Dr. Raghvendra Mall 🇮🇳🇧🇪🇶🇦🇺🇲🇦🇪👨💻
@MallRaghvendra
Followers
121
Following
4K
Media
15
Statuses
208
PI | ML Scientist | Comp Bio | Network Bio | SMIEEE | Opinions my own | 🕉️ | Hiding in the shadows ! Past: TII | St. Jude | QCRI | KU Leuven | INRIA | IIIT-H
Abu Dhabi, UAE
Joined January 2015
Anti-PD1 @DR_E_A_M Challenge paper out. Key insights:.a) Federated learning is the future of CTs.b) Prior Knowledge FTW in absence of training data.c) Gene expression based signature (I-MIRACLE) can identify patient strata where IO is beneficial for OS/PFS.
biorxiv.org
Purpose Predictive biomarkers of immune checkpoint inhibitors (ICIs) efficacy are currently lacking for non-small cell lung cancer (NSCLC). Here, we describe the results from the Anti–PD-1 Response...
1
0
8
RT @rajukarki16: Just out in Nature Comms: acrolein promotes ferroptosis but blocks necroptosis, impairing chemo response. Blocking acrolei….
nature.com
Nature Communications - Acrolein, a byproduct of polyamine metabolism and chemotherapeutic agents, is also found in cigarette smoke. Here the authors report that acrolein mediates spermine-induced...
0
4
0
Check out our latest article: 🧬 "Patchwork Biology: Reconstructing Gene Expression in Inflammatory Bowel Disease from Vision and Attention" via @LinkedIn.
linkedin.com
Autoimmune diseases like Inflammatory Bowel Disease (IBD) affect millions and are rising globally, with IBD posing serious risks such as persistent inflammation and a two-fold increased risk of...
0
0
0
Super grateful to be among the recipients.
#TechNews: Announcing the Recipients of Computing’s Top 30 Early Career Professionals for 2024
1
0
3
Super excited to share this joint work with colleagues @Caltech. Currently at @biorxivpreprint !!.
Benchmarking Protein Language Models for Protein Crystallization. 1/ A new study benchmarks open Protein Language Models (PLMs) to predict the crystallization propensity of proteins using TRILL, a platform that democratizes the use of PLMs for such tasks. 2/ The authors
1
1
3
Many thanks to @TIIuae BRC team for contributions and support and many congratulations to co-coressponding author Ankita Singh.
0
0
1
5. VISH-Pred is available as a user-friendly web service for the ease of usage of nonexperts. (n/n).
1
0
1
4. Benchmarking different ESM2 language model configurations provided insights into size versus performance trade-offs. (5/n).
1
0
1
3. VISH-Pred achieves over 10% increase in performance for key metrics, F1-score and MCC, which are imperative for screening candidates for protein-based therapeutics. (4/n).
1
0
0
2. VISH-Pred efficiently handles humongous class-imbalance in training set (ratio of 1:91) for toxic versus non-toxic peptides using an under-sampling approach and ensembles fine-tuned models to mitigate the risk of majority class prediction. (3/n).
1
0
1
Key insights include:.1. Ensemble of fine-tuned ESM2 models (VISH-Pred) outperforms existing protein toxicity predictors like CSM-Toxin, ToxinPred2, ToxinPred3, ToxClassifier, ToxIBTL, Toxify, etc. on three independent test sets. (2/n).
1
0
1
Excited to share our latest method, VISH-Pred, built by fine-tuning ensemble of ESM2 models for the task of peptide / protein toxicity 🐍🦂prediction out in @BriefingBioinfo. (1/n).
academic.oup.com
Abstract. Peptide- and protein-based therapeutics are becoming a promising treatment regimen for myriad diseases. Toxicity of proteins is the primary hurdl
1
0
3
RT @KannegantiLab: Congrats first authors @JooHuiHan & @rajukarki16 on elucidating role of NINJ1 in #infection & he….
0
11
0
RT @mceccarelli: A community challenge to predict clinical outcomes after #immunecheckpoint blockade in non-small cell #lungcancer. Our iMI….
0
2
0
RT @KannegantiLab: Today @CommsBio: new work from first authors Mrk Malireddi and Ratnakar Bynigeri showing the utility of a #celldeath #CR….
nature.com
Communications Biology - A CRISPR screen identified host factors that promote viral entry and inflammatory cell death, PANoptosis, upon infection with the murine hepatitis virus, a type of...
0
6
0
Downstream pathway enrichment identifies Epethelial to Mesenchymal transistion, TGF-b signaling, Toll-like receptor signaling, cytokine & inflammatory response getting activated in highly invasive cancers creating feasible env for metastasis. More info at:
0
2
2
Very excited to share our latest article on pan🎗️ invasiveness. Invasiveness ∝ with worse survival in almost all 🎗️in TCGA. Consensus of master regulator analysis identify key transcriptional regulators of invasiveness independent of 🎗️type. Collab with @mceccarelli @mjethalia6.
1
1
6
This is how co-first authorship should always be decided !!.
0
1
6
Super happy to present our work on PANOptosis markers and its relevance in cancer at #ISMBECCB2023 #Lyon previously published in #NAR cancer
1
0
10