{ "fetched_at": "2026-10-19T07:46:59Z", "source_url": "https://www.kaggle.com/competitions/echoes-of-silenced-genes/data", "pages": [ { "name": "data-description", "content": "Your task is to predict expression changes in scRNA-seq data induced by CRISPRi perturbations. In addition to the files which are strictly necessary for a successful submission, we provide additional files which might be useful, depending on your solution. Note that you are not restricted to these files - external data can be used as well. \n\n# Quickstart\n **sample_submission.csv** shows the required format. \n\n[This notebook](https://www.kaggle.com/code/mylliabiotechnology/echoes-of-silenced-genes-sample-submission) shows how the sample submission was created.\n\n# What to submit\nThe task is to predict delta average expression (log2 fold change) of 5127 genes for each perturbation. The genes to predict are defined by the columns of **training_data_means.csv**, as well as **sample_submission.csv** (except for the `pert_symbol`/`pert_id` columns). \n\nIn total, you will predict the effects of 120 perturbations. Sixty will be used for the leaderboard (validation set) and sixty for the final evaluation (test set). The 60 leaderboard perturbations are listed in **pert_ids_val.csv**. The `pert_id` column of your submission must contain IDs as stated in this file, i.e. in `pert_i` format. The test set of the remaining 60 perturbations for final evaluation will only be released one week before the end of the challenge. Nevertheless, the submission format is constant, requiring dummy values for the as-yet-unknown test perturbations. In other words, **all submissions must have exactly 120 rows**, with values of `pert_1`...`pert_120` in the `pert_id` column. Only the first 60 rows, `pert_1`...`pert_60`, are used for the leaderboard. Until the final test set of perturbations is released, the actual values in rows `pert_61`...`pert_120` play no role.\n\n# Where to find the dataset in Kaggle notebooks\nIn case you want to use a Kaggle notebook and don't see the dataset under \"competition datasets\" (as reported by users), it can be additionally found in \"datasets\". The name is \"Myllia Echoes of silenced genes competition data\". https://www.kaggle.com/datasets/mylliabiotechnology/myllia-echoes-of-silenced-genes-competition-data\n\n# Main files\n**training_data_means.csv** \nAverage expression values of unperturbed cells (non-targeting sgRNA) and cells with 80 selected perturbations. These cells are from the same experiment as the cells in the validation and test datasets. The last row, containing `non-targeting` in the `pert_symbol` column, is the baseline expression used for reference. **All submissions should contain delta expression relative to this row**. \nSee section \"Normalization Details\" for the exact process by which this file was generated from raw UMI counts. \n\n**Columns** \n`pert_symbol` - gene symbol of the perturbation \n`A1BG, A1CF, AADAC, ..., ZWINT, ZYX` - average expression values of the 5127 genes relevant to this challenge. \n\n**pert_ids_val.csv** \nThis file provides the link between the required perturbation ID and the actual gene symbol for the 60 leaderboard (validation set) perturbations. One week before the end of the challenge, we will release another file, **pert_ids_test.csv**, containing the ID mapping for the perturbations used in the final evaluation.\n\n **Columns** \n`pert` - gene symbol of the perturbation \n`class` - type of dataset (`val` or `test`; currently only `val` perturbations are released) \n`pert_id` - perturbation ID to be used in submissions\n\n# Supplementary files\n**training_cells.h5ad**, **training_cells.RDS** - single-cell resolution raw data used to create **training_data_means.csv**, provided in Scanpy h5ad and Seurat formats. These files contain raw UMI counts for 19,226 genes, as well as batch information (in the `channel` column). See section \"Normalization Details\" for how exactly the raw UMI counts were processed to create **training_data_means.csv**. \n\n**training_data_ground_truth_table.csv** - this file contains all the inputs needed to run the actual scoring function on the 80 perturbations from the training dataset. Specifically, it contains delta values, gene weights, and baseline WMAE scores. It can be directly used as input for \n[the scoring function](https://www.kaggle.com/code/mylliabiotechnology/relative-wmae-multiplied-by-wcosine).\n\n# Normalization details\nWe start from UMI counts of 19,226 genes. The gene list is defined by Gencode v.46. \nRaw counts are first log-normalized: \n* Divide the UMI counts in each cell by the total UMI count in that cell\n* Multiply by 10,000\n* Log-transform with log1p (log(x + 1)); logarithm base = 2. \n\nNormalization is performed on **all 19,226 genes** to facilitate compatibility with other pre-processed datasets. The normalized data are then subset to the 5,127 genes relevant for the challenge. Finally, expression values for each gene are averaged per perturbation. We use a simple arithmetic mean, disregarding batch information.\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "Single-cell RNA-seq has been used to catalog mRNA expression levels of almost all accessible cell types. Summarized in large atlases like [CELLxGENE](https://cellxgene.cziscience.com/) or [scBaseCount](https://github.com/ArcInstitute/arc-virtual-cell-atlas/tree/main/scBaseCount), this type of data attracts data scientists eager to mine it for biological insights. While the bulk of these datasets contains only information on steady-state cells, the advent of techniques like CROP-seq and pertrub-seq has enabled the generation of very large datasets containing transcriptomes of cells after a CRISPR perturbation. Some of the largest public CROP-seq/perturb-seq datsets include: \n\n[Replogle et al., 2022](https://www.cell.com/cell/fulltext/S0092-8674(22)00597-9) \n[Nourreddine et al., 2024](https://www.biorxiv.org/content/10.1101/2024.11.03.621734v2.full) \n[Huang et al., 2025](https://www.biorxiv.org/content/10.1101/2025.06.11.659105v1.full) \n[Jiang et al., 2025](https://www.nature.com/articles/s41556-025-01622-z) \n[Nadig et al., 2025](https://www.nature.com/articles/s41588-025-02169-3) \n[Song et al., 2025](https://www.nature.com/articles/s41556-025-01626-9) \n[Zhu et al., 2026](https://www.biorxiv.org/content/10.64898/2025.12.23.696273v1) \n\nThe increasing abundance of such datasets naturally triggers ideas like:\n*Having seen what the perturbation does in one cell type, can we predict what it will do in another?* \n\nInitial works in this area suggest it might be possible, but arguably, a model generating predictions actually useful in practice is yet to be published. \n\nBut what makes a prediction useful in practice? The sparse nature of scRNA-seq data, together with mostly sparse effects of perturbations make model evaluation a topic on its own. Several publications, even challenges similar to this one, have introduced different metrics, putting emphasis on different features of the predictions and generating vastly different quality measures. \n\nIn this challenge, we want to evaluate how well do current models master the *perturbation transfer* task: Based on unperturbed transcriptomes of *many* cell types (publicly available), perturbed transcriptomes of *some* cell types (publicly available), and *a few* perturbations in the target cell type (provided here), can you predict the outcomes of arbitrary gene perturbations? \n\nTo this end, we have designed a new evaluation metric, which should capture the important information in the sparse and noisy datasets. However, since the question of the ideal metric is far from universally answered, after the end of the challenge, we will publish the best submitted predictions together with ground truth data, so that the community can evaluate the current best predictions using any metric. \n\nWinners will be announced on the [High-Content CRISPR Screening Conference](https://www.perturb2026.bio/) in March 2026 in Vienna, Austria.\n\n##### About the organizer\n[Myllia Biotechnology](https://myllia.com/) is a biotech company based in Vienna, Austria. Its technology platform combines CRISPR perturbation screens with single-cell RNA sequencing in primary human cells to deliver deeply physiologic, mechanistic insights. By generating large-scale, custom perturbation datasets, we enable AI-driven foundation models of virtual cells that infer causal relationships, reveal mechanisms of action, and accelerate unbiased target discovery.\n\n##### Acknowledgements\nBig thanks to members of the Virtual Cell Research Community for valuable feedback - Kendall, Philipp, Mauro and others, as well as to Giovanni for coming up with the name.\nTo discuss everything virtual cell, [join the community discord channel](https://discord.gg/ksptEXV2r).\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "##ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.\n\n*The Competition named below is a skills-based competition to promote and further the field of data science. You must register via the Competition Website to enter. To enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules herein (collectively, the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that Submission in the Competition constitutes agreement to these Rules. You may not submit to the Competition and are not eligible to receive the prizes associated with this Competition unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition. Your competition Submissions must conform to the requirements stated on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website. Subject to compliance with the Competition Rules, Prizes, if any, will be awarded to Participants with the best scores, based on the merits of the data science models submitted. See below for the complete Competition Rules.*\n\n**You cannot sign up to Kaggle from multiple accounts and therefore you cannot enter or submit from multiple accounts.**\n\n

1. COMPETITION-SPECIFIC TERMS

\n

1. COMPETITION TITLE

Echoes of Silenced Genes: A Cell Challenge\n

2. COMPETITION SPONSOR

Myllia Biotechnology\n

3. COMPETITION SPONSOR ADDRESS

Am Kanal 27, 1110, Vienna, Austria\n

4. COMPETITION WEBSITE

https://www.kaggle.com/competitions/echoesofgenes\n

5. TOTAL PRIZES AVAILABLE: 3500 EUR

\nFirst Prize: 2000 EUR
\nSecond Prize: 1000 EUR
\nThird Prize: 500 EUR\n

6. WINNER LICENSE TYPE

N/A\n

7. DATA ACCESS AND USE

CC BY-NC 4.0\n\n\n###2. COMPETITION-SPECIFIC RULES \nIn addition to the provisions of the General Competition Rules below, you understand and agree to these Competition-Specific Rules required by the Competition Sponsor:\n\n####1. TEAM LIMITS\na. The maximum Team size is six (6).\nb. Team mergers are allowed and can be performed by the Team leader. In order to merge, the combined Team must have a total Submission count less than or equal to the maximum allowed as of the Team Merger Deadline. The maximum allowed is the number of Submissions per day multiplied by the number of days the competition has been running.\n\n####2. SUBMISSION LIMITS\na. You may submit a maximum of one (1) Submission per day.\nb. You may select up to two (2) Final Submissions for judging.\n\n####3. COMPETITION TIMELINE\na. Competition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s Overview > Timeline page.\n\n####4. COMPETITION DATA\n\na. Data Access and Use.\n\n1. You may access and use the Competition Data for non-commercial purposes only, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any Participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.\n\nb. Data Security. \n\n1. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.\n\n#### 5. SUBMISSION REQUIREMENTS; SUBMISSION LICENSE (ALL PARTICIPANTS)\n\n##### 5.1 Machine Learning Predictions Only\n\na. **Model-generated outputs required.** Each Submission (including any leaderboard Submission and any final Submission) must consist solely of prediction values generated by a machine learning model developed by you (or your Team).\n\nb. **No raw experimental results as submissions.** You may not submit experimental measurements or laboratory results as your Submission (whether in raw form or lightly transformed), and you may not substitute experimental results for model outputs.\n\nc. **No manual post-processing to improve score.** You may not manually revise, adjust, select, blend, override, or otherwise modify prediction values after they are generated by your model using human judgment or any non-model procedure intended to improve the Submission score (including edits informed by ground truth, target labels, or other evaluation information that is not legitimately available under the Competition rules).\n\nd. **Enforcement.** Sponsor may audit, test, or evaluate Submissions for compliance with this Section and may disqualify any Submission or Participant that Sponsor believes, in its sole discretion, violates these Rules or undermines the integrity or spirit of the Competition.\n\n\n##### 5.2 License Grant for Submitted Prediction Values (All Participants)\n\na. **License limited to Submission values.** By submitting a Submission, you grant to Competition Sponsor and its designees a worldwide, non-exclusive, sublicensable, transferable, fully paid-up, royalty-free, perpetual, irrevocable license to use, host, store, reproduce, analyze, evaluate, test, publish, display, perform, distribute, and create derivative works from the Submission values you upload to Kaggle for this Competition (i.e., the prediction outputs), in any media now known or later developed, for any purpose, commercial or otherwise, without further approval by or payment to you.\n\nb. **No license to your code or model.** For clarity, this license applies only to the Submission values (prediction outputs) and does not require you to provide, license, or transfer any rights in any software code, model weights, training pipeline, notebooks, data, or other tools used to generate the Submission.\n\nc. **Rights to grant.** You represent and warrant that you have all rights necessary to grant the license in this Section with respect to the Submission values you upload.\n\n#### 6. WINNER LICENSE\n\na. **No additional winner license.** There is no additional license obligation for Prize winners beyond the Submission license granted by all Participants in Section 5.2. Prize winners are not required to provide, license, or open-source any code, model, weights, data, or other materials used to generate a winning Submission.\n\n#### 7. EXTERNAL DATA AND TOOLS\n\na. **Use permitted.** You may use any data, software, services, models, tools, compute resources, and other materials (“External Resources”) to develop, train, validate, and generate your Submissions, provided that you have legal access to and rights to use those External Resources for these purposes.\n\nb. **No general restrictions.** There are no Competition-imposed limits on the type, source, cost, location, licensing terms, or accessibility of External Resources you use (including paid, proprietary, non-public, or otherwise restricted resources), except as otherwise expressly stated in these Rules.\n\nc. **Compliance remains your responsibility.** Your use of External Resources must comply with: (i) these Rules (including Section 5.1 **Machine Learning Predictions Only**); (ii) all applicable laws and regulations (including export controls, sanctions, and data protection/privacy laws); and (iii) any contractual, license, confidentiality, or other obligations that apply to you.\n\nd. **No new rights in External Resources.** Nothing in these Rules grants Sponsor or any other party any rights in External Resources you use. Your Submission license obligations (Section 5.2) apply only to the Submission values you upload (the prediction outputs), not to any External Resources, code, models, weights, datasets, or tools used to generate them.\n\ne. **Sponsor may request confirmation.** Sponsor may request reasonable information from you (including Prize winners under Section 8) to confirm that your use of External Resources complied with these Rules and applicable law, and to verify eligibility for prizes.\n\n\n####8. ELIGIBILITY\n\na. Unless otherwise stated in the Competition-Specific Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition, but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., and their respective parent companies, subsidiaries and affiliates. If you are such a Participant from a Competition Entity, you are subject to all applicable internal policies of your employer with respect to your participation.\n\nb. Score threshold for prizes. To be eligible to receive any Prize, a Participant (or Team) must have a score strictly greater than 0 on the applicable final scoring basis used for prize determination (private leaderboard score). Submissions or Entries with a final score of 0 or less are not eligible for Prizes, regardless of rank.\n\n#### 9. WINNER’S OBLIGATIONS\n\n##### 9.1 Methods Description (Required)\n\na. As a condition of receiving a Prize, the Prize-winning Entry must provide Sponsor, by a deadline specified by Sponsor, a written description of how the winning approach was produced, at a high level sufficient for a technical audience to understand the approach. For Team entries, this description may be submitted by the Team Captain or an authorized representative on behalf of the Team. Sponsor may request reasonable clarifications from any Team member and may require individual confirmations regarding eligibility and compliance with the Rules.\n\nb. The description must include:\n\n1. Model approach (e.g., general architecture/class of methods, training objective at a high level).\n2. Training procedure (e.g., what was trained vs. fine-tuned; general workflow).\n3. Datasets used to train/fine-tune/validate, i.e. nature of datasets and size.\n4. Any use of third-party tools or pretrained components (e.g., foundation models).\n\nc. **No code requirement.** For clarity, winners are not required to provide code, model weights, or a runnable environment, unless Sponsor and the winner separately agree in writing.\n\n\n##### 9.2 Verification / Eligibility / Compliance Requests\n\na. Prize winners must promptly provide any additional information Sponsor reasonably requests to verify, to Sponsor’s satisfaction, that: (i) the winner(s) are eligible; (ii) the winning Submission complies with these Rules (including Section 5.1); and (iii) awarding the Prize complies with applicable law.\n\n\n##### 9.3 Paperwork; Payment Information\n\na. Prize winners must sign and return any Prize acceptance documents reasonably required by Sponsor or Kaggle, which may include applicable tax forms and payment documentation and provide payment details necessary to deliver the Prize.\n\n\n##### 9.4 Public Summary (Optional)\n\na. Sponsor may publish a summary of the winning method description, in whole or in part, and winners agree to cooperate in good faith on a publishable version that does not disclose the winner’s confidential information, trade secrets, or proprietary implementation details, provided that Sponsor may still require sufficient detail under Section 8.1 for verification and integrity purposes.\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "abstract", "content": "# Data, write-ups, and more published on:\n\n[https://myllia.notion.site/echoes-of-silenced-genes2026](https://myllia.notion.site/echoes-of-silenced-genes2026)\n\n

\n\n\n\nModelling cell behavior in response to stimuli and perturbations has been an increasingly popular topic. The so-called *virtual cell* models promise to navigate, or even replace lab experiments and thus significantly contribute to advances in medical research. However, we are yet to see such a capable model. In fact, we are yet to see a definition of what a good model is - the evaluation of prediction quality itself is not a simple task. \n\nYour objective in this challenge is to predict how a human cancer cell line responds to perturbations induced by CRISPR-interference. We organize this challenge to: \n\n* See how capable current models of cell response are.\n* Evaluate a new metric of prediction quality.\n* Have fun.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "foundational-rules", "content": "The following Kaggle Competition Foundational Rules (“ Foundational Rules ”) apply to every competition regardless of whether the Sponsor creates competition-specific rules. Any competition-specific rules provided by the Sponsor are in addition to these rules, and in the case of any conflict or inconsistency, these Foundational Rules control and nullify contrary competition-specific rules.\n###GENERAL COMPETITION RULES - BINDING AGREEMENT\n####1. ELIGIBILITY\na. To be eligible to enter the Competition, you must be:\n1. a registered account holder at Kaggle.com; \n2. the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor); \n3. not a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea; and\n4. not a person or representative of an entity under U.S. export controls or sanctions (see: [https://www.treasury.gov/resourcecenter/sanctions/Programs/Pages/Programs.aspx][1]).\n\nb. Competitions are open to residents of the United States and worldwide, except that if you are a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, North Korea, or are subject to U.S. export controls or sanctions, you may not enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure that you are eligible to participate in skills-based competitions. The Competition Host reserves the right to forego or award alternative Prizes where needed to comply with local laws. If a winner is located in a country where prizes cannot be awarded, then they are not eligible to receive a prize.\n\nc. If you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and the entity you represent or where you are an employee. If you are acting within the scope of your employment, or as an agent of another party, you warrant that such party or your employer has full knowledge of your actions and has consented thereto, including your potential receipt of a Prize. You further warrant that your actions do not violate your employer's or entity's policies and procedures. \n\nd. The Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.\n\n####2. SPONSOR AND HOSTING PLATFORM\n\na. The Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of Competition Sponsor, and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at [www.kaggle.com/terms][2] in addition to these Rules.\n\n####3. COMPETITION PERIOD\na. For the purposes of Prizes, the Competition will run from the Start Date and time to the Final Submission Deadline (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.\n\n####4. COMPETITION ENTRY\na. NO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\nb. Submissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.\nc. If the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.\nd. Submissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. \n\n####5. INDIVIDUALS AND TEAMS\na. Individual Account. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website. \nb. Teams. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a Team; however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\nc. Team Merger. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. \nd. Private Sharing. No private sharing outside of Teams. Privately sharing code or data outside of Teams is not permitted. It's okay to share code if made available to all Participants on the forums.\n\n####6. SUBMISSION CODE REQUIREMENTS\na. Private Code Sharing. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.\nb. Public Code Sharing. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or notebooks associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][3]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\nc. Use of Open Source. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][4]) that in no event limits commercial use of such code or model containing or depending on such code.\n\n####7. DETERMINING WINNERS\na. Each Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's Public Leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the Private Leaderboard, subject to compliance with these Rules. The Public Leaderboard will be based on the public test set and the Private Leaderboard will be based on the private test set.\nb. In the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.\n\n####8. NOTIFICATION OF WINNERS & DISQUALIFICATION\na. The potential winner(s) will be notified by email. \nb. If a potential winner (i) does not respond to the notification attempt within one (1) week from the first notification attempt or (ii) notifies Kaggle within one week after the Final Submission Deadline that the potential winner does not want to be nominated as a winner or does not want to receive a Prize, then, in each case (i) and (ii) such potential winner will not receive any Prize, and an alternate potential winner will be selected from among all eligible entries received based on the Competition’s judging criteria.\nc. In case (i) and (ii) above Kaggle may disqualify the Participant. However, in case (ii) above, if requested by Kaggle, such potential winner may provide code and documentation to verify the Participant’s compliance with these Rules. If the potential winner provides code and documentation to the satisfaction of Kaggle, the Participant will not be disqualified pursuant to this paragraph.\nd. Competition Sponsor reserves the right to disqualify any Participant from the Competition if the Competition Sponsor reasonably believes that the Participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other Participants, Competition Sponsor or Kaggle.\ne. A disqualified Participant may be removed from the Competition leaderboard, at Kaggle's sole discretion. If a Participant is removed from the Competition Leaderboard, additional winning features associated with the Kaggle competition platform, for example Kaggle points or medals, may also not be awarded.\nf. The final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.\n\n####9. PRIZES\na. Prize(s) are as described on the Competition Website and are only available for winning during the time period described on the Competition Website. The odds of winning any Prize depends on the number of eligible Submissions received during the Competition Period and the skill of the Participants. \nb. All Prizes are subject to Competition Sponsor's review and verification of the Participant’s eligibility and compliance with these Rules, and the compliance of the winning Submissions with the Submissions Requirements. In the event that the Submission demonstrates non-compliance with these Competition Rules, Competition Sponsor may at its discretion take either of the following actions: (i) disqualify the Submission(s); or (ii) require the potential winner to remediate within one week after notice all issues identified in the Submission(s) (including, without limitation, the resolution of license conflicts, the fulfillment of all obligations required by software licenses, and the removal of any software that violates the software restrictions).\nc. A potential winner may decline to be nominated as a Competition winner in accordance with Section 3.8.\nd. Potential winners must return all required Prize acceptance documents within two (2) weeks following notification of such required documents, or such potential winner will be deemed to have forfeited the prize and another potential winner will be selected. Prize(s) will be awarded within approximately thirty (30) days after receipt by Competition Sponsor or Kaggle of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed. \ne. You are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2.7 and Section 3.1 above.\nf. If a Team wins a monetary Prize, the Prize money will be allocated in even shares between the eligible Team members, unless the Team unanimously opts for a different Prize split and notifies Kaggle before Prizes are issued.\n\n####10. TAXES\na. ALL TAXES IMPOSED ON PRIZES ARE THE SOLE RESPONSIBILITY OF THE WINNERS. Payments to potential winners are subject to the express requirement that they submit all documentation requested by Competition Sponsor or Kaggle for compliance with applicable state, federal, local and foreign (including provincial) tax reporting and withholding requirements. Prizes will be net of any taxes that Competition Sponsor is required by law to withhold. If a potential winner fails to provide any required documentation or comply with applicable laws, the Prize may be forfeited and Competition Sponsor may select an alternative potential winner. Any winners who are U.S. residents will receive an IRS Form-1099 in the amount of their Prize.\n\n####11. GENERAL CONDITIONS\na. All federal, state, provincial and local laws and regulations apply.\n\n####12. PUBLICITY\na. You agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation, unless prohibited by law.\n\n####13. PRIVACY\na. You acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <[www.kaggle.com/privacy][6]>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <[www.kaggle.com/contact][7]>.\nb. As part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.\n\n####14. WARRANTY, INDEMNITY AND RELEASE \na. You warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\nb. To the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.\nc. You hereby release Competition Entities from any liability associated with: (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.\n\n####15. INTERNET\na. Competition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a Participant’s ability to participate.\n\n####16. RIGHT TO CANCEL, MODIFY OR DISQUALIFY\na. If for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any Participant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by a Participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such Participant to the fullest extent of the applicable law.\n\n####17. NOT AN OFFER OR CONTRACT OF EMPLOYMENT\na. Under no circumstances will the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n\n####18. DEFINITIONS\na. \"Competition Data\" are the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to Participants. \nb. An “Entry” is when a Participant has joined, signed up, or accepted the rules of a competition. Entry is required to make a Submission to a competition.\nc. A “Final Submission” is the Submission selected by the user, or automatically selected by Kaggle in the event not selected by the user, that is/are used for final placement on the competition leaderboard.\nd. A “Participant” or “Participant User” is an individual who participates in a competition by entering the competition and making a Submission.\ne. The “Private Leaderboard” is a ranked display of Participants’ Submission scores against the private test set. The Private Leaderboard determines the final standing in the competition.\nf. The “Public Leaderboard” is a ranked display of Participants’ Submission scores against a representative sample of the test data. This leaderboard is visible throughout the competition.\ng. A “Sponsor” is responsible for hosting the competition, which includes but is not limited to providing the data for the competition, determining winners, and enforcing competition rules.\nh. A “Submission” is anything provided by the Participant to the Sponsor to be evaluated for competition purposes and determine leaderboard position. A Submission may be made as a model, notebook, prediction file, or other format as determined by the Sponsor.\ni. A “Team” is one or more Participants participating together in a Kaggle competition, by officially merging together as a Team within the competition platform.\n\n [1]: https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx\n [2]: http://www.kaggle.com/terms\n [3]: http://www.opensource.org\n [4]: http://www.opensource.org\n [5]: https://www.kaggle.com/WinningModelDocumentationGuidelines\n [6]: http://www.kaggle.com/privacy\n [7]: http://www.kaggle.com/contact\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The metric used in this challenge consists of 2 parts: Weighted Mean Absolute Error Ratio and Weighted Cosine Similarity. Importantly, WMAE is normalized against a baseline prediction (average of the training data). Submissions need to perform better than the baseline in terms of WMAE to get a positive score.\n\n## Weighted Mean Absolute Error (WMAE)\nInspired by [Mejia et al.](https://arxiv.org/abs/2506.22641), we define the WMAE for a single perturbation as: \n\n$$\n\\mathrm{WMAE}(true, pred)\n= \\frac{1}{n}\\sum_{i=1}^{n} w_i \\,\\left|\\, true_i - pred_i \\,\\right|.\n$$\n\nwhere \\\\(true\\\\) and \\\\(pred\\\\) are the vectors of ground-truth and predicted delta expression values across \\\\(n\\\\) genes and \\\\(w = (w_1,\\ldots,w_n) \\in \\mathbb{R}^n\\\\) is a vector of nonnegative weights with the same length as \\\\(true\\\\) and \\\\(pred\\\\), satisfying\n\n$$\nw_i \\ge 0 \\quad \\text{for } i=1,\\ldots,n,\n\\qquad \\sum_{i=1}^{n} w_i = n.\n$$\n\nThe weights vector is calculated using the moderated t-statistic from the [limma](https://www.bioconductor.org/packages/release/bioc/html/limma.html) package. \n\nLet \\\\(t = (t_1,\\ldots,t_n) \\in \\mathbb{R}^n\\\\) be the vector of moderated t-statistics for a single perturbation. Define\n\n$$\nc_i = \\min\\bigl(|t_i|+0.1,\\;10\\bigr), \\qquad i=1,\\ldots,n.\n$$\n\nIf the perturbation targets gene with index \\\\(g \\in \\{1,\\ldots,n\\}\\\\), set \\\\(c_g = 0\\\\).\n\nLet \n$$\nM = \\max_{1\\le j \\le n} c_j\n$$\n\nWe define the weight vector \\\\(w = (w_1,\\ldots,w_n) \\in \\mathbb{R}^n\\\\) as\n\n$$\nw_i\n= n \\cdot\n\\frac{\\left(\\dfrac{c_i}{M}\\right)^2}{\\sum_{k=1}^{n}\\left(\\dfrac{c_k}{M}\\right)^2},\n\\qquad i=1,\\ldots,n.\n$$\n\n\nFinally, to aggregate over multiple perturbations, we define the WMAE ratio score \\\\(W\\\\) over \\\\(L\\\\) perturbations as\n\n$$\nW\n= \\sum_{l=1}^{L}\n\\min\\left(\n5,\\;\n\\log_2 \\left( \\frac{WMAE^{base}_l}{WMAE^{pred}_l} \\right)\n\\right).\n$$\n\nHere, \\\\(\\mathrm{WMAE}^{\\mathrm{base}}_l\\\\) is the WMAE for perturbation \\\\(l\\\\) of the baseline prediction, and \\\\(\\mathrm{WMAE}^{\\mathrm{pred}}_l\\\\) is the WMAE for perturbation \\\\(l\\\\) of the model prediction. The threshold of 5 serves only to safeguard against outlier cases. \n\nIn this instance, the baseline prediction is the same for all perturbations and is defined as the arithmetic mean of the log fold-change vectors across the 80 training perturbations. Let \\\\(x^{(j)} \\in \\mathbb{R}^n\\\\) denote the log fold-change vector for training perturbation \\\\(j\\\\), for \\\\(j=1,\\ldots,80\\\\). The baseline prediction vector is\n\n$$\n\\bar{x} = \\frac{1}{80}\\sum_{j=1}^{80} x^{(j)}.\n$$\n\n\n## Weighted Cosine Similarity (Wcos)\n\nWe define the weighted cosine similarity score \\\\(Wcos\\\\) between two vectors \\\\(a,b \\in \\mathbb{R}^m\\\\). In our setting, \\\\(a\\\\) is the single concatenated ground-truth delta vector across all genes in all perturbations of length \\\\(m = L \\times n \\\\), and \\\\(b\\\\) is the corresponding concatenated predictions vector.\n\nLet the smoothstep function be defined as\n$$\ns(t) = t^2(3-2t).\n$$\n\nWe fix the gating constants \\\\(left = 0\\\\) and \\\\(right = 0.3\\\\). For each coordinate in the concatenated vectors \\\\(i=1,\\ldots,m\\\\), we define\n$$\nx_i = \\max(|a_i|,\\;|b_i|),\n\\qquad\nt_i = \\frac{x_i - left}{right - left} = \\frac{x_i}{0.3},\n\\qquad\n\\tilde t_i = \\min\\bigl(1,\\max(0,t_i)\\bigr),\n$$\nand the (smooth) gate weight\n$$\nw_i = s(\\tilde t_i).\n$$\n\nLet \\\\(w_i^2\\\\) denote the squared weights. Then the weighted cosine similarity is\n\n$$\nWcos(a,b) = \\frac{\\sum\\_{i=1}^{m} w\\_i^{2}\\, a\\_i b\\_i}{\\left(\\sum\\_{i=1}^{m} w\\_i^{2}\\, a\\_i^{2}\\right)^{1/2}\\left(\\sum\\_{i=1}^{m} w\\_i^{2}\\, b\\_i^{2}\\right)^{1/2}}.\n$$\n\n(If the denominator is zero, define \\\\(Wcos(a,b)=0\\\\).)\n\n## The scoring metric\nThe final score used in this is the multiplication of the aggregated WMAE ratio scores and the weighted cosine. \n\n$$\nW \\times \\max(0,Wcos)\n$$\n\nSee [the implementation](https://www.kaggle.com/code/mylliabiotechnology/relative-wmae-multiplied-by-wcosine)\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "Total Prizes Available: 3500 EUR\n- **1st Place** - 2000 EUR\n- **2nd Place** - 1000 EUR\n- **3rd Place** - 500 EUR\n\nWinners will be announced on the [High-Content CRISPR Screening Conference](https://www.perturb2026.bio/) in March 2026 in Vienna, Austria.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "FAQs", "content": "## Can I use external datasets? \nYes, without limits. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.\n\n## What about private datasets? \nPrivate datasets are allowed. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.\n\n## Do I need to submit/licence/publish my code/model/data ? \nNo. You only grant us the permission to use the predicted values you submit. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.\n\n## Even if I'm eligible for a prize? \nStill no. Winners are only asked to submit a high-level description of the methods and data used. See the [rules](https://www.kaggle.com/competitions/echoes-of-silenced-genes/rules) for details.\n\n## How does the public/private leaderboard work? \nThe public leaderboard is based on predictions of 60 perturbations. The private leaderboard (final evaluation) will be based on 60 different perturbations, whose gene symbols will be released one week before the end of the challenge. See the [data](https://www.kaggle.com/competitions/echoes-of-silenced-genes/data) section for details.\n\n## What type of values should I submit?\nDelta expression on log2 scale. See the [data](https://www.kaggle.com/competitions/echoes-of-silenced-genes/data) section for details.\n\n## How are the training and ground-truth datasets normalized?\nLog1p-normalization, followed by simple arithmetic mean per perturbation. See the [data](https://www.kaggle.com/competitions/echoes-of-silenced-genes/data) section for details.\n\n## Will you release the ground-truth data after the end of the contest? \nYes, we will release the test dataset ground-truth, as well as the winning predictions. \n\n## Will you publish the high-level methods descriptions submitted by the winners? \nYes.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }