalises unseen drugs, scaffolds, and targets. In few-shot scenarios for targets such as USP7 and Mpro, it outperforms traditional machine learning and docking methods, including AutoDock Vina. Adoption of our target-based evaluation methods will allow a more stringent evaluation of machine learning-based scoring tools. Our protein prediction framework shows good performance, is computationally efficient, and is highly adaptable within this evaluation setting, making it practical for early-stage drug discovery screening.

bioinformatics↗

bioRxiv2023

Benchmarking active learning protocols for ligand binding affinity prediction

Active learning (AL) has become a powerful tool in computational drug discovery, enabling the identification of top binders from vast molecular libraries with reduced costs for relative binding free energy calculations and experiments. To design a robust AL protocol, it is important to understand the influence of AL parameters, as well as the features of the datasets on the outcomes. We use four affinity datasets for different targets (TYK2, USP7, D2R, Mpro) to systematically evaluate the performance of machine learning models (Gaussian Process model, Chemprop), sample selection protocols, as well as the batch size based on metrics describing the overall predictive power of the model (R2, Spearman rank, RMSE) as well as the accurate identification of top 2% / 5% binders (Recall, F1 score). Both models have a comparable Recall of top binders on large datasets, but the GP models surpass Chemprop when training data is sparse. A larger initial batch size, especially on diverse datasets, increased the Recall of both models as well as overall correlation metrics. However, for subsequent cycles, smaller batch sizes of 20 or 30 compounds proved to be desirable. Furthermore, the presence of Gaussian noise to the data, up to a certain threshold, still allowed the model to identify clusters with top-scoring compounds. However, excessive noise (<1{sigma}) did impact the models predictive and exploitative capabilities. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=111 SRC="FIGDIR/small/568570v1_ufig1.gif" ALT="Figure 1"> View larger version (28K): org.highwire.dtl.DTLVardef@cefb11org.highwire.dtl.DTLVardef@c522bcorg.highwire.dtl.DTLVardef@6b8f18org.highwire.dtl.DTLVardef@17f7706_HPS_FORMAT_FIGEXP M_FIG O_FLOATNOTOC GraphicC_FLOATNO C_FIG

bioinformatics↗

bioRxiv2023

Horizontally transferred cell-free chromatin particles function as miniature predatory genomes and vehicles for transposable elements within host cells

BackgroundHorizontal gene transfer (HGT) plays an important evolutionary role in prokaryotes, but it is thought to be less frequent in mammals. We previously reported that cell-free chromatin particles (cfChPs) - chromosomal fragments released from the billions of dying cells that circulate in human blood - are horizontally transferred to healthy cells with biological effects. However, the underlying mechanism and function of these effects remained unclear. MethodsWe treated NIH3T3 mouse fibroblasts cells with cfChPs isolated from human serum and serially passaged the cells. The intracellular activities of cfChPs were analysed using chromatin fibre fluorography, cytogenetic analysis, immuno-fluorescence and fluorescent in situ hybridisation. ResultsWe discovered that the internalised cfChPs were almost exclusively comprised of non-coding DNA, and the disparate DNA sequences contained within them had randomly combined to form complex concatemers some of which were ostensibly multi-mega base pairs in size. The concatemers exhibited variable and bizarre spatial relationships with the host cell interphase DNA with many remaining in the cytoplasm and others aligning themselves with the mouse chromosomal DNA. The concatemers autonomously performed many functions attributable to the nuclear genome. Being associated with DNA polymerase, the concatemers could synthesize DNA and autonomously replicate themselves without heed to the mitotic cycle of the host cell. They could synthesise RNA, RNA polymerase, ribosomal RNA, ribosomal proteins, and generate numerous human proteins, including oncogenes, within the mouse cells which manifested as complex and highly amplified multi-peptide fusion proteins. The concatemers harboured human LINE-1 and Alu elements, which being associated with DNA polymerase, reverse transcriptase and transposes could markedly amplify themselves and increase their copy number with time in culture with the potential to rearrange themselves within the mouse genome. The above findings were reproducible in four other cell lines derived from different species suggesting that horizontal transfer of cfChPs may be a universal phenomenon. ConclusionsOur results lead us to propose that: 1) a cell simultaneously harbours two autonomous genome forms: one that is inherited (hereditary genome) and numerous others that are acquired (satellite genomes); 2) satellite genomes may potentially have evolutionary functions given their ability to serve as vehicles for transposable elements and to generate a plethora of novel proteins; 3) transposable elements are "foreign" genetic elements that are acquired from dying cells via HGT; 4) non-coding DNA has many hidden biological functions that remain dormant but are activated following cellular apoptosis to become detectable in association with the cfChP concatemers; 5) "within-self" HGT occurs in mammals on a massive scale via the medium of cfChP concatemers that have undergone extensive and complex modifications resulting in their behaviour as "foreign" genetic elements. Video Abstracthttps://drive.google.com/file/d/1I6NbrYmT9BRM63ywYj47AU0O9WJ_NrcR/view?usp=drive_link

evolutionary biology↗

bioRxiv2023

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Accurate in silico prediction of protein-ligand binding affinity is important in the early stages of drug discovery. Deep learning-based methods exist but have yet to overtake more conventional methods such as giga-docking largely due to their lack of generalisability. To improve generalizability we need to understand what these models learn from input protein and ligand data. We systematically investigated a sequence-based deep learning framework to assess the impact of protein and ligand encodings on predicting binding affinities for commonly used kinase data sets. The role of proteins is studied using convolutional neural network-based encodings obtained from sequences and graph neural network-based encodings enriched with structural information from contact maps. Ligand-based encodings are generated from graph-neural networks. We test different ligand perturbations by randomizing node and edge properties. For proteins we make use of 3 different protein contact generation methods (AlphaFold2, Pconsc4, and ESM-1b) and compare these with a random control. Our investigation shows that protein encodings do not substantially impact the binding predictions, with no statistically significant difference in binding affinity for KIBA in the investigated metrics (concordance index, Pearsons R Spearmans Rank, and RMSE). Significant differences are seen for ligand encodings with random ligands and random ligand node properties, suggesting a much bigger reliance on ligand data for the learning tasks. Using different ways to combine protein and ligand encodings, did not show a significant change in performance. TOC Graphic O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=111 SRC="FIGDIR/small/551483v1_ufig1.gif" ALT="Figure 1"> View larger version (25K): org.highwire.dtl.DTLVardef@117f37forg.highwire.dtl.DTLVardef@173427eorg.highwire.dtl.DTLVardef@126a39org.highwire.dtl.DTLVardef@fbcc6d_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2019

DMENet: Diabetic Macular Edema Diagnosis using Hierarchical Ensemble of CNNs

Diabetic Macular Edema (DME) is an advanced stage of Diabetic Retinopathy (DR) and can lead to permanent vision loss. Currently, it affects 26.7 million people globally and on account of such huge number of DME cases and limited number of ophthalmologists, it is desirable to automate the diagnosis process. Computer-assisted, deep learning based diagnosis will help in early detection, following which appropriate medication can help to mitigate the vision loss. Method: In order to automate the screening of DME, we propose a novel DMENet Algorithm which is built on the pillars of Convolutional Neural Networks (CNNs). DMENet analyses the preprocessed color fundus images and passes it through a two-stage pipeline. The first stage detects the presence or absence of DME whereas the second stage takes the positive cases and grades the images based on severity. In both the stages, we use a novel Hierarchical Ensemble of CNNs (HE-CNN). This paper uses two of the popular publicly available datasets IDRiD and MESSIDOR for classification. Preprocessing on the images is performed using morphological opening, Gaussian kernel and the dataset is augmented to solve the class imbalance problem. Results: The proposed methodology achieved an Accuracy of 96.12%, Sensitivity of 96.32%, Specificity of 95.84%, and F-1 score of 0.9609. Conclusion: These excellent results establishes the validity of the proposed methodology for use in DME screening and solidifies the applicability of HE-CNN classification technique in the domain of bio-medical imaging.

bioengineering↗